]>
Commit | Line | Data |
---|---|---|
4fa74b52 RG |
1 | #!/usr/bin/env python |
2 | # -*- coding: utf-8 -*- | |
2770590d GV |
3 | |
4 | __author__ = ( | |
2c8d32de PH |
5 | 'Ricardo Garcia Gonzalez', |
6 | 'Danny Colligan', | |
7 | 'Benjamin Johnson', | |
8 | 'Vasyl\' Vavrychuk', | |
9 | 'Witold Baryluk', | |
10 | 'Paweł Paprota', | |
11 | 'Gergely Imreh', | |
6ae796b1 | 12 | 'Rogério Brito', |
eb11aacc | 13 | 'Philipp Hagemeister', |
6fc5b0bb | 14 | 'Sören Schulze', |
2770590d GV |
15 | ) |
16 | ||
2c8d32de | 17 | __license__ = 'Public Domain' |
54d47874 | 18 | __version__ = '2011.09.30' |
2770590d | 19 | |
8236e851 | 20 | UPDATE_URL = 'https://raw.github.com/rg3/youtube-dl/master/youtube-dl' |
d207e7cf | 21 | |
80066952 | 22 | import cookielib |
a1f03c7b | 23 | import datetime |
1987c232 | 24 | import gzip |
4fa74b52 | 25 | import htmlentitydefs |
f9c68787 | 26 | import HTMLParser |
4fa74b52 | 27 | import httplib |
2546e767 | 28 | import locale |
4fa74b52 RG |
29 | import math |
30 | import netrc | |
31 | import os | |
32 | import os.path | |
33 | import re | |
34 | import socket | |
35 | import string | |
0487b407 | 36 | import subprocess |
4fa74b52 RG |
37 | import sys |
38 | import time | |
39 | import urllib | |
40 | import urllib2 | |
c6b55a8d | 41 | import warnings |
1987c232 | 42 | import zlib |
a04e80a4 | 43 | |
0a3c8b62 PH |
44 | if os.name == 'nt': |
45 | import ctypes | |
46 | ||
47 | try: | |
48 | import email.utils | |
49 | except ImportError: # Python 2.4 | |
50 | import email.Utils | |
c6b55a8d PH |
51 | try: |
52 | import cStringIO as StringIO | |
53 | except ImportError: | |
54 | import StringIO | |
55 | ||
a04e80a4 RG |
56 | # parse_qs was moved from the cgi module to the urlparse module recently. |
57 | try: | |
58 | from urlparse import parse_qs | |
59 | except ImportError: | |
60 | from cgi import parse_qs | |
4fa74b52 | 61 | |
c6b55a8d PH |
62 | try: |
63 | import lxml.etree | |
2b70537d | 64 | except ImportError: |
c6b55a8d PH |
65 | pass # Handled below |
66 | ||
c8e30044 PH |
67 | try: |
68 | import xml.etree.ElementTree | |
afb5b55d PH |
69 | except ImportError: # Python<2.5: Not officially supported, but let it slip |
70 | warnings.warn('xml.etree.ElementTree support is missing. Consider upgrading to Python >= 2.5 if you get related errors.') | |
c8e30044 | 71 | |
f995f712 | 72 | std_headers = { |
c44b9ee9 | 73 | 'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64; rv:5.0.1) Gecko/20100101 Firefox/5.0.1', |
4fa74b52 | 74 | 'Accept-Charset': 'ISO-8859-1,utf-8;q=0.7,*;q=0.7', |
96942e62 | 75 | 'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8', |
a57ed21f | 76 | 'Accept-Encoding': 'gzip, deflate', |
4fa74b52 RG |
77 | 'Accept-Language': 'en-us,en;q=0.5', |
78 | } | |
79 | ||
80 | simple_title_chars = string.ascii_letters.decode('ascii') + string.digits.decode('ascii') | |
81 | ||
437d76c1 PH |
82 | try: |
83 | import json | |
91e6a385 | 84 | except ImportError: # Python <2.6, use trivialjson (https://github.com/phihag/trivialjson): |
437d76c1 PH |
85 | import re |
86 | class json(object): | |
87 | @staticmethod | |
88 | def loads(s): | |
89 | s = s.decode('UTF-8') | |
90 | def raiseError(msg, i): | |
91 | raise ValueError(msg + ' at position ' + str(i) + ' of ' + repr(s) + ': ' + repr(s[i:])) | |
92 | def skipSpace(i, expectMore=True): | |
93 | while i < len(s) and s[i] in ' \t\r\n': | |
94 | i += 1 | |
95 | if expectMore: | |
96 | if i >= len(s): | |
97 | raiseError('Premature end', i) | |
98 | return i | |
99 | def decodeEscape(match): | |
100 | esc = match.group(1) | |
101 | _STATIC = { | |
102 | '"': '"', | |
103 | '\\': '\\', | |
104 | '/': '/', | |
105 | 'b': unichr(0x8), | |
106 | 'f': unichr(0xc), | |
107 | 'n': '\n', | |
108 | 'r': '\r', | |
109 | 't': '\t', | |
110 | } | |
111 | if esc in _STATIC: | |
112 | return _STATIC[esc] | |
113 | if esc[0] == 'u': | |
114 | if len(esc) == 1+4: | |
115 | return unichr(int(esc[1:5], 16)) | |
116 | if len(esc) == 5+6 and esc[5:7] == '\\u': | |
117 | hi = int(esc[1:5], 16) | |
118 | low = int(esc[7:11], 16) | |
119 | return unichr((hi - 0xd800) * 0x400 + low - 0xdc00 + 0x10000) | |
120 | raise ValueError('Unknown escape ' + str(esc)) | |
121 | def parseString(i): | |
122 | i += 1 | |
123 | e = i | |
124 | while True: | |
125 | e = s.index('"', e) | |
126 | bslashes = 0 | |
127 | while s[e-bslashes-1] == '\\': | |
128 | bslashes += 1 | |
129 | if bslashes % 2 == 1: | |
130 | e += 1 | |
