]>
Commit | Line | Data |
---|---|---|
235b3ba4 PH |
1 | #!/usr/bin/env python |
2 | # -*- coding: utf-8 -*- | |
3 | ||
3906e6ce | 4 | __authors__ = ( |
235b3ba4 PH |
5 | 'Ricardo Garcia Gonzalez', |
6 | 'Danny Colligan', | |
7 | 'Benjamin Johnson', | |
8 | 'Vasyl\' Vavrychuk', | |
9 | 'Witold Baryluk', | |
10 | 'Paweł Paprota', | |
11 | 'Gergely Imreh', | |
12 | 'Rogério Brito', | |
13 | 'Philipp Hagemeister', | |
14 | 'Sören Schulze', | |
15 | 'Kevin Ngo', | |
16 | 'Ori Avtalion', | |
b88a5250 | 17 | 'shizeeg', |
235b3ba4 PH |
18 | ) |
19 | ||
20 | __license__ = 'Public Domain' | |
9c228928 | 21 | __version__ = '2012.02.27' |
235b3ba4 PH |
22 | |
23 | UPDATE_URL = 'https://raw.github.com/rg3/youtube-dl/master/youtube-dl' | |
24 | ||
c9ed14e6 | 25 | |
235b3ba4 PH |
26 | import cookielib |
27 | import datetime | |
c9ed14e6 | 28 | import getpass |
235b3ba4 PH |
29 | import gzip |
30 | import htmlentitydefs | |
31 | import HTMLParser | |
32 | import httplib | |
33 | import locale | |
34 | import math | |
35 | import netrc | |
c9ed14e6 | 36 | import optparse |
235b3ba4 PH |
37 | import os |
38 | import os.path | |
39 | import re | |
c9ed14e6 | 40 | import shlex |
235b3ba4 PH |
41 | import socket |
42 | import string | |
43 | import subprocess | |
44 | import sys | |
45 | import time | |
46 | import urllib | |
47 | import urllib2 | |
48 | import warnings | |
49 | import zlib | |
50 | ||
51 | if os.name == 'nt': | |
52 | import ctypes | |
53 | ||
54 | try: | |
55 | import email.utils | |
56 | except ImportError: # Python 2.4 | |
57 | import email.Utils | |
58 | try: | |
59 | import cStringIO as StringIO | |
60 | except ImportError: | |
61 | import StringIO | |
62 | ||
63 | # parse_qs was moved from the cgi module to the urlparse module recently. | |
64 | try: | |
65 | from urlparse import parse_qs | |
66 | except ImportError: | |
67 | from cgi import parse_qs | |
68 | ||
69 | try: | |
70 | import lxml.etree | |
71 | except ImportError: | |
72 | pass # Handled below | |
73 | ||
74 | try: | |
75 | import xml.etree.ElementTree | |
76 | except ImportError: # Python<2.5: Not officially supported, but let it slip | |
77 | warnings.warn('xml.etree.ElementTree support is missing. Consider upgrading to Python >= 2.5 if you get related errors.') | |
78 | ||
79 | std_headers = { | |
80 | 'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64; rv:5.0.1) Gecko/20100101 Firefox/5.0.1', | |
81 | 'Accept-Charset': 'ISO-8859-1,utf-8;q=0.7,*;q=0.7', | |
82 | 'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8', | |
83 | 'Accept-Encoding': 'gzip, deflate', | |
84 | 'Accept-Language': 'en-us,en;q=0.5', | |
85 | } | |
86 | ||
235b3ba4 PH |
87 | try: |
88 | import json | |
89 | except ImportError: # Python <2.6, use trivialjson (https://github.com/phihag/trivialjson): | |
90 | import re | |
91 | class json(object): | |
92 | @staticmethod | |
93 | def loads(s): | |
94 | s = s.decode('UTF-8') | |
95 | def raiseError(msg, i): | |
96 | raise ValueError(msg + ' at position ' + str(i) + ' of ' + repr(s) + ': ' + repr(s[i:])) | |
97 | def skipSpace(i, expectMore=True): | |
98 | while i < len(s) and s[i] in ' \t\r\n': | |
99 | i += 1 | |
100 | if expectMore: | |
101 | if i >= len(s): | |
102 | raiseError('Premature end', i) | |
103 | return i | |
104 | def decodeEscape(match): | |
105 | esc = match.group(1) | |
106 | _STATIC = { | |
107 | '"': '"', | |
108 | '\\': '\\', | |
109 | '/': '/', | |
110 | 'b': unichr(0x8), | |
111 | 'f': unichr(0xc), | |
112 | 'n': '\n', | |
113 | 'r': '\r', | |
114 | 't': '\t', | |
115 | } | |
116 | if esc in _STATIC: | |
117 | return _STATIC[esc] | |
118 | if esc[0] == 'u': | |
119 | if len(esc) == 1+4: | |
120 | return unichr(int(esc[1:5], 16)) | |
121 | if len(esc) == 5+6 and esc[5:7] == '\\u': | |
122 | hi = int(esc[1:5], 16) | |
123 | low = int(esc[7:11], 16) | |
124 | return unichr((hi - 0xd800) * 0x400 + low - 0xdc00 + 0x10000) | |
125 | raise ValueError('Unknown escape ' + str(esc)) | |
126 | def parseString(i): | |
127 | i += 1 | |
128 | e = i | |
129 | while True: | |
130 | e = s.index('"', e) | |
131 | bslashes = 0 | |
132 | while s[e-bslashes-1] == '\\': | |
133 | bslashes += 1 | |
134 | if bslashes % 2 == 1: | |
135 | e += 1 | |
136 | continue | |
137 | break | |
138 | rexp = re.compile(r'\\(u[dD][89aAbB][0-9a-fA-F]{2}\\u[0-9a-fA-F]{4}|u[0-9a-fA-F]{4}|.|$)') | |
139 | stri = rexp.sub(decodeEscape, s[i:e]) | |
140 | return (e+1,stri) | |
141 | def parseObj(i): | |
142 | i += 1 | |
143 | res = {} | |
144 | i = skipSpace(i) | |
145 | if s[i] == '}': # Empty dictionary | |
146 | return (i+1,res) | |
147 | while True: | |
148 | if s[i] != '"': | |
149 | raiseError('Expected a string object key', i) | |
150 | i,key = parseString(i) | |
151 | i = skipSpace(i) | |
152 | if i >= len(s) or s[i] != ':': | |
153 | raiseError('Expected a colon', i) | |
154 | i,val = parse(i+1) | |
155 | res[key] = val | |
156 | i = skipSpace(i) | |
157 | if s[i] == '}': | |
158 | return (i+1, res) | |
159 | if s[i] != ',': | |
160 | raiseError('Expected comma or closing curly brace', i) | |
161 | i = skipSpace(i+1) | |
162 | def parseArray(i): | |
163 | res = [] | |
164 | i = skipSpace(i+1) | |
165 | if s[i] == ']': # Empty array | |
166 | return (i+1,res) | |
167 | while True: | |
168 | i,val = parse(i) | |
169 | res.append(val) | |
170 | i = skipSpace(i) # Raise exception if premature end | |
171 | if s[i] == ']': | |
172 | return (i+1, res) | |
173 | if s[i] != ',': | |
174 | raiseError('Expected a comma or closing bracket', i) | |
175 | i = skipSpace(i+1) | |
176 | def parseDiscrete(i): | |
177 | for k,v in {'true': True, 'false': False, 'null': None}.items(): | |
178 | if s.startswith(k, i): | |
179 | return (i+len(k), v) | |
180 | raiseError('Not a boolean (or null)', i) | |
181 | def parseNumber(i): | |
182 | mobj = re.match('^(-?(0|[1-9][0-9]*)(\.[0-9]*)?([eE][+-]?[0-9]+)?)', s[i:]) | |
183 | if mobj is None: | |
184 | raiseError('Not a number', i) | |
185 | nums = mobj.group(1) | |
186 | if '.' in nums or 'e' in nums or 'E' in nums: | |
187 | return (i+len(nums), float(nums)) | |
188 | return (i+len(nums), int(nums)) | |
189 | CHARMAP = {'{': parseObj, '[': parseArray, '"': parseString, 't': parseDiscrete, 'f': parseDiscrete, 'n': parseDiscrete} | |
190 | def parse(i): | |
191 | i = skipSpace(i) | |
192 | i,res = CHARMAP.get(s[i], parseNumber)(i) | |
193 | i = skipSpace(i, False) | |
194 | return (i,res) | |
195 | i,res = parse(0) | |
196 | if i < len(s): | |
197 | raise ValueError('Extra data at end of input (index ' + str(i) + ' of ' + repr(s) + ': ' + repr(s[i:]) + ')') | |
198 | return res | |
199 | ||
200 | def preferredencoding(): | |
201 | """Get preferred encoding. | |
202 | ||
203 | Returns the best encoding scheme for the system, based on | |
204 | locale.getpreferredencoding() and some further tweaks. | |
205 | """ | |
206 | def yield_preferredencoding(): | |
207 | try: | |
208 | pref = locale.getpreferredencoding() | |
209 | u'TEST'.encode(pref) | |
210 | except: | |
211 | pref = 'UTF-8' | |
212 | while True: | |
213 | yield pref | |
214 | return yield_preferredencoding().next() | |
215 | ||
216 | ||
217 | def htmlentity_transform(matchobj): | |
218 | """Transforms an HTML entity to a Unicode character. | |
219 | ||
220 | This function receives a match object and is intended to be used with | |
221 | the re.sub() function. | |
222 | """ | |
223 | entity = matchobj.group(1) | |
224 | ||
225 | # Known non-numeric HTML entity | |
226 | if entity in htmlentitydefs.name2codepoint: | |
227 | return unichr(htmlentitydefs.name2codepoint[entity]) | |
228 | ||
229 | # Unicode character | |
230 | mobj = re.match(ur'(?u)#(x?\d+)', entity) | |
231 | if mobj is not None: | |
232 | numstr = mobj.group(1) | |
233 | if numstr.startswith(u'x'): | |
234 | base = 16 | |
235 | numstr = u'0%s' % numstr | |
236 | else: | |
237 | base = 10 | |
238 | return unichr(long(numstr, base)) | |
239 | ||
240 | # Unknown entity in name, return its literal representation | |
241 | return (u'&%s;' % entity) | |
242 | ||
243 | ||
244 | def sanitize_title(utitle): | |
245 | """Sanitizes a video title so it could be used as part of a filename.""" | |
246 | utitle = re.sub(ur'(?u)&(.+?);', htmlentity_transform, utitle) | |
247 | return utitle.replace(unicode(os.sep), u'%') | |
248 | ||
249 | ||
250 | def sanitize_open(filename, open_mode): | |
251 | """Try to open the given filename, and slightly tweak it if this fails. | |
252 | ||
253 | Attempts to open the given filename. If this fails, it tries to change | |
254 | the filename slightly, step by step, until it's either able to open it | |
255 | or it fails and raises a final exception, like the standard open() | |
256 | function. | |
257 | ||
258 | It returns the tuple (stream, definitive_file_name). | |
259 | """ | |
260 | try: | |
261 | if filename == u'-': | |
262 | if sys.platform == 'win32': | |
263 | import msvcrt | |
264 | msvcrt.setmode(sys.stdout.fileno(), os.O_BINARY) | |
265 | return (sys.stdout, filename) | |
fefb166c | 266 | stream = open(_encodeFilename(filename), open_mode) |
235b3ba4 PH |
267 | return (stream, filename) |
268 | except (IOError, OSError), err: | |
269 | # In case of error, try to remove win32 forbidden chars | |
270 | filename = re.sub(ur'[/<>:"\|\?\*]', u'#', filename) | |
271 | ||
272 | # An exception here should be caught in the caller | |
fefb166c | 273 | stream = open(_encodeFilename(filename), open_mode) |
235b3ba4 PH |
274 | return (stream, filename) |
275 | ||
276 | ||
277 | def timeconvert(timestr): | |
278 | """Convert RFC 2822 defined time string into system timestamp""" | |
279 | timestamp = None | |
280 | timetuple = email.utils.parsedate_tz(timestr) | |
281 | if timetuple is not None: | |
282 | timestamp = email.utils.mktime_tz(timetuple) | |
283 | return timestamp | |
284 | ||
e33e3045 | 285 | def _simplify_title(title): |
af8e8d63 PH |
286 | expr = re.compile(ur'[^\w\d_\-]+', flags=re.UNICODE) |
287 | return expr.sub(u'_', title).strip(u'_') | |
235b3ba4 | 288 | |
0b14e0b3 PH |
289 | def _orderedSet(iterable): |
290 | """ Remove all duplicates from the input iterable """ | |
291 | res = [] | |
292 | for el in iterable: | |
293 | if el not in res: | |
294 | res.append(el) | |
295 | return res | |
296 | ||
1413cd87 | 297 | def _unescapeHTML(s): |
fefb166c PH |
298 | """ |
299 | @param s a string (of type unicode) | |
300 | """ | |
301 | assert type(s) == type(u'') | |
302 | ||
303 | htmlParser = HTMLParser.HTMLParser() | |
304 | return htmlParser.unescape(s) | |
1413cd87 | 305 | |
fefb166c PH |
306 | def _encodeFilename(s): |
307 | """ | |
308 | @param s The name of the file (of type unicode) | |
309 | """ | |
310 | ||
311 | assert type(s) == type(u'') | |
4afdff39 MM |
312 | |
313 | if sys.platform == 'win32' and sys.getwindowsversion().major >= 5: | |
314 | # Pass u'' directly to use Unicode APIs on Windows 2000 and up | |
315 | # (Detecting Windows NT 4 is tricky because 'major >= 4' would | |
316 | # match Windows 9x series as well. Besides, NT 4 is obsolete.) | |
317 | return s | |
318 | else: | |
319 | return s.encode(sys.getfilesystemencoding(), 'ignore') | |
1413cd87 | 320 | |
235b3ba4 PH |
321 | class DownloadError(Exception): |
322 | """Download Error exception. | |
323 | ||
324 | This exception may be thrown by FileDownloader objects if they are not | |
325 | configured to continue on errors. They will contain the appropriate | |
326 | error message. | |
327 | """ | |
328 | pass | |
329 | ||
330 | ||
331 | class SameFileError(Exception): | |
332 | """Same File exception. | |
333 | ||
334 | This exception will be thrown by FileDownloader objects if they detect | |
335 | multiple files would have to be downloaded to the same file on disk. | |
336 | """ | |
337 | pass | |
338 | ||
339 | ||
340 | class PostProcessingError(Exception): | |
341 | """Post Processing exception. | |
342 | ||
343 | This exception may be raised by PostProcessor's .run() method to | |
344 | indicate an error in the postprocessing task. | |
345 | """ | |
346 | pass | |
347 | ||
94fd3201 PH |
348 | class MaxDownloadsReached(Exception): |
349 | """ --max-downloads limit has been reached. """ | |
350 | pass | |
351 | ||
235b3ba4 PH |
352 | |
353 | class UnavailableVideoError(Exception): | |
354 | """Unavailable Format exception. | |
355 | ||
356 | This exception will be thrown when a video is requested | |
357 | in a format that is not available for that video. | |
358 | """ | |
359 | pass | |
360 | ||
361 | ||
362 | class ContentTooShortError(Exception): | |
363 | """Content Too Short exception. | |
364 | ||
365 | This exception may be raised by FileDownloader objects when a file they | |
366 | download is too small for what the server announced first, indicating | |
367 | the connection was probably interrupted. | |
368 | """ | |
369 | # Both in bytes | |
370 | downloaded = None | |
371 | expected = None | |
372 | ||
373 | def __init__(self, downloaded, expected): | |
374 | self.downloaded = downloaded | |
375 | self.expected = expected | |
376 | ||
377 | ||
378 | class YoutubeDLHandler(urllib2.HTTPHandler): | |
379 | """Handler for HTTP requests and responses. | |
380 | ||
381 | This class, when installed with an OpenerDirector, automatically adds | |
382 | the standard headers to every HTTP request and handles gzipped and | |
383 | deflated responses from web servers. If compression is to be avoided in | |
384 | a particular request, the original request in the program code only has | |
385 | to include the HTTP header "Youtubedl-No-Compression", which will be | |
386 | removed before making the real request. | |
387 | ||
388 | Part of this code was copied from: | |
389 | ||
390 | http://techknack.net/python-urllib2-handlers/ | |
391 | ||
392 | Andrew Rowls, the author of that code, agreed to release it to the | |
393 | public domain. | |
394 | """ | |
395 | ||
396 | @staticmethod | |
397 | def deflate(data): | |
398 | try: | |
399 | return zlib.decompress(data, -zlib.MAX_WBITS) | |
400 | except zlib.error: | |
401 | return zlib.decompress(data) | |
402 | ||
403 | @staticmethod | |
404 | def addinfourl_wrapper(stream, headers, url, code): | |
405 | if hasattr(urllib2.addinfourl, 'getcode'): | |
406 | return urllib2.addinfourl(stream, headers, url, code) | |
407 | ret = urllib2.addinfourl(stream, headers, url) | |
408 | ret.code = code | |
409 | return ret | |
410 | ||
411 | def http_request(self, req): | |
412 | for h in std_headers: | |
413 | if h in req.headers: | |
414 | del req.headers[h] | |
415 | req.add_header(h, std_headers[h]) | |
416 | if 'Youtubedl-no-compression' in req.headers: | |
417 | if 'Accept-encoding' in req.headers: | |
418 | del req.headers['Accept-encoding'] | |
419 | del req.headers['Youtubedl-no-compression'] | |
420 | return req | |
421 | ||
422 | def http_response(self, req, resp): | |
423 | old_resp = resp | |
424 | # gzip | |
425 | if resp.headers.get('Content-encoding', '') == 'gzip': | |
426 | gz = gzip.GzipFile(fileobj=StringIO.StringIO(resp.read()), mode='r') | |
427 | resp = self.addinfourl_wrapper(gz, old_resp.headers, old_resp.url, old_resp.code) | |
428 | resp.msg = old_resp.msg | |
429 | # deflate | |
430 | if resp.headers.get('Content-encoding', '') == 'deflate': | |
431 | gz = StringIO.StringIO(self.deflate(resp.read())) | |
432 | resp = self.addinfourl_wrapper(gz, old_resp.headers, old_resp.url, old_resp.code) | |
433 | resp.msg = old_resp.msg | |
434 | return resp | |
435 | ||
436 | ||
437 | class FileDownloader(object): | |
438 | """File Downloader class. | |
439 | ||
440 | File downloader objects are the ones responsible of downloading the | |
441 | actual video file and writing it to disk if the user has requested | |
442 | it, among some other tasks. In most cases there should be one per | |
443 | program. As, given a video URL, the downloader doesn't know how to | |
444 | extract all the needed information, task that InfoExtractors do, it | |
445 | has to pass the URL to one of them. | |
446 | ||
447 | For this, file downloader objects have a method that allows | |
448 | InfoExtractors to be registered in a given order. When it is passed | |
449 | a URL, the file downloader handles it to the first InfoExtractor it | |
450 | finds that reports being able to handle it. The InfoExtractor extracts | |
451 | all the information about the video or videos the URL refers to, and | |
452 | asks the FileDownloader to process the video information, possibly | |
453 | downloading the video. | |
454 | ||
455 | File downloaders accept a lot of parameters. In order not to saturate | |
456 | the object constructor with arguments, it receives a dictionary of | |
457 | options instead. These options are available through the params | |
458 | attribute for the InfoExtractors to use. The FileDownloader also | |
459 | registers itself as the downloader in charge for the InfoExtractors | |
460 | that are added to it, so this is a "mutual registration". | |
461 | ||
462 | Available options: | |
463 | ||
464 | username: Username for authentication purposes. | |
465 | password: Password for authentication purposes. | |
466 | usenetrc: Use netrc for authentication instead. | |
467 | quiet: Do not print messages to stdout. | |
468 | forceurl: Force printing final URL. | |
469 | forcetitle: Force printing title. | |
470 | forcethumbnail: Force printing thumbnail URL. | |
471 | forcedescription: Force printing description. | |
472 | forcefilename: Force printing final filename. | |
473 | simulate: Do not download the video files. | |
474 | format: Video format code. | |
475 | format_limit: Highest quality format to try. | |
476 | outtmpl: Template for output names. | |
477 | ignoreerrors: Do not stop on download errors. | |
478 | ratelimit: Download speed limit, in bytes/sec. | |
479 | nooverwrites: Prevent overwriting files. | |
480 | retries: Number of times to retry for HTTP error 5xx | |
481 | continuedl: Try to continue downloads if possible. | |
482 | noprogress: Do not print the progress bar. | |
483 | playliststart: Playlist item to start at. | |
484 | playlistend: Playlist item to end at. | |
485 | matchtitle: Download only matching titles. | |
486 | rejecttitle: Reject downloads for matching titles. | |
487 | logtostderr: Log messages to stderr instead of stdout. | |
488 | consoletitle: Display progress in console window's titlebar. | |
489 | nopart: Do not use temporary .part files. | |
490 | updatetime: Use the Last-modified header to set output file timestamps. | |
491 | writedescription: Write the video description to a .description file | |
492 | writeinfojson: Write the video description to a .info.json file | |
a0432a1e FV |
493 | writesubtitles: Write the video subtitles to a .srt file |
494 | subtitleslang: Language of the subtitles to download | |
235b3ba4 PH |
495 | """ |
496 | ||
497 | params = None | |
498 | _ies = [] | |
499 | _pps = [] | |
500 | _download_retcode = None | |
501 | _num_downloads = None | |
502 | _screen_file = None | |
503 | ||
504 | def __init__(self, params): | |
505 | """Create a FileDownloader object with the given options.""" | |
506 | self._ies = [] | |
507 | self._pps = [] | |
508 | self._download_retcode = 0 | |
509 | self._num_downloads = 0 | |
510 | self._screen_file = [sys.stdout, sys.stderr][params.get('logtostderr', False)] | |
511 | self.params = params | |
512 | ||
513 | @staticmethod | |
514 | def format_bytes(bytes): | |
515 | if bytes is None: | |
516 | return 'N/A' | |
517 | if type(bytes) is str: | |
518 | bytes = float(bytes) | |
519 | if bytes == 0.0: | |
520 | exponent = 0 | |
521 | else: | |
522 | exponent = long(math.log(bytes, 1024.0)) | |
523 | suffix = 'bkMGTPEZY'[exponent] | |
524 | converted = float(bytes) / float(1024 ** exponent) | |
525 | return '%.2f%s' % (converted, suffix) | |
526 | ||
527 | @staticmethod | |
528 | def calc_percent(byte_counter, data_len): | |
529 | if data_len is None: | |
530 | return '---.-%' | |
531 | return '%6s' % ('%3.1f%%' % (float(byte_counter) / float(data_len) * 100.0)) | |
532 | ||
533 | @staticmethod | |
534 | def calc_eta(start, now, total, current): | |
535 | if total is None: | |
536 | return '--:--' | |
537 | dif = now - start | |
538 | if current == 0 or dif < 0.001: # One millisecond | |
539 | return '--:--' | |
540 | rate = float(current) / dif | |
541 | eta = long((float(total) - float(current)) / rate) | |
542 | (eta_mins, eta_secs) = divmod(eta, 60) | |
543 | if eta_mins > 99: | |
544 | return '--:--' | |
545 | return '%02d:%02d' % (eta_mins, eta_secs) | |
546 | ||
547 | @staticmethod | |
548 | def calc_speed(start, now, bytes): | |
549 | dif = now - start | |
550 | if bytes == 0 or dif < 0.001: # One millisecond | |
551 | return '%10s' % '---b/s' | |
552 | return '%10s' % ('%s/s' % FileDownloader.format_bytes(float(bytes) / dif)) | |
553 | ||
554 | @staticmethod | |
555 | def best_block_size(elapsed_time, bytes): | |
556 | new_min = max(bytes / 2.0, 1.0) | |
557 | new_max = min(max(bytes * 2.0, 1.0), 4194304) # Do not surpass 4 MB | |
558 | if elapsed_time < 0.001: | |
559 | return long(new_max) | |
560 | rate = bytes / elapsed_time | |
561 | if rate > new_max: | |
562 | return long(new_max) | |
563 | if rate < new_min: | |
564 | return long(new_min) | |
565 | return long(rate) | |
566 | ||
567 | @staticmethod | |
568 | def parse_bytes(bytestr): | |
569 | """Parse a string indicating a byte quantity into a long integer.""" | |
570 | matchobj = re.match(r'(?i)^(\d+(?:\.\d+)?)([kMGTPEZY]?)$', bytestr) | |
571 | if matchobj is None: | |
572 | return None | |
573 | number = float(matchobj.group(1)) | |
574 | multiplier = 1024.0 ** 'bkmgtpezy'.index(matchobj.group(2).lower()) | |
575 | return long(round(number * multiplier)) | |
576 | ||
577 | def add_info_extractor(self, ie): | |
578 | """Add an InfoExtractor object to the end of the list.""" | |
579 | self._ies.append(ie) | |
580 | ie.set_downloader(self) | |
581 | ||
582 | def add_post_processor(self, pp): | |
583 | """Add a PostProcessor object to the end of the chain.""" | |
584 | self._pps.append(pp) | |
585 | pp.set_downloader(self) | |
586 | ||
fefb166c | 587 | def to_screen(self, message, skip_eol=False): |
235b3ba4 | 588 | """Print message to stdout if not in quiet mode.""" |
fefb166c PH |
589 | assert type(message) == type(u'') |
590 | if not self.params.get('quiet', False): | |
591 | terminator = [u'\n', u''][skip_eol] | |
592 | output = message + terminator | |
593 | ||
594 | if 'b' not in self._screen_file.mode or sys.version_info[0] < 3: # Python 2 lies about the mode of sys.stdout/sys.stderr | |
595 | output = output.encode(preferredencoding(), 'ignore') | |
596 | self._screen_file.write(output) | |
235b3ba4 | 597 | self._screen_file.flush() |
235b3ba4 PH |
598 | |
599 | def to_stderr(self, message): | |
600 | """Print message to stderr.""" | |
601 | print >>sys.stderr, message.encode(preferredencoding()) | |
602 | ||
603 | def to_cons_title(self, message): | |
604 | """Set console/terminal window title to message.""" | |
605 | if not self.params.get('consoletitle', False): | |
606 | return | |
607 | if os.name == 'nt' and ctypes.windll.kernel32.GetConsoleWindow(): | |
608 | # c_wchar_p() might not be necessary if `message` is | |
609 | # already of type unicode() | |
610 | ctypes.windll.kernel32.SetConsoleTitleW(ctypes.c_wchar_p(message)) | |
611 | elif 'TERM' in os.environ: | |
612 | sys.stderr.write('\033]0;%s\007' % message.encode(preferredencoding())) | |
613 | ||
614 | def fixed_template(self): | |
615 | """Checks if the output template is fixed.""" | |
616 | return (re.search(ur'(?u)%\(.+?\)s', self.params['outtmpl']) is None) | |
617 | ||
618 | def trouble(self, message=None): | |
619 | """Determine action to take when a download problem appears. | |
620 | ||
621 | Depending on if the downloader has been configured to ignore | |
622 | download errors or not, this method may throw an exception or | |
623 | not when errors are found, after printing the message. | |
624 | """ | |
625 | if message is not None: | |
626 | self.to_stderr(message) | |
627 | if not self.params.get('ignoreerrors', False): | |
628 | raise DownloadError(message) | |
629 | self._download_retcode = 1 | |
630 | ||
631 | def slow_down(self, start_time, byte_counter): | |
632 | """Sleep if the download speed is over the rate limit.""" | |
633 | rate_limit = self.params.get('ratelimit', None) | |
634 | if rate_limit is None or byte_counter == 0: | |
635 | return | |
636 | now = time.time() | |
637 | elapsed = now - start_time | |
638 | if elapsed <= 0.0: | |
639 | return | |
640 | speed = float(byte_counter) / elapsed | |
641 | if speed > rate_limit: | |
642 | time.sleep((byte_counter - rate_limit * (now - start_time)) / rate_limit) | |
643 | ||
644 | def temp_name(self, filename): | |
645 | """Returns a temporary filename for the given filename.""" | |
646 | if self.params.get('nopart', False) or filename == u'-' or \ | |
fefb166c | 647 | (os.path.exists(_encodeFilename(filename)) and not os.path.isfile(_encodeFilename(filename))): |
235b3ba4 PH |
648 | return filename |
649 | return filename + u'.part' | |
650 | ||
651 | def undo_temp_name(self, filename): | |
652 | if filename.endswith(u'.part'): | |
653 | return filename[:-len(u'.part')] | |
654 | return filename | |
655 | ||
656 | def try_rename(self, old_filename, new_filename): | |
657 | try: | |
658 | if old_filename == new_filename: | |
659 | return | |
fefb166c | 660 | os.rename(_encodeFilename(old_filename), _encodeFilename(new_filename)) |
235b3ba4 PH |
661 | except (IOError, OSError), err: |
662 | self.trouble(u'ERROR: unable to rename file') | |
663 | ||
664 | def try_utime(self, filename, last_modified_hdr): | |
665 | """Try to set the last-modified time of the given file.""" | |
666 | if last_modified_hdr is None: | |
667 | return | |
fefb166c | 668 | if not os.path.isfile(_encodeFilename(filename)): |
235b3ba4 PH |
669 | return |
670 | timestr = last_modified_hdr | |
671 | if timestr is None: | |
672 | return | |
673 | filetime = timeconvert(timestr) | |
674 | if filetime is None: | |
675 | return filetime | |
676 | try: | |
677 | os.utime(filename, (time.time(), filetime)) | |
678 | except: | |
679 | pass | |
680 | return filetime | |
681 | ||
682 | def report_writedescription(self, descfn): | |
683 | """ Report that the description file is being written """ | |
fefb166c | 684 | self.to_screen(u'[info] Writing video description to: ' + descfn) |
235b3ba4 | 685 | |
a0432a1e FV |
686 | def report_writesubtitles(self, srtfn): |
687 | """ Report that the subtitles file is being written """ | |
688 | self.to_screen(u'[info] Writing video subtitles to: ' + srtfn) | |
689 | ||
235b3ba4 PH |
690 | def report_writeinfojson(self, infofn): |
691 | """ Report that the metadata file has been written """ | |
fefb166c | 692 | self.to_screen(u'[info] Video description metadata as JSON to: ' + infofn) |
235b3ba4 PH |
693 | |
694 | def report_destination(self, filename): | |
695 | """Report destination filename.""" | |
fefb166c | 696 | self.to_screen(u'[download] Destination: ' + filename) |
235b3ba4 PH |
697 | |
698 | def report_progress(self, percent_str, data_len_str, speed_str, eta_str): | |
699 | """Report download progress.""" | |
700 | if self.params.get('noprogress', False): | |
701 | return | |
702 | self.to_screen(u'\r[download] %s of %s at %s ETA %s' % | |
703 | (percent_str, data_len_str, speed_str, eta_str), skip_eol=True) | |
704 | self.to_cons_title(u'youtube-dl - %s of %s at %s ETA %s' % | |
705 | (percent_str.strip(), data_len_str.strip(), speed_str.strip(), eta_str.strip())) | |
706 | ||
707 | def report_resuming_byte(self, resume_len): | |
708 | """Report attempt to resume at given byte.""" | |
709 | self.to_screen(u'[download] Resuming download at byte %s' % resume_len) | |
710 | ||
711 | def report_retry(self, count, retries): | |
712 | """Report retry in case of HTTP error 5xx""" | |
713 | self.to_screen(u'[download] Got server HTTP error. Retrying (attempt %d of %d)...' % (count, retries)) | |
714 | ||
715 | def report_file_already_downloaded(self, file_name): | |
716 | """Report file has already been fully downloaded.""" | |
717 | try: | |
718 | self.to_screen(u'[download] %s has already been downloaded' % file_name) | |
719 | except (UnicodeEncodeError), err: | |
720 | self.to_screen(u'[download] The file has already been downloaded') | |
721 | ||
722 | def report_unable_to_resume(self): | |
723 | """Report it was impossible to resume download.""" | |
724 | self.to_screen(u'[download] Unable to resume') | |
725 | ||
726 | def report_finish(self): | |
727 | """Report download finished.""" | |
728 | if self.params.get('noprogress', False): | |
729 | self.to_screen(u'[download] Download completed') | |
730 | else: | |
731 | self.to_screen(u'') | |
732 | ||
733 | def increment_downloads(self): | |
734 | """Increment the ordinal that assigns a number to each file.""" | |
735 | self._num_downloads += 1 | |
736 | ||
737 | def prepare_filename(self, info_dict): | |
738 | """Generate the output filename.""" | |
739 | try: | |
740 | template_dict = dict(info_dict) | |
741 | template_dict['epoch'] = unicode(long(time.time())) | |
742 | template_dict['autonumber'] = unicode('%05d' % self._num_downloads) | |
743 | filename = self.params['outtmpl'] % template_dict | |
744 | return filename | |
745 | except (ValueError, KeyError), err: | |
746 | self.trouble(u'ERROR: invalid system charset or erroneous output template') | |
747 | return None | |
748 | ||
77315556 PH |
749 | def _match_entry(self, info_dict): |
750 | """ Returns None iff the file should be downloaded """ | |
751 | ||
752 | title = info_dict['title'] | |
753 | matchtitle = self.params.get('matchtitle', False) | |
754 | if matchtitle and not re.search(matchtitle, title, re.IGNORECASE): | |
755 | return u'[download] "' + title + '" title did not match pattern "' + matchtitle + '"' | |
756 | rejecttitle = self.params.get('rejecttitle', False) | |
757 | if rejecttitle and re.search(rejecttitle, title, re.IGNORECASE): | |
758 | return u'"' + title + '" title matched reject pattern "' + rejecttitle + '"' | |
759 | return None | |
760 | ||
235b3ba4 PH |
761 | def process_info(self, info_dict): |
762 | """Process a single dictionary returned by an InfoExtractor.""" | |
b88a5250 | 763 | |
77315556 PH |
764 | reason = self._match_entry(info_dict) |
765 | if reason is not None: | |
766 | self.to_screen(u'[download] ' + reason) | |
767 | return | |
768 | ||
c379c181 | 769 | max_downloads = self.params.get('max_downloads') |
b88a5250 | 770 | if max_downloads is not None: |
c379c181 | 771 | if self._num_downloads > int(max_downloads): |
94fd3201 | 772 | raise MaxDownloadsReached() |
77315556 | 773 | |
235b3ba4 PH |
774 | filename = self.prepare_filename(info_dict) |
775 | ||
776 | # Forced printings | |
777 | if self.params.get('forcetitle', False): | |
778 | print info_dict['title'].encode(preferredencoding(), 'xmlcharrefreplace') | |
779 | if self.params.get('forceurl', False): | |
780 | print info_dict['url'].encode(preferredencoding(), 'xmlcharrefreplace') | |
781 | if self.params.get('forcethumbnail', False) and 'thumbnail' in info_dict: | |
782 | print info_dict['thumbnail'].encode(preferredencoding(), 'xmlcharrefreplace') | |
783 | if self.params.get('forcedescription', False) and 'description' in info_dict: | |
784 | print info_dict['description'].encode(preferredencoding(), 'xmlcharrefreplace') | |
785 | if self.params.get('forcefilename', False) and filename is not None: | |
786 | print filename.encode(preferredencoding(), 'xmlcharrefreplace') | |
787 | if self.params.get('forceformat', False): | |
788 | print info_dict['format'].encode(preferredencoding(), 'xmlcharrefreplace') | |
789 | ||
790 | # Do nothing else if in simulate mode | |
791 | if self.params.get('simulate', False): | |
792 | return | |
793 | ||
794 | if filename is None: | |
795 | return | |
796 | ||
235b3ba4 | 797 | try: |
fefb166c PH |
798 | dn = os.path.dirname(_encodeFilename(filename)) |
799 | if dn != '' and not os.path.exists(dn): # dn is already encoded | |
235b3ba4 PH |
800 | os.makedirs(dn) |
801 | except (OSError, IOError), err: | |
802 | self.trouble(u'ERROR: unable to create directory ' + unicode(err)) | |
803 | return | |
804 | ||
805 | if self.params.get('writedescription', False): | |
806 | try: | |
fefb166c | 807 | descfn = filename + u'.description' |
235b3ba4 | 808 | self.report_writedescription(descfn) |
fefb166c | 809 | descfile = open(_encodeFilename(descfn), 'wb') |
235b3ba4 PH |
810 | try: |
811 | descfile.write(info_dict['description'].encode('utf-8')) | |
812 | finally: | |
813 | descfile.close() | |
814 | except (OSError, IOError): | |
815 | self.trouble(u'ERROR: Cannot write description file ' + descfn) | |
816 | return | |
a0432a1e FV |
817 | |
818 | if self.params.get('writesubtitles', False) and 'subtitles' in info_dict and info_dict['subtitles']: | |
819 | # subtitles download errors are already managed as troubles in relevant IE | |
820 | # that way it will silently go on when used with unsupporting IE | |
821 | try: | |
822 | srtfn = filename.rsplit('.', 1)[0] + u'.srt' | |
823 | self.report_writesubtitles(srtfn) | |
824 | srtfile = open(_encodeFilename(srtfn), 'wb') | |
825 | try: | |
826 | srtfile.write(info_dict['subtitles'].encode('utf-8')) | |
827 | finally: | |
828 | srtfile.close() | |
829 | except (OSError, IOError): | |
830 | self.trouble(u'ERROR: Cannot write subtitles file ' + descfn) | |
831 | return | |
235b3ba4 PH |
832 | |
833 | if self.params.get('writeinfojson', False): | |
fefb166c | 834 | infofn = filename + u'.info.json' |
235b3ba4 PH |
835 | self.report_writeinfojson(infofn) |
836 | try: | |
837 | json.dump | |
838 | except (NameError,AttributeError): | |
839 | self.trouble(u'ERROR: No JSON encoder found. Update to Python 2.6+, setup a json module, or leave out --write-info-json.') | |
840 | return | |
841 | try: | |
fefb166c | 842 | infof = open(_encodeFilename(infofn), 'wb') |
235b3ba4 PH |
843 | try: |
844 | json_info_dict = dict((k,v) for k,v in info_dict.iteritems() if not k in ('urlhandle',)) | |
845 | json.dump(json_info_dict, infof) | |
846 | finally: | |
847 | infof.close() | |
848 | except (OSError, IOError): | |
849 | self.trouble(u'ERROR: Cannot write metadata to JSON file ' + infofn) | |
850 | return | |
851 | ||
852 | if not self.params.get('skip_download', False): | |
fefb166c | 853 | if self.params.get('nooverwrites', False) and os.path.exists(_encodeFilename(filename)): |
a5647b79 PH |
854 | success = True |
855 | else: | |
856 | try: | |
857 | success = self._do_download(filename, info_dict) | |
858 | except (OSError, IOError), err: | |
859 | raise UnavailableVideoError | |
860 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
861 | self.trouble(u'ERROR: unable to download video data: %s' % str(err)) | |
862 | return | |
863 | except (ContentTooShortError, ), err: | |
864 | self.trouble(u'ERROR: content too short (expected %s bytes and served %s)' % (err.expected, err.downloaded)) | |
865 | return | |
235b3ba4 PH |
866 | |
867 | if success: | |
868 | try: | |
869 | self.post_process(filename, info_dict) | |
870 | except (PostProcessingError), err: | |
871 | self.trouble(u'ERROR: postprocessing: %s' % str(err)) | |
872 | return | |
873 | ||
874 | def download(self, url_list): | |
875 | """Download a given list of URLs.""" | |
876 | if len(url_list) > 1 and self.fixed_template(): | |
877 | raise SameFileError(self.params['outtmpl']) | |
878 | ||
879 | for url in url_list: | |
880 | suitable_found = False | |
881 | for ie in self._ies: | |
882 | # Go to next InfoExtractor if not suitable | |
883 | if not ie.suitable(url): | |
884 | continue | |
885 | ||
886 | # Suitable InfoExtractor found | |
887 | suitable_found = True | |
888 | ||
889 | # Extract information from URL and process it | |
890 | ie.extract(url) | |
891 | ||
892 | # Suitable InfoExtractor had been found; go to next URL | |
893 | break | |
894 | ||
895 | if not suitable_found: | |
896 | self.trouble(u'ERROR: no suitable InfoExtractor: %s' % url) | |
897 | ||
898 | return self._download_retcode | |
899 | ||
900 | def post_process(self, filename, ie_info): | |
901 | """Run the postprocessing chain on the given file.""" | |
902 | info = dict(ie_info) | |
903 | info['filepath'] = filename | |
904 | for pp in self._pps: | |
905 | info = pp.run(info) | |
906 | if info is None: | |
907 | break | |
908 | ||
909 | def _download_with_rtmpdump(self, filename, url, player_url): | |
910 | self.report_destination(filename) | |
911 | tmpfilename = self.temp_name(filename) | |
912 | ||
913 | # Check for rtmpdump first | |
914 | try: | |
915 | subprocess.call(['rtmpdump', '-h'], stdout=(file(os.path.devnull, 'w')), stderr=subprocess.STDOUT) | |
916 | except (OSError, IOError): | |
917 | self.trouble(u'ERROR: RTMP download detected but "rtmpdump" could not be run') | |
918 | return False | |
919 | ||
920 | # Download using rtmpdump. rtmpdump returns exit code 2 when | |
921 | # the connection was interrumpted and resuming appears to be | |
922 | # possible. This is part of rtmpdump's normal usage, AFAIK. | |
923 | basic_args = ['rtmpdump', '-q'] + [[], ['-W', player_url]][player_url is not None] + ['-r', url, '-o', tmpfilename] | |
871dbd3c | 924 | args = basic_args + [[], ['-e', '-k', '1']][self.params.get('continuedl', False)] |
ff3a2b8e | 925 | if self.params.get('verbose', False): |
871dbd3c PH |
926 | try: |
927 | import pipes | |
928 | shell_quote = lambda args: ' '.join(map(pipes.quote, args)) | |
929 | except ImportError: | |
930 | shell_quote = repr | |
931 | self.to_screen(u'[debug] rtmpdump command line: ' + shell_quote(args)) | |
932 | retval = subprocess.call(args) | |
235b3ba4 | 933 | while retval == 2 or retval == 1: |
fefb166c | 934 | prevsize = os.path.getsize(_encodeFilename(tmpfilename)) |
235b3ba4 PH |
935 | self.to_screen(u'\r[rtmpdump] %s bytes' % prevsize, skip_eol=True) |
936 | time.sleep(5.0) # This seems to be needed | |
937 | retval = subprocess.call(basic_args + ['-e'] + [[], ['-k', '1']][retval == 1]) | |
fefb166c | 938 | cursize = os.path.getsize(_encodeFilename(tmpfilename)) |
235b3ba4 PH |
939 | if prevsize == cursize and retval == 1: |
940 | break | |
941 | # Some rtmp streams seem abort after ~ 99.8%. Don't complain for those | |
942 | if prevsize == cursize and retval == 2 and cursize > 1024: | |
943 | self.to_screen(u'\r[rtmpdump] Could not download the whole video. This can happen for some advertisements.') | |
944 | retval = 0 | |
945 | break | |
946 | if retval == 0: | |
fefb166c | 947 | self.to_screen(u'\r[rtmpdump] %s bytes' % os.path.getsize(_encodeFilename(tmpfilename))) |
235b3ba4 PH |
948 | self.try_rename(tmpfilename, filename) |
949 | return True | |
950 | else: | |
951 | self.trouble(u'\nERROR: rtmpdump exited with code %d' % retval) | |
952 | return False | |
953 | ||
954 | def _do_download(self, filename, info_dict): | |
955 | url = info_dict['url'] | |
956 | player_url = info_dict.get('player_url', None) | |
957 | ||
958 | # Check file already present | |
fefb166c | 959 | if self.params.get('continuedl', False) and os.path.isfile(_encodeFilename(filename)) and not self.params.get('nopart', False): |
235b3ba4 PH |
960 | self.report_file_already_downloaded(filename) |
961 | return True | |
962 | ||
963 | # Attempt to download using rtmpdump | |
964 | if url.startswith('rtmp'): | |
965 | return self._download_with_rtmpdump(filename, url, player_url) | |
966 | ||
967 | tmpfilename = self.temp_name(filename) | |
968 | stream = None | |
969 | ||
970 | # Do not include the Accept-Encoding header | |
971 | headers = {'Youtubedl-no-compression': 'True'} | |
972 | basic_request = urllib2.Request(url, None, headers) | |
973 | request = urllib2.Request(url, None, headers) | |
974 | ||
975 | # Establish possible resume length | |
fefb166c PH |
976 | if os.path.isfile(_encodeFilename(tmpfilename)): |
977 | resume_len = os.path.getsize(_encodeFilename(tmpfilename)) | |
235b3ba4 PH |
978 | else: |
979 | resume_len = 0 | |
980 | ||
981 | open_mode = 'wb' | |
982 | if resume_len != 0: | |
983 | if self.params.get('continuedl', False): | |
984 | self.report_resuming_byte(resume_len) | |
985 | request.add_header('Range','bytes=%d-' % resume_len) | |
986 | open_mode = 'ab' | |
987 | else: | |
988 | resume_len = 0 | |
989 | ||
990 | count = 0 | |
991 | retries = self.params.get('retries', 0) | |
992 | while count <= retries: | |
993 | # Establish connection | |
994 | try: | |
995 | if count == 0 and 'urlhandle' in info_dict: | |
996 | data = info_dict['urlhandle'] | |
997 | data = urllib2.urlopen(request) | |
998 | break | |
999 | except (urllib2.HTTPError, ), err: | |
1000 | if (err.code < 500 or err.code >= 600) and err.code != 416: | |
1001 | # Unexpected HTTP error | |
1002 | raise | |
1003 | elif err.code == 416: | |
1004 | # Unable to resume (requested range not satisfiable) | |
1005 | try: | |
1006 | # Open the connection again without the range header | |
1007 | data = urllib2.urlopen(basic_request) | |
1008 | content_length = data.info()['Content-Length'] | |
1009 | except (urllib2.HTTPError, ), err: | |
1010 | if err.code < 500 or err.code >= 600: | |
1011 | raise | |
1012 | else: | |
1013 | # Examine the reported length | |
1014 | if (content_length is not None and | |
1015 | (resume_len - 100 < long(content_length) < resume_len + 100)): | |
1016 | # The file had already been fully downloaded. | |
1017 | # Explanation to the above condition: in issue #175 it was revealed that | |
1018 | # YouTube sometimes adds or removes a few bytes from the end of the file, | |
1019 | # changing the file size slightly and causing problems for some users. So | |
1020 | # I decided to implement a suggested change and consider the file | |
1021 | # completely downloaded if the file size differs less than 100 bytes from | |
1022 | # the one in the hard drive. | |
1023 | self.report_file_already_downloaded(filename) | |
1024 | self.try_rename(tmpfilename, filename) | |
1025 | return True | |
1026 | else: | |
1027 | # The length does not match, we start the download over | |
1028 | self.report_unable_to_resume() | |
1029 | open_mode = 'wb' | |
1030 | break | |
1031 | # Retry | |
1032 | count += 1 | |
1033 | if count <= retries: | |
1034 | self.report_retry(count, retries) | |
1035 | ||
1036 | if count > retries: | |
1037 | self.trouble(u'ERROR: giving up after %s retries' % retries) | |
1038 | return False | |
1039 | ||
1040 | data_len = data.info().get('Content-length', None) | |
1041 | if data_len is not None: | |
1042 | data_len = long(data_len) + resume_len | |
1043 | data_len_str = self.format_bytes(data_len) | |
1044 | byte_counter = 0 + resume_len | |
1045 | block_size = 1024 | |
1046 | start = time.time() | |
1047 | while True: | |
1048 | # Download and write | |
1049 | before = time.time() | |
1050 | data_block = data.read(block_size) | |
1051 | after = time.time() | |
1052 | if len(data_block) == 0: | |
1053 | break | |
1054 | byte_counter += len(data_block) | |
1055 | ||
1056 | # Open file just in time | |
1057 | if stream is None: | |
1058 | try: | |
1059 | (stream, tmpfilename) = sanitize_open(tmpfilename, open_mode) | |
1060 | assert stream is not None | |
1061 | filename = self.undo_temp_name(tmpfilename) | |
1062 | self.report_destination(filename) | |
1063 | except (OSError, IOError), err: | |
1064 | self.trouble(u'ERROR: unable to open for writing: %s' % str(err)) | |
1065 | return False | |
1066 | try: | |
1067 | stream.write(data_block) | |
1068 | except (IOError, OSError), err: | |
1069 | self.trouble(u'\nERROR: unable to write data: %s' % str(err)) | |
1070 | return False | |
1071 | block_size = self.best_block_size(after - before, len(data_block)) | |
1072 | ||
1073 | # Progress message | |
1074 | speed_str = self.calc_speed(start, time.time(), byte_counter - resume_len) | |
1075 | if data_len is None: | |
1076 | self.report_progress('Unknown %', data_len_str, speed_str, 'Unknown ETA') | |
1077 | else: | |
1078 | percent_str = self.calc_percent(byte_counter, data_len) | |
1079 | eta_str = self.calc_eta(start, time.time(), data_len - resume_len, byte_counter - resume_len) | |
1080 | self.report_progress(percent_str, data_len_str, speed_str, eta_str) | |
1081 | ||
1082 | # Apply rate limit | |
1083 | self.slow_down(start, byte_counter - resume_len) | |
1084 | ||
1085 | if stream is None: | |
1086 | self.trouble(u'\nERROR: Did not get any data blocks') | |
1087 | return False | |
1088 | stream.close() | |
1089 | self.report_finish() | |
1090 | if data_len is not None and byte_counter != data_len: | |
1091 | raise ContentTooShortError(byte_counter, long(data_len)) | |
1092 | self.try_rename(tmpfilename, filename) | |
1093 | ||
1094 | # Update file modification time | |
1095 | if self.params.get('updatetime', True): | |
1096 | info_dict['filetime'] = self.try_utime(filename, data.info().get('last-modified', None)) | |
1097 | ||
1098 | return True | |
1099 | ||
1100 | ||
1101 | class InfoExtractor(object): | |
1102 | """Information Extractor class. | |
1103 | ||
1104 | Information extractors are the classes that, given a URL, extract | |
1105 | information from the video (or videos) the URL refers to. This | |
1106 | information includes the real video URL, the video title and simplified | |
1107 | title, author and others. The information is stored in a dictionary | |
1108 | which is then passed to the FileDownloader. The FileDownloader | |
1109 | processes this information possibly downloading the video to the file | |
1110 | system, among other possible outcomes. The dictionaries must include | |
1111 | the following fields: | |
1112 | ||
1113 | id: Video identifier. | |
1114 | url: Final video URL. | |
1115 | uploader: Nickname of the video uploader. | |
1116 | title: Literal title. | |
1117 | stitle: Simplified title. | |
1118 | ext: Video filename extension. | |
1119 | format: Video format. | |
1120 | player_url: SWF Player URL (may be None). | |
1121 | ||
1122 | The following fields are optional. Their primary purpose is to allow | |
1123 | youtube-dl to serve as the backend for a video search function, such | |
1124 | as the one in youtube2mp3. They are only used when their respective | |
1125 | forced printing functions are called: | |
1126 | ||
1127 | thumbnail: Full URL to a video thumbnail image. | |
1128 | description: One-line video description. | |
1129 | ||
1130 | Subclasses of this one should re-define the _real_initialize() and | |
1131 | _real_extract() methods and define a _VALID_URL regexp. | |
1132 | Probably, they should also be added to the list of extractors. | |
1133 | """ | |
1134 | ||
1135 | _ready = False | |
1136 | _downloader = None | |
1137 | ||
1138 | def __init__(self, downloader=None): | |
1139 | """Constructor. Receives an optional downloader.""" | |
1140 | self._ready = False | |
1141 | self.set_downloader(downloader) | |
1142 | ||
1143 | def suitable(self, url): | |
1144 | """Receives a URL and returns True if suitable for this IE.""" | |
1145 | return re.match(self._VALID_URL, url) is not None | |
1146 | ||
1147 | def initialize(self): | |
1148 | """Initializes an instance (authentication, etc).""" | |
1149 | if not self._ready: | |
1150 | self._real_initialize() | |
1151 | self._ready = True | |
1152 | ||
1153 | def extract(self, url): | |
1154 | """Extracts URL information and returns it in list of dicts.""" | |
1155 | self.initialize() | |
1156 | return self._real_extract(url) | |
1157 | ||
1158 | def set_downloader(self, downloader): | |
1159 | """Sets the downloader for this IE.""" | |
1160 | self._downloader = downloader | |
1161 | ||
1162 | def _real_initialize(self): | |
1163 | """Real initialization process. Redefine in subclasses.""" | |
1164 | pass | |
1165 | ||
1166 | def _real_extract(self, url): | |
1167 | """Real extraction process. Redefine in subclasses.""" | |
1168 | pass | |
1169 | ||
1170 | ||
1171 | class YoutubeIE(InfoExtractor): | |
1172 | """Information extractor for youtube.com.""" | |
1173 | ||
1174 | _VALID_URL = r'^((?:https?://)?(?:youtu\.be/|(?:\w+\.)?youtube(?:-nocookie)?\.com/)(?!view_play_list|my_playlists|artist|playlist)(?:(?:(?:v|embed|e)/)|(?:(?:watch(?:_popup)?(?:\.php)?)?(?:\?|#!?)(?:.+&)?v=))?)?([0-9A-Za-z_-]+)(?(1).+)?$' | |
1175 | _LANG_URL = r'http://www.youtube.com/?hl=en&persist_hl=1&gl=US&persist_gl=1&opt_out_ackd=1' | |
1176 | _LOGIN_URL = 'https://www.youtube.com/signup?next=/&gl=US&hl=en' | |
1177 | _AGE_URL = 'http://www.youtube.com/verify_age?next_url=/&gl=US&hl=en' | |
1178 | _NETRC_MACHINE = 'youtube' | |
1179 | # Listed in order of quality | |
1180 | _available_formats = ['38', '37', '22', '45', '35', '44', '34', '18', '43', '6', '5', '17', '13'] | |
23e6b8ad | 1181 | _available_formats_prefer_free = ['38', '37', '45', '22', '44', '35', '43', '34', '18', '6', '5', '17', '13'] |
235b3ba4 PH |
1182 | _video_extensions = { |
1183 | '13': '3gp', | |
1184 | '17': 'mp4', | |
1185 | '18': 'mp4', | |
1186 | '22': 'mp4', | |
1187 | '37': 'mp4', | |
1188 | '38': 'video', # You actually don't know if this will be MOV, AVI or whatever | |
1189 | '43': 'webm', | |
1190 | '44': 'webm', | |
1191 | '45': 'webm', | |
1192 | } | |
1193 | _video_dimensions = { | |
1194 | '5': '240x400', | |
1195 | '6': '???', | |
1196 | '13': '???', | |
1197 | '17': '144x176', | |
1198 | '18': '360x640', | |
1199 | '22': '720x1280', | |
1200 | '34': '360x640', | |
1201 | '35': '480x854', | |
1202 | '37': '1080x1920', | |
1203 | '38': '3072x4096', | |
1204 | '43': '360x640', | |
1205 | '44': '480x854', | |
1206 | '45': '720x1280', | |
1207 | } | |
1208 | IE_NAME = u'youtube' | |
1209 | ||
1210 | def report_lang(self): | |
1211 | """Report attempt to set language.""" | |
1212 | self._downloader.to_screen(u'[youtube] Setting language') | |
1213 | ||
1214 | def report_login(self): | |
1215 | """Report attempt to log in.""" | |
1216 | self._downloader.to_screen(u'[youtube] Logging in') | |
1217 | ||
1218 | def report_age_confirmation(self): | |
1219 | """Report attempt to confirm age.""" | |
1220 | self._downloader.to_screen(u'[youtube] Confirming age') | |
1221 | ||
1222 | def report_video_webpage_download(self, video_id): | |
1223 | """Report attempt to download video webpage.""" | |
1224 | self._downloader.to_screen(u'[youtube] %s: Downloading video webpage' % video_id) | |
1225 | ||
1226 | def report_video_info_webpage_download(self, video_id): | |
1227 | """Report attempt to download video info webpage.""" | |
1228 | self._downloader.to_screen(u'[youtube] %s: Downloading video info webpage' % video_id) | |
1229 | ||
a0432a1e FV |
1230 | def report_video_subtitles_download(self, video_id): |
1231 | """Report attempt to download video info webpage.""" | |
1232 | self._downloader.to_screen(u'[youtube] %s: Downloading video subtitles' % video_id) | |
1233 | ||
235b3ba4 PH |
1234 | def report_information_extraction(self, video_id): |
1235 | """Report attempt to extract video information.""" | |