131 | continue | |
132 | break | |
133 | rexp = re.compile(r'\\(u[dD][89aAbB][0-9a-fA-F]{2}\\u[0-9a-fA-F]{4}|u[0-9a-fA-F]{4}|.|$)') | |
134 | stri = rexp.sub(decodeEscape, s[i:e]) | |
135 | return (e+1,stri) | |
136 | def parseObj(i): | |
137 | i += 1 | |
138 | res = {} | |
139 | i = skipSpace(i) | |
140 | if s[i] == '}': # Empty dictionary | |
141 | return (i+1,res) | |
142 | while True: | |
143 | if s[i] != '"': | |
144 | raiseError('Expected a string object key', i) | |
145 | i,key = parseString(i) | |
146 | i = skipSpace(i) | |
147 | if i >= len(s) or s[i] != ':': | |
148 | raiseError('Expected a colon', i) | |
149 | i,val = parse(i+1) | |
150 | res[key] = val | |
151 | i = skipSpace(i) | |
152 | if s[i] == '}': | |
153 | return (i+1, res) | |
154 | if s[i] != ',': | |
155 | raiseError('Expected comma or closing curly brace', i) | |
156 | i = skipSpace(i+1) | |
157 | def parseArray(i): | |
158 | res = [] | |
159 | i = skipSpace(i+1) | |
160 | if s[i] == ']': # Empty array | |
161 | return (i+1,res) | |
162 | while True: | |
163 | i,val = parse(i) | |
164 | res.append(val) | |
165 | i = skipSpace(i) # Raise exception if premature end | |
166 | if s[i] == ']': | |
167 | return (i+1, res) | |
168 | if s[i] != ',': | |
169 | raiseError('Expected a comma or closing bracket', i) | |
170 | i = skipSpace(i+1) | |
171 | def parseDiscrete(i): | |
172 | for k,v in {'true': True, 'false': False, 'null': None}.items(): | |
173 | if s.startswith(k, i): | |
174 | return (i+len(k), v) | |
175 | raiseError('Not a boolean (or null)', i) | |
176 | def parseNumber(i): | |
177 | mobj = re.match('^(-?(0|[1-9][0-9]*)(\.[0-9]*)?([eE][+-]?[0-9]+)?)', s[i:]) | |
178 | if mobj is None: | |
179 | raiseError('Not a number', i) | |
180 | nums = mobj.group(1) | |
181 | if '.' in nums or 'e' in nums or 'E' in nums: | |
182 | return (i+len(nums), float(nums)) | |
183 | return (i+len(nums), int(nums)) | |
184 | CHARMAP = {'{': parseObj, '[': parseArray, '"': parseString, 't': parseDiscrete, 'f': parseDiscrete, 'n': parseDiscrete} | |
185 | def parse(i): | |
186 | i = skipSpace(i) | |
187 | i,res = CHARMAP.get(s[i], parseNumber)(i) | |
188 | i = skipSpace(i, False) | |
189 | return (i,res) | |
190 | i,res = parse(0) | |
191 | if i < len(s): | |
192 | raise ValueError('Extra data at end of input (index ' + str(i) + ' of ' + repr(s) + ': ' + repr(s[i:]) + ')') | |
193 | return res | |
194 | ||
eae2666c RG |
195 | def preferredencoding(): |
196 | """Get preferred encoding. | |
197 | ||
198 | Returns the best encoding scheme for the system, based on | |
199 | locale.getpreferredencoding() and some further tweaks. | |
200 | """ | |
f94b636c RG |
201 | def yield_preferredencoding(): |
202 | try: | |
203 | pref = locale.getpreferredencoding() | |
204 | u'TEST'.encode(pref) | |
205 | except: | |
206 | pref = 'UTF-8' | |
207 | while True: | |
208 | yield pref | |
209 | return yield_preferredencoding().next() | |
eae2666c | 210 | |
c0a10ca8 | 211 | |
490fd7ae RG |
212 | def htmlentity_transform(matchobj): |
213 | """Transforms an HTML entity to a Unicode character. | |
d3975459 | 214 | |
490fd7ae RG |
215 | This function receives a match object and is intended to be used with |
216 | the re.sub() function. | |
217 | """ | |
218 | entity = matchobj.group(1) | |
219 | ||
220 | # Known non-numeric HTML entity | |
221 | if entity in htmlentitydefs.name2codepoint: | |
222 | return unichr(htmlentitydefs.name2codepoint[entity]) | |
223 | ||
224 | # Unicode character | |
225 | mobj = re.match(ur'(?u)#(x?\d+)', entity) | |
226 | if mobj is not None: | |
227 | numstr = mobj.group(1) | |
228 | if numstr.startswith(u'x'): | |
229 | base = 16 | |
230 | numstr = u'0%s' % numstr | |
231 | else: | |
232 | base = 10 | |
233 | return unichr(long(numstr, base)) | |
234 | ||
235 | # Unknown entity in name, return its literal representation | |
236 | return (u'&%s;' % entity) | |
237 | ||
c0a10ca8 | 238 | |
490fd7ae | 239 | def sanitize_title(utitle): |
31bcb480 | 240 | """Sanitizes a video title so it could be used as part of a filename.""" |
490fd7ae | 241 | utitle = re.sub(ur'(?u)&(.+?);', htmlentity_transform, utitle) |
490fd7ae RG |
242 | return utitle.replace(unicode(os.sep), u'%') |
243 | ||
c0a10ca8 | 244 | |
31bcb480 RG |
245 | def sanitize_open(filename, open_mode): |
246 | """Try to open the given filename, and slightly tweak it if this fails. | |
247 | ||
248 | Attempts to open the given filename. If this fails, it tries to change | |