1236 | self._downloader.to_screen(u'[youtube] %s: Extracting video information' % video_id) | |
1237 | ||
1238 | def report_unavailable_format(self, video_id, format): | |
1239 | """Report extracted video URL.""" | |
1240 | self._downloader.to_screen(u'[youtube] %s: Format %s not available' % (video_id, format)) | |
1241 | ||
1242 | def report_rtmp_download(self): | |
1243 | """Indicate the download will use the RTMP protocol.""" | |
1244 | self._downloader.to_screen(u'[youtube] RTMP download detected') | |
1245 | ||
a0432a1e FV |
1246 | def _closed_captions_xml_to_srt(self, xml_string): |
1247 | srt = '' | |
1248 | texts = re.findall(r'<text start="([\d\.]+)"( dur="([\d\.]+)")?>([^<]+)</text>', xml_string, re.MULTILINE) | |
1249 | # TODO parse xml instead of regex | |
1250 | for n, (start, dur_tag, dur, caption) in enumerate(texts): | |
1251 | if not dur: dur = '4' | |
1252 | start = float(start) | |
1253 | end = start + float(dur) | |
1254 | start = "%02i:%02i:%02i,%03i" %(start/(60*60), start/60%60, start%60, start%1*1000) | |
1255 | end = "%02i:%02i:%02i,%03i" %(end/(60*60), end/60%60, end%60, end%1*1000) | |
1256 | caption = re.sub(ur'(?u)&(.+?);', htmlentity_transform, caption) | |
1257 | caption = re.sub(ur'(?u)&(.+?);', htmlentity_transform, caption) # double cycle, inentional | |
1258 | srt += str(n) + '\n' | |
1259 | srt += start + ' --> ' + end + '\n' | |
1260 | srt += caption + '\n\n' | |
1261 | return srt | |
1262 | ||
235b3ba4 PH |
1263 | def _print_formats(self, formats): |
1264 | print 'Available formats:' | |
1265 | for x in formats: | |
1266 | print '%s\t:\t%s\t[%s]' %(x, self._video_extensions.get(x, 'flv'), self._video_dimensions.get(x, '???')) | |
1267 | ||
1268 | def _real_initialize(self): | |
1269 | if self._downloader is None: | |
1270 | return | |
1271 | ||
1272 | username = None | |
1273 | password = None | |
1274 | downloader_params = self._downloader.params | |
1275 | ||
1276 | # Attempt to use provided username and password or .netrc data | |
1277 | if downloader_params.get('username', None) is not None: | |
1278 | username = downloader_params['username'] | |
1279 | password = downloader_params['password'] | |
1280 | elif downloader_params.get('usenetrc', False): | |
1281 | try: | |
1282 | info = netrc.netrc().authenticators(self._NETRC_MACHINE) | |
1283 | if info is not None: | |
1284 | username = info[0] | |
1285 | password = info[2] | |
1286 | else: | |
1287 | raise netrc.NetrcParseError('No authenticators for %s' % self._NETRC_MACHINE) | |
1288 | except (IOError, netrc.NetrcParseError), err: | |
1289 | self._downloader.to_stderr(u'WARNING: parsing .netrc: %s' % str(err)) | |
1290 | return | |
1291 | ||
1292 | # Set language | |
1293 | request = urllib2.Request(self._LANG_URL) | |
1294 | try: | |
1295 | self.report_lang() | |
1296 | urllib2.urlopen(request).read() | |
1297 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
1298 | self._downloader.to_stderr(u'WARNING: unable to set language: %s' % str(err)) | |
1299 | return | |
1300 | ||
1301 | # No authentication to be performed | |
1302 | if username is None: | |
1303 | return | |
1304 | ||
1305 | # Log in | |
1306 | login_form = { | |
1307 | 'current_form': 'loginForm', | |
1308 | 'next': '/', | |
1309 | 'action_login': 'Log In', | |
1310 | 'username': username, | |
1311 | 'password': password, | |
1312 | } | |
1313 | request = urllib2.Request(self._LOGIN_URL, urllib.urlencode(login_form)) | |
1314 | try: | |
1315 | self.report_login() | |
1316 | login_results = urllib2.urlopen(request).read() | |
1317 | if re.search(r'(?i)<form[^>]* name="loginForm"', login_results) is not None: | |
1318 | self._downloader.to_stderr(u'WARNING: unable to log in: bad username or password') | |
1319 | return | |
1320 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
1321 | self._downloader.to_stderr(u'WARNING: unable to log in: %s' % str(err)) | |
1322 | return | |
1323 | ||
1324 | # Confirm age | |
1325 | age_form = { | |
1326 | 'next_url': '/', | |
1327 | 'action_confirm': 'Confirm', | |
1328 | } | |
1329 | request = urllib2.Request(self._AGE_URL, urllib.urlencode(age_form)) | |
1330 | try: | |
1331 | self.report_age_confirmation() | |
1332 | age_results = urllib2.urlopen(request).read() | |
1333 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
1334 | self._downloader.trouble(u'ERROR: unable to confirm age: %s' % str(err)) | |
1335 | return | |
1336 | ||
1337 | def _real_extract(self, url): | |
1338 | # Extract video id from URL | |
1339 | mobj = re.match(self._VALID_URL, url) | |
1340 | if mobj is None: | |
1341 | self._downloader.trouble(u'ERROR: invalid URL: %s' % url) | |
1342 | return | |
1343 | video_id = mobj.group(2) | |
1344 | ||
1345 | # Get video webpage | |
1346 | self.report_video_webpage_download(video_id) | |
1347 | request = urllib2.Request('http://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1' % video_id) | |
1348 | try: | |
1349 | video_webpage = urllib2.urlopen(request).read() | |
1350 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
1351 | self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % str(err)) | |
1352 | return | |
1353 | ||
1354 | # Attempt to extract SWF player URL | |
1355 | mobj = re.search(r'swfConfig.*?"(http:\\/\\/.*?watch.*?-.*?\.swf)"', video_webpage) | |
1356 | if mobj is not None: | |
1357 | player_url = re.sub(r'\\(.)', r'\1', mobj.group(1)) | |
1358 | else: | |
1359 | player_url = None | |
1360 | ||
1361 | # Get video info | |
1362 | self.report_video_info_webpage_download(video_id) | |
1363 | for el_type in ['&el=embedded', '&el=detailpage', '&el=vevo', '']: | |
1364 | video_info_url = ('http://www.youtube.com/get_video_info?&video_id=%s%s&ps=default&eurl=&gl=US&hl=en' | |
1365 | % (video_id, el_type)) | |
1366 | request = urllib2.Request(video_info_url) | |
1367 | try: | |
1368 | video_info_webpage = urllib2.urlopen(request).read() | |
1369 | video_info = parse_qs(video_info_webpage) | |
1370 | if 'token' in video_info: | |
1371 | break | |
1372 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
1373 | self._downloader.trouble(u'ERROR: unable to download video info webpage: %s' % str(err)) | |
1374 | return | |
1375 | if 'token' not in video_info: | |
1376 | if 'reason' in video_info: | |
1377 | self._downloader.trouble(u'ERROR: YouTube said: %s' % video_info['reason'][0].decode('utf-8')) | |
1378 | else: | |
1379 | self._downloader.trouble(u'ERROR: "token" parameter not in video info for unknown reason') | |
1380 | return | |
1381 | ||
1382 | # Start extracting information | |
1383 | self.report_information_extraction(video_id) | |
1384 | ||
1385 | # uploader | |
1386 | if 'author' not in video_info: | |
1387 | self._downloader.trouble(u'ERROR: unable to extract uploader nickname') | |
1388 | return | |
1389 | video_uploader = urllib.unquote_plus(video_info['author'][0]) | |
1390 | ||
1391 | # title | |
1392 | if 'title' not in video_info: | |
1393 | self._downloader.trouble(u'ERROR: unable to extract video title') | |
1394 | return | |
1395 | video_title = urllib.unquote_plus(video_info['title'][0]) | |
1396 | video_title = video_title.decode('utf-8') | |
1397 | video_title = sanitize_title(video_title) | |
1398 | ||
1399 | # simplified title | |
e092418d | 1400 | simple_title = _simplify_title(video_title) |
235b3ba4 PH |
1401 | |
1402 | # thumbnail image | |
1403 | if 'thumbnail_url' not in video_info: | |
1404 | self._downloader.trouble(u'WARNING: unable to extract video thumbnail') | |
1405 | video_thumbnail = '' | |
1406 | else: # don't panic if we can't find it | |
1407 | video_thumbnail = urllib.unquote_plus(video_info['thumbnail_url'][0]) | |
1408 | ||
1409 | # upload date | |
1410 | upload_date = u'NA' | |
1411 | mobj = re.search(r'id="eow-date.*?>(.*?)</span>', video_webpage, re.DOTALL) | |
1412 | if mobj is not None: | |
1413 | upload_date = ' '.join(re.sub(r'[/,-]', r' ', mobj.group(1)).split()) | |
1414 | format_expressions = ['%d %B %Y', '%B %d %Y', '%b %d %Y'] | |
1415 | for expression in format_expressions: | |
1416 | try: | |
1417 | upload_date = datetime.datetime.strptime(upload_date, expression).strftime('%Y%m%d') | |
1418 | except: | |
1419 | pass | |
1420 | ||
1421 | # description | |
1422 | try: | |
1423 | lxml.etree | |
1424 | except NameError: | |
1425 | video_description = u'No description available.' | |
ff3a2b8e PH |
1426 | mobj = re.search(r'<meta name="description" content="(.*?)">', video_webpage) |
1427 | if mobj is not None: | |
1428 | video_description = mobj.group(1).decode('utf-8') | |
235b3ba4 PH |
1429 | else: |
1430 | html_parser = lxml.etree.HTMLParser(encoding='utf-8') | |
1431 | vwebpage_doc = lxml.etree.parse(StringIO.StringIO(video_webpage), html_parser) | |
1432 | video_description = u''.join(vwebpage_doc.xpath('id("eow-description")//text()')) | |
1433 | # TODO use another parser | |
a0432a1e FV |
1434 | |
1435 | # closed captions | |
1436 | video_subtitles = None | |
1437 | if self._downloader.params.get('writesubtitles', False): | |
1438 | self.report_video_subtitles_download(video_id) | |
1439 | request = urllib2.Request('http://video.google.com/timedtext?hl=en&type=list&v=%s' % video_id) | |
1440 | try: | |
1441 | srt_list = urllib2.urlopen(request).read() | |
1442 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
1443 | self._downloader.trouble(u'WARNING: unable to download video subtitles: %s' % str(err)) | |
1444 | else: | |
1445 | srt_lang_list = re.findall(r'lang_code="([\w\-]+)"', srt_list) | |
1446 | if srt_lang_list: | |
1447 | if self._downloader.params.get('subtitleslang', False): | |
1448 | srt_lang = self._downloader.params.get('subtitleslang') | |
1449 | elif 'en' in srt_lang_list: | |
1450 | srt_lang = 'en' | |
1451 | else: | |
1452 | srt_lang = srt_lang_list[0] | |
1453 | if not srt_lang in srt_lang_list: | |
1454 | self._downloader.trouble(u'WARNING: no closed captions found in the specified language') | |
1455 | else: | |
1456 | request = urllib2.Request('http://video.google.com/timedtext?hl=en&lang=%s&v=%s' % (srt_lang, video_id)) | |
1457 | try: | |
1458 | srt_xml = urllib2.urlopen(request).read() | |
1459 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
1460 | self._downloader.trouble(u'WARNING: unable to download video subtitles: %s' % str(err)) | |
1461 | else: | |
1462 | video_subtitles = self._closed_captions_xml_to_srt(srt_xml.decode('utf-8')) | |
1463 | else: | |
1464 | self._downloader.trouble(u'WARNING: video has no closed captions') | |
235b3ba4 PH |
1465 | |
1466 | # token | |
1467 | video_token = urllib.unquote_plus(video_info['token'][0]) | |
1468 | ||
1469 | # Decide which formats to download | |
1470 | req_format = self._downloader.params.get('format', None) | |
1471 | ||
1472 | if 'conn' in video_info and video_info['conn'][0].startswith('rtmp'): | |
1473 | self.report_rtmp_download() | |
1474 | video_url_list = [(None, video_info['conn'][0])] | |
1475 | elif 'url_encoded_fmt_stream_map' in video_info and len(video_info['url_encoded_fmt_stream_map']) >= 1: | |
1476 | url_data_strs = video_info['url_encoded_fmt_stream_map'][0].split(',') | |
1477 | url_data = [parse_qs(uds) for uds in url_data_strs] | |
1478 | url_data = filter(lambda ud: 'itag' in ud and 'url' in ud, url_data) | |
1479 | url_map = dict((ud['itag'][0], ud['url'][0]) for ud in url_data) | |
1480 | ||
1481 | format_limit = self._downloader.params.get('format_limit', None) | |
23e6b8ad PH |
1482 | available_formats = self._available_formats_prefer_free if self._downloader.params.get('prefer_free_formats', False) else self._available_formats |
1483 | if format_limit is not None and format_limit in available_formats: | |
1484 | format_list = available_formats[available_formats.index(format_limit):] | |
235b3ba4 | 1485 | else: |
23e6b8ad | 1486 | format_list = available_formats |
235b3ba4 PH |
1487 | existing_formats = [x for x in format_list if x in url_map] |
1488 | if len(existing_formats) == 0: | |
1489 | self._downloader.trouble(u'ERROR: no known formats available for video') | |
1490 | return | |
1491 | if self._downloader.params.get('listformats', None): | |
1492 | self._print_formats(existing_formats) | |
1493 | return | |
1494 | if req_format is None or req_format == 'best': | |
1495 | video_url_list = [(existing_formats[0], url_map[existing_formats[0]])] # Best quality | |
1496 | elif req_format == 'worst': | |
1497 | video_url_list = [(existing_formats[len(existing_formats)-1], url_map[existing_formats[len(existing_formats)-1]])] # worst quality | |
1498 | elif req_format in ('-1', 'all'): | |
1499 | video_url_list = [(f, url_map[f]) for f in existing_formats] # All formats | |
1500 | else: | |
1501 | # Specific formats. We pick the first in a slash-delimeted sequence. | |
1502 | # For example, if '1/2/3/4' is requested and '2' and '4' are available, we pick '2'. | |
1503 | req_formats = req_format.split('/') | |
1504 | video_url_list = None | |
1505 | for rf in req_formats: | |
1506 | if rf in url_map: | |
1507 | video_url_list = [(rf, url_map[rf])] | |
1508 | break | |
1509 | if video_url_list is None: | |
1510 | self._downloader.trouble(u'ERROR: requested format not available') | |
1511 | return | |
1512 | else: | |
1513 | self._downloader.trouble(u'ERROR: no conn or url_encoded_fmt_stream_map information found in video info') | |
1514 | return | |
1515 | ||
1516 | for format_param, video_real_url in video_url_list: | |
1517 | # At this point we have a new video | |
1518 | self._downloader.increment_downloads() | |
1519 | ||
1520 | # Extension | |
1521 | video_extension = self._video_extensions.get(format_param, 'flv') | |
1522 | ||
1523 | try: | |
1524 | # Process video information | |
1525 | self._downloader.process_info({ | |
1526 | 'id': video_id.decode('utf-8'), | |
1527 | 'url': video_real_url.decode('utf-8'), | |
1528 | 'uploader': video_uploader.decode('utf-8'), | |
1529 | 'upload_date': upload_date, | |
1530 | 'title': video_title, | |
1531 | 'stitle': simple_title, | |
1532 | 'ext': video_extension.decode('utf-8'), | |
1533 | 'format': (format_param is None and u'NA' or format_param.decode('utf-8')), | |
1534 | 'thumbnail': video_thumbnail.decode('utf-8'), | |
1535 | 'description': video_description, | |
1536 | 'player_url': player_url, | |
a0432a1e | 1537 | 'subtitles': video_subtitles |
235b3ba4 PH |
1538 | }) |
1539 | except UnavailableVideoError, err: | |
1540 | self._downloader.trouble(u'\nERROR: unable to download video') | |
1541 | ||
1542 | ||
1543 | class MetacafeIE(InfoExtractor): | |
1544 | """Information Extractor for metacafe.com.""" | |
1545 | ||
1546 | _VALID_URL = r'(?:http://)?(?:www\.)?metacafe\.com/watch/([^/]+)/([^/]+)/.*' | |
1547 | _DISCLAIMER = 'http://www.metacafe.com/family_filter/' | |
1548 | _FILTER_POST = 'http://www.metacafe.com/f/index.php?inputType=filter&controllerGroup=user' | |
1549 | _youtube_ie = None | |
1550 | IE_NAME = u'metacafe' | |
1551 | ||
1552 | def __init__(self, youtube_ie, downloader=None): | |
1553 | InfoExtractor.__init__(self, downloader) | |
1554 | self._youtube_ie = youtube_ie | |
1555 | ||
1556 | def report_disclaimer(self): | |
1557 | """Report disclaimer retrieval.""" | |
1558 | self._downloader.to_screen(u'[metacafe] Retrieving disclaimer') | |
1559 | ||
1560 | def report_age_confirmation(self): | |
1561 | """Report attempt to confirm age.""" | |
1562 | self._downloader.to_screen(u'[metacafe] Confirming age') | |
1563 | ||
1564 | def report_download_webpage(self, video_id): | |
1565 | """Report webpage download.""" | |
1566 | self._downloader.to_screen(u'[metacafe] %s: Downloading webpage' % video_id) | |
1567 | ||
1568 | def report_extraction(self, video_id): | |
1569 | """Report information extraction.""" | |
1570 | self._downloader.to_screen(u'[metacafe] %s: Extracting information' % video_id) | |
1571 | ||
1572 | def _real_initialize(self): | |
1573 | # Retrieve disclaimer | |
1574 | request = urllib2.Request(self._DISCLAIMER) | |
1575 | try: | |
1576 | self.report_disclaimer() | |
1577 | disclaimer = urllib2.urlopen(request).read() | |
1578 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
1579 | self._downloader.trouble(u'ERROR: unable to retrieve disclaimer: %s' % str(err)) | |
1580 | return | |
1581 | ||
1582 | # Confirm age | |
1583 | disclaimer_form = { | |
1584 | 'filters': '0', | |
1585 | 'submit': "Continue - I'm over 18", | |
1586 | } | |
1587 | request = urllib2.Request(self._FILTER_POST, urllib.urlencode(disclaimer_form)) | |
1588 | try: | |
1589 | self.report_age_confirmation() | |
1590 | disclaimer = urllib2.urlopen(request).read() | |
1591 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
1592 | self._downloader.trouble(u'ERROR: unable to confirm age: %s' % str(err)) | |
1593 | return | |
1594 | ||
1595 | def _real_extract(self, url): | |
1596 | # Extract id and simplified title from URL | |
1597 | mobj = re.match(self._VALID_URL, url) | |
1598 | if mobj is None: | |
1599 | self._downloader.trouble(u'ERROR: invalid URL: %s' % url) | |
1600 | return | |
1601 | ||
1602 | video_id = mobj.group(1) | |
1603 | ||
1604 | # Check if video comes from YouTube | |
1605 | mobj2 = re.match(r'^yt-(.*)$', video_id) | |
1606 | if mobj2 is not None: | |
1607 | self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % mobj2.group(1)) | |
1608 | return | |
1609 | ||
1610 | # At this point we have a new video | |
1611 | self._downloader.increment_downloads() | |
1612 | ||
1613 | simple_title = mobj.group(2).decode('utf-8') | |
1614 | ||
1615 | # Retrieve video webpage to extract further information | |
1616 | request = urllib2.Request('http://www.metacafe.com/watch/%s/' % video_id) | |
1617 | try: | |
1618 | self.report_download_webpage(video_id) | |
1619 | webpage = urllib2.urlopen(request).read() | |
1620 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
1621 | self._downloader.trouble(u'ERROR: unable retrieve video webpage: %s' % str(err)) | |
1622 | return | |
1623 | ||
1624 | # Extract URL, uploader and title from webpage | |
1625 | self.report_extraction(video_id) | |
1626 | mobj = re.search(r'(?m)&mediaURL=([^&]+)', webpage) | |
1627 | if mobj is not None: | |
1628 | mediaURL = urllib.unquote(mobj.group(1)) | |
1629 | video_extension = mediaURL[-3:] | |
1630 | ||
1631 | # Extract gdaKey if available | |
1632 | mobj = re.search(r'(?m)&gdaKey=(.*?)&', webpage) | |
1633 | if mobj is None: | |
1634 | video_url = mediaURL | |
1635 | else: | |
1636 | gdaKey = mobj.group(1) | |
1637 | video_url = '%s?__gda__=%s' % (mediaURL, gdaKey) | |
1638 | else: | |
1639 | mobj = re.search(r' name="flashvars" value="(.*?)"', webpage) | |
1640 | if mobj is None: | |
1641 | self._downloader.trouble(u'ERROR: unable to extract media URL') | |
1642 | return | |
1643 | vardict = parse_qs(mobj.group(1)) | |
1644 | if 'mediaData' not in vardict: | |
1645 | self._downloader.trouble(u'ERROR: unable to extract media URL') | |
1646 | return | |
1647 | mobj = re.search(r'"mediaURL":"(http.*?)","key":"(.*?)"', vardict['mediaData'][0]) | |
1648 | if mobj is None: | |
1649 | self._downloader.trouble(u'ERROR: unable to extract media URL') | |
1650 | return | |
1651 | mediaURL = mobj.group(1).replace('\\/', '/') | |
1652 | video_extension = mediaURL[-3:] | |
1653 | video_url = '%s?__gda__=%s' % (mediaURL, mobj.group(2)) | |
1654 | ||
1655 | mobj = re.search(r'(?im)<title>(.*) - Video</title>', webpage) | |
1656 | if mobj is None: | |
1657 | self._downloader.trouble(u'ERROR: unable to extract title') | |
1658 | return | |
1659 | video_title = mobj.group(1).decode('utf-8') | |
1660 | video_title = sanitize_title(video_title) | |
1661 | ||
1662 | mobj = re.search(r'(?ms)By:\s*<a .*?>(.+?)<', webpage) | |
1663 | if mobj is None: | |
1664 | self._downloader.trouble(u'ERROR: unable to extract uploader nickname') | |
1665 | return | |
1666 | video_uploader = mobj.group(1) | |
1667 | ||
1668 | try: | |
1669 | # Process video information | |
1670 | self._downloader.process_info({ | |
1671 | 'id': video_id.decode('utf-8'), | |
1672 | 'url': video_url.decode('utf-8'), | |
1673 | 'uploader': video_uploader.decode('utf-8'), | |
1674 | 'upload_date': u'NA', | |
1675 | 'title': video_title, | |
1676 | 'stitle': simple_title, | |
1677 | 'ext': video_extension.decode('utf-8'), | |
1678 | 'format': u'NA', | |
1679 | 'player_url': None, | |
1680 | }) | |
1681 | except UnavailableVideoError: | |
1682 | self._downloader.trouble(u'\nERROR: unable to download video') | |
1683 | ||
1684 | ||
1685 | class DailymotionIE(InfoExtractor): | |
1686 | """Information Extractor for Dailymotion""" | |
1687 | ||
1688 | _VALID_URL = r'(?i)(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/video/([^_/]+)_([^/]+)' | |
1689 | IE_NAME = u'dailymotion' | |
1690 | ||
1691 | def __init__(self, downloader=None): | |
1692 | InfoExtractor.__init__(self, downloader) | |
1693 | ||
1694 | def report_download_webpage(self, video_id): | |
1695 | """Report webpage download.""" | |
1696 | self._downloader.to_screen(u'[dailymotion] %s: Downloading webpage' % video_id) | |
1697 | ||
1698 | def report_extraction(self, video_id): | |
1699 | """Report information extraction.""" | |
1700 | self._downloader.to_screen(u'[dailymotion] %s: Extracting information' % video_id) | |
1701 | ||
1702 | def _real_extract(self, url): | |
1703 | # Extract id and simplified title from URL | |
1704 | mobj = re.match(self._VALID_URL, url) | |
1705 | if mobj is None: | |
1706 | self._downloader.trouble(u'ERROR: invalid URL: %s' % url) | |
1707 | return | |
1708 | ||
1709 | # At this point we have a new video | |
1710 | self._downloader.increment_downloads() | |
1711 | video_id = mobj.group(1) | |
1712 | ||
235b3ba4 PH |
1713 | video_extension = 'flv' |
1714 | ||
1715 | # Retrieve video webpage to extract further information | |
1716 | request = urllib2.Request(url) | |
1717 | request.add_header('Cookie', 'family_filter=off') | |
1718 | try: | |
1719 | self.report_download_webpage(video_id) | |
1720 | webpage = urllib2.urlopen(request).read() | |
1721 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
1722 | self._downloader.trouble(u'ERROR: unable retrieve video webpage: %s' % str(err)) | |
1723 | return | |
1724 | ||
1725 | # Extract URL, uploader and title from webpage | |
1726 | self.report_extraction(video_id) | |
1727 | mobj = re.search(r'(?i)addVariable\(\"sequence\"\s*,\s*\"([^\"]+?)\"\)', webpage) | |
1728 | if mobj is None: | |
1729 | self._downloader.trouble(u'ERROR: unable to extract media URL') | |
1730 | return | |
1731 | sequence = urllib.unquote(mobj.group(1)) | |
1732 | mobj = re.search(r',\"sdURL\"\:\"([^\"]+?)\",', sequence) | |
1733 | if mobj is None: | |
1734 | self._downloader.trouble(u'ERROR: unable to extract media URL') | |
1735 | return | |
1736 | mediaURL = urllib.unquote(mobj.group(1)).replace('\\', '') | |
1737 | ||
1738 | # if needed add http://www.dailymotion.com/ if relative URL | |
1739 | ||
1740 | video_url = mediaURL | |
1741 | ||
bb8abbbb | 1742 | mobj = re.search(r'<meta property="og:title" content="(?P<title>[^"]*)" />', webpage) |
235b3ba4 PH |
1743 | if mobj is None: |
1744 | self._downloader.trouble(u'ERROR: unable to extract title') | |
1745 | return | |
1413cd87 | 1746 | video_title = _unescapeHTML(mobj.group('title').decode('utf-8')) |
235b3ba4 | 1747 | video_title = sanitize_title(video_title) |
bb8abbbb | 1748 | simple_title = _simplify_title(video_title) |
235b3ba4 PH |
1749 | |
1750 | mobj = re.search(r'(?im)<span class="owner[^\"]+?">[^<]+?<a [^>]+?>([^<]+?)</a></span>', webpage) | |
1751 | if mobj is None: | |
1752 | self._downloader.trouble(u'ERROR: unable to extract uploader nickname') | |
1753 | return | |
1754 | video_uploader = mobj.group(1) | |
1755 | ||
1756 | try: | |
1757 | # Process video information | |
1758 | self._downloader.process_info({ | |
1759 | 'id': video_id.decode('utf-8'), | |
1760 | 'url': video_url.decode('utf-8'), | |
1761 | 'uploader': video_uploader.decode('utf-8'), | |
1762 | 'upload_date': u'NA', | |
1763 | 'title': video_title, | |
1764 | 'stitle': simple_title, | |
1765 | 'ext': video_extension.decode('utf-8'), | |
1766 | 'format': u'NA', | |
1767 | 'player_url': None, | |
1768 | }) | |
1769 | except UnavailableVideoError: | |
1770 | self._downloader.trouble(u'\nERROR: unable to download video') | |
1771 | ||
1772 | ||
1773 | class GoogleIE(InfoExtractor): | |
1774 | """Information extractor for video.google.com.""" | |
1775 | ||
1776 | _VALID_URL = r'(?:http://)?video\.google\.(?:com(?:\.au)?|co\.(?:uk|jp|kr|cr)|ca|de|es|fr|it|nl|pl)/videoplay\?docid=([^\&]+).*' | |
1777 | IE_NAME = u'video.google' | |
1778 | ||
1779 | def __init__(self, downloader=None): | |
1780 | InfoExtractor.__init__(self, downloader) | |
1781 | ||
1782 | def report_download_webpage(self, video_id): | |
1783 | """Report webpage download.""" | |
1784 | self._downloader.to_screen(u'[video.google] %s: Downloading webpage' % video_id) | |
1785 | ||
1786 | def report_extraction(self, video_id): | |
1787 | """Report information extraction.""" | |
1788 | self._downloader.to_screen(u'[video.google] %s: Extracting information' % video_id) | |
1789 | ||
1790 | def _real_extract(self, url): | |
1791 | # Extract id from URL | |
1792 | mobj = re.match(self._VALID_URL, url) | |
1793 | if mobj is None: | |
1794 | self._downloader.trouble(u'ERROR: Invalid URL: %s' % url) | |
1795 | return | |
1796 | ||
1797 | # At this point we have a new video | |
1798 | self._downloader.increment_downloads() | |
1799 | video_id = mobj.group(1) | |
1800 | ||
1801 | video_extension = 'mp4' | |
1802 | ||
1803 | # Retrieve video webpage to extract further information | |
1804 | request = urllib2.Request('http://video.google.com/videoplay?docid=%s&hl=en&oe=utf-8' % video_id) | |
1805 | try: | |
1806 | self.report_download_webpage(video_id) | |
1807 | webpage = urllib2.urlopen(request).read() | |
1808 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
1809 | self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err)) | |
1810 | return | |
1811 | ||
1812 | # Extract URL, uploader, and title from webpage | |
1813 | self.report_extraction(video_id) | |
1814 | mobj = re.search(r"download_url:'([^']+)'", webpage) | |
1815 | if mobj is None: | |
1816 | video_extension = 'flv' | |
1817 | mobj = re.search(r"(?i)videoUrl\\x3d(.+?)\\x26", webpage) | |
1818 | if mobj is None: | |
1819 | self._downloader.trouble(u'ERROR: unable to extract media URL') | |
1820 | return | |
1821 | mediaURL = urllib.unquote(mobj.group(1)) | |
1822 | mediaURL = mediaURL.replace('\\x3d', '\x3d') | |
1823 | mediaURL = mediaURL.replace('\\x26', '\x26') | |
1824 | ||
1825 | video_url = mediaURL | |
1826 | ||
1827 | mobj = re.search(r'<title>(.*)</title>', webpage) | |
1828 | if mobj is None: | |
1829 | self._downloader.trouble(u'ERROR: unable to extract title') | |
1830 | return | |
1831 | video_title = mobj.group(1).decode('utf-8') | |
1832 | video_title = sanitize_title(video_title) | |
e092418d | 1833 | simple_title = _simplify_title(video_title) |
235b3ba4 PH |
1834 | |
1835 | # Extract video description | |
1836 | mobj = re.search(r'<span id=short-desc-content>([^<]*)</span>', webpage) | |
1837 | if mobj is None: | |
1838 | self._downloader.trouble(u'ERROR: unable to extract video description') | |
1839 | return | |
1840 | video_description = mobj.group(1).decode('utf-8') | |
1841 | if not video_description: | |
1842 | video_description = 'No description available.' | |
1843 | ||
1844 | # Extract video thumbnail | |
1845 | if self._downloader.params.get('forcethumbnail', False): | |
1846 | request = urllib2.Request('http://video.google.com/videosearch?q=%s+site:video.google.com&hl=en' % abs(int(video_id))) | |
1847 | try: | |
1848 | webpage = urllib2.urlopen(request).read() | |
1849 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
1850 | self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err)) | |
1851 | return | |
1852 | mobj = re.search(r'<img class=thumbnail-img (?:.* )?src=(http.*)>', webpage) | |
1853 | if mobj is None: | |
1854 | self._downloader.trouble(u'ERROR: unable to extract video thumbnail') | |
1855 | return | |
1856 | video_thumbnail = mobj.group(1) | |
1857 | else: # we need something to pass to process_info | |
1858 | video_thumbnail = '' | |
1859 | ||
1860 | try: | |
1861 | # Process video information | |
1862 | self._downloader.process_info({ | |
1863 | 'id': video_id.decode('utf-8'), | |
1864 | 'url': video_url.decode('utf-8'), | |
1865 | 'uploader': u'NA', | |
1866 | 'upload_date': u'NA', | |
1867 | 'title': video_title, | |
1868 | 'stitle': simple_title, | |
1869 | 'ext': video_extension.decode('utf-8'), | |
1870 | 'format': u'NA', | |
1871 | 'player_url': None, | |
1872 | }) | |
1873 | except UnavailableVideoError: | |
1874 | self._downloader.trouble(u'\nERROR: unable to download video') | |
1875 | ||
1876 | ||
1877 | class PhotobucketIE(InfoExtractor): | |
1878 | """Information extractor for photobucket.com.""" | |
1879 | ||
1880 | _VALID_URL = r'(?:http://)?(?:[a-z0-9]+\.)?photobucket\.com/.*[\?\&]current=(.*\.flv)' | |
1881 | IE_NAME = u'photobucket' | |
1882 | ||
1883 | def __init__(self, downloader=None): | |
1884 | InfoExtractor.__init__(self, downloader) | |
1885 | ||
1886 | def report_download_webpage(self, video_id): | |
1887 | """Report webpage download.""" | |
1888 | self._downloader.to_screen(u'[photobucket] %s: Downloading webpage' % video_id) | |
1889 | ||
1890 | def report_extraction(self, video_id): | |
1891 | """Report information extraction.""" | |
1892 | self._downloader.to_screen(u'[photobucket] %s: Extracting information' % video_id) | |
1893 | ||
1894 | def _real_extract(self, url): | |
1895 | # Extract id from URL | |
1896 | mobj = re.match(self._VALID_URL, url) | |
1897 | if mobj is None: | |
1898 | self._downloader.trouble(u'ERROR: Invalid URL: %s' % url) | |
1899 | return | |
1900 | ||
1901 | # At this point we have a new video | |
1902 | self._downloader.increment_downloads() | |
1903 | video_id = mobj.group(1) | |
1904 | ||
1905 | video_extension = 'flv' | |
1906 | ||
1907 | # Retrieve video webpage to extract further information | |
1908 | request = urllib2.Request(url) | |
1909 | try: | |
1910 | self.report_download_webpage(video_id) | |
1911 | webpage = urllib2.urlopen(request).read() | |
1912 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
1913 | self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err)) | |
1914 | return | |
1915 | ||
1916 | # Extract URL, uploader, and title from webpage | |
1917 | self.report_extraction(video_id) | |
1918 | mobj = re.search(r'<link rel="video_src" href=".*\?file=([^"]+)" />', webpage) | |
1919 | if mobj is None: | |
1920 | self._downloader.trouble(u'ERROR: unable to extract media URL') | |
1921 | return | |
1922 | mediaURL = urllib.unquote(mobj.group(1)) | |
1923 | ||
1924 | video_url = mediaURL | |
1925 | ||
1926 | mobj = re.search(r'<title>(.*) video by (.*) - Photobucket</title>', webpage) | |
1927 | if mobj is None: | |
1928 | self._downloader.trouble(u'ERROR: unable to extract title') | |
1929 | return | |
1930 | video_title = mobj.group(1).decode('utf-8') | |
1931 | video_title = sanitize_title(video_title) | |
e092418d | 1932 | simple_title = _simplify_title(vide_title) |
235b3ba4 PH |
1933 | |
1934 | video_uploader = mobj.group(2).decode('utf-8') | |
1935 | ||
1936 | try: | |
1937 | # Process video information | |
1938 | self._downloader.process_info({ | |
1939 | 'id': video_id.decode('utf-8'), | |
1940 | 'url': video_url.decode('utf-8'), | |
1941 | 'uploader': video_uploader, | |
1942 | 'upload_date': u'NA', | |
1943 | 'title': video_title, | |
1944 | 'stitle': simple_title, | |
1945 | 'ext': video_extension.decode('utf-8'), | |
1946 | 'format': u'NA', | |
1947 | 'player_url': None, | |
1948 | }) | |
1949 | except UnavailableVideoError: | |
1950 | self._downloader.trouble(u'\nERROR: unable to download video') | |
1951 | ||
1952 | ||
1953 | class YahooIE(InfoExtractor): | |
1954 | """Information extractor for video.yahoo.com.""" | |
1955 | ||
1956 | # _VALID_URL matches all Yahoo! Video URLs | |
1957 | # _VPAGE_URL matches only the extractable '/watch/' URLs | |
1958 | _VALID_URL = r'(?:http://)?(?:[a-z]+\.)?video\.yahoo\.com/(?:watch|network)/([0-9]+)(?:/|\?v=)([0-9]+)(?:[#\?].*)?' | |
1959 | _VPAGE_URL = r'(?:http://)?video\.yahoo\.com/watch/([0-9]+)/([0-9]+)(?:[#\?].*)?' | |
1960 | IE_NAME = u'video.yahoo' | |
1961 | ||
1962 | def __init__(self, downloader=None): | |
1963 | InfoExtractor.__init__(self, downloader) | |
1964 | ||
1965 | def report_download_webpage(self, video_id): | |
1966 | """Report webpage download.""" | |
1967 | self._downloader.to_screen(u'[video.yahoo] %s: Downloading webpage' % video_id) | |
1968 | ||
1969 | def report_extraction(self, video_id): | |
1970 | """Report information extraction.""" | |
1971 | self._downloader.to_screen(u'[video.yahoo] %s: Extracting information' % video_id) | |
1972 | ||
1973 | def _real_extract(self, url, new_video=True): | |
1974 | # Extract ID from URL | |
1975 | mobj = re.match(self._VALID_URL, url) | |
1976 | if mobj is None: | |
1977 | self._downloader.trouble(u'ERROR: Invalid URL: %s' % url) | |
1978 | return | |
1979 | ||
1980 | # At this point we have a new video | |
1981 | self._downloader.increment_downloads() | |
1982 | video_id = mobj.group(2) | |
1983 | video_extension = 'flv' | |
1984 | ||
1985 | # Rewrite valid but non-extractable URLs as | |
1986 | # extractable English language /watch/ URLs | |
1987 | if re.match(self._VPAGE_URL, url) is None: | |
1988 | request = urllib2.Request(url) | |
1989 | try: | |
1990 | webpage = urllib2.urlopen(request).read() | |
1991 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
1992 | self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err)) | |
1993 | return | |
1994 | ||
1995 | mobj = re.search(r'\("id", "([0-9]+)"\);', webpage) | |
1996 | if mobj is None: | |
1997 | self._downloader.trouble(u'ERROR: Unable to extract id field') | |
1998 | return | |
1999 | yahoo_id = mobj.group(1) | |
2000 | ||
2001 | mobj = re.search(r'\("vid", "([0-9]+)"\);', webpage) | |
2002 | if mobj is None: | |
2003 | self._downloader.trouble(u'ERROR: Unable to extract vid field') | |
2004 | return | |
2005 | yahoo_vid = mobj.group(1) | |
2006 | ||
2007 | url = 'http://video.yahoo.com/watch/%s/%s' % (yahoo_vid, yahoo_id) | |
2008 | return self._real_extract(url, new_video=False) | |
2009 | ||
2010 | # Retrieve video webpage to extract further information | |
2011 | request = urllib2.Request(url) | |
2012 | try: | |
2013 | self.report_download_webpage(video_id) | |
2014 | webpage = urllib2.urlopen(request).read() | |
2015 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
2016 | self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err)) | |
2017 | return | |
2018 | ||
2019 | # Extract uploader and title from webpage | |
2020 | self.report_extraction(video_id) | |
2021 | mobj = re.search(r'<meta name="title" content="(.*)" />', webpage) | |
2022 | if mobj is None: | |
2023 | self._downloader.trouble(u'ERROR: unable to extract video title') | |
2024 | return | |
2025 | video_title = mobj.group(1).decode('utf-8') | |
e092418d | 2026 | simple_title = _simplify_title(video_title) |
235b3ba4 PH |
2027 | |
2028 | mobj = re.search(r'<h2 class="ti-5"><a href="http://video\.yahoo\.com/(people|profile)/[0-9]+" beacon=".*">(.*)</a></h2>', webpage) | |
2029 | if mobj is None: | |
2030 | self._downloader.trouble(u'ERROR: unable to extract video uploader') | |
2031 | return | |
2032 | video_uploader = mobj.group(1).decode('utf-8') | |
2033 | ||
2034 | # Extract video thumbnail | |
2035 | mobj = re.search(r'<link rel="image_src" href="(.*)" />', webpage) | |
2036 | if mobj is None: | |
2037 | self._downloader.trouble(u'ERROR: unable to extract video thumbnail') | |
2038 | return | |
2039 | video_thumbnail = mobj.group(1).decode('utf-8') | |
2040 | ||
2041 | # Extract video description | |
2042 | mobj = re.search(r'<meta name="description" content="(.*)" />', webpage) | |
2043 | if mobj is None: | |
2044 | self._downloader.trouble(u'ERROR: unable to extract video description') | |
2045 | return | |
2046 | video_description = mobj.group(1).decode('utf-8') | |
2047 | if not video_description: | |
2048 | video_description = 'No description available.' | |
2049 | ||
2050 | # Extract video height and width | |
2051 | mobj = re.search(r'<meta name="video_height" content="([0-9]+)" />', webpage) | |
2052 | if mobj is None: | |
2053 | self._downloader.trouble(u'ERROR: unable to extract video height') | |
2054 | return | |
2055 | yv_video_height = mobj.group(1) | |
2056 | ||
2057 | mobj = re.search(r'<meta name="video_width" content="([0-9]+)" />', webpage) | |
2058 | if mobj is None: | |
2059 | self._downloader.trouble(u'ERROR: unable to extract video width') | |
2060 | return | |
2061 | yv_video_width = mobj.group(1) | |
2062 | ||
2063 | # Retrieve video playlist to extract media URL | |
2064 | # I'm not completely sure what all these options are, but we | |
2065 | # seem to need most of them, otherwise the server sends a 401. | |
2066 | yv_lg = 'R0xx6idZnW2zlrKP8xxAIR' # not sure what this represents | |
2067 | yv_bitrate = '700' # according to Wikipedia this is hard-coded | |
2068 | request = urllib2.Request('http://cosmos.bcst.yahoo.com/up/yep/process/getPlaylistFOP.php?node_id=' + video_id + | |
2069 | '&tech=flash&mode=playlist&lg=' + yv_lg + '&bitrate=' + yv_bitrate + '&vidH=' + yv_video_height + | |
2070 | '&vidW=' + yv_video_width + '&swf=as3&rd=video.yahoo.com&tk=null&adsupported=v1,v2,&eventid=1301797') | |
2071 | try: | |
2072 | self.report_download_webpage(video_id) | |
2073 | webpage = urllib2.urlopen(request).read() | |
2074 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
2075 | self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err)) | |
2076 | return | |
2077 | ||
2078 | # Extract media URL from playlist XML | |
2079 | mobj = re.search(r'<STREAM APP="(http://.*)" FULLPATH="/?(/.*\.flv\?[^"]*)"', webpage) | |
2080 | if mobj is None: | |
2081 | self._downloader.trouble(u'ERROR: Unable to extract media URL') | |
2082 | return | |
2083 | video_url = urllib.unquote(mobj.group(1) + mobj.group(2)).decode('utf-8') | |
2084 | video_url = re.sub(r'(?u)&(.+?);', htmlentity_transform, video_url) | |
2085 | ||
2086 | try: | |
2087 | # Process video information | |
2088 | self._downloader.process_info({ | |
2089 | 'id': video_id.decode('utf-8'), | |
2090 | 'url': video_url, | |
2091 | 'uploader': video_uploader, | |
2092 | 'upload_date': u'NA', | |
2093 | 'title': video_title, | |
2094 | 'stitle': simple_title, | |
2095 | 'ext': video_extension.decode('utf-8'), | |
2096 | 'thumbnail': video_thumbnail.decode('utf-8'), | |
2097 | 'description': video_description, | |
2098 | 'thumbnail': video_thumbnail, | |
2099 | 'player_url': None, | |
2100 | }) | |
2101 | except UnavailableVideoError: | |
2102 | self._downloader.trouble(u'\nERROR: unable to download video') | |
2103 | ||
2104 | ||
2105 | class VimeoIE(InfoExtractor): | |
2106 | """Information extractor for vimeo.com.""" | |
2107 | ||
2108 | # _VALID_URL matches Vimeo URLs | |
2109 | _VALID_URL = r'(?:https?://)?(?:(?:www|player).)?vimeo\.com/(?:groups/[^/]+/)?(?:videos?/)?([0-9]+)' | |
2110 | IE_NAME = u'vimeo' | |
2111 | ||
2112 | def __init__(self, downloader=None): | |
2113 | InfoExtractor.__init__(self, downloader) | |
2114 | ||
2115 | def report_download_webpage(self, video_id): | |
2116 | """Report webpage download.""" | |
2117 | self._downloader.to_screen(u'[vimeo] %s: Downloading webpage' % video_id) | |
2118 | ||
2119 | def report_extraction(self, video_id): | |
2120 | """Report information extraction.""" | |
2121 | self._downloader.to_screen(u'[vimeo] %s: Extracting information' % video_id) | |
2122 | ||
2123 | def _real_extract(self, url, new_video=True): | |
2124 | # Extract ID from URL | |
2125 | mobj = re.match(self._VALID_URL, url) | |
2126 | if mobj is None: | |
2127 | self._downloader.trouble(u'ERROR: Invalid URL: %s' % url) | |
2128 | return | |
2129 | ||
2130 | # At this point we have a new video | |
2131 | self._downloader.increment_downloads() | |
2132 | video_id = mobj.group(1) | |
2133 | ||
2134 | # Retrieve video webpage to extract further information | |
4a34b725 | 2135 | request = urllib2.Request(url, None, std_headers) |
235b3ba4 PH |
2136 | try: |
2137 | self.report_download_webpage(video_id) | |
2138 | webpage = urllib2.urlopen(request).read() | |
2139 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
2140 | self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err)) | |
2141 | return | |
2142 | ||
2143 | # Now we begin extracting as much information as we can from what we | |
2144 | # retrieved. First we extract the information common to all extractors, | |
2145 | # and latter we extract those that are Vimeo specific. | |
2146 | self.report_extraction(video_id) | |
2147 | ||
4a34b725 PH |
2148 | # Extract the config JSON |
2149 | config = webpage.split(' = {config:')[1].split(',assets:')[0] | |
2150 | try: | |
2151 | config = json.loads(config) | |
2152 | except: | |
2153 | self._downloader.trouble(u'ERROR: unable to extract info section') | |
235b3ba4 | 2154 | return |
4a34b725 PH |
2155 | |
2156 | # Extract title | |
2157 | video_title = config["video"]["title"] | |
fa2672f9 | 2158 | simple_title = _simplify_title(video_title) |
235b3ba4 PH |
2159 | |
2160 | # Extract uploader | |
4a34b725 | 2161 | video_uploader = config["video"]["owner"]["name"] |
235b3ba4 PH |
2162 | |
2163 | # Extract video thumbnail | |
4a34b725 | 2164 | video_thumbnail = config["video"]["thumbnail"] |
235b3ba4 | 2165 | |
4a34b725 PH |
2166 | # Extract video description |
2167 | try: | |
2168 | lxml.etree | |
2169 | except NameError: | |
2170 | video_description = u'No description available.' | |
2171 | mobj = re.search(r'<meta name="description" content="(.*?)" />', webpage, re.MULTILINE) | |
2172 | if mobj is not None: | |
2173 | video_description = mobj.group(1) | |
235b3ba4 | 2174 | else: |
4a34b725 PH |
2175 | html_parser = lxml.etree.HTMLParser() |
2176 | vwebpage_doc = lxml.etree.parse(StringIO.StringIO(webpage), html_parser) | |
2177 | video_description = u''.join(vwebpage_doc.xpath('id("description")//text()')).strip() | |
2178 | # TODO use another parser | |
235b3ba4 | 2179 | |
4a34b725 PH |
2180 | # Extract upload date |
2181 | video_upload_date = u'NA' | |
2182 | mobj = re.search(r'<span id="clip-date" style="display:none">[^:]*: (.*?)( \([^\(]*\))?</span>', webpage) | |
2183 | if mobj is not None: | |
2184 | video_upload_date = mobj.group(1) | |
2185 | ||
2186 | # Vimeo specific: extract request signature and timestamp | |
2187 | sig = config['request']['signature'] | |
2188 | timestamp = config['request']['timestamp'] | |
2189 | ||
2190 | # Vimeo specific: extract video codec and quality information | |
2191 | # TODO bind to format param | |
2192 | codecs = [('h264', 'mp4'), ('vp8', 'flv'), ('vp6', 'flv')] | |
2193 | for codec in codecs: | |
2194 | if codec[0] in config["video"]["files"]: | |
2195 | video_codec = codec[0] | |
2196 | video_extension = codec[1] | |
2197 | if 'hd' in config["video"]["files"][codec[0]]: quality = 'hd' | |
2198 | else: quality = 'sd' | |
2199 | break | |
2200 | else: | |
2201 | self._downloader.trouble(u'ERROR: no known codec found') | |
235b3ba4 | 2202 | return |
235b3ba4 | 2203 | |
4a34b725 PH |
2204 | video_url = "http://player.vimeo.com/play_redirect?clip_id=%s&sig=%s&time=%s&quality=%s&codecs=%s&type=moogaloop_local&embed_location=" \ |
2205 | %(video_id, sig, timestamp, quality, video_codec.upper()) | |
235b3ba4 PH |
2206 | |
2207 | try: | |
2208 | # Process video information | |
2209 | self._downloader.process_info({ | |
4a34b725 | 2210 | 'id': video_id, |
235b3ba4 PH |
2211 | 'url': video_url, |
2212 | 'uploader': video_uploader, | |
4a34b725 | 2213 | 'upload_date': video_upload_date, |
235b3ba4 PH |
2214 | 'title': video_title, |
2215 | 'stitle': simple_title, | |
4a34b725 | 2216 | 'ext': video_extension, |
235b3ba4 PH |
2217 | 'thumbnail': video_thumbnail, |
2218 | 'description': video_description, | |
2219 | 'player_url': None, | |
2220 | }) | |
2221 | except UnavailableVideoError: | |
2222 | self._downloader.trouble(u'ERROR: unable to download video') | |
2223 | ||
2224 | ||
2225 | class GenericIE(InfoExtractor): | |
2226 | """Generic last-resort information extractor.""" | |
2227 | ||
2228 | _VALID_URL = r'.*' | |
2229 | IE_NAME = u'generic' | |
2230 | ||
2231 | def __init__(self, downloader=None): | |
2232 | InfoExtractor.__init__(self, downloader) | |
2233 | ||
2234 | def report_download_webpage(self, video_id): | |
2235 | """Report webpage download.""" | |
2236 | self._downloader.to_screen(u'WARNING: Falling back on generic information extractor.') | |
2237 | self._downloader.to_screen(u'[generic] %s: Downloading webpage' % video_id) | |
2238 | ||
2239 | def report_extraction(self, video_id): | |
2240 | """Report information extraction.""" | |
2241 | self._downloader.to_screen(u'[generic] %s: Extracting information' % video_id) | |
2242 | ||
2243 | def _real_extract(self, url): | |
2244 | # At this point we have a new video | |
2245 | self._downloader.increment_downloads() | |
2246 | ||
2247 | video_id = url.split('/')[-1] | |
2248 | request = urllib2.Request(url) | |
2249 | try: | |
2250 | self.report_download_webpage(video_id) | |
2251 | webpage = urllib2.urlopen(request).read() | |
2252 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
2253 | self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err)) | |
2254 | return | |
2255 | except ValueError, err: | |
2256 | # since this is the last-resort InfoExtractor, if | |
2257 | # this error is thrown, it'll be thrown here | |
2258 | self._downloader.trouble(u'ERROR: Invalid URL: %s' % url) | |
2259 | return | |
2260 | ||
2261 | self.report_extraction(video_id) | |
2262 | # Start with something easy: JW Player in SWFObject | |
2263 | mobj = re.search(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage) | |
2264 | if mobj is None: | |
2265 | # Broaden the search a little bit | |
2266 | mobj = re.search(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage) | |
2267 | if mobj is None: | |
2268 | self._downloader.trouble(u'ERROR: Invalid URL: %s' % url) | |
2269 | return | |
2270 | ||
2271 | # It's possible that one of the regexes | |
2272 | # matched, but returned an empty group: | |
2273 | if mobj.group(1) is None: | |
2274 | self._downloader.trouble(u'ERROR: Invalid URL: %s' % url) | |
2275 | return | |
2276 | ||
2277 | video_url = urllib.unquote(mobj.group(1)) | |
2278 | video_id = os.path.basename(video_url) | |
2279 | ||
2280 | # here's a fun little line of code for you: | |
2281 | video_extension = os.path.splitext(video_id)[1][1:] | |
2282 | video_id = os.path.splitext(video_id)[0] | |
2283 | ||
2284 | # it's tempting to parse this further, but you would | |
2285 | # have to take into account all the variations like | |
2286 | # Video Title - Site Name | |
2287 | # Site Name | Video Title | |
2288 | # Video Title - Tagline | Site Name | |
2289 | # and so on and so forth; it's just not practical | |
2290 | mobj = re.search(r'<title>(.*)</title>', webpage) | |
2291 | if mobj is None: | |
2292 | self._downloader.trouble(u'ERROR: unable to extract title') | |
2293 | return | |
2294 | video_title = mobj.group(1).decode('utf-8') | |
2295 | video_title = sanitize_title(video_title) | |
e092418d | 2296 | simple_title = _simplify_title(video_title) |
235b3ba4 PH |
2297 | |
2298 | # video uploader is domain name | |
2299 | mobj = re.match(r'(?:https?://)?([^/]*)/.*', url) | |
2300 | if mobj is None: | |
2301 | self._downloader.trouble(u'ERROR: unable to extract title') | |
2302 | return | |
2303 | video_uploader = mobj.group(1).decode('utf-8') | |
2304 | ||
2305 | try: | |
2306 | # Process video information | |
2307 | self._downloader.process_info({ | |
2308 | 'id': video_id.decode('utf-8'), | |
2309 | 'url': video_url.decode('utf-8'), | |
2310 | 'uploader': video_uploader, | |
2311 | 'upload_date': u'NA', | |
2312 | 'title': video_title, | |
2313 | 'stitle': simple_title, | |
2314 | 'ext': video_extension.decode('utf-8'), | |
2315 | 'format': u'NA', | |
2316 | 'player_url': None, | |
2317 | }) | |
2318 | except UnavailableVideoError, err: | |
2319 | self._downloader.trouble(u'\nERROR: unable to download video') | |
2320 | ||
2321 | ||
2322 | class YoutubeSearchIE(InfoExtractor): | |
2323 | """Information Extractor for YouTube search queries.""" | |
2324 | _VALID_URL = r'ytsearch(\d+|all)?:[\s\S]+' | |
4a34b725 | 2325 | _API_URL = 'https://gdata.youtube.com/feeds/api/videos?q=%s&start-index=%i&max-results=50&v=2&alt=jsonc' |
235b3ba4 PH |
2326 | _youtube_ie = None |
2327 | _max_youtube_results = 1000 | |
2328 | IE_NAME = u'youtube:search' | |
2329 | ||
2330 | def __init__(self, youtube_ie, downloader=None): | |
2331 | InfoExtractor.__init__(self, downloader) | |
2332 | self._youtube_ie = youtube_ie | |
2333 | ||
2334 | def report_download_page(self, query, pagenum): | |
2335 | """Report attempt to download playlist page with given number.""" | |
2336 | query = query.decode(preferredencoding()) | |
2337 | self._downloader.to_screen(u'[youtube] query "%s": Downloading page %s' % (query, pagenum)) | |
2338 | ||
2339 | def _real_initialize(self): | |
2340 | self._youtube_ie.initialize() | |
2341 | ||
2342 | def _real_extract(self, query): | |
2343 | mobj = re.match(self._VALID_URL, query) | |
2344 | if mobj is None: | |
2345 | self._downloader.trouble(u'ERROR: invalid search query "%s"' % query) | |
2346 | return | |
2347 | ||
2348 | prefix, query = query.split(':') | |
2349 | prefix = prefix[8:] | |
2350 | query = query.encode('utf-8') | |
2351 | if prefix == '': | |
2352 | self._download_n_results(query, 1) | |
2353 | return | |
2354 | elif prefix == 'all': | |
2355 | self._download_n_results(query, self._max_youtube_results) | |
2356 | return | |
2357 | else: | |
2358 | try: | |
2359 | n = long(prefix) | |
2360 | if n <= 0: | |
2361 | self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query)) | |
2362 | return | |
2363 | elif n > self._max_youtube_results: | |
2364 | self._downloader.to_stderr(u'WARNING: ytsearch returns max %i results (you requested %i)' % (self._max_youtube_results, n)) | |
2365 | n = self._max_youtube_results | |
2366 | self._download_n_results(query, n) | |
2367 | return | |
2368 | except ValueError: # parsing prefix as integer fails | |
2369 | self._download_n_results(query, 1) | |
2370 | return | |
2371 | ||
2372 | def _download_n_results(self, query, n): | |
2373 | """Downloads a specified number of results for a query""" | |
2374 | ||
2375 | video_ids = [] | |
4a34b725 PH |
2376 | pagenum = 0 |
2377 | limit = n | |
235b3ba4 | 2378 | |
4a34b725 PH |
2379 | while (50 * pagenum) < limit: |
2380 | self.report_download_page(query, pagenum+1) | |
2381 | result_url = self._API_URL % (urllib.quote_plus(query), (50*pagenum)+1) | |
235b3ba4 PH |
2382 | request = urllib2.Request(result_url) |
2383 | try: | |
4a34b725 | 2384 | data = urllib2.urlopen(request).read() |