249 | the filename slightly, step by step, until it's either able to open it | |
250 | or it fails and raises a final exception, like the standard open() | |
251 | function. | |
252 | ||
253 | It returns the tuple (stream, definitive_file_name). | |
254 | """ | |
255 | try: | |
131bc765 | 256 | if filename == u'-': |
e08878f4 RG |
257 | if sys.platform == 'win32': |
258 | import msvcrt | |
259 | msvcrt.setmode(sys.stdout.fileno(), os.O_BINARY) | |
131bc765 | 260 | return (sys.stdout, filename) |
31bcb480 RG |
261 | stream = open(filename, open_mode) |
262 | return (stream, filename) | |
263 | except (IOError, OSError), err: | |
264 | # In case of error, try to remove win32 forbidden chars | |
ca6a11fa | 265 | filename = re.sub(ur'[/<>:"\|\?\*]', u'#', filename) |
31bcb480 RG |
266 | |
267 | # An exception here should be caught in the caller | |
268 | stream = open(filename, open_mode) | |
269 | return (stream, filename) | |
270 | ||
c0a10ca8 | 271 | |
09bd408c | 272 | def timeconvert(timestr): |
c0a10ca8 F |
273 | """Convert RFC 2822 defined time string into system timestamp""" |
274 | timestamp = None | |
275 | timetuple = email.utils.parsedate_tz(timestr) | |
276 | if timetuple is not None: | |
277 | timestamp = email.utils.mktime_tz(timetuple) | |
278 | return timestamp | |
279 | ||
09bd408c | 280 | |
e5bf0f55 RG |
281 | class DownloadError(Exception): |
282 | """Download Error exception. | |
d3975459 | 283 | |
e5bf0f55 RG |
284 | This exception may be thrown by FileDownloader objects if they are not |
285 | configured to continue on errors. They will contain the appropriate | |
286 | error message. | |
287 | """ | |
288 | pass | |
289 | ||
c0a10ca8 | 290 | |
e5bf0f55 RG |
291 | class SameFileError(Exception): |
292 | """Same File exception. | |
293 | ||
294 | This exception will be thrown by FileDownloader objects if they detect | |
295 | multiple files would have to be downloaded to the same file on disk. | |
296 | """ | |
297 | pass | |
298 | ||
c0a10ca8 | 299 | |
65cd34c5 RG |
300 | class PostProcessingError(Exception): |
301 | """Post Processing exception. | |
302 | ||
303 | This exception may be raised by PostProcessor's .run() method to | |
304 | indicate an error in the postprocessing task. | |
305 | """ | |
306 | pass | |
307 | ||
c0a10ca8 | 308 | |
73f4e7af | 309 | class UnavailableVideoError(Exception): |
7b7759f5 | 310 | """Unavailable Format exception. |
311 | ||
312 | This exception will be thrown when a video is requested | |
313 | in a format that is not available for that video. | |
314 | """ | |
d69a1c91 RG |
315 | pass |
316 | ||
c0a10ca8 | 317 | |
d69a1c91 RG |
318 | class ContentTooShortError(Exception): |
319 | """Content Too Short exception. | |
320 | ||
321 | This exception may be raised by FileDownloader objects when a file they | |
322 | download is too small for what the server announced first, indicating | |
323 | the connection was probably interrupted. | |
324 | """ | |
325 | # Both in bytes | |
326 | downloaded = None | |
327 | expected = None | |
328 | ||
329 | def __init__(self, downloaded, expected): | |
330 | self.downloaded = downloaded | |
331 | self.expected = expected | |
7b7759f5 | 332 | |
c0a10ca8 | 333 | |
1987c232 RG |
334 | class YoutubeDLHandler(urllib2.HTTPHandler): |
335 | """Handler for HTTP requests and responses. | |
336 | ||
337 | This class, when installed with an OpenerDirector, automatically adds | |
338 | the standard headers to every HTTP request and handles gzipped and | |
339 | deflated responses from web servers. If compression is to be avoided in | |
340 | a particular request, the original request in the program code only has | |
341 | to include the HTTP header "Youtubedl-No-Compression", which will be | |
342 | removed before making the real request. | |
c0a10ca8 | 343 | |
1987c232 RG |
344 | Part of this code was copied from: |
345 | ||
c0a10ca8 F |
346 | http://techknack.net/python-urllib2-handlers/ |
347 | ||
1987c232 RG |
348 | Andrew Rowls, the author of that code, agreed to release it to the |
349 | public domain. | |
350 | """ | |
351 | ||
352 | @staticmethod | |
353 | def deflate(data): | |
354 | try: | |
355 | return zlib.decompress(data, -zlib.MAX_WBITS) | |
356 | except zlib.error: | |
357 | return zlib.decompress(data) | |
c0a10ca8 | 358 | |
7b531c0b RG |
359 | @staticmethod |
360 | def addinfourl_wrapper(stream, headers, url, code): | |
361 | if hasattr(urllib2.addinfourl, 'getcode'): | |
362 | return urllib2.addinfourl(stream, headers, url, code) | |
0f6b00b5 RG |
363 | ret = urllib2.addinfourl(stream, headers, url) |
364 | ret.code = code | |
365 | return ret | |
c0a10ca8 | 366 | |
1987c232 RG |
367 | def http_request(self, req): |
368 | for h in std_headers: | |
369 | if h in req.headers: | |
370 | del req.headers[h] | |
371 | req.add_header(h, std_headers[h]) | |
372 | if 'Youtubedl-no-compression' in req.headers: | |
373 | if 'Accept-encoding' in req.headers: | |
374 | del req.headers['Accept-encoding'] | |
375 | del req.headers['Youtubedl-no-compression'] | |
376 | return req | |
377 | ||
378 | def http_response(self, req, resp): | |
379 | old_resp = resp | |
380 | # gzip | |
381 | if resp.headers.get('Content-encoding', '') == 'gzip': | |
382 | gz = gzip.GzipFile(fileobj=StringIO.StringIO(resp.read()), mode='r') | |
7b531c0b | 383 | resp = self.addinfourl_wrapper(gz, old_resp.headers, old_resp.url, old_resp.code) |
1987c232 RG |
384 | resp.msg = old_resp.msg |
385 | # deflate | |
386 | if resp.headers.get('Content-encoding', '') == 'deflate': | |
387 | gz = StringIO.StringIO(self.deflate(resp.read())) | |
7b531c0b | 388 | resp = self.addinfourl_wrapper(gz, old_resp.headers, old_resp.url, old_resp.code) |
1987c232 RG |
389 | resp.msg = old_resp.msg |
390 | return resp | |
391 | ||
c0a10ca8 | 392 | |
4fa74b52 RG |
393 | class FileDownloader(object): |
394 | """File Downloader class. | |
395 | ||
396 | File downloader objects are the ones responsible of downloading the | |
397 | actual video file and writing it to disk if the user has requested | |
398 | it, among some other tasks. In most cases there should be one per | |
399 | program. As, given a video URL, the downloader doesn't know how to | |
400 | extract all the needed information, task that InfoExtractors do, it | |
401 | has to pass the URL to one of them. | |
402 | ||
403 | For this, file downloader objects have a method that allows | |
404 | InfoExtractors to be registered in a given order. When it is passed | |
405 | a URL, the file downloader handles it to the first InfoExtractor it | |
2851b2ca RG |
406 | finds that reports being able to handle it. The InfoExtractor extracts |
407 | all the information about the video or videos the URL refers to, and | |
408 | asks the FileDownloader to process the video information, possibly | |
409 | downloading the video. | |
4fa74b52 RG |
410 | |
411 | File downloaders accept a lot of parameters. In order not to saturate | |
412 | the object constructor with arguments, it receives a dictionary of | |
d0a9affb RG |
413 | options instead. These options are available through the params |
414 | attribute for the InfoExtractors to use. The FileDownloader also | |
415 | registers itself as the downloader in charge for the InfoExtractors | |
416 | that are added to it, so this is a "mutual registration". | |
4fa74b52 RG |
417 | |
418 | Available options: | |
419 | ||
80066952 RG |
420 | username: Username for authentication purposes. |
421 | password: Password for authentication purposes. | |
422 | usenetrc: Use netrc for authentication instead. | |
423 | quiet: Do not print messages to stdout. | |
424 | forceurl: Force printing final URL. | |
425 | forcetitle: Force printing title. | |
426 | forcethumbnail: Force printing thumbnail URL. | |
427 | forcedescription: Force printing description. | |
9f796346 | 428 | forcefilename: Force printing final filename. |
80066952 RG |
429 | simulate: Do not download the video files. |
430 | format: Video format code. | |
431 | format_limit: Highest quality format to try. | |
432 | outtmpl: Template for output names. | |
433 | ignoreerrors: Do not stop on download errors. | |
434 | ratelimit: Download speed limit, in bytes/sec. | |
435 | nooverwrites: Prevent overwriting files. | |
436 | retries: Number of times to retry for HTTP error 5xx | |
437 | continuedl: Try to continue downloads if possible. | |
438 | noprogress: Do not print the progress bar. | |
439 | playliststart: Playlist item to start at. | |
8cc44341 | 440 | playlistend: Playlist item to end at. |
20e91e83 ABP |
441 | matchtitle: Download only matching titles. |
442 | rejecttitle: Reject downloads for matching titles. | |
331ce0a0 | 443 | logtostderr: Log messages to stderr instead of stdout. |
ccbd296b | 444 | consoletitle: Display progress in console window's titlebar. |
3fb2c487 | 445 | nopart: Do not use temporary .part files. |