235b3ba4 | 2385 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: |
4a34b725 | 2386 | self._downloader.trouble(u'ERROR: unable to download API page: %s' % str(err)) |
235b3ba4 | 2387 | return |
4a34b725 | 2388 | api_response = json.loads(data)['data'] |
235b3ba4 | 2389 | |
4a34b725 PH |
2390 | new_ids = list(video['id'] for video in api_response['items']) |
2391 | video_ids += new_ids | |
2392 | ||
2393 | limit = min(n, api_response['totalItems']) | |
2394 | pagenum += 1 | |
235b3ba4 | 2395 | |
4a34b725 PH |
2396 | if len(video_ids) > n: |
2397 | video_ids = video_ids[:n] | |
2398 | for id in video_ids: | |
2399 | self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id) | |
2400 | return | |
235b3ba4 PH |
2401 | |
2402 | ||
2403 | class GoogleSearchIE(InfoExtractor): | |
2404 | """Information Extractor for Google Video search queries.""" | |
2405 | _VALID_URL = r'gvsearch(\d+|all)?:[\s\S]+' | |
2406 | _TEMPLATE_URL = 'http://video.google.com/videosearch?q=%s+site:video.google.com&start=%s&hl=en' | |
7e45ec57 PH |
2407 | _VIDEO_INDICATOR = r'<a href="http://video\.google\.com/videoplay\?docid=([^"\&]+)' |
2408 | _MORE_PAGES_INDICATOR = r'class="pn" id="pnnext"' | |
235b3ba4 PH |
2409 | _google_ie = None |
2410 | _max_google_results = 1000 | |
2411 | IE_NAME = u'video.google:search' | |
2412 | ||
2413 | def __init__(self, google_ie, downloader=None): | |
2414 | InfoExtractor.__init__(self, downloader) | |
2415 | self._google_ie = google_ie | |
2416 | ||
2417 | def report_download_page(self, query, pagenum): | |
2418 | """Report attempt to download playlist page with given number.""" | |
2419 | query = query.decode(preferredencoding()) | |
2420 | self._downloader.to_screen(u'[video.google] query "%s": Downloading page %s' % (query, pagenum)) | |
2421 | ||
2422 | def _real_initialize(self): | |
2423 | self._google_ie.initialize() | |
2424 | ||
2425 | def _real_extract(self, query): | |
2426 | mobj = re.match(self._VALID_URL, query) | |
2427 | if mobj is None: | |
2428 | self._downloader.trouble(u'ERROR: invalid search query "%s"' % query) | |
2429 | return | |
2430 | ||
2431 | prefix, query = query.split(':') | |
2432 | prefix = prefix[8:] | |
2433 | query = query.encode('utf-8') | |
2434 | if prefix == '': | |
2435 | self._download_n_results(query, 1) | |
2436 | return | |
2437 | elif prefix == 'all': | |
2438 | self._download_n_results(query, self._max_google_results) | |
2439 | return | |
2440 | else: | |
2441 | try: | |
2442 | n = long(prefix) | |
2443 | if n <= 0: | |
2444 | self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query)) | |
2445 | return | |
2446 | elif n > self._max_google_results: | |
2447 | self._downloader.to_stderr(u'WARNING: gvsearch returns max %i results (you requested %i)' % (self._max_google_results, n)) | |
2448 | n = self._max_google_results | |
2449 | self._download_n_results(query, n) | |
2450 | return | |
2451 | except ValueError: # parsing prefix as integer fails | |
2452 | self._download_n_results(query, 1) | |
2453 | return | |
2454 | ||
2455 | def _download_n_results(self, query, n): | |
2456 | """Downloads a specified number of results for a query""" | |
2457 | ||
2458 | video_ids = [] | |
7e45ec57 | 2459 | pagenum = 0 |
235b3ba4 PH |
2460 | |
2461 | while True: | |
2462 | self.report_download_page(query, pagenum) | |
7e45ec57 | 2463 | result_url = self._TEMPLATE_URL % (urllib.quote_plus(query), pagenum*10) |
235b3ba4 PH |
2464 | request = urllib2.Request(result_url) |
2465 | try: | |
2466 | page = urllib2.urlopen(request).read() | |
2467 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
2468 | self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err)) | |
2469 | return | |
2470 | ||
2471 | # Extract video identifiers | |
2472 | for mobj in re.finditer(self._VIDEO_INDICATOR, page): | |
2473 | video_id = mobj.group(1) | |
7e45ec57 | 2474 | if video_id not in video_ids: |
235b3ba4 | 2475 | video_ids.append(video_id) |
235b3ba4 PH |
2476 | if len(video_ids) == n: |
2477 | # Specified n videos reached | |
2478 | for id in video_ids: | |
2479 | self._google_ie.extract('http://video.google.com/videoplay?docid=%s' % id) | |
2480 | return | |
2481 | ||
2482 | if re.search(self._MORE_PAGES_INDICATOR, page) is None: | |
2483 | for id in video_ids: | |
2484 | self._google_ie.extract('http://video.google.com/videoplay?docid=%s' % id) | |
2485 | return | |
2486 | ||
2487 | pagenum = pagenum + 1 | |
2488 | ||
2489 | ||
2490 | class YahooSearchIE(InfoExtractor): | |
2491 | """Information Extractor for Yahoo! Video search queries.""" | |
2492 | _VALID_URL = r'yvsearch(\d+|all)?:[\s\S]+' | |
2493 | _TEMPLATE_URL = 'http://video.yahoo.com/search/?p=%s&o=%s' | |
2494 | _VIDEO_INDICATOR = r'href="http://video\.yahoo\.com/watch/([0-9]+/[0-9]+)"' | |
2495 | _MORE_PAGES_INDICATOR = r'\s*Next' | |
2496 | _yahoo_ie = None | |
2497 | _max_yahoo_results = 1000 | |
2498 | IE_NAME = u'video.yahoo:search' | |
2499 | ||
2500 | def __init__(self, yahoo_ie, downloader=None): | |
2501 | InfoExtractor.__init__(self, downloader) | |
2502 | self._yahoo_ie = yahoo_ie | |
2503 | ||
2504 | def report_download_page(self, query, pagenum): | |
2505 | """Report attempt to download playlist page with given number.""" | |
2506 | query = query.decode(preferredencoding()) | |
2507 | self._downloader.to_screen(u'[video.yahoo] query "%s": Downloading page %s' % (query, pagenum)) | |
2508 | ||
2509 | def _real_initialize(self): | |
2510 | self._yahoo_ie.initialize() | |
2511 | ||
2512 | def _real_extract(self, query): | |
2513 | mobj = re.match(self._VALID_URL, query) | |
2514 | if mobj is None: | |
2515 | self._downloader.trouble(u'ERROR: invalid search query "%s"' % query) | |
2516 | return | |
2517 | ||
2518 | prefix, query = query.split(':') | |
2519 | prefix = prefix[8:] | |
2520 | query = query.encode('utf-8') | |
2521 | if prefix == '': | |
2522 | self._download_n_results(query, 1) | |
2523 | return | |
2524 | elif prefix == 'all': | |
2525 | self._download_n_results(query, self._max_yahoo_results) | |
2526 | return | |
2527 | else: | |
2528 | try: | |
2529 | n = long(prefix) | |
2530 | if n <= 0: | |
2531 | self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query)) | |
2532 | return | |
2533 | elif n > self._max_yahoo_results: | |
2534 | self._downloader.to_stderr(u'WARNING: yvsearch returns max %i results (you requested %i)' % (self._max_yahoo_results, n)) | |
2535 | n = self._max_yahoo_results | |
2536 | self._download_n_results(query, n) | |
2537 | return | |
2538 | except ValueError: # parsing prefix as integer fails | |
2539 | self._download_n_results(query, 1) | |
2540 | return | |
2541 | ||
2542 | def _download_n_results(self, query, n): | |
2543 | """Downloads a specified number of results for a query""" | |
2544 | ||
2545 | video_ids = [] | |
2546 | already_seen = set() | |
2547 | pagenum = 1 | |
2548 | ||
2549 | while True: | |
2550 | self.report_download_page(query, pagenum) | |
2551 | result_url = self._TEMPLATE_URL % (urllib.quote_plus(query), pagenum) | |
2552 | request = urllib2.Request(result_url) | |
2553 | try: | |
2554 | page = urllib2.urlopen(request).read() | |
2555 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
2556 | self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err)) | |
2557 | return | |
2558 | ||
2559 | # Extract video identifiers | |
2560 | for mobj in re.finditer(self._VIDEO_INDICATOR, page): | |
2561 | video_id = mobj.group(1) | |
2562 | if video_id not in already_seen: | |
2563 | video_ids.append(video_id) | |
2564 | already_seen.add(video_id) | |
2565 | if len(video_ids) == n: | |
2566 | # Specified n videos reached | |
2567 | for id in video_ids: | |
2568 | self._yahoo_ie.extract('http://video.yahoo.com/watch/%s' % id) | |
2569 | return | |
2570 | ||
2571 | if re.search(self._MORE_PAGES_INDICATOR, page) is None: | |
2572 | for id in video_ids: | |
2573 | self._yahoo_ie.extract('http://video.yahoo.com/watch/%s' % id) | |
2574 | return | |
2575 | ||
2576 | pagenum = pagenum + 1 | |
2577 | ||
2578 | ||
2579 | class YoutubePlaylistIE(InfoExtractor): | |
2580 | """Information Extractor for YouTube playlists.""" | |
2581 | ||
2582 | _VALID_URL = r'(?:https?://)?(?:\w+\.)?youtube\.com/(?:(?:course|view_play_list|my_playlists|artist|playlist)\?.*?(p|a|list)=|user/.*?/user/|p/|user/.*?#[pg]/c/)(?:PL)?([0-9A-Za-z-_]+)(?:/.*?/([0-9A-Za-z_-]+))?.*' | |
2583 | _TEMPLATE_URL = 'http://www.youtube.com/%s?%s=%s&page=%s&gl=US&hl=en' | |
a67bdc34 | 2584 | _VIDEO_INDICATOR_TEMPLATE = r'/watch\?v=(.+?)&list=PL%s&' |
235b3ba4 PH |
2585 | _MORE_PAGES_INDICATOR = r'(?m)>\s*Next\s*</a>' |
2586 | _youtube_ie = None | |
2587 | IE_NAME = u'youtube:playlist' | |
2588 | ||
2589 | def __init__(self, youtube_ie, downloader=None): | |
2590 | InfoExtractor.__init__(self, downloader) | |
2591 | self._youtube_ie = youtube_ie | |
2592 | ||
2593 | def report_download_page(self, playlist_id, pagenum): | |
2594 | """Report attempt to download playlist page with given number.""" | |
2595 | self._downloader.to_screen(u'[youtube] PL %s: Downloading page #%s' % (playlist_id, pagenum)) | |
2596 | ||
2597 | def _real_initialize(self): | |
2598 | self._youtube_ie.initialize() | |
2599 | ||
2600 | def _real_extract(self, url): | |
2601 | # Extract playlist id | |
2602 | mobj = re.match(self._VALID_URL, url) | |
2603 | if mobj is None: | |
2604 | self._downloader.trouble(u'ERROR: invalid url: %s' % url) | |
2605 | return | |
2606 | ||
2607 | # Single video case | |
2608 | if mobj.group(3) is not None: | |
2609 | self._youtube_ie.extract(mobj.group(3)) | |
2610 | return | |
2611 | ||
2612 | # Download playlist pages | |
2613 | # prefix is 'p' as default for playlists but there are other types that need extra care | |
2614 | playlist_prefix = mobj.group(1) | |
2615 | if playlist_prefix == 'a': | |
2616 | playlist_access = 'artist' | |
2617 | else: | |
2618 | playlist_prefix = 'p' | |
2619 | playlist_access = 'view_play_list' | |
2620 | playlist_id = mobj.group(2) | |
2621 | video_ids = [] | |
2622 | pagenum = 1 | |
2623 | ||
2624 | while True: | |
2625 | self.report_download_page(playlist_id, pagenum) | |
2626 | url = self._TEMPLATE_URL % (playlist_access, playlist_prefix, playlist_id, pagenum) | |
2627 | request = urllib2.Request(url) | |
2628 | try: | |
2629 | page = urllib2.urlopen(request).read() | |
2630 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
2631 | self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err)) | |
2632 | return | |
2633 | ||
2634 | # Extract video identifiers | |
2635 | ids_in_page = [] | |
a67bdc34 | 2636 | for mobj in re.finditer(self._VIDEO_INDICATOR_TEMPLATE % playlist_id, page): |
235b3ba4 PH |
2637 | if mobj.group(1) not in ids_in_page: |
2638 | ids_in_page.append(mobj.group(1)) | |
2639 | video_ids.extend(ids_in_page) | |
2640 | ||
2641 | if re.search(self._MORE_PAGES_INDICATOR, page) is None: | |
2642 | break | |
2643 | pagenum = pagenum + 1 | |
2644 | ||
2645 | playliststart = self._downloader.params.get('playliststart', 1) - 1 | |
2646 | playlistend = self._downloader.params.get('playlistend', -1) | |
a67bdc34 PH |
2647 | if playlistend == -1: |
2648 | video_ids = video_ids[playliststart:] | |
2649 | else: | |
2650 | video_ids = video_ids[playliststart:playlistend] | |
235b3ba4 PH |
2651 | |
2652 | for id in video_ids: | |
2653 | self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id) | |
2654 | return | |
2655 | ||
2656 | ||
2657 | class YoutubeUserIE(InfoExtractor): | |
2658 | """Information Extractor for YouTube users.""" | |
2659 | ||
2660 | _VALID_URL = r'(?:(?:(?:https?://)?(?:\w+\.)?youtube\.com/user/)|ytuser:)([A-Za-z0-9_-]+)' | |
2661 | _TEMPLATE_URL = 'http://gdata.youtube.com/feeds/api/users/%s' | |
2662 | _GDATA_PAGE_SIZE = 50 | |
2663 | _GDATA_URL = 'http://gdata.youtube.com/feeds/api/users/%s/uploads?max-results=%d&start-index=%d' | |
2664 | _VIDEO_INDICATOR = r'/watch\?v=(.+?)[\<&]' | |
2665 | _youtube_ie = None | |
2666 | IE_NAME = u'youtube:user' | |
2667 | ||
2668 | def __init__(self, youtube_ie, downloader=None): | |
2669 | InfoExtractor.__init__(self, downloader) | |
2670 | self._youtube_ie = youtube_ie | |
2671 | ||
2672 | def report_download_page(self, username, start_index): | |
2673 | """Report attempt to download user page.""" | |
2674 | self._downloader.to_screen(u'[youtube] user %s: Downloading video ids from %d to %d' % | |
2675 | (username, start_index, start_index + self._GDATA_PAGE_SIZE)) | |
2676 | ||
2677 | def _real_initialize(self): | |
2678 | self._youtube_ie.initialize() | |
2679 | ||
2680 | def _real_extract(self, url): | |
2681 | # Extract username | |
2682 | mobj = re.match(self._VALID_URL, url) | |
2683 | if mobj is None: | |
2684 | self._downloader.trouble(u'ERROR: invalid url: %s' % url) | |
2685 | return | |
2686 | ||
2687 | username = mobj.group(1) | |
2688 | ||
2689 | # Download video ids using YouTube Data API. Result size per | |
2690 | # query is limited (currently to 50 videos) so we need to query | |
2691 | # page by page until there are no video ids - it means we got | |
2692 | # all of them. | |
2693 | ||
2694 | video_ids = [] | |
2695 | pagenum = 0 | |
2696 | ||
2697 | while True: | |
2698 | start_index = pagenum * self._GDATA_PAGE_SIZE + 1 | |
2699 | self.report_download_page(username, start_index) | |
2700 | ||
2701 | request = urllib2.Request(self._GDATA_URL % (username, self._GDATA_PAGE_SIZE, start_index)) | |
2702 | ||
2703 | try: | |
2704 | page = urllib2.urlopen(request).read() | |
2705 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
2706 | self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err)) | |
2707 | return | |
2708 | ||
2709 | # Extract video identifiers | |
2710 | ids_in_page = [] | |
2711 | ||
2712 | for mobj in re.finditer(self._VIDEO_INDICATOR, page): | |
2713 | if mobj.group(1) not in ids_in_page: | |
2714 | ids_in_page.append(mobj.group(1)) | |
2715 | ||
2716 | video_ids.extend(ids_in_page) | |
2717 | ||
2718 | # A little optimization - if current page is not | |
2719 | # "full", ie. does not contain PAGE_SIZE video ids then | |
2720 | # we can assume that this page is the last one - there | |
2721 | # are no more ids on further pages - no need to query | |
2722 | # again. | |
2723 | ||
2724 | if len(ids_in_page) < self._GDATA_PAGE_SIZE: | |
2725 | break | |
2726 | ||
2727 | pagenum += 1 | |
2728 | ||
2729 | all_ids_count = len(video_ids) | |
2730 | playliststart = self._downloader.params.get('playliststart', 1) - 1 | |
2731 | playlistend = self._downloader.params.get('playlistend', -1) | |
2732 | ||
2733 | if playlistend == -1: | |
2734 | video_ids = video_ids[playliststart:] | |
2735 | else: | |
2736 | video_ids = video_ids[playliststart:playlistend] | |
2737 | ||
6d58c454 | 2738 | self._downloader.to_screen(u"[youtube] user %s: Collected %d video ids (downloading %d of them)" % |
235b3ba4 PH |
2739 | (username, all_ids_count, len(video_ids))) |
2740 | ||
2741 | for video_id in video_ids: | |
2742 | self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % video_id) | |
2743 | ||
2744 | ||
2745 | class DepositFilesIE(InfoExtractor): | |
2746 | """Information extractor for depositfiles.com""" | |
2747 | ||
2748 | _VALID_URL = r'(?:http://)?(?:\w+\.)?depositfiles\.com/(?:../(?#locale))?files/(.+)' | |
2749 | IE_NAME = u'DepositFiles' | |
2750 | ||
2751 | def __init__(self, downloader=None): | |
2752 | InfoExtractor.__init__(self, downloader) | |
2753 | ||
2754 | def report_download_webpage(self, file_id): | |
2755 | """Report webpage download.""" | |
2756 | self._downloader.to_screen(u'[DepositFiles] %s: Downloading webpage' % file_id) | |
2757 | ||
2758 | def report_extraction(self, file_id): | |
2759 | """Report information extraction.""" | |
2760 | self._downloader.to_screen(u'[DepositFiles] %s: Extracting information' % file_id) | |
2761 | ||
2762 | def _real_extract(self, url): | |
2763 | # At this point we have a new file | |
2764 | self._downloader.increment_downloads() | |
2765 | ||
2766 | file_id = url.split('/')[-1] | |
2767 | # Rebuild url in english locale | |
2768 | url = 'http://depositfiles.com/en/files/' + file_id | |
2769 | ||
2770 | # Retrieve file webpage with 'Free download' button pressed | |
2771 | free_download_indication = { 'gateway_result' : '1' } | |
2772 | request = urllib2.Request(url, urllib.urlencode(free_download_indication)) | |
2773 | try: | |
2774 | self.report_download_webpage(file_id) | |
2775 | webpage = urllib2.urlopen(request).read() | |
2776 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
2777 | self._downloader.trouble(u'ERROR: Unable to retrieve file webpage: %s' % str(err)) | |
2778 | return | |
2779 | ||
2780 | # Search for the real file URL | |
2781 | mobj = re.search(r'<form action="(http://fileshare.+?)"', webpage) | |
2782 | if (mobj is None) or (mobj.group(1) is None): | |
2783 | # Try to figure out reason of the error. | |
2784 | mobj = re.search(r'<strong>(Attention.*?)</strong>', webpage, re.DOTALL) | |
2785 | if (mobj is not None) and (mobj.group(1) is not None): | |
2786 | restriction_message = re.sub('\s+', ' ', mobj.group(1)).strip() | |
2787 | self._downloader.trouble(u'ERROR: %s' % restriction_message) | |
2788 | else: | |
2789 | self._downloader.trouble(u'ERROR: unable to extract download URL from: %s' % url) | |
2790 | return | |
2791 | ||
2792 | file_url = mobj.group(1) | |
2793 | file_extension = os.path.splitext(file_url)[1][1:] | |
2794 | ||
2795 | # Search for file title | |
2796 | mobj = re.search(r'<b title="(.*?)">', webpage) | |
2797 | if mobj is None: | |
2798 | self._downloader.trouble(u'ERROR: unable to extract title') | |
2799 | return | |
2800 | file_title = mobj.group(1).decode('utf-8') | |
2801 | ||
2802 | try: | |
2803 | # Process file information | |
2804 | self._downloader.process_info({ | |
2805 | 'id': file_id.decode('utf-8'), | |
2806 | 'url': file_url.decode('utf-8'), | |
2807 | 'uploader': u'NA', | |
2808 | 'upload_date': u'NA', | |
2809 | 'title': file_title, | |
2810 | 'stitle': file_title, | |
2811 | 'ext': file_extension.decode('utf-8'), | |
2812 | 'format': u'NA', | |
2813 | 'player_url': None, | |
2814 | }) | |
2815 | except UnavailableVideoError, err: | |
2816 | self._downloader.trouble(u'ERROR: unable to download file') | |
2817 | ||
2818 | ||
2819 | class FacebookIE(InfoExtractor): | |
2820 | """Information Extractor for Facebook""" | |
2821 | ||
2822 | _VALID_URL = r'^(?:https?://)?(?:\w+\.)?facebook\.com/(?:video/video|photo)\.php\?(?:.*?)v=(?P<ID>\d+)(?:.*)' | |
2823 | _LOGIN_URL = 'https://login.facebook.com/login.php?m&next=http%3A%2F%2Fm.facebook.com%2Fhome.php&' | |
2824 | _NETRC_MACHINE = 'facebook' | |
2825 | _available_formats = ['video', 'highqual', 'lowqual'] | |
2826 | _video_extensions = { | |
2827 | 'video': 'mp4', | |
2828 | 'highqual': 'mp4', | |
2829 | 'lowqual': 'mp4', | |
2830 | } | |
2831 | IE_NAME = u'facebook' | |
2832 | ||
2833 | def __init__(self, downloader=None): | |
2834 | InfoExtractor.__init__(self, downloader) | |
2835 | ||
2836 | def _reporter(self, message): | |
2837 | """Add header and report message.""" | |
2838 | self._downloader.to_screen(u'[facebook] %s' % message) | |
2839 | ||
2840 | def report_login(self): | |
2841 | """Report attempt to log in.""" | |
2842 | self._reporter(u'Logging in') | |
2843 | ||
2844 | def report_video_webpage_download(self, video_id): | |
2845 | """Report attempt to download video webpage.""" | |
2846 | self._reporter(u'%s: Downloading video webpage' % video_id) | |
2847 | ||
2848 | def report_information_extraction(self, video_id): | |
2849 | """Report attempt to extract video information.""" | |
2850 | self._reporter(u'%s: Extracting video information' % video_id) | |
2851 | ||
2852 | def _parse_page(self, video_webpage): | |
2853 | """Extract video information from page""" | |
2854 | # General data | |
2855 | data = {'title': r'\("video_title", "(.*?)"\)', | |
2856 | 'description': r'<div class="datawrap">(.*?)</div>', | |
2857 | 'owner': r'\("video_owner_name", "(.*?)"\)', | |
2858 | 'thumbnail': r'\("thumb_url", "(?P<THUMB>.*?)"\)', | |
2859 | } | |
2860 | video_info = {} | |
2861 | for piece in data.keys(): | |
2862 | mobj = re.search(data[piece], video_webpage) | |
2863 | if mobj is not None: | |
2864 | video_info[piece] = urllib.unquote_plus(mobj.group(1).decode("unicode_escape")) | |
2865 | ||
2866 | # Video urls | |
2867 | video_urls = {} | |
2868 | for fmt in self._available_formats: | |
2869 | mobj = re.search(r'\("%s_src\", "(.+?)"\)' % fmt, video_webpage) | |
2870 | if mobj is not None: | |
2871 | # URL is in a Javascript segment inside an escaped Unicode format within | |
2872 | # the generally utf-8 page | |
2873 | video_urls[fmt] = urllib.unquote_plus(mobj.group(1).decode("unicode_escape")) | |
2874 | video_info['video_urls'] = video_urls | |
2875 | ||
2876 | return video_info | |
2877 | ||
2878 | def _real_initialize(self): | |
2879 | if self._downloader is None: | |
2880 | return | |
2881 | ||
2882 | useremail = None | |
2883 | password = None | |
2884 | downloader_params = self._downloader.params | |
2885 | ||
2886 | # Attempt to use provided username and password or .netrc data | |
2887 | if downloader_params.get('username', None) is not None: | |
2888 | useremail = downloader_params['username'] | |
2889 | password = downloader_params['password'] | |
2890 | elif downloader_params.get('usenetrc', False): | |
2891 | try: | |
2892 | info = netrc.netrc().authenticators(self._NETRC_MACHINE) | |
2893 | if info is not None: | |
2894 | useremail = info[0] | |
2895 | password = info[2] | |
2896 | else: | |
2897 | raise netrc.NetrcParseError('No authenticators for %s' % self._NETRC_MACHINE) | |
2898 | except (IOError, netrc.NetrcParseError), err: | |
2899 | self._downloader.to_stderr(u'WARNING: parsing .netrc: %s' % str(err)) | |
2900 | return | |
2901 | ||
2902 | if useremail is None: | |
2903 | return | |
2904 | ||
2905 | # Log in | |
2906 | login_form = { | |
2907 | 'email': useremail, | |
2908 | 'pass': password, | |
2909 | 'login': 'Log+In' | |
2910 | } | |
2911 | request = urllib2.Request(self._LOGIN_URL, urllib.urlencode(login_form)) | |
2912 | try: | |
2913 | self.report_login() | |
2914 | login_results = urllib2.urlopen(request).read() | |
2915 | if re.search(r'<form(.*)name="login"(.*)</form>', login_results) is not None: | |
2916 | self._downloader.to_stderr(u'WARNING: unable to log in: bad username/password, or exceded login rate limit (~3/min). Check credentials or wait.') | |
2917 | return | |
2918 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
2919 | self._downloader.to_stderr(u'WARNING: unable to log in: %s' % str(err)) | |
2920 | return | |
2921 | ||
2922 | def _real_extract(self, url): | |
2923 | mobj = re.match(self._VALID_URL, url) | |
2924 | if mobj is None: | |
2925 | self._downloader.trouble(u'ERROR: invalid URL: %s' % url) | |
2926 | return | |
2927 | video_id = mobj.group('ID') | |
2928 | ||
2929 | # Get video webpage | |
2930 | self.report_video_webpage_download(video_id) | |
2931 | request = urllib2.Request('https://www.facebook.com/video/video.php?v=%s' % video_id) | |
2932 | try: | |
2933 | page = urllib2.urlopen(request) | |
2934 | video_webpage = page.read() | |
2935 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
2936 | self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % str(err)) | |
2937 | return | |
2938 | ||
2939 | # Start extracting information | |
2940 | self.report_information_extraction(video_id) | |
2941 | ||
2942 | # Extract information | |
2943 | video_info = self._parse_page(video_webpage) | |
2944 | ||
2945 | # uploader | |
2946 | if 'owner' not in video_info: | |
2947 | self._downloader.trouble(u'ERROR: unable to extract uploader nickname') | |
2948 | return | |
2949 | video_uploader = video_info['owner'] | |
2950 | ||
2951 | # title | |
2952 | if 'title' not in video_info: | |
2953 | self._downloader.trouble(u'ERROR: unable to extract video title') | |
2954 | return | |
2955 | video_title = video_info['title'] | |
2956 | video_title = video_title.decode('utf-8') | |
2957 | video_title = sanitize_title(video_title) | |
2958 | ||
e092418d | 2959 | simple_title = _simplify_title(video_title) |
235b3ba4 PH |
2960 | |
2961 | # thumbnail image | |
2962 | if 'thumbnail' not in video_info: | |
2963 | self._downloader.trouble(u'WARNING: unable to extract video thumbnail') | |
2964 | video_thumbnail = '' | |
2965 | else: | |
2966 | video_thumbnail = video_info['thumbnail'] | |
2967 | ||
2968 | # upload date | |
2969 | upload_date = u'NA' | |
2970 | if 'upload_date' in video_info: | |
2971 | upload_time = video_info['upload_date'] | |
2972 | timetuple = email.utils.parsedate_tz(upload_time) | |
2973 | if timetuple is not None: | |
2974 | try: | |
2975 | upload_date = time.strftime('%Y%m%d', timetuple[0:9]) | |
2976 | except: | |
2977 | pass | |
2978 | ||
2979 | # description | |
2980 | video_description = video_info.get('description', 'No description available.') | |
2981 | ||
2982 | url_map = video_info['video_urls'] | |
2983 | if len(url_map.keys()) > 0: | |
2984 | # Decide which formats to download | |
2985 | req_format = self._downloader.params.get('format', None) | |
2986 | format_limit = self._downloader.params.get('format_limit', None) | |
2987 | ||
2988 | if format_limit is not None and format_limit in self._available_formats: | |
2989 | format_list = self._available_formats[self._available_formats.index(format_limit):] | |
2990 | else: | |
2991 | format_list = self._available_formats | |
2992 | existing_formats = [x for x in format_list if x in url_map] | |