e3018902 | 446 | updatetime: Use the Last-modified header to set output file timestamps. |
8b95c387 | 447 | writedescription: Write the video description to a .description file |
6eb08fbf | 448 | writeinfojson: Write the video description to a .info.json file |
4fa74b52 RG |
449 | """ |
450 | ||
d0a9affb | 451 | params = None |
4fa74b52 | 452 | _ies = [] |
65cd34c5 | 453 | _pps = [] |
9bf386d7 | 454 | _download_retcode = None |
7d8d0612 | 455 | _num_downloads = None |
331ce0a0 | 456 | _screen_file = None |
4fa74b52 RG |
457 | |
458 | def __init__(self, params): | |
1c5e2302 | 459 | """Create a FileDownloader object with the given options.""" |
4fa74b52 | 460 | self._ies = [] |
65cd34c5 | 461 | self._pps = [] |
9bf386d7 | 462 | self._download_retcode = 0 |
7d8d0612 | 463 | self._num_downloads = 0 |
331ce0a0 | 464 | self._screen_file = [sys.stdout, sys.stderr][params.get('logtostderr', False)] |
d0a9affb | 465 | self.params = params |
d3975459 | 466 | |
4fa74b52 RG |
467 | @staticmethod |
468 | def format_bytes(bytes): | |
469 | if bytes is None: | |
470 | return 'N/A' | |
8497c36d RG |
471 | if type(bytes) is str: |
472 | bytes = float(bytes) | |
473 | if bytes == 0.0: | |
4fa74b52 RG |
474 | exponent = 0 |
475 | else: | |
8497c36d | 476 | exponent = long(math.log(bytes, 1024.0)) |
4fa74b52 | 477 | suffix = 'bkMGTPEZY'[exponent] |
c0a10ca8 | 478 | converted = float(bytes) / float(1024 ** exponent) |
4fa74b52 RG |
479 | return '%.2f%s' % (converted, suffix) |
480 | ||
481 | @staticmethod | |
482 | def calc_percent(byte_counter, data_len): | |
483 | if data_len is None: | |
484 | return '---.-%' | |
485 | return '%6s' % ('%3.1f%%' % (float(byte_counter) / float(data_len) * 100.0)) | |
486 | ||
487 | @staticmethod | |
488 | def calc_eta(start, now, total, current): | |
489 | if total is None: | |
490 | return '--:--' | |
491 | dif = now - start | |
492 | if current == 0 or dif < 0.001: # One millisecond | |
493 | return '--:--' | |
494 | rate = float(current) / dif | |
495 | eta = long((float(total) - float(current)) / rate) | |
496 | (eta_mins, eta_secs) = divmod(eta, 60) | |
497 | if eta_mins > 99: | |
498 | return '--:--' | |
499 | return '%02d:%02d' % (eta_mins, eta_secs) | |
500 | ||
5121ef20 | 501 | @staticmethod |
4fa74b52 RG |
502 | def calc_speed(start, now, bytes): |
503 | dif = now - start | |
504 | if bytes == 0 or dif < 0.001: # One millisecond | |
9fcd8355 | 505 | return '%10s' % '---b/s' |
4fa74b52 RG |
506 | return '%10s' % ('%s/s' % FileDownloader.format_bytes(float(bytes) / dif)) |
507 | ||
508 | @staticmethod | |
509 | def best_block_size(elapsed_time, bytes): | |
510 | new_min = max(bytes / 2.0, 1.0) | |
511 | new_max = min(max(bytes * 2.0, 1.0), 4194304) # Do not surpass 4 MB | |
512 | if elapsed_time < 0.001: | |
e1f18b8a | 513 | return long(new_max) |
4fa74b52 RG |
514 | rate = bytes / elapsed_time |
515 | if rate > new_max: | |
e1f18b8a | 516 | return long(new_max) |
4fa74b52 | 517 | if rate < new_min: |
e1f18b8a RG |
518 | return long(new_min) |
519 | return long(rate) | |
4fa74b52 | 520 | |
acd3d842 RG |
521 | @staticmethod |
522 | def parse_bytes(bytestr): | |
523 | """Parse a string indicating a byte quantity into a long integer.""" | |
524 | matchobj = re.match(r'(?i)^(\d+(?:\.\d+)?)([kMGTPEZY]?)$', bytestr) | |
525 | if matchobj is None: | |
526 | return None | |
527 | number = float(matchobj.group(1)) | |
528 | multiplier = 1024.0 ** 'bkmgtpezy'.index(matchobj.group(2).lower()) | |
529 | return long(round(number * multiplier)) | |
530 | ||
4fa74b52 RG |
531 | def add_info_extractor(self, ie): |
532 | """Add an InfoExtractor object to the end of the list.""" | |
533 | self._ies.append(ie) | |
534 | ie.set_downloader(self) | |
d3975459 | 535 | |
65cd34c5 RG |
536 | def add_post_processor(self, pp): |
537 | """Add a PostProcessor object to the end of the chain.""" | |
538 | self._pps.append(pp) | |
539 | pp.set_downloader(self) | |
d3975459 | 540 | |
331ce0a0 | 541 | def to_screen(self, message, skip_eol=False, ignore_encoding_errors=False): |
9fcd8355 | 542 | """Print message to stdout if not in quiet mode.""" |
43ab0ca4 RG |
543 | try: |
544 | if not self.params.get('quiet', False): | |
331ce0a0 RG |
545 | terminator = [u'\n', u''][skip_eol] |
546 | print >>self._screen_file, (u'%s%s' % (message, terminator)).encode(preferredencoding()), | |
547 | self._screen_file.flush() | |
43ab0ca4 RG |
548 | except (UnicodeEncodeError), err: |
549 | if not ignore_encoding_errors: | |
550 | raise | |
d3975459 | 551 | |
7e5cab67 RG |
552 | def to_stderr(self, message): |
553 | """Print message to stderr.""" | |
eae2666c | 554 | print >>sys.stderr, message.encode(preferredencoding()) |
d3975459 | 555 | |
ccbd296b MM |
556 | def to_cons_title(self, message): |
557 | """Set console/terminal window title to message.""" | |
558 | if not self.params.get('consoletitle', False): | |
559 | return | |
560 | if os.name == 'nt' and ctypes.windll.kernel32.GetConsoleWindow(): | |
561 | # c_wchar_p() might not be necessary if `message` is | |
562 | # already of type unicode() | |
563 | ctypes.windll.kernel32.SetConsoleTitleW(ctypes.c_wchar_p(message)) | |
564 | elif 'TERM' in os.environ: | |
565 | sys.stderr.write('\033]0;%s\007' % message.encode(preferredencoding())) | |
566 | ||
22899cea RG |
567 | def fixed_template(self): |
568 | """Checks if the output template is fixed.""" | |
d0a9affb | 569 | return (re.search(ur'(?u)%\(.+?\)s', self.params['outtmpl']) is None) |
9fcd8355 | 570 | |
0086d1ec RG |
571 | def trouble(self, message=None): |
572 | """Determine action to take when a download problem appears. | |
573 | ||
574 | Depending on if the downloader has been configured to ignore | |
e5bf0f55 | 575 | download errors or not, this method may throw an exception or |
9bf386d7 | 576 | not when errors are found, after printing the message. |
0086d1ec RG |
577 | """ |
578 | if message is not None: | |
579 | self.to_stderr(message) | |
d0a9affb | 580 | if not self.params.get('ignoreerrors', False): |
e5bf0f55 | 581 | raise DownloadError(message) |
9bf386d7 | 582 | self._download_retcode = 1 |
0086d1ec | 583 | |
acd3d842 RG |
584 | def slow_down(self, start_time, byte_counter): |
585 | """Sleep if the download speed is over the rate limit.""" | |
d0a9affb | 586 | rate_limit = self.params.get('ratelimit', None) |
acd3d842 RG |
587 | if rate_limit is None or byte_counter == 0: |
588 | return | |
589 | now = time.time() | |
590 | elapsed = now - start_time | |
591 | if elapsed <= 0.0: | |
592 | return | |
593 | speed = float(byte_counter) / elapsed | |
594 | if speed > rate_limit: | |
595 | time.sleep((byte_counter - rate_limit * (now - start_time)) / rate_limit) | |
3fb2c487 RG |
596 | |
597 | def temp_name(self, filename): | |
598 | """Returns a temporary filename for the given filename.""" | |
599 | if self.params.get('nopart', False) or filename == u'-' or \ | |
600 | (os.path.exists(filename) and not os.path.isfile(filename)): | |
601 | return filename | |
602 | return filename + u'.part' | |
603 | ||
8cc42e7c RG |
604 | def undo_temp_name(self, filename): |
605 | if filename.endswith(u'.part'): | |
606 | return filename[:-len(u'.part')] | |
607 | return filename | |
608 | ||
62cf7aaf RG |
609 | def try_rename(self, old_filename, new_filename): |
610 | try: | |
7d950ca1 RG |
611 | if old_filename == new_filename: |
612 | return | |
62cf7aaf RG |
613 | os.rename(old_filename, new_filename) |
614 | except (IOError, OSError), err: | |
615 | self.trouble(u'ERROR: unable to rename file') | |
c0a10ca8 | 616 | |
e3018902 RG |
617 | def try_utime(self, filename, last_modified_hdr): |
618 | """Try to set the last-modified time of the given file.""" | |
619 | if last_modified_hdr is None: | |
620 | return | |
621 | if not os.path.isfile(filename): | |
622 | return | |
623 | timestr = last_modified_hdr | |
624 | if timestr is None: | |
625 | return | |
626 | filetime = timeconvert(timestr) | |
627 | if filetime is None: | |
36597dc4 | 628 | return filetime |
e3018902 | 629 | try: |
c0a10ca8 | 630 | os.utime(filename, (time.time(), filetime)) |
e3018902 RG |
631 | except: |
632 | pass | |
36597dc4 | 633 | return filetime |
acd3d842 | 634 | |
8b95c387 | 635 | def report_writedescription(self, descfn): |
6eb08fbf PH |
636 | """ Report that the description file is being written """ |
637 | self.to_screen(u'[info] Writing video description to: %s' % descfn, ignore_encoding_errors=True) | |
638 | ||
639 | def report_writeinfojson(self, infofn): | |
640 | """ Report that the metadata file has been written """ | |
641 | self.to_screen(u'[info] Video description metadata as JSON to: %s' % infofn, ignore_encoding_errors=True) | |
8b95c387 | 642 | |
bafa5cd9 RG |
643 | def report_destination(self, filename): |
644 | """Report destination filename.""" | |
331ce0a0 | 645 | self.to_screen(u'[download] Destination: %s' % filename, ignore_encoding_errors=True) |