2993 | if len(existing_formats) == 0: | |
2994 | self._downloader.trouble(u'ERROR: no known formats available for video') | |
2995 | return | |
2996 | if req_format is None: | |
2997 | video_url_list = [(existing_formats[0], url_map[existing_formats[0]])] # Best quality | |
2998 | elif req_format == 'worst': | |
2999 | video_url_list = [(existing_formats[len(existing_formats)-1], url_map[existing_formats[len(existing_formats)-1]])] # worst quality | |
3000 | elif req_format == '-1': | |
3001 | video_url_list = [(f, url_map[f]) for f in existing_formats] # All formats | |
3002 | else: | |
3003 | # Specific format | |
3004 | if req_format not in url_map: | |
3005 | self._downloader.trouble(u'ERROR: requested format not available') | |
3006 | return | |
3007 | video_url_list = [(req_format, url_map[req_format])] # Specific format | |
3008 | ||
3009 | for format_param, video_real_url in video_url_list: | |
3010 | ||
3011 | # At this point we have a new video | |
3012 | self._downloader.increment_downloads() | |
3013 | ||
3014 | # Extension | |
3015 | video_extension = self._video_extensions.get(format_param, 'mp4') | |
3016 | ||
3017 | try: | |
3018 | # Process video information | |
3019 | self._downloader.process_info({ | |
3020 | 'id': video_id.decode('utf-8'), | |
3021 | 'url': video_real_url.decode('utf-8'), | |
3022 | 'uploader': video_uploader.decode('utf-8'), | |
3023 | 'upload_date': upload_date, | |
3024 | 'title': video_title, | |
3025 | 'stitle': simple_title, | |
3026 | 'ext': video_extension.decode('utf-8'), | |
3027 | 'format': (format_param is None and u'NA' or format_param.decode('utf-8')), | |
3028 | 'thumbnail': video_thumbnail.decode('utf-8'), | |
3029 | 'description': video_description.decode('utf-8'), | |
3030 | 'player_url': None, | |
3031 | }) | |
3032 | except UnavailableVideoError, err: | |
3033 | self._downloader.trouble(u'\nERROR: unable to download video') | |
3034 | ||
3035 | class BlipTVIE(InfoExtractor): | |
3036 | """Information extractor for blip.tv""" | |
3037 | ||
3038 | _VALID_URL = r'^(?:https?://)?(?:\w+\.)?blip\.tv(/.+)$' | |
3039 | _URL_EXT = r'^.*\.([a-z0-9]+)$' | |
3040 | IE_NAME = u'blip.tv' | |
3041 | ||
3042 | def report_extraction(self, file_id): | |
3043 | """Report information extraction.""" | |
3044 | self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, file_id)) | |
3045 | ||
3046 | def report_direct_download(self, title): | |
3047 | """Report information extraction.""" | |
3048 | self._downloader.to_screen(u'[%s] %s: Direct download detected' % (self.IE_NAME, title)) | |
3049 | ||
235b3ba4 PH |
3050 | def _real_extract(self, url): |
3051 | mobj = re.match(self._VALID_URL, url) | |
3052 | if mobj is None: | |
3053 | self._downloader.trouble(u'ERROR: invalid URL: %s' % url) | |
3054 | return | |
3055 | ||
3056 | if '?' in url: | |
3057 | cchar = '&' | |
3058 | else: | |
3059 | cchar = '?' | |
3060 | json_url = url + cchar + 'skin=json&version=2&no_wrap=1' | |
3061 | request = urllib2.Request(json_url) | |
3062 | self.report_extraction(mobj.group(1)) | |
3063 | info = None | |
3064 | try: | |
3065 | urlh = urllib2.urlopen(request) | |
3066 | if urlh.headers.get('Content-Type', '').startswith('video/'): # Direct download | |
3067 | basename = url.split('/')[-1] | |
3068 | title,ext = os.path.splitext(basename) | |
af8e8d63 | 3069 | title = title.decode('UTF-8') |
235b3ba4 PH |
3070 | ext = ext.replace('.', '') |
3071 | self.report_direct_download(title) | |
3072 | info = { | |
3073 | 'id': title, | |
3074 | 'url': url, | |
3075 | 'title': title, | |
e092418d | 3076 | 'stitle': _simplify_title(title), |
235b3ba4 PH |
3077 | 'ext': ext, |
3078 | 'urlhandle': urlh | |
3079 | } | |
3080 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
3081 | self._downloader.trouble(u'ERROR: unable to download video info webpage: %s' % str(err)) | |
3082 | return | |
3083 | if info is None: # Regular URL | |
3084 | try: | |
3085 | json_code = urlh.read() | |
3086 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
3087 | self._downloader.trouble(u'ERROR: unable to read video info webpage: %s' % str(err)) | |
3088 | return | |
3089 | ||
3090 | try: | |
3091 | json_data = json.loads(json_code) | |
3092 | if 'Post' in json_data: | |
3093 | data = json_data['Post'] | |
3094 | else: | |
3095 | data = json_data | |
3096 | ||
3097 | upload_date = datetime.datetime.strptime(data['datestamp'], '%m-%d-%y %H:%M%p').strftime('%Y%m%d') | |
3098 | video_url = data['media']['url'] | |
3099 | umobj = re.match(self._URL_EXT, video_url) | |
3100 | if umobj is None: | |
3101 | raise ValueError('Can not determine filename extension') | |
3102 | ext = umobj.group(1) | |
3103 | ||
3104 | info = { | |
3105 | 'id': data['item_id'], | |
3106 | 'url': video_url, | |
3107 | 'uploader': data['display_name'], | |
3108 | 'upload_date': upload_date, | |
3109 | 'title': data['title'], | |
e092418d | 3110 | 'stitle': _simplify_title(data['title']), |
235b3ba4 PH |
3111 | 'ext': ext, |
3112 | 'format': data['media']['mimeType'], | |
3113 | 'thumbnail': data['thumbnailUrl'], | |
3114 | 'description': data['description'], | |
3115 | 'player_url': data['embedUrl'] | |
3116 | } | |
3117 | except (ValueError,KeyError), err: | |
3118 | self._downloader.trouble(u'ERROR: unable to parse video information: %s' % repr(err)) | |
3119 | return | |
3120 | ||
3121 | self._downloader.increment_downloads() | |
3122 | ||
3123 | try: | |
3124 | self._downloader.process_info(info) | |
3125 | except UnavailableVideoError, err: | |
3126 | self._downloader.trouble(u'\nERROR: unable to download video') | |
3127 | ||
3128 | ||
3129 | class MyVideoIE(InfoExtractor): | |
3130 | """Information Extractor for myvideo.de.""" | |
3131 | ||
3132 | _VALID_URL = r'(?:http://)?(?:www\.)?myvideo\.de/watch/([0-9]+)/([^?/]+).*' | |
3133 | IE_NAME = u'myvideo' | |
3134 | ||
3135 | def __init__(self, downloader=None): | |
3136 | InfoExtractor.__init__(self, downloader) | |
3137 | ||
3138 | def report_download_webpage(self, video_id): | |
3139 | """Report webpage download.""" | |
3140 | self._downloader.to_screen(u'[myvideo] %s: Downloading webpage' % video_id) | |
3141 | ||
3142 | def report_extraction(self, video_id): | |
3143 | """Report information extraction.""" | |
3144 | self._downloader.to_screen(u'[myvideo] %s: Extracting information' % video_id) | |
3145 | ||
3146 | def _real_extract(self,url): | |
3147 | mobj = re.match(self._VALID_URL, url) | |
3148 | if mobj is None: | |
3149 | self._download.trouble(u'ERROR: invalid URL: %s' % url) | |
3150 | return | |
3151 | ||
3152 | video_id = mobj.group(1) | |
235b3ba4 PH |
3153 | |
3154 | # Get video webpage | |
3155 | request = urllib2.Request('http://www.myvideo.de/watch/%s' % video_id) | |
3156 | try: | |
3157 | self.report_download_webpage(video_id) | |
3158 | webpage = urllib2.urlopen(request).read() | |
3159 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
3160 | self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err)) | |
3161 | return | |
3162 | ||
3163 | self.report_extraction(video_id) | |
3164 | mobj = re.search(r'<link rel=\'image_src\' href=\'(http://is[0-9].myvideo\.de/de/movie[0-9]+/[a-f0-9]+)/thumbs/[^.]+\.jpg\' />', | |
3165 | webpage) | |
3166 | if mobj is None: | |
3167 | self._downloader.trouble(u'ERROR: unable to extract media URL') | |
3168 | return | |
3169 | video_url = mobj.group(1) + ('/%s.flv' % video_id) | |
3170 | ||
3171 | mobj = re.search('<title>([^<]+)</title>', webpage) | |
3172 | if mobj is None: | |
3173 | self._downloader.trouble(u'ERROR: unable to extract title') | |
3174 | return | |
3175 | ||
3176 | video_title = mobj.group(1) | |
3177 | video_title = sanitize_title(video_title) | |
3178 | ||
e092418d PH |
3179 | simple_title = _simplify_title(video_title) |
3180 | ||
235b3ba4 PH |
3181 | try: |
3182 | self._downloader.process_info({ | |
3183 | 'id': video_id, | |
3184 | 'url': video_url, | |
3185 | 'uploader': u'NA', | |
3186 | 'upload_date': u'NA', | |
3187 | 'title': video_title, | |
3188 | 'stitle': simple_title, | |
3189 | 'ext': u'flv', | |
3190 | 'format': u'NA', | |
3191 | 'player_url': None, | |
3192 | }) | |
3193 | except UnavailableVideoError: | |
3194 | self._downloader.trouble(u'\nERROR: Unable to download video') | |
3195 | ||
3196 | class ComedyCentralIE(InfoExtractor): | |
3197 | """Information extractor for The Daily Show and Colbert Report """ | |
3198 | ||
3199 | _VALID_URL = r'^(:(?P<shortname>tds|thedailyshow|cr|colbert|colbertnation|colbertreport))|(https?://)?(www\.)?(?P<showname>thedailyshow|colbertnation)\.com/full-episodes/(?P<episode>.*)$' | |
3200 | IE_NAME = u'comedycentral' | |
3201 | ||
3202 | def report_extraction(self, episode_id): | |
3203 | self._downloader.to_screen(u'[comedycentral] %s: Extracting information' % episode_id) | |
3204 | ||
3205 | def report_config_download(self, episode_id): | |
3206 | self._downloader.to_screen(u'[comedycentral] %s: Downloading configuration' % episode_id) | |
3207 | ||
3208 | def report_index_download(self, episode_id): | |
3209 | self._downloader.to_screen(u'[comedycentral] %s: Downloading show index' % episode_id) | |
3210 | ||
3211 | def report_player_url(self, episode_id): | |
3212 | self._downloader.to_screen(u'[comedycentral] %s: Determining player URL' % episode_id) | |
3213 | ||
235b3ba4 PH |
3214 | def _real_extract(self, url): |
3215 | mobj = re.match(self._VALID_URL, url) | |
3216 | if mobj is None: | |
3217 | self._downloader.trouble(u'ERROR: invalid URL: %s' % url) | |
3218 | return | |
3219 | ||
3220 | if mobj.group('shortname'): | |
3221 | if mobj.group('shortname') in ('tds', 'thedailyshow'): | |
af8e8d63 | 3222 | url = u'http://www.thedailyshow.com/full-episodes/' |
235b3ba4 | 3223 | else: |
af8e8d63 | 3224 | url = u'http://www.colbertnation.com/full-episodes/' |
235b3ba4 PH |
3225 | mobj = re.match(self._VALID_URL, url) |
3226 | assert mobj is not None | |
3227 | ||
3228 | dlNewest = not mobj.group('episode') | |
3229 | if dlNewest: | |
3230 | epTitle = mobj.group('showname') | |
3231 | else: | |
3232 | epTitle = mobj.group('episode') | |
3233 | ||
3234 | req = urllib2.Request(url) | |
3235 | self.report_extraction(epTitle) | |
3236 | try: | |
3237 | htmlHandle = urllib2.urlopen(req) | |
3238 | html = htmlHandle.read() | |
3239 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
3240 | self._downloader.trouble(u'ERROR: unable to download webpage: %s' % unicode(err)) | |
3241 | return | |
3242 | if dlNewest: | |
3243 | url = htmlHandle.geturl() | |
3244 | mobj = re.match(self._VALID_URL, url) | |
3245 | if mobj is None: | |
3246 | self._downloader.trouble(u'ERROR: Invalid redirected URL: ' + url) | |
3247 | return | |
3248 | if mobj.group('episode') == '': | |
3249 | self._downloader.trouble(u'ERROR: Redirected URL is still not specific: ' + url) | |
3250 | return | |
3251 | epTitle = mobj.group('episode') | |
3252 | ||
c92e184f | 3253 | mMovieParams = re.findall('(?:<param name="movie" value="|var url = ")(http://media.mtvnservices.com/([^"]*episode.*?:.*?))"', html) |
235b3ba4 PH |
3254 | if len(mMovieParams) == 0: |
3255 | self._downloader.trouble(u'ERROR: unable to find Flash URL in webpage ' + url) | |
3256 | return | |
3257 | ||
3258 | playerUrl_raw = mMovieParams[0][0] | |
3259 | self.report_player_url(epTitle) | |
3260 | try: | |
3261 | urlHandle = urllib2.urlopen(playerUrl_raw) | |
3262 | playerUrl = urlHandle.geturl() | |
3263 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
3264 | self._downloader.trouble(u'ERROR: unable to find out player URL: ' + unicode(err)) | |
3265 | return | |
3266 | ||
3267 | uri = mMovieParams[0][1] | |
3268 | indexUrl = 'http://shadow.comedycentral.com/feeds/video_player/mrss/?' + urllib.urlencode({'uri': uri}) | |
3269 | self.report_index_download(epTitle) | |
3270 | try: | |
3271 | indexXml = urllib2.urlopen(indexUrl).read() | |
3272 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
3273 | self._downloader.trouble(u'ERROR: unable to download episode index: ' + unicode(err)) | |
3274 | return | |
3275 | ||
3276 | idoc = xml.etree.ElementTree.fromstring(indexXml) | |
3277 | itemEls = idoc.findall('.//item') | |
3278 | for itemEl in itemEls: | |
3279 | mediaId = itemEl.findall('./guid')[0].text | |
3280 | shortMediaId = mediaId.split(':')[-1] | |
3281 | showId = mediaId.split(':')[-2].replace('.com', '') | |
3282 | officialTitle = itemEl.findall('./title')[0].text | |
3283 | officialDate = itemEl.findall('./pubDate')[0].text | |
3284 | ||
3285 | configUrl = ('http://www.comedycentral.com/global/feeds/entertainment/media/mediaGenEntertainment.jhtml?' + | |
3286 | urllib.urlencode({'uri': mediaId})) | |
3287 | configReq = urllib2.Request(configUrl) | |
3288 | self.report_config_download(epTitle) | |
3289 | try: | |
3290 | configXml = urllib2.urlopen(configReq).read() | |
3291 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
3292 | self._downloader.trouble(u'ERROR: unable to download webpage: %s' % unicode(err)) | |
3293 | return | |
3294 | ||
3295 | cdoc = xml.etree.ElementTree.fromstring(configXml) | |
3296 | turls = [] | |
3297 | for rendition in cdoc.findall('.//rendition'): | |
3298 | finfo = (rendition.attrib['bitrate'], rendition.findall('./src')[0].text) | |
3299 | turls.append(finfo) | |
3300 | ||
3301 | if len(turls) == 0: | |
3302 | self._downloader.trouble(u'\nERROR: unable to download ' + mediaId + ': No videos found') | |
3303 | continue | |
3304 | ||
3305 | # For now, just pick the highest bitrate | |
3306 | format,video_url = turls[-1] | |
3307 | ||
3308 | self._downloader.increment_downloads() | |
3309 | ||
af8e8d63 | 3310 | effTitle = showId + u'-' + epTitle |
235b3ba4 PH |
3311 | info = { |
3312 | 'id': shortMediaId, | |
3313 | 'url': video_url, | |
3314 | 'uploader': showId, | |
3315 | 'upload_date': officialDate, | |
3316 | 'title': effTitle, | |
208e095f | 3317 | 'stitle': _simplify_title(effTitle), |
235b3ba4 PH |
3318 | 'ext': 'mp4', |
3319 | 'format': format, | |
3320 | 'thumbnail': None, | |
3321 | 'description': officialTitle, | |
3322 | 'player_url': playerUrl | |
3323 | } | |
3324 | ||
3325 | try: | |
3326 | self._downloader.process_info(info) | |
3327 | except UnavailableVideoError, err: | |
3328 | self._downloader.trouble(u'\nERROR: unable to download ' + mediaId) | |
3329 | continue | |
3330 | ||
3331 | ||
3332 | class EscapistIE(InfoExtractor): | |
3333 | """Information extractor for The Escapist """ | |
3334 | ||
3335 | _VALID_URL = r'^(https?://)?(www\.)?escapistmagazine\.com/videos/view/(?P<showname>[^/]+)/(?P<episode>[^/?]+)[/?]?.*$' | |
3336 | IE_NAME = u'escapist' | |
3337 | ||
3338 | def report_extraction(self, showName): | |
3339 | self._downloader.to_screen(u'[escapist] %s: Extracting information' % showName) | |
3340 | ||
3341 | def report_config_download(self, showName): | |
3342 | self._downloader.to_screen(u'[escapist] %s: Downloading configuration' % showName) | |
3343 | ||
235b3ba4 PH |
3344 | def _real_extract(self, url): |
3345 | htmlParser = HTMLParser.HTMLParser() | |
3346 | ||
3347 | mobj = re.match(self._VALID_URL, url) | |
3348 | if mobj is None: | |
3349 | self._downloader.trouble(u'ERROR: invalid URL: %s' % url) | |
3350 | return | |
3351 | showName = mobj.group('showname') | |
3352 | videoId = mobj.group('episode') | |
3353 | ||
3354 | self.report_extraction(showName) | |
3355 | try: | |
3356 | webPage = urllib2.urlopen(url).read() | |
3357 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
3358 | self._downloader.trouble(u'ERROR: unable to download webpage: ' + unicode(err)) | |
3359 | return | |
3360 | ||
3361 | descMatch = re.search('<meta name="description" content="([^"]*)"', webPage) | |
3362 | description = htmlParser.unescape(descMatch.group(1)) | |
3363 | imgMatch = re.search('<meta property="og:image" content="([^"]*)"', webPage) | |
3364 | imgUrl = htmlParser.unescape(imgMatch.group(1)) | |
3365 | playerUrlMatch = re.search('<meta property="og:video" content="([^"]*)"', webPage) | |
3366 | playerUrl = htmlParser.unescape(playerUrlMatch.group(1)) | |
3367 | configUrlMatch = re.search('config=(.*)$', playerUrl) | |
3368 | configUrl = urllib2.unquote(configUrlMatch.group(1)) | |
3369 | ||
3370 | self.report_config_download(showName) | |
3371 | try: | |
3372 | configJSON = urllib2.urlopen(configUrl).read() | |
3373 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
3374 | self._downloader.trouble(u'ERROR: unable to download configuration: ' + unicode(err)) | |
3375 | return | |
3376 | ||
3377 | # Technically, it's JavaScript, not JSON | |
3378 | configJSON = configJSON.replace("'", '"') | |
3379 | ||
3380 | try: | |
3381 | config = json.loads(configJSON) | |
3382 | except (ValueError,), err: | |
3383 | self._downloader.trouble(u'ERROR: Invalid JSON in configuration file: ' + unicode(err)) | |
3384 | return | |
3385 | ||
3386 | playlist = config['playlist'] | |
3387 | videoUrl = playlist[1]['url'] | |
3388 | ||
3389 | self._downloader.increment_downloads() | |
3390 | info = { | |
3391 | 'id': videoId, | |
3392 | 'url': videoUrl, | |
3393 | 'uploader': showName, | |
3394 | 'upload_date': None, | |
3395 | 'title': showName, | |
e092418d | 3396 | 'stitle': _simplify_title(showName), |
235b3ba4 PH |
3397 | 'ext': 'flv', |
3398 | 'format': 'flv', | |
3399 | 'thumbnail': imgUrl, | |
3400 | 'description': description, | |
3401 | 'player_url': playerUrl, | |
3402 | } | |
3403 | ||
3404 | try: | |
3405 | self._downloader.process_info(info) | |
3406 | except UnavailableVideoError, err: | |
3407 | self._downloader.trouble(u'\nERROR: unable to download ' + videoId) | |
3408 | ||
3409 | ||
3410 | class CollegeHumorIE(InfoExtractor): | |
3411 | """Information extractor for collegehumor.com""" | |
3412 | ||
3413 | _VALID_URL = r'^(?:https?://)?(?:www\.)?collegehumor\.com/video/(?P<videoid>[0-9]+)/(?P<shorttitle>.*)$' | |
3414 | IE_NAME = u'collegehumor' | |
3415 | ||
3416 | def report_webpage(self, video_id): | |
3417 | """Report information extraction.""" | |
3418 | self._downloader.to_screen(u'[%s] %s: Downloading webpage' % (self.IE_NAME, video_id)) | |
3419 | ||
3420 | def report_extraction(self, video_id): | |
3421 | """Report information extraction.""" | |
3422 | self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id)) | |
3423 | ||
235b3ba4 PH |
3424 | def _real_extract(self, url): |
3425 | htmlParser = HTMLParser.HTMLParser() | |
3426 | ||
3427 | mobj = re.match(self._VALID_URL, url) | |
3428 | if mobj is None: | |
3429 | self._downloader.trouble(u'ERROR: invalid URL: %s' % url) | |
3430 | return | |
3431 | video_id = mobj.group('videoid') | |
3432 | ||
3433 | self.report_webpage(video_id) | |
3434 | request = urllib2.Request(url) | |
3435 | try: | |
3436 | webpage = urllib2.urlopen(request).read() | |
3437 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
3438 | self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % str(err)) | |
3439 | return | |
3440 | ||
3441 | m = re.search(r'id="video:(?P<internalvideoid>[0-9]+)"', webpage) | |
3442 | if m is None: | |
3443 | self._downloader.trouble(u'ERROR: Cannot extract internal video ID') | |
3444 | return | |
3445 | internal_video_id = m.group('internalvideoid') | |
3446 | ||
3447 | info = { | |
3448 | 'id': video_id, | |
3449 | 'internal_id': internal_video_id, | |
3450 | } | |
3451 | ||
3452 | self.report_extraction(video_id) | |
3453 | xmlUrl = 'http://www.collegehumor.com/moogaloop/video:' + internal_video_id | |
3454 | try: | |
3455 | metaXml = urllib2.urlopen(xmlUrl).read() | |
3456 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
3457 | self._downloader.trouble(u'ERROR: unable to download video info XML: %s' % str(err)) | |
3458 | return | |
3459 | ||
3460 | mdoc = xml.etree.ElementTree.fromstring(metaXml) | |
3461 | try: | |
3462 | videoNode = mdoc.findall('./video')[0] | |
3463 | info['description'] = videoNode.findall('./description')[0].text | |
3464 | info['title'] = videoNode.findall('./caption')[0].text | |
e092418d | 3465 | info['stitle'] = _simplify_title(info['title']) |
235b3ba4 PH |
3466 | info['url'] = videoNode.findall('./file')[0].text |
3467 | info['thumbnail'] = videoNode.findall('./thumbnail')[0].text | |
3468 | info['ext'] = info['url'].rpartition('.')[2] | |
3469 | info['format'] = info['ext'] | |
3470 | except IndexError: | |
3471 | self._downloader.trouble(u'\nERROR: Invalid metadata XML file') | |
3472 | return | |
3473 | ||
3474 | self._downloader.increment_downloads() | |
3475 | ||
3476 | try: | |
3477 | self._downloader.process_info(info) | |
3478 | except UnavailableVideoError, err: | |
3479 | self._downloader.trouble(u'\nERROR: unable to download video') | |
3480 | ||
3481 | ||
3482 | class XVideosIE(InfoExtractor): | |
3483 | """Information extractor for xvideos.com""" | |
3484 | ||
3485 | _VALID_URL = r'^(?:https?://)?(?:www\.)?xvideos\.com/video([0-9]+)(?:.*)' | |
3486 | IE_NAME = u'xvideos' | |
3487 | ||
3488 | def report_webpage(self, video_id): | |
3489 | """Report information extraction.""" | |
3490 | self._downloader.to_screen(u'[%s] %s: Downloading webpage' % (self.IE_NAME, video_id)) | |
3491 | ||
3492 | def report_extraction(self, video_id): | |
3493 | """Report information extraction.""" | |
3494 | self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id)) | |
3495 | ||
235b3ba4 PH |
3496 | def _real_extract(self, url): |
3497 | htmlParser = HTMLParser.HTMLParser() | |
3498 | ||
3499 | mobj = re.match(self._VALID_URL, url) | |
3500 | if mobj is None: | |
3501 | self._downloader.trouble(u'ERROR: invalid URL: %s' % url) | |
3502 | return | |
3503 | video_id = mobj.group(1).decode('utf-8') | |
3504 | ||
3505 | self.report_webpage(video_id) | |
3506 | ||
3507 | request = urllib2.Request(r'http://www.xvideos.com/video' + video_id) | |
3508 | try: | |
3509 | webpage = urllib2.urlopen(request).read() | |
3510 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
3511 | self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % str(err)) | |
3512 | return | |
3513 | ||
3514 | self.report_extraction(video_id) | |
3515 | ||
3516 | ||
3517 | # Extract video URL | |
3518 | mobj = re.search(r'flv_url=(.+?)&', webpage) | |
3519 | if mobj is None: | |
3520 | self._downloader.trouble(u'ERROR: unable to extract video url') | |
3521 | return | |
3522 | video_url = urllib2.unquote(mobj.group(1).decode('utf-8')) | |
3523 | ||
3524 | ||
3525 | # Extract title | |
3526 | mobj = re.search(r'<title>(.*?)\s+-\s+XVID', webpage) | |
3527 | if mobj is None: | |
3528 | self._downloader.trouble(u'ERROR: unable to extract video title') | |
3529 | return | |
3530 | video_title = mobj.group(1).decode('utf-8') | |
3531 | ||
3532 | ||
3533 | # Extract video thumbnail | |
3534 | mobj = re.search(r'http://(?:img.*?\.)xvideos.com/videos/thumbs/[a-fA-F0-9]/[a-fA-F0-9]/[a-fA-F0-9]/([a-fA-F0-9.]+jpg)', webpage) | |
3535 | if mobj is None: | |
3536 | self._downloader.trouble(u'ERROR: unable to extract video thumbnail') | |
3537 | return | |
3538 | video_thumbnail = mobj.group(1).decode('utf-8') | |
3539 | ||
3540 | ||
3541 | ||
3542 | self._downloader.increment_downloads() | |
3543 | info = { | |
3544 | 'id': video_id, | |
3545 | 'url': video_url, | |
3546 | 'uploader': None, | |
3547 | 'upload_date': None, | |
3548 | 'title': video_title, | |
e092418d | 3549 | 'stitle': _simplify_title(video_title), |
235b3ba4 PH |
3550 | 'ext': 'flv', |
3551 | 'format': 'flv', | |
3552 | 'thumbnail': video_thumbnail, | |
3553 | 'description': None, | |
3554 | 'player_url': None, | |
3555 | } | |
3556 | ||
3557 | try: | |
3558 | self._downloader.process_info(info) | |
3559 | except UnavailableVideoError, err: | |
3560 | self._downloader.trouble(u'\nERROR: unable to download ' + video_id) | |
3561 | ||
3562 | ||
3563 | class SoundcloudIE(InfoExtractor): | |
3564 | """Information extractor for soundcloud.com | |
3565 | To access the media, the uid of the song and a stream token | |
3566 | must be extracted from the page source and the script must make | |
3567 | a request to media.soundcloud.com/crossdomain.xml. Then | |
3568 | the media can be grabbed by requesting from an url composed | |
3569 | of the stream token and uid | |
3570 | """ | |
3571 | ||
3572 | _VALID_URL = r'^(?:https?://)?(?:www\.)?soundcloud\.com/([\w\d-]+)/([\w\d-]+)' | |
3573 | IE_NAME = u'soundcloud' | |
3574 | ||
3575 | def __init__(self, downloader=None): | |
3576 | InfoExtractor.__init__(self, downloader) | |
3577 | ||
3578 | def report_webpage(self, video_id): | |
3579 | """Report information extraction.""" | |
3580 | self._downloader.to_screen(u'[%s] %s: Downloading webpage' % (self.IE_NAME, video_id)) | |
3581 | ||
3582 | def report_extraction(self, video_id): | |
3583 | """Report information extraction.""" | |
3584 | self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id)) | |
3585 | ||
3586 | def _real_extract(self, url): | |
3587 | htmlParser = HTMLParser.HTMLParser() | |
3588 | ||
3589 | mobj = re.match(self._VALID_URL, url) | |
3590 | if mobj is None: | |
3591 | self._downloader.trouble(u'ERROR: invalid URL: %s' % url) | |
3592 | return | |
3593 | ||
3594 | # extract uploader (which is in the url) | |
3595 | uploader = mobj.group(1).decode('utf-8') | |
3596 | # extract simple title (uploader + slug of song title) | |
3597 | slug_title = mobj.group(2).decode('utf-8') | |
3598 | simple_title = uploader + '-' + slug_title | |
3599 | ||
3600 | self.report_webpage('%s/%s' % (uploader, slug_title)) | |
3601 | ||
3602 | request = urllib2.Request('http://soundcloud.com/%s/%s' % (uploader, slug_title)) | |
3603 | try: | |
3604 | webpage = urllib2.urlopen(request).read() | |
3605 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
3606 | self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % str(err)) | |
3607 | return | |
3608 | ||
3609 | self.report_extraction('%s/%s' % (uploader, slug_title)) | |
3610 | ||
3611 | # extract uid and stream token that soundcloud hands out for access | |
3612 | mobj = re.search('"uid":"([\w\d]+?)".*?stream_token=([\w\d]+)', webpage) | |
3613 | if mobj: | |
3614 | video_id = mobj.group(1) | |
3615 | stream_token = mobj.group(2) | |
3616 | ||
3617 | # extract unsimplified title | |
3618 | mobj = re.search('"title":"(.*?)",', webpage) | |
3619 | if mobj: | |
3620 | title = mobj.group(1) | |
3621 | ||
3622 | # construct media url (with uid/token) | |
3623 | mediaURL = "http://media.soundcloud.com/stream/%s?stream_token=%s" | |
3624 | mediaURL = mediaURL % (video_id, stream_token) | |
3625 | ||
3626 | # description | |
3627 | description = u'No description available' | |
3628 | mobj = re.search('track-description-value"><p>(.*?)</p>', webpage) | |
3629 | if mobj: | |
3630 | description = mobj.group(1) | |
3631 | ||
3632 | # upload date | |
3633 | upload_date = None | |
3634 | mobj = re.search("pretty-date'>on ([\w]+ [\d]+, [\d]+ \d+:\d+)</abbr></h2>", webpage) | |
3635 | if mobj: | |
3636 | try: | |
3637 | upload_date = datetime.datetime.strptime(mobj.group(1), '%B %d, %Y %H:%M').strftime('%Y%m%d') | |
dc0a294a | 3638 | except Exception, e: |
235b3ba4 PH |
3639 | print str(e) |
3640 | ||
3641 | # for soundcloud, a request to a cross domain is required for cookies | |
3642 | request = urllib2.Request('http://media.soundcloud.com/crossdomain.xml', std_headers) | |
3643 | ||
3644 | try: | |
3645 | self._downloader.process_info({ | |
3646 | 'id': video_id.decode('utf-8'), | |
3647 | 'url': mediaURL, | |
3648 | 'uploader': uploader.decode('utf-8'), | |
3649 | 'upload_date': upload_date, | |
3650 | 'title': simple_title.decode('utf-8'), | |
3651 | 'stitle': simple_title.decode('utf-8'), | |
3652 | 'ext': u'mp3', | |
3653 | 'format': u'NA', | |
3654 | 'player_url': None, | |
3655 | 'description': description.decode('utf-8') | |
3656 | }) | |
3657 | except UnavailableVideoError: | |
3658 | self._downloader.trouble(u'\nERROR: unable to download video') | |
3659 | ||
3660 | ||
3661 | class InfoQIE(InfoExtractor): | |
3662 | """Information extractor for infoq.com""" | |
3663 | ||
3664 | _VALID_URL = r'^(?:https?://)?(?:www\.)?infoq\.com/[^/]+/[^/]+$' | |
3665 | IE_NAME = u'infoq' | |
3666 | ||
3667 | def report_webpage(self, video_id): | |
3668 | """Report information extraction.""" | |
3669 | self._downloader.to_screen(u'[%s] %s: Downloading webpage' % (self.IE_NAME, video_id)) | |
3670 | ||
3671 | def report_extraction(self, video_id): | |
3672 | """Report information extraction.""" | |
3673 | self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id)) | |
3674 | ||
235b3ba4 PH |
3675 | def _real_extract(self, url): |
3676 | htmlParser = HTMLParser.HTMLParser() | |
3677 | ||
3678 | mobj = re.match(self._VALID_URL, url) | |
3679 | if mobj is None: | |
3680 | self._downloader.trouble(u'ERROR: invalid URL: %s' % url) | |
3681 | return | |
3682 | ||
3683 | self.report_webpage(url) | |
3684 | ||
3685 | request = urllib2.Request(url) | |
3686 | try: | |
3687 | webpage = urllib2.urlopen(request).read() | |
3688 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
3689 | self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % str(err)) | |
3690 | return | |
3691 | ||
3692 | self.report_extraction(url) | |
3693 | ||
3694 | ||
3695 | # Extract video URL | |
3696 | mobj = re.search(r"jsclassref='([^']*)'", webpage) | |
3697 | if mobj is None: | |
3698 | self._downloader.trouble(u'ERROR: unable to extract video url') | |
3699 | return | |
3700 | video_url = 'rtmpe://video.infoq.com/cfx/st/' + urllib2.unquote(mobj.group(1).decode('base64')) | |
3701 | ||
3702 | ||
3703 | # Extract title | |
3704 | mobj = re.search(r'contentTitle = "(.*?)";', webpage) | |
3705 | if mobj is None: | |
3706 | self._downloader.trouble(u'ERROR: unable to extract video title') | |
3707 | return | |
3708 | video_title = mobj.group(1).decode('utf-8') | |
3709 | ||
3710 | # Extract description | |
3711 | video_description = u'No description available.' | |
3712 | mobj = re.search(r'<meta name="description" content="(.*)"(?:\s*/)?>', webpage) | |
3713 | if mobj is not None: | |
3714 | video_description = mobj.group(1).decode('utf-8') | |
3715 | ||
3716 | video_filename = video_url.split('/')[-1] | |
3717 | video_id, extension = video_filename.split('.') | |
3718 | ||
3719 | self._downloader.increment_downloads() | |
3720 | info = { | |
3721 | 'id': video_id, | |
3722 | 'url': video_url, | |
3723 | 'uploader': None, | |
3724 | 'upload_date': None, | |
3725 | 'title': video_title, | |
e092418d | 3726 | 'stitle': _simplify_title(video_title), |
235b3ba4 PH |
3727 | 'ext': extension, |
3728 | 'format': extension, # Extension is always(?) mp4, but seems to be flv | |
3729 | 'thumbnail': None, | |
3730 | 'description': video_description, | |
3731 | 'player_url': None, | |
3732 | } | |
3733 | ||
3734 | try: | |
3735 | self._downloader.process_info(info) | |
3736 | except UnavailableVideoError, err: | |
3737 | self._downloader.trouble(u'\nERROR: unable to download ' + video_url) | |
3738 | ||
849edab8 PH |
3739 | class MixcloudIE(InfoExtractor): |
3740 | """Information extractor for www.mixcloud.com""" | |
3741 | _VALID_URL = r'^(?:https?://)?(?:www\.)?mixcloud\.com/([\w\d-]+)/([\w\d-]+)' | |
3742 | IE_NAME = u'mixcloud' | |
3743 | ||
3744 | def __init__(self, downloader=None): | |
3745 | InfoExtractor.__init__(self, downloader) | |
3746 | ||
3747 | def report_download_json(self, file_id): | |
3748 | """Report JSON download.""" | |
3749 | self._downloader.to_screen(u'[%s] Downloading json' % self.IE_NAME) | |
3750 | ||
3751 | def report_extraction(self, file_id): | |
3752 | """Report information extraction.""" | |
3753 | self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, file_id)) | |
3754 | ||
3755 | def get_urls(self, jsonData, fmt, bitrate='best'): | |
3756 | """Get urls from 'audio_formats' section in json""" | |
3757 | file_url = None | |
3758 | try: | |
3759 | bitrate_list = jsonData[fmt] | |
3760 | if bitrate is None or bitrate == 'best' or bitrate not in bitrate_list: | |
3761 | bitrate = max(bitrate_list) # select highest | |
3762 | ||
3763 | url_list = jsonData[fmt][bitrate] | |
3764 | except TypeError: # we have no bitrate info. | |
3765 | url_list = jsonData[fmt] | |
3766 | ||
3767 | return url_list | |
3768 | ||
3769 | def check_urls(self, url_list): | |
3770 | """Returns 1st active url from list""" | |
3771 | for url in url_list: | |
3772 | try: | |
3773 | urllib2.urlopen(url) | |
3774 | return url | |
3775 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
3776 | url = None | |
3777 | ||
3778 | return None | |
3779 | ||
3780 | def _print_formats(self, formats): | |
3781 | print 'Available formats:' | |
3782 | for fmt in formats.keys(): | |
3783 | for b in formats[fmt]: | |
3784 | try: | |
3785 | ext = formats[fmt][b][0] | |
3786 | print '%s\t%s\t[%s]' % (fmt, b, ext.split('.')[-1]) | |
3787 | except TypeError: # we have no bitrate info | |
3788 | ext = formats[fmt][0] | |
3789 | print '%s\t%s\t[%s]' % (fmt, '??', ext.split('.')[-1]) | |
3790 | break | |
3791 | ||
3792 | def _real_extract(self, url): | |
3793 | mobj = re.match(self._VALID_URL, url) | |
3794 | if mobj is None: | |
3795 | self._downloader.trouble(u'ERROR: invalid URL: %s' % url) | |
3796 | return | |
3797 | # extract uploader & filename from url | |
3798 | uploader = mobj.group(1).decode('utf-8') | |
3799 | file_id = uploader + "-" + mobj.group(2).decode('utf-8') | |
3800 | ||
3801 | # construct API request | |
3802 | file_url = 'http://www.mixcloud.com/api/1/cloudcast/' + '/'.join(url.split('/')[-3:-1]) + '.json' | |
3803 | # retrieve .json file with links to files | |
3804 | request = urllib2.Request(file_url) | |
3805 | try: | |
3806 | self.report_download_json(file_url) | |
3807 | jsonData = urllib2.urlopen(request).read() | |
3808 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
3809 | self._downloader.trouble(u'ERROR: Unable to retrieve file: %s' % str(err)) | |
3810 | return | |
3811 | ||
3812 | # parse JSON | |
3813 | json_data = json.loads(jsonData) | |
3814 | player_url = json_data['player_swf_url'] | |
3815 | formats = dict(json_data['audio_formats']) | |
3816 | ||
3817 | req_format = self._downloader.params.get('format', None) | |
3818 | bitrate = None | |
3819 | ||
3820 | if self._downloader.params.get('listformats', None): | |
3821 | self._print_formats(formats) | |
3822 | return | |
3823 | ||
3824 | if req_format is None or req_format == 'best': | |
3825 | for format_param in formats.keys(): | |
3826 | url_list = self.get_urls(formats, format_param) | |
3827 | # check urls | |
3828 | file_url = self.check_urls(url_list) | |
3829 | if file_url is not None: | |
3830 | break # got it! | |
3831 | else: | |
3832 | if req_format not in formats.keys(): | |
3833 | self._downloader.trouble(u'ERROR: format is not available') | |
3834 | return | |
3835 | ||
3836 | url_list = self.get_urls(formats, req_format) | |
3837 | file_url = self.check_urls(url_list) | |
3838 | format_param = req_format | |
3839 | ||
3840 | # We have audio | |
3841 | self._downloader.increment_downloads() | |
3842 | try: | |
3843 | # Process file information | |
3844 | self._downloader.process_info({ | |
fefb166c PH |
3845 | 'id': file_id.decode('utf-8'), |
3846 | 'url': file_url.decode('utf-8'), | |
849edab8 | 3847 | 'uploader': uploader.decode('utf-8'), |
fefb166c PH |
3848 | 'upload_date': u'NA', |
3849 | 'title': json_data['name'], | |
3850 | 'stitle': _simplify_title(json_data['name']), | |
3851 | 'ext': file_url.split('.')[-1].decode('utf-8'), | |
3852 | 'format': (format_param is None and u'NA' or format_param.decode('utf-8')), | |
3853 | 'thumbnail': json_data['thumbnail_url'], | |
3854 | 'description': json_data['description'], | |
3855 | 'player_url': player_url.decode('utf-8'), | |
849edab8 PH |
3856 | }) |
3857 | except UnavailableVideoError, err: | |
3858 | self._downloader.trouble(u'ERROR: unable to download file') | |
3859 | ||
dd17922a PH |
3860 | class StanfordOpenClassroomIE(InfoExtractor): |
3861 | """Information extractor for Stanford's Open ClassRoom""" | |
3862 | ||
0b14e0b3 | 3863 | _VALID_URL = r'^(?:https?://)?openclassroom.stanford.edu(?P<path>/?|(/MainFolder/(?:HomePage|CoursePage|VideoPage)\.php([?]course=(?P<course>[^&]+)(&video=(?P<video>[^&]+))?(&.*)?)?))$' |
dd17922a PH |
3864 | IE_NAME = u'stanfordoc' |
3865 | ||
0b14e0b3 PH |
3866 | def report_download_webpage(self, objid): |
3867 | """Report information extraction.""" | |
3868 | self._downloader.to_screen(u'[%s] %s: Downloading webpage' % (self.IE_NAME, objid)) | |
3869 | ||
dd17922a PH |
3870 | def report_extraction(self, video_id): |
3871 | """Report information extraction.""" | |
3872 | self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id)) | |
3873 | ||
3874 | def _real_extract(self, url): | |
3875 | mobj = re.match(self._VALID_URL, url) | |
3876 | if mobj is None: | |
3877 | self._downloader.trouble(u'ERROR: invalid URL: %s' % url) | |
3878 | return | |
3879 | ||
3880 | if mobj.group('course') and mobj.group('video'): # A specific video | |
3881 | course = mobj.group('course') | |
3882 | video = mobj.group('video') | |
3883 | info = { | |
3884 | 'id': _simplify_title(course + '_' + video), | |
3885 | } | |
3886 | ||
3887 | self.report_extraction(info['id']) | |
3888 | baseUrl = 'http://openclassroom.stanford.edu/MainFolder/courses/' + course + '/videos/' | |
3889 | xmlUrl = baseUrl + video + '.xml' | |
3890 | try: | |
3891 | metaXml = urllib2.urlopen(xmlUrl).read() | |
3892 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
0b14e0b3 | 3893 | self._downloader.trouble(u'ERROR: unable to download video info XML: %s' % unicode(err)) |
dd17922a PH |
3894 | return |
3895 | mdoc = xml.etree.ElementTree.fromstring(metaXml) | |
3896 | try: | |
3897 | info['title'] = mdoc.findall('./title')[0].text | |
3898 | info['url'] = baseUrl + mdoc.findall('./videoFile')[0].text | |
3899 | except IndexError: | |
3900 | self._downloader.trouble(u'\nERROR: Invalid metadata XML file') | |
3901 | return | |
3902 | info['stitle'] = _simplify_title(info['title']) | |
3903 | info['ext'] = info['url'].rpartition('.')[2] | |
3904 | info['format'] = info['ext'] | |
3905 | self._downloader.increment_downloads() | |
3906 | try: | |
3907 | self._downloader.process_info(info) | |
3908 | except UnavailableVideoError, err: | |
3909 | self._downloader.trouble(u'\nERROR: unable to download video') | |
0b14e0b3 PH |
3910 | elif mobj.group('course'): # A course page |
3911 | unescapeHTML = HTMLParser.HTMLParser().unescape | |
dd17922a | 3912 | |
0b14e0b3 PH |
3913 | course = mobj.group('course') |
3914 | info = { | |
3915 | 'id': _simplify_title(course), | |
3916 | 'type': 'playlist', | |
3917 | } | |
dd17922a | 3918 | |
0b14e0b3 PH |
3919 | self.report_download_webpage(info['id']) |
3920 | try: | |
3921 | coursepage = urllib2.urlopen(url).read() | |
3922 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
3923 | self._downloader.trouble(u'ERROR: unable to download course info page: ' + unicode(err)) | |
3924 | return | |
dd17922a | 3925 | |
0b14e0b3 PH |
3926 | m = re.search('<h1>([^<]+)</h1>', coursepage) |
3927 | if m: | |
3928 | info['title'] = unescapeHTML(m.group(1)) | |
3929 | else: | |
3930 | info['title'] = info['id'] | |
3931 | info['stitle'] = _simplify_title(info['title']) | |
3932 | ||
3933 | m = re.search('<description>([^<]+)</description>', coursepage) | |
3934 | if m: | |
3935 | info['description'] = unescapeHTML(m.group(1)) | |
3936 | ||
3937 | links = _orderedSet(re.findall('<a href="(VideoPage.php\?[^"]+)">', coursepage)) | |
3938 | info['list'] = [ | |
3939 | { | |
3940 | 'type': 'reference', | |
3941 | 'url': 'http://openclassroom.stanford.edu/MainFolder/' + unescapeHTML(vpage), | |
3942 | } | |
3943 | for vpage in links] | |
3944 | ||
3945 | for entry in info['list']: | |
3946 | assert entry['type'] == 'reference' | |
3947 | self.extract(entry['url']) | |
3948 | else: # Root page | |
3949 | unescapeHTML = HTMLParser.HTMLParser().unescape | |
3950 | ||
3951 | info = { | |
3952 | 'id': 'Stanford OpenClassroom', | |
3953 | 'type': 'playlist', | |
3954 | } | |
3955 | ||
3956 | self.report_download_webpage(info['id']) | |
3957 | rootURL = 'http://openclassroom.stanford.edu/MainFolder/HomePage.php' | |
3958 | try: | |
3959 | rootpage = urllib2.urlopen(rootURL).read() | |
3960 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
3961 | self._downloader.trouble(u'ERROR: unable to download course info page: ' + unicode(err)) | |
3962 | return | |
3963 | ||
3964 | info['title'] = info['id'] | |
3965 | info['stitle'] = _simplify_title(info['title']) | |
3966 | ||
3967 | links = _orderedSet(re.findall('<a href="(CoursePage.php\?[^"]+)">', rootpage)) | |
3968 | info['list'] = [ | |
3969 | { | |
3970 | 'type': 'reference', | |
3971 | 'url': 'http://openclassroom.stanford.edu/MainFolder/' + unescapeHTML(cpage), | |
3972 | } | |
3973 | for cpage in links] | |
dd17922a | 3974 | |
0b14e0b3 PH |
3975 | for entry in info['list']: |
3976 | assert entry['type'] == 'reference' | |
3977 | self.extract(entry['url']) | |
235b3ba4 | 3978 | |
dcb3c22e | 3979 | class MTVIE(InfoExtractor): |
fefb166c PH |
3980 | """Information extractor for MTV.com""" |
3981 | ||
3982 | _VALID_URL = r'^(?P<proto>https?://)?(?:www\.)?mtv\.com/videos/[^/]+/(?P<videoid>[0-9]+)/[^/]+$' | |
3983 | IE_NAME = u'mtv' | |
3984 | ||
3985 | def report_webpage(self, video_id): | |
3986 | """Report information extraction.""" | |
3987 | self._downloader.to_screen(u'[%s] %s: Downloading webpage' % (self.IE_NAME, video_id)) | |
3988 | ||
3989 | def report_extraction(self, video_id): | |
3990 | """Report information extraction.""" | |
3991 | self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id)) | |
3992 | ||
3993 | def _real_extract(self, url): | |
3994 | mobj = re.match(self._VALID_URL, url) | |
3995 | if mobj is None: | |
3996 | self._downloader.trouble(u'ERROR: invalid URL: %s' % url) | |
3997 | return | |
3998 | if not mobj.group('proto'): | |
3999 | url = 'http://' + url | |
4000 | video_id = mobj.group('videoid') | |
4001 | self.report_webpage(video_id) | |
4002 | ||
4003 | request = urllib2.Request(url) | |
4004 | try: | |
4005 | webpage = urllib2.urlopen(request).read() | |
4006 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
4007 | self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % str(err)) | |
4008 | return | |
4009 | ||
4010 | mobj = re.search(r'<meta name="mtv_vt" content="([^"]+)"/>', webpage) | |
4011 | if mobj is None: | |
4012 | self._downloader.trouble(u'ERROR: unable to extract song name') | |
4013 | return | |
4014 | song_name = _unescapeHTML(mobj.group(1).decode('iso-8859-1')) | |
4015 | mobj = re.search(r'<meta name="mtv_an" content="([^"]+)"/>', webpage) | |
4016 | if mobj is None: | |
4017 | self._downloader.trouble(u'ERROR: unable to extract performer') | |
4018 | return | |
4019 | performer = _unescapeHTML(mobj.group(1).decode('iso-8859-1')) | |
4020 | video_title = performer + ' - ' + song_name | |
4021 | ||
4022 | mobj = re.search(r'<meta name="mtvn_uri" content="([^"]+)"/>', webpage) | |
4023 | if mobj is None: | |
4024 | self._downloader.trouble(u'ERROR: unable to mtvn_uri') | |
4025 | return | |
4026 | mtvn_uri = mobj.group(1) | |
4027 | ||
4028 | mobj = re.search(r'MTVN.Player.defaultPlaylistId = ([0-9]+);', webpage) | |
4029 | if mobj is None: | |
4030 | self._downloader.trouble(u'ERROR: unable to extract content id') | |
4031 | return | |
4032 | content_id = mobj.group(1) | |
4033 | ||
4034 | videogen_url = 'http://www.mtv.com/player/includes/mediaGen.jhtml?uri=' + mtvn_uri + '&id=' + content_id + '&vid=' + video_id + '&ref=www.mtvn.com&viewUri=' + mtvn_uri | |
4035 | self.report_extraction(video_id) | |
4036 | request = urllib2.Request(videogen_url) | |
4037 | try: | |
4038 | metadataXml = urllib2.urlopen(request).read() | |
4039 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
4040 | self._downloader.trouble(u'ERROR: unable to download video metadata: %s' % str(err)) | |
4041 | return | |
4042 | ||
4043 | mdoc = xml.etree.ElementTree.fromstring(metadataXml) | |
4044 | renditions = mdoc.findall('.//rendition') | |
4045 | ||
4046 | # For now, always pick the highest quality. | |
4047 | rendition = renditions[-1] | |
4048 | ||
4049 | try: | |
4050 | _,_,ext = rendition.attrib['type'].partition('/') | |
4051 | format = ext + '-' + rendition.attrib['width'] + 'x' + rendition.attrib['height'] + '_' + rendition.attrib['bitrate'] | |
4052 | video_url = rendition.find('./src').text | |
4053 | except KeyError: | |
4054 | self._downloader.trouble('Invalid rendition field.') | |
4055 | return | |
4056 | ||
4057 | self._downloader.increment_downloads() | |
4058 | info = { | |
4059 | 'id': video_id, | |
4060 | 'url': video_url, | |
4061 | 'uploader': performer, | |
4062 | 'title': video_title, | |
4063 | 'stitle': _simplify_title(video_title), | |
4064 | 'ext': ext, | |
4065 | 'format': format, | |
4066 | } | |
4067 | ||
4068 | try: | |
4069 | self._downloader.process_info(info) | |
4070 | except UnavailableVideoError, err: | |
4071 | self._downloader.trouble(u'\nERROR: unable to download ' + video_id) | |
dcb3c22e | 4072 | |
235b3ba4 PH |
4073 | |
4074 | class PostProcessor(object): | |
4075 | """Post Processor class. | |
4076 | ||
4077 | PostProcessor objects can be added to downloaders with their | |
4078 | add_post_processor() method. When the downloader has finished a | |
4079 | successful download, it will take its internal chain of PostProcessors | |
4080 | and start calling the run() method on each one of them, first with | |
4081 | an initial argument and then with the returned value of the previous | |
4082 | PostProcessor. | |
4083 | ||
4084 | The chain will be stopped if one of them ever returns None or the end | |
4085 | of the chain is reached. | |
4086 | ||
4087 | PostProcessor objects follow a "mutual registration" process similar | |
4088 | to InfoExtractor objects. | |
4089 | """ | |
4090 | ||
4091 | _downloader = None | |
4092 | ||
4093 | def __init__(self, downloader=None): | |
4094 | self._downloader = downloader | |
4095 | ||
4096 | def set_downloader(self, downloader): | |
4097 | """Sets the downloader for this PP.""" | |
4098 | self._downloader = downloader | |
4099 | ||
4100 | def run(self, information): | |
4101 | """Run the PostProcessor. | |
4102 | ||
4103 | The "information" argument is a dictionary like the ones | |
4104 | composed by InfoExtractors. The only difference is that this | |
4105 | one has an extra field called "filepath" that points to the | |
4106 | downloaded file. | |
4107 | ||
4108 | When this method returns None, the postprocessing chain is | |
4109 | stopped. However, this method may return an information | |
4110 | dictionary that will be passed to the next postprocessing | |
4111 | object in the chain. It can be the one it received after | |
4112 | changing some fields. | |
4113 | ||
4114 | In addition, this method may raise a PostProcessingError | |
4115 | exception that will be taken into account by the downloader | |
4116 | it was called from. | |
4117 | """ | |
4118 | return information # by default, do nothing | |
4119 | ||
633cf7cb PH |
4120 | class AudioConversionError(BaseException): |
4121 | def __init__(self, message): | |
4122 | self.message = message | |
235b3ba4 PH |
4123 | |
4124 | class FFmpegExtractAudioPP(PostProcessor): | |
4125 | ||
4126 | def __init__(self, downloader=None, preferredcodec=None, preferredquality=None, keepvideo=False): | |
4127 | PostProcessor.__init__(self, downloader) | |
4128 | if preferredcodec is None: | |
4129 | preferredcodec = 'best' | |
4130 | self._preferredcodec = preferredcodec | |
4131 | self._preferredquality = preferredquality | |
4132 | self._keepvideo = keepvideo | |
4133 | ||
4134 | @staticmethod | |
4135 | def get_audio_codec(path): | |
4136 | try: | |
fefb166c | 4137 | cmd = ['ffprobe', '-show_streams', '--', _encodeFilename(path)] |
235b3ba4 PH |
4138 | handle = subprocess.Popen(cmd, stderr=file(os.path.devnull, 'w'), stdout=subprocess.PIPE) |
4139 | output = handle.communicate()[0] | |
4140 | if handle.wait() != 0: | |
4141 | return None | |
4142 | except (IOError, OSError): | |
4143 | return None | |
4144 | audio_codec = None | |
4145 | for line in output.split('\n'): | |
4146 | if line.startswith('codec_name='): | |
4147 | audio_codec = line.split('=')[1].strip() | |
4148 | elif line.strip() == 'codec_type=audio' and audio_codec is not None: | |
4149 | return audio_codec | |
4150 | return None | |
4151 | ||
4152 | @staticmethod | |
4153 | def run_ffmpeg(path, out_path, codec, more_opts): | |
633cf7cb PH |
4154 | if codec is None: |
4155 | acodec_opts = [] | |
4156 | else: | |
4157 | acodec_opts = ['-acodec', codec] | |
fefb166c | 4158 | cmd = ['ffmpeg', '-y', '-i', _encodeFilename(path), '-vn'] + acodec_opts + more_opts + ['--', _encodeFilename(out_path)] |
235b3ba4 | 4159 | try: |
633cf7cb PH |
4160 | p = subprocess.Popen(cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE) |
4161 | stdout,stderr = p.communicate() | |
235b3ba4 | 4162 | except (IOError, OSError): |
633cf7cb PH |
4163 | e = sys.exc_info()[1] |
4164 | if isinstance(e, OSError) and e.errno == 2: | |
4165 | raise AudioConversionError('ffmpeg not found. Please install ffmpeg.') | |
4166 | else: | |
4167 | raise e | |
4168 | if p.returncode != 0: | |
4169 | msg = stderr.strip().split('\n')[-1] | |
4170 | raise AudioConversionError(msg) | |
235b3ba4 PH |
4171 | |
4172 | def run(self, information): | |
4173 | path = information['filepath'] | |
4174 | ||
4175 | filecodec = self.get_audio_codec(path) | |
4176 | if filecodec is None: | |
4177 | self._downloader.to_stderr(u'WARNING: unable to obtain file audio codec with ffprobe') | |
4178 | return None | |
4179 | ||
4180 | more_opts = [] | |
3e0ea7d0 PH |
4181 | if self._preferredcodec == 'best' or self._preferredcodec == filecodec or (self._preferredcodec == 'm4a' and filecodec == 'aac'): |
4182 | if self._preferredcodec == 'm4a' and filecodec == 'aac': | |
4183 | # Lossless, but in another container | |
4184 | acodec = 'copy' | |
4185 | extension = self._preferredcodec | |
4186 | more_opts = ['-absf', 'aac_adtstoasc'] | |
4187 | elif filecodec in ['aac', 'mp3', 'vorbis']: | |
235b3ba4 PH |
4188 | # Lossless if possible |
4189 | acodec = 'copy' | |
4190 | extension = filecodec | |
4191 | if filecodec == 'aac': | |
4192 | more_opts = ['-f', 'adts'] | |
4193 | if filecodec == 'vorbis': | |
4194 | extension = 'ogg' | |
4195 | else: | |
4196 | # MP3 otherwise. | |
4197 | acodec = 'libmp3lame' | |
4198 | extension = 'mp3' | |
4199 | more_opts = [] | |
4200 | if self._preferredquality is not None: | |
4201 | more_opts += ['-ab', self._preferredquality] | |
4202 | else: | |
4203 | # We convert the audio (lossy) | |
633cf7cb | 4204 | acodec = {'mp3': 'libmp3lame', 'aac': 'aac', 'm4a': 'aac', 'vorbis': 'libvorbis', 'wav': None}[self._preferredcodec] |
235b3ba4 PH |
4205 | extension = self._preferredcodec |
4206 | more_opts = [] | |
4207 | if self._preferredquality is not None: | |
4208 | more_opts += ['-ab', self._preferredquality] | |
4209 | if self._preferredcodec == 'aac': | |