d3975459 | 646 | |
bafa5cd9 RG |
647 | def report_progress(self, percent_str, data_len_str, speed_str, eta_str): |
648 | """Report download progress.""" | |
d9835247 RG |
649 | if self.params.get('noprogress', False): |
650 | return | |
331ce0a0 | 651 | self.to_screen(u'\r[download] %s of %s at %s ETA %s' % |
bafa5cd9 | 652 | (percent_str, data_len_str, speed_str, eta_str), skip_eol=True) |
ccbd296b MM |
653 | self.to_cons_title(u'youtube-dl - %s of %s at %s ETA %s' % |
654 | (percent_str.strip(), data_len_str.strip(), speed_str.strip(), eta_str.strip())) | |
7db85b2c RG |
655 | |
656 | def report_resuming_byte(self, resume_len): | |
8a9f53be | 657 | """Report attempt to resume at given byte.""" |
331ce0a0 | 658 | self.to_screen(u'[download] Resuming download at byte %s' % resume_len) |
d3975459 | 659 | |
7031008c | 660 | def report_retry(self, count, retries): |
e86e9474 | 661 | """Report retry in case of HTTP error 5xx""" |
331ce0a0 | 662 | self.to_screen(u'[download] Got server HTTP error. Retrying (attempt %d of %d)...' % (count, retries)) |
d3975459 | 663 | |
7db85b2c RG |
664 | def report_file_already_downloaded(self, file_name): |
665 | """Report file has already been fully downloaded.""" | |
43ab0ca4 | 666 | try: |
331ce0a0 | 667 | self.to_screen(u'[download] %s has already been downloaded' % file_name) |
43ab0ca4 | 668 | except (UnicodeEncodeError), err: |
331ce0a0 | 669 | self.to_screen(u'[download] The file has already been downloaded') |
d3975459 | 670 | |
7db85b2c RG |
671 | def report_unable_to_resume(self): |
672 | """Report it was impossible to resume download.""" | |
331ce0a0 | 673 | self.to_screen(u'[download] Unable to resume') |
d3975459 | 674 | |
bafa5cd9 RG |
675 | def report_finish(self): |
676 | """Report download finished.""" | |
d9835247 | 677 | if self.params.get('noprogress', False): |
331ce0a0 | 678 | self.to_screen(u'[download] Download completed') |
d9835247 | 679 | else: |
331ce0a0 | 680 | self.to_screen(u'') |
d3975459 | 681 | |
df372a65 RG |
682 | def increment_downloads(self): |
683 | """Increment the ordinal that assigns a number to each file.""" | |
684 | self._num_downloads += 1 | |
bafa5cd9 | 685 | |
9f796346 GI |
686 | def prepare_filename(self, info_dict): |
687 | """Generate the output filename.""" | |
688 | try: | |
689 | template_dict = dict(info_dict) | |
690 | template_dict['epoch'] = unicode(long(time.time())) | |
691 | template_dict['autonumber'] = unicode('%05d' % self._num_downloads) | |
692 | filename = self.params['outtmpl'] % template_dict | |
693 | return filename | |
694 | except (ValueError, KeyError), err: | |
695 | self.trouble(u'ERROR: invalid system charset or erroneous output template') | |
696 | return None | |
697 | ||
c8619e01 RG |
698 | def process_info(self, info_dict): |
699 | """Process a single dictionary returned by an InfoExtractor.""" | |
9f796346 | 700 | filename = self.prepare_filename(info_dict) |
9b4556c4 PH |
701 | |
702 | # Forced printings | |
703 | if self.params.get('forcetitle', False): | |
704 | print info_dict['title'].encode(preferredencoding(), 'xmlcharrefreplace') | |
705 | if self.params.get('forceurl', False): | |
706 | print info_dict['url'].encode(preferredencoding(), 'xmlcharrefreplace') | |
707 | if self.params.get('forcethumbnail', False) and 'thumbnail' in info_dict: | |
708 | print info_dict['thumbnail'].encode(preferredencoding(), 'xmlcharrefreplace') | |
709 | if self.params.get('forcedescription', False) and 'description' in info_dict: | |
710 | print info_dict['description'].encode(preferredencoding(), 'xmlcharrefreplace') | |
711 | if self.params.get('forcefilename', False) and filename is not None: | |
712 | print filename.encode(preferredencoding(), 'xmlcharrefreplace') | |
da0db53a DH |
713 | if self.params.get('forceformat', False): |
714 | print info_dict['format'].encode(preferredencoding(), 'xmlcharrefreplace') | |
9b4556c4 | 715 | |
c8619e01 RG |
716 | # Do nothing else if in simulate mode |
717 | if self.params.get('simulate', False): | |
9bf386d7 | 718 | return |
d3975459 | 719 | |
9f796346 | 720 | if filename is None: |
38ed1344 | 721 | return |
20e91e83 ABP |
722 | |
723 | matchtitle=self.params.get('matchtitle',False) | |
724 | rejecttitle=self.params.get('rejecttitle',False) | |
725 | title=info_dict['title'].encode(preferredencoding(), 'xmlcharrefreplace') | |
726 | if matchtitle and not re.search(matchtitle, title, re.IGNORECASE): | |