4210 | more_opts += ['-f', 'adts'] | |
3e0ea7d0 PH |
4211 | if self._preferredcodec == 'm4a': |
4212 | more_opts += ['-absf', 'aac_adtstoasc'] | |
235b3ba4 PH |
4213 | if self._preferredcodec == 'vorbis': |
4214 | extension = 'ogg' | |
633cf7cb PH |
4215 | if self._preferredcodec == 'wav': |
4216 | extension = 'wav' | |
4217 | more_opts += ['-f', 'wav'] | |
235b3ba4 | 4218 | |
fefb166c PH |
4219 | prefix, sep, ext = path.rpartition(u'.') # not os.path.splitext, since the latter does not work on unicode in all setups |
4220 | new_path = prefix + sep + extension | |
4221 | self._downloader.to_screen(u'[ffmpeg] Destination: ' + new_path) | |
633cf7cb PH |
4222 | try: |
4223 | self.run_ffmpeg(path, new_path, acodec, more_opts) | |
4224 | except: | |
4225 | etype,e,tb = sys.exc_info() | |
4226 | if isinstance(e, AudioConversionError): | |
4227 | self._downloader.to_stderr(u'ERROR: audio conversion failed: ' + e.message) | |
4228 | else: | |
4229 | self._downloader.to_stderr(u'ERROR: error running ffmpeg') | |
235b3ba4 PH |
4230 | return None |
4231 | ||
4232 | # Try to update the date time for extracted audio file. | |
4233 | if information.get('filetime') is not None: | |
4234 | try: | |
fefb166c | 4235 | os.utime(_encodeFilename(new_path), (time.time(), information['filetime'])) |
235b3ba4 PH |
4236 | except: |
4237 | self._downloader.to_stderr(u'WARNING: Cannot update utime of audio file') | |
4238 | ||
4239 | if not self._keepvideo: | |
4240 | try: | |
fefb166c | 4241 | os.remove(_encodeFilename(path)) |
235b3ba4 PH |
4242 | except (IOError, OSError): |
4243 | self._downloader.to_stderr(u'WARNING: Unable to remove downloaded video file') | |
4244 | return None | |
4245 | ||
4246 | information['filepath'] = new_path | |
4247 | return information | |
4248 | ||
4249 | ||
4250 | def updateSelf(downloader, filename): | |
4251 | ''' Update the program file with the latest version from the repository ''' | |
4252 | # Note: downloader only used for options | |
4253 | if not os.access(filename, os.W_OK): | |
4254 | sys.exit('ERROR: no write permissions on %s' % filename) | |
4255 | ||
6d58c454 | 4256 | downloader.to_screen(u'Updating to latest version...') |
235b3ba4 PH |
4257 | |
4258 | try: | |
4259 | try: | |
4260 | urlh = urllib.urlopen(UPDATE_URL) | |
4261 | newcontent = urlh.read() | |
4262 | ||
4263 | vmatch = re.search("__version__ = '([^']+)'", newcontent) | |
4264 | if vmatch is not None and vmatch.group(1) == __version__: | |
6d58c454 | 4265 | downloader.to_screen(u'youtube-dl is up-to-date (' + __version__ + ')') |
235b3ba4 PH |
4266 | return |
4267 | finally: | |
4268 | urlh.close() | |
4269 | except (IOError, OSError), err: | |
4270 | sys.exit('ERROR: unable to download latest version') | |
4271 | ||
4272 | try: | |
4273 | outf = open(filename, 'wb') | |
4274 | try: | |
4275 | outf.write(newcontent) | |
4276 | finally: | |
4277 | outf.close() | |
4278 | except (IOError, OSError), err: | |
4279 | sys.exit('ERROR: unable to overwrite current version') | |
4280 | ||
6d58c454 | 4281 | downloader.to_screen(u'Updated youtube-dl. Restart youtube-dl to use the new version.') |
235b3ba4 PH |
4282 | |
4283 | def parseOpts(): | |
fefb166c | 4284 | def _readOptions(filename_bytes): |
c379c181 | 4285 | try: |
fefb166c | 4286 | optionf = open(filename_bytes) |
c379c181 PH |
4287 | except IOError: |
4288 | return [] # silently skip if file is not present | |
4289 | try: | |
4290 | res = [] | |
4291 | for l in optionf: | |
4292 | res += shlex.split(l, comments=True) | |
4293 | finally: | |
4294 | optionf.close() | |
4295 | return res | |
235b3ba4 PH |
4296 | |
4297 | def _format_option_string(option): | |
4298 | ''' ('-o', '--option') -> -o, --format METAVAR''' | |
4299 | ||
4300 | opts = [] | |
4301 | ||
4302 | if option._short_opts: opts.append(option._short_opts[0]) | |
4303 | if option._long_opts: opts.append(option._long_opts[0]) | |
4304 | if len(opts) > 1: opts.insert(1, ', ') | |
4305 | ||
4306 | if option.takes_value(): opts.append(' %s' % option.metavar) | |
4307 | ||
4308 | return "".join(opts) | |
4309 | ||
4310 | def _find_term_columns(): | |
4311 | columns = os.environ.get('COLUMNS', None) | |
4312 | if columns: | |
4313 | return int(columns) | |
4314 | ||
4315 | try: | |
4316 | sp = subprocess.Popen(['stty', 'size'], stdout=subprocess.PIPE, stderr=subprocess.PIPE) | |
4317 | out,err = sp.communicate() | |
4318 | return int(out.split()[1]) | |
4319 | except: | |
4320 | pass | |
4321 | return None | |
4322 | ||
4323 | max_width = 80 | |
4324 | max_help_position = 80 | |
4325 | ||
4326 | # No need to wrap help messages if we're on a wide console | |
4327 | columns = _find_term_columns() | |
4328 | if columns: max_width = columns | |
4329 | ||
4330 | fmt = optparse.IndentedHelpFormatter(width=max_width, max_help_position=max_help_position) | |
4331 | fmt.format_option_strings = _format_option_string | |
4332 | ||
4333 | kw = { | |
4334 | 'version' : __version__, | |
4335 | 'formatter' : fmt, | |
4336 | 'usage' : '%prog [options] url [url...]', | |
4337 | 'conflict_handler' : 'resolve', | |
4338 | } | |
4339 | ||
4340 | parser = optparse.OptionParser(**kw) | |
4341 | ||
4342 | # option groups | |
4343 | general = optparse.OptionGroup(parser, 'General Options') | |
4344 | selection = optparse.OptionGroup(parser, 'Video Selection') | |
4345 | authentication = optparse.OptionGroup(parser, 'Authentication Options') | |
4346 | video_format = optparse.OptionGroup(parser, 'Video Format Options') | |
4347 | postproc = optparse.OptionGroup(parser, 'Post-processing Options') | |
4348 | filesystem = optparse.OptionGroup(parser, 'Filesystem Options') | |
4349 | verbosity = optparse.OptionGroup(parser, 'Verbosity / Simulation Options') | |
4350 | ||
4351 | general.add_option('-h', '--help', | |
4352 | action='help', help='print this help text and exit') | |
4353 | general.add_option('-v', '--version', | |
4354 | action='version', help='print program version and exit') | |
4355 | general.add_option('-U', '--update', | |
4356 | action='store_true', dest='update_self', help='update this program to latest version') | |
4357 | general.add_option('-i', '--ignore-errors', | |
4358 | action='store_true', dest='ignoreerrors', help='continue on download errors', default=False) | |
4359 | general.add_option('-r', '--rate-limit', | |
4360 | dest='ratelimit', metavar='LIMIT', help='download rate limit (e.g. 50k or 44.6m)') | |
4361 | general.add_option('-R', '--retries', | |
4362 | dest='retries', metavar='RETRIES', help='number of retries (default is 10)', default=10) | |
4363 | general.add_option('--dump-user-agent', | |
4364 | action='store_true', dest='dump_user_agent', | |
4365 | help='display the current browser identification', default=False) | |
4366 | general.add_option('--list-extractors', | |
4367 | action='store_true', dest='list_extractors', | |
4368 | help='List all supported extractors and the URLs they would handle', default=False) | |
4369 | ||
4370 | selection.add_option('--playlist-start', | |
4371 | dest='playliststart', metavar='NUMBER', help='playlist video to start at (default is 1)', default=1) | |
4372 | selection.add_option('--playlist-end', | |
4373 | dest='playlistend', metavar='NUMBER', help='playlist video to end at (default is last)', default=-1) | |
4374 | selection.add_option('--match-title', dest='matchtitle', metavar='REGEX',help='download only matching titles (regex or caseless sub-string)') | |
4375 | selection.add_option('--reject-title', dest='rejecttitle', metavar='REGEX',help='skip download for matching titles (regex or caseless sub-string)') | |
b88a5250 | 4376 | selection.add_option('--max-downloads', metavar='NUMBER', dest='max_downloads', help='Abort after downloading NUMBER files', default=None) |
235b3ba4 PH |
4377 | |
4378 | authentication.add_option('-u', '--username', | |
4379 | dest='username', metavar='USERNAME', help='account username') | |
4380 | authentication.add_option('-p', '--password', | |
4381 | dest='password', metavar='PASSWORD', help='account password') | |
4382 | authentication.add_option('-n', '--netrc', | |
4383 | action='store_true', dest='usenetrc', help='use .netrc authentication data', default=False) | |
4384 | ||
4385 | ||
4386 | video_format.add_option('-f', '--format', | |
4387 | action='store', dest='format', metavar='FORMAT', help='video format code') | |
4388 | video_format.add_option('--all-formats', | |
4389 | action='store_const', dest='format', help='download all available video formats', const='all') | |
23e6b8ad PH |
4390 | video_format.add_option('--prefer-free-formats', |
4391 | action='store_true', dest='prefer_free_formats', default=False, help='prefer free video formats unless a specific one is requested') | |
235b3ba4 PH |
4392 | video_format.add_option('--max-quality', |
4393 | action='store', dest='format_limit', metavar='FORMAT', help='highest quality format to download') | |
4394 | video_format.add_option('-F', '--list-formats', | |
4395 | action='store_true', dest='listformats', help='list all available formats (currently youtube only)') | |
a0432a1e FV |
4396 | video_format.add_option('--write-srt', |
4397 | action='store_true', dest='writesubtitles', | |
4398 | help='write video closed captions to a .srt file (currently youtube only)', default=False) | |
4399 | video_format.add_option('--srt-lang', | |
4400 | action='store', dest='subtitleslang', metavar='LANG', | |
4401 | help='language of the closed captions to download (optional) use IETF language tags like \'en\'') | |
235b3ba4 PH |
4402 | |
4403 | ||
4404 | verbosity.add_option('-q', '--quiet', | |
4405 | action='store_true', dest='quiet', help='activates quiet mode', default=False) | |
4406 | verbosity.add_option('-s', '--simulate', | |
4407 | action='store_true', dest='simulate', help='do not download the video and do not write anything to disk', default=False) | |
4408 | verbosity.add_option('--skip-download', | |
4409 | action='store_true', dest='skip_download', help='do not download the video', default=False) | |
4410 | verbosity.add_option('-g', '--get-url', | |
4411 | action='store_true', dest='geturl', help='simulate, quiet but print URL', default=False) | |
4412 | verbosity.add_option('-e', '--get-title', | |
4413 | action='store_true', dest='gettitle', help='simulate, quiet but print title', default=False) | |
4414 | verbosity.add_option('--get-thumbnail', | |
4415 | action='store_true', dest='getthumbnail', | |
4416 | help='simulate, quiet but print thumbnail URL', default=False) | |
4417 | verbosity.add_option('--get-description', | |
4418 | action='store_true', dest='getdescription', | |
4419 | help='simulate, quiet but print video description', default=False) | |
4420 | verbosity.add_option('--get-filename', | |
4421 | action='store_true', dest='getfilename', | |
4422 | help='simulate, quiet but print output filename', default=False) | |
4423 | verbosity.add_option('--get-format', | |
4424 | action='store_true', dest='getformat', | |
4425 | help='simulate, quiet but print output format', default=False) | |
4426 | verbosity.add_option('--no-progress', | |
4427 | action='store_true', dest='noprogress', help='do not print progress bar', default=False) | |
4428 | verbosity.add_option('--console-title', | |
4429 | action='store_true', dest='consoletitle', | |
4430 | help='display progress in console titlebar', default=False) | |
09fbc6c9 PH |
4431 | verbosity.add_option('-v', '--verbose', |
4432 | action='store_true', dest='verbose', help='print various debugging information', default=False) | |
235b3ba4 PH |
4433 | |
4434 | ||
4435 | filesystem.add_option('-t', '--title', | |
4436 | action='store_true', dest='usetitle', help='use title in file name', default=False) | |
4437 | filesystem.add_option('-l', '--literal', | |
4438 | action='store_true', dest='useliteral', help='use literal title in file name', default=False) | |
4439 | filesystem.add_option('-A', '--auto-number', | |
4440 | action='store_true', dest='autonumber', | |
4441 | help='number downloaded files starting from 00000', default=False) | |
4442 | filesystem.add_option('-o', '--output', | |
c95da745 | 4443 | dest='outtmpl', metavar='TEMPLATE', help='output filename template. Use %(stitle)s to get the title, %(uploader)s for the uploader name, %(autonumber)s to get an automatically incremented number, %(ext)s for the filename extension, %(upload_date)s for the upload date (YYYYMMDD), and %% for a literal percent. Use - to output to stdout.') |
235b3ba4 PH |
4444 | filesystem.add_option('-a', '--batch-file', |
4445 | dest='batchfile', metavar='FILE', help='file containing URLs to download (\'-\' for stdin)') | |
4446 | filesystem.add_option('-w', '--no-overwrites', | |
4447 | action='store_true', dest='nooverwrites', help='do not overwrite files', default=False) | |
4448 | filesystem.add_option('-c', '--continue', | |
1ad85e50 | 4449 | action='store_true', dest='continue_dl', help='resume partially downloaded files', default=True) |
235b3ba4 PH |
4450 | filesystem.add_option('--no-continue', |
4451 | action='store_false', dest='continue_dl', | |
4452 | help='do not resume partially downloaded files (restart from beginning)') | |
4453 | filesystem.add_option('--cookies', | |
4454 | dest='cookiefile', metavar='FILE', help='file to read cookies from and dump cookie jar in') | |
4455 | filesystem.add_option('--no-part', | |
4456 | action='store_true', dest='nopart', help='do not use .part files', default=False) | |
4457 | filesystem.add_option('--no-mtime', | |
4458 | action='store_false', dest='updatetime', | |
4459 | help='do not use the Last-modified header to set the file modification time', default=True) | |
4460 | filesystem.add_option('--write-description', | |
4461 | action='store_true', dest='writedescription', | |
4462 | help='write video description to a .description file', default=False) | |
4463 | filesystem.add_option('--write-info-json', | |
4464 | action='store_true', dest='writeinfojson', | |
4465 | help='write video metadata to a .info.json file', default=False) | |
4466 | ||
4467 | ||
4468 | postproc.add_option('--extract-audio', action='store_true', dest='extractaudio', default=False, | |
4469 | help='convert video files to audio-only files (requires ffmpeg and ffprobe)') | |
4470 | postproc.add_option('--audio-format', metavar='FORMAT', dest='audioformat', default='best', | |
633cf7cb | 4471 | help='"best", "aac", "vorbis", "mp3", "m4a", or "wav"; best by default') |
235b3ba4 PH |
4472 | postproc.add_option('--audio-quality', metavar='QUALITY', dest='audioquality', default='128K', |
4473 | help='ffmpeg audio bitrate specification, 128k by default') | |
4474 | postproc.add_option('-k', '--keep-video', action='store_true', dest='keepvideo', default=False, | |
4475 | help='keeps the video file on disk after the post-processing; the video is erased by default') | |
4476 | ||
4477 | ||
4478 | parser.add_option_group(general) | |
4479 | parser.add_option_group(selection) | |
4480 | parser.add_option_group(filesystem) | |
4481 | parser.add_option_group(verbosity) | |
4482 | parser.add_option_group(video_format) | |
4483 | parser.add_option_group(authentication) | |
4484 | parser.add_option_group(postproc) | |
4485 | ||
0cd235ee PH |
4486 | xdg_config_home = os.environ.get('XDG_CONFIG_HOME') |
4487 | if xdg_config_home: | |
4488 | userConf = os.path.join(xdg_config_home, 'youtube-dl.conf') | |
4489 | else: | |
4490 | userConf = os.path.join(os.path.expanduser('~'), '.config', 'youtube-dl.conf') | |
4491 | argv = _readOptions('/etc/youtube-dl.conf') + _readOptions(userConf) + sys.argv[1:] | |
c379c181 | 4492 | opts, args = parser.parse_args(argv) |
235b3ba4 PH |
4493 | |
4494 | return parser, opts, args | |
4495 | ||
4496 | def gen_extractors(): | |
4497 | """ Return a list of an instance of every supported extractor. | |
4498 | The order does matter; the first extractor matched is the one handling the URL. | |
4499 | """ | |
4500 | youtube_ie = YoutubeIE() | |
4501 | google_ie = GoogleIE() | |
4502 | yahoo_ie = YahooIE() | |
4503 | return [ | |
4504 | YoutubePlaylistIE(youtube_ie), | |
4505 | YoutubeUserIE(youtube_ie), | |
4506 | YoutubeSearchIE(youtube_ie), | |
4507 | youtube_ie, | |
4508 | MetacafeIE(youtube_ie), | |
4509 | DailymotionIE(), | |
4510 | google_ie, | |
4511 | GoogleSearchIE(google_ie), | |
4512 | PhotobucketIE(), | |
4513 | yahoo_ie, | |
4514 | YahooSearchIE(yahoo_ie), | |
4515 | DepositFilesIE(), | |
4516 | FacebookIE(), | |
4517 | BlipTVIE(), | |
4518 | VimeoIE(), | |
4519 | MyVideoIE(), | |
4520 | ComedyCentralIE(), | |
4521 | EscapistIE(), | |
4522 | CollegeHumorIE(), | |
4523 | XVideosIE(), | |
4524 | SoundcloudIE(), | |
4525 | InfoQIE(), | |
849edab8 | 4526 | MixcloudIE(), |
dd17922a | 4527 | StanfordOpenClassroomIE(), |
dcb3c22e | 4528 | MTVIE(), |
235b3ba4 PH |
4529 | |
4530 | GenericIE() | |
4531 | ] | |
4532 | ||
4533 | def _real_main(): | |
4534 | parser, opts, args = parseOpts() | |
4535 | ||
4536 | # Open appropriate CookieJar | |
4537 | if opts.cookiefile is None: | |
4538 | jar = cookielib.CookieJar() | |
4539 | else: | |
4540 | try: | |
4541 | jar = cookielib.MozillaCookieJar(opts.cookiefile) | |
4542 | if os.path.isfile(opts.cookiefile) and os.access(opts.cookiefile, os.R_OK): | |
4543 | jar.load() | |
4544 | except (IOError, OSError), err: | |
4545 | sys.exit(u'ERROR: unable to open cookie file') | |
4546 | ||
4547 | # Dump user agent | |
4548 | if opts.dump_user_agent: | |
4549 | print std_headers['User-Agent'] | |
4550 | sys.exit(0) | |
4551 | ||
4552 | # Batch file verification | |
4553 | batchurls = [] | |
4554 | if opts.batchfile is not None: | |
4555 | try: | |
4556 | if opts.batchfile == '-': | |
4557 | batchfd = sys.stdin | |
4558 | else: | |
4559 | batchfd = open(opts.batchfile, 'r') | |
4560 | batchurls = batchfd.readlines() | |
4561 | batchurls = [x.strip() for x in batchurls] | |
4562 | batchurls = [x for x in batchurls if len(x) > 0 and not re.search(r'^[#/;]', x)] | |
4563 | except IOError: | |
4564 | sys.exit(u'ERROR: batch file could not be read') | |
4565 | all_urls = batchurls + args | |
4566 | ||
4567 | # General configuration | |
4568 | cookie_processor = urllib2.HTTPCookieProcessor(jar) | |
09fbc6c9 PH |
4569 | proxy_handler = urllib2.ProxyHandler() |
4570 | opener = urllib2.build_opener(proxy_handler, cookie_processor, YoutubeDLHandler()) | |
235b3ba4 PH |
4571 | urllib2.install_opener(opener) |
4572 | socket.setdefaulttimeout(300) # 5 minutes should be enough (famous last words) | |
4573 | ||
09fbc6c9 PH |
4574 | if opts.verbose: |
4575 | print(u'[debug] Proxy map: ' + str(proxy_handler.proxies)) | |
4576 | ||
235b3ba4 PH |
4577 | extractors = gen_extractors() |
4578 | ||
4579 | if opts.list_extractors: | |
4580 | for ie in extractors: | |
4581 | print(ie.IE_NAME) | |
4582 | matchedUrls = filter(lambda url: ie.suitable(url), all_urls) | |
4583 | all_urls = filter(lambda url: url not in matchedUrls, all_urls) | |
4584 | for mu in matchedUrls: | |
4585 | print(u' ' + mu) | |
4586 | sys.exit(0) | |
4587 | ||
4588 | # Conflicting, missing and erroneous options | |
4589 | if opts.usenetrc and (opts.username is not None or opts.password is not None): | |
4590 | parser.error(u'using .netrc conflicts with giving username/password') | |
4591 | if opts.password is not None and opts.username is None: | |
4592 | parser.error(u'account username missing') | |
4593 | if opts.outtmpl is not None and (opts.useliteral or opts.usetitle or opts.autonumber): | |
4594 | parser.error(u'using output template conflicts with using title, literal title or auto number') | |
4595 | if opts.usetitle and opts.useliteral: | |
4596 | parser.error(u'using title conflicts with using literal title') | |
4597 | if opts.username is not None and opts.password is None: | |
4598 | opts.password = getpass.getpass(u'Type account password and press return:') | |
4599 | if opts.ratelimit is not None: | |
4600 | numeric_limit = FileDownloader.parse_bytes(opts.ratelimit) | |
4601 | if numeric_limit is None: | |
4602 | parser.error(u'invalid rate limit specified') | |
4603 | opts.ratelimit = numeric_limit | |
4604 | if opts.retries is not None: | |
4605 | try: | |
4606 | opts.retries = long(opts.retries) | |
4607 | except (TypeError, ValueError), err: | |
4608 | parser.error(u'invalid retry count specified') | |
4609 | try: | |
4610 | opts.playliststart = int(opts.playliststart) | |
4611 | if opts.playliststart <= 0: | |
4612 | raise ValueError(u'Playlist start must be positive') | |
4613 | except (TypeError, ValueError), err: | |
4614 | parser.error(u'invalid playlist start number specified') | |
4615 | try: | |
4616 | opts.playlistend = int(opts.playlistend) | |
4617 | if opts.playlistend != -1 and (opts.playlistend <= 0 or opts.playlistend < opts.playliststart): | |
4618 | raise ValueError(u'Playlist end must be greater than playlist start') | |
4619 | except (TypeError, ValueError), err: | |
4620 | parser.error(u'invalid playlist end number specified') | |
4621 | if opts.extractaudio: | |
633cf7cb | 4622 | if opts.audioformat not in ['best', 'aac', 'mp3', 'vorbis', 'm4a', 'wav']: |
235b3ba4 PH |
4623 | parser.error(u'invalid audio format specified') |
4624 | ||
4625 | # File downloader | |
4626 | fd = FileDownloader({ | |
4627 | 'usenetrc': opts.usenetrc, | |
4628 | 'username': opts.username, | |
4629 | 'password': opts.password, | |
4630 | 'quiet': (opts.quiet or opts.geturl or opts.gettitle or opts.getthumbnail or opts.getdescription or opts.getfilename or opts.getformat), | |
4631 | 'forceurl': opts.geturl, | |
4632 | 'forcetitle': opts.gettitle, | |
4633 | 'forcethumbnail': opts.getthumbnail, | |
4634 | 'forcedescription': opts.getdescription, | |
4635 | 'forcefilename': opts.getfilename, | |
4636 | 'forceformat': opts.getformat, | |
4637 | 'simulate': opts.simulate, | |
4638 | 'skip_download': (opts.skip_download or opts.simulate or opts.geturl or opts.gettitle or opts.getthumbnail or opts.getdescription or opts.getfilename or opts.getformat), | |
4639 | 'format': opts.format, | |
4640 | 'format_limit': opts.format_limit, | |
4641 | 'listformats': opts.listformats, | |
4642 | 'outtmpl': ((opts.outtmpl is not None and opts.outtmpl.decode(preferredencoding())) | |
4643 | or (opts.format == '-1' and opts.usetitle and u'%(stitle)s-%(id)s-%(format)s.%(ext)s') | |
4644 | or (opts.format == '-1' and opts.useliteral and u'%(title)s-%(id)s-%(format)s.%(ext)s') | |
4645 | or (opts.format == '-1' and u'%(id)s-%(format)s.%(ext)s') | |
4646 | or (opts.usetitle and opts.autonumber and u'%(autonumber)s-%(stitle)s-%(id)s.%(ext)s') | |
4647 | or (opts.useliteral and opts.autonumber and u'%(autonumber)s-%(title)s-%(id)s.%(ext)s') | |
4648 | or (opts.usetitle and u'%(stitle)s-%(id)s.%(ext)s') | |
4649 | or (opts.useliteral and u'%(title)s-%(id)s.%(ext)s') | |
4650 | or (opts.autonumber and u'%(autonumber)s-%(id)s.%(ext)s') | |
4651 | or u'%(id)s.%(ext)s'), | |
4652 | 'ignoreerrors': opts.ignoreerrors, | |
4653 | 'ratelimit': opts.ratelimit, | |
4654 | 'nooverwrites': opts.nooverwrites, | |
4655 | 'retries': opts.retries, | |
4656 | 'continuedl': opts.continue_dl, | |
4657 | 'noprogress': opts.noprogress, | |
4658 | 'playliststart': opts.playliststart, | |
4659 | 'playlistend': opts.playlistend, | |
4660 | 'logtostderr': opts.outtmpl == '-', | |
4661 | 'consoletitle': opts.consoletitle, | |
4662 | 'nopart': opts.nopart, | |
4663 | 'updatetime': opts.updatetime, | |
4664 | 'writedescription': opts.writedescription, | |
4665 | 'writeinfojson': opts.writeinfojson, | |
a0432a1e FV |
4666 | 'writesubtitles': opts.writesubtitles, |
4667 | 'subtitleslang': opts.subtitleslang, | |
235b3ba4 PH |
4668 | 'matchtitle': opts.matchtitle, |
4669 | 'rejecttitle': opts.rejecttitle, | |
c379c181 | 4670 | 'max_downloads': opts.max_downloads, |
23e6b8ad | 4671 | 'prefer_free_formats': opts.prefer_free_formats, |
871dbd3c | 4672 | 'verbose': opts.verbose, |
235b3ba4 PH |
4673 | }) |
4674 | for extractor in extractors: | |
4675 | fd.add_info_extractor(extractor) | |
4676 | ||
4677 | # PostProcessors | |
4678 | if opts.extractaudio: | |
4679 | fd.add_post_processor(FFmpegExtractAudioPP(preferredcodec=opts.audioformat, preferredquality=opts.audioquality, keepvideo=opts.keepvideo)) | |
4680 | ||
4681 | # Update version | |
4682 | if opts.update_self: | |
4683 | updateSelf(fd, sys.argv[0]) | |
4684 | ||
4685 | # Maybe do nothing | |
4686 | if len(all_urls) < 1: | |
4687 | if not opts.update_self: | |
4688 | parser.error(u'you must provide at least one URL') | |
4689 | else: | |
4690 | sys.exit() | |
94fd3201 PH |
4691 | |
4692 | try: | |
4693 | retcode = fd.download(all_urls) | |
4694 | except MaxDownloadsReached: | |
4695 | fd.to_screen(u'--max-download limit reached, aborting.') | |
4696 | retcode = 101 | |
235b3ba4 PH |
4697 | |
4698 | # Dump cookie jar if requested | |
4699 | if opts.cookiefile is not None: | |
4700 | try: | |
4701 | jar.save() | |
4702 | except (IOError, OSError), err: | |
4703 | sys.exit(u'ERROR: unable to save cookie jar') | |
4704 | ||
4705 | sys.exit(retcode) | |
4706 | ||
4707 | def main(): | |
4708 | try: | |
4709 | _real_main() | |
4710 | except DownloadError: | |
4711 | sys.exit(1) | |
4712 | except SameFileError: | |
4713 | sys.exit(u'ERROR: fixed output name but more than one file to download') | |
4714 | except KeyboardInterrupt: | |
4715 | sys.exit(u'\nERROR: Interrupted by user') | |
4716 | ||
4717 | if __name__ == '__main__': | |
4718 | main() | |
4719 | ||
4720 | # vim: set ts=4 sw=4 sts=4 noet ai si filetype=python: |