727 | self.to_screen(u'[download] "%s" title did not match pattern "%s"' % (title, matchtitle)) | |
728 | return | |
729 | if rejecttitle and re.search(rejecttitle, title, re.IGNORECASE): | |
730 | self.to_screen(u'[download] "%s" title matched reject pattern "%s"' % (title, rejecttitle)) | |
731 | return | |
732 | ||
850ab765 | 733 | if self.params.get('nooverwrites', False) and os.path.exists(filename): |
5c44af18 | 734 | self.to_stderr(u'WARNING: file exists and will be skipped') |
9bf386d7 | 735 | return |
7b7759f5 | 736 | |
c8619e01 | 737 | try: |
e5e74ffb PH |
738 | dn = os.path.dirname(filename) |
739 | if dn != '' and not os.path.exists(dn): | |
740 | os.makedirs(dn) | |
c8619e01 | 741 | except (OSError, IOError), err: |
cec3a53c | 742 | self.trouble(u'ERROR: unable to create directory ' + unicode(err)) |
9bf386d7 | 743 | return |
7b7759f5 | 744 | |
8b95c387 PH |
745 | if self.params.get('writedescription', False): |
746 | try: | |
747 | descfn = filename + '.description' | |
6eb08fbf | 748 | self.report_writedescription(descfn) |
1293ce58 PH |
749 | descfile = open(descfn, 'wb') |
750 | try: | |
8b95c387 | 751 | descfile.write(info_dict['description'].encode('utf-8')) |
1293ce58 PH |
752 | finally: |
753 | descfile.close() | |
8b95c387 | 754 | except (OSError, IOError): |
cec3a53c | 755 | self.trouble(u'ERROR: Cannot write description file ' + descfn) |
8b95c387 PH |
756 | return |
757 | ||
6eb08fbf PH |
758 | if self.params.get('writeinfojson', False): |
759 | infofn = filename + '.info.json' | |
760 | self.report_writeinfojson(infofn) | |
761 | try: | |
762 | json.dump | |
763 | except (NameError,AttributeError): | |
764 | self.trouble(u'ERROR: No JSON encoder found. Update to Python 2.6+, setup a json module, or leave out --write-info-json.') | |
765 | return | |
766 | try: | |
1293ce58 PH |
767 | infof = open(infofn, 'wb') |
768 | try: | |
54f329fe PH |
769 | json_info_dict = dict((k,v) for k,v in info_dict.iteritems() if not k in ('urlhandle',)) |
770 | json.dump(json_info_dict, infof) | |
1293ce58 PH |
771 | finally: |
772 | infof.close() | |
6eb08fbf | 773 | except (OSError, IOError): |
cec3a53c | 774 | self.trouble(u'ERROR: Cannot write metadata to JSON file ' + infofn) |
6eb08fbf PH |
775 | return |
776 | ||
9b4556c4 | 777 | if not self.params.get('skip_download', False): |
55e7c75e | 778 | try: |
366cbfb0 | 779 | success = self._do_download(filename, info_dict) |
9b4556c4 PH |
780 | except (OSError, IOError), err: |
781 | raise UnavailableVideoError | |
782 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
783 | self.trouble(u'ERROR: unable to download video data: %s' % str(err)) | |
784 | return | |
785 | except (ContentTooShortError, ), err: | |
786 | self.trouble(u'ERROR: content too short (expected %s bytes and served %s)' % (err.expected, err.downloaded)) | |
55e7c75e | 787 | return |
9b4556c4 PH |
788 | |
789 | if success: | |
790 | try: | |
791 | self.post_process(filename, info_dict) | |
792 | except (PostProcessingError), err: | |
793 | self.trouble(u'ERROR: postprocessing: %s' % str(err)) | |
794 | return | |
c8619e01 | 795 | |
4fa74b52 RG |
796 | def download(self, url_list): |
797 | """Download a given list of URLs.""" | |
22899cea | 798 | if len(url_list) > 1 and self.fixed_template(): |
d0a9affb | 799 | raise SameFileError(self.params['outtmpl']) |
22899cea | 800 | |
4fa74b52 RG |
801 | for url in url_list: |
802 | suitable_found = False | |
803 | for ie in self._ies: | |
c8619e01 | 804 | # Go to next InfoExtractor if not suitable |
4fa74b52 RG |
805 | if not ie.suitable(url): |
806 | continue | |
c8619e01 | 807 | |
4fa74b52 RG |
808 | # Suitable InfoExtractor found |
809 | suitable_found = True | |
c8619e01 | 810 | |
6f21f686 RG |
811 | # Extract information from URL and process it |
812 | ie.extract(url) | |
65cd34c5 | 813 | |
c8619e01 | 814 | # Suitable InfoExtractor had been found; go to next URL |
4fa74b52 | 815 | break |
c8619e01 | 816 | |
4fa74b52 | 817 | if not suitable_found: |
db7e31b8 | 818 | self.trouble(u'ERROR: no suitable InfoExtractor: %s' % url) |
bb681b88 | 819 | |
9bf386d7 | 820 | return self._download_retcode |
65cd34c5 RG |
821 | |
822 | def post_process(self, filename, ie_info): | |
823 | """Run the postprocessing chain on the given file.""" | |
824 | info = dict(ie_info) | |
825 | info['filepath'] = filename | |
826 | for pp in self._pps: | |
827 | info = pp.run(info) | |
828 | if info is None: | |
829 | break | |
d3975459 | 830 | |
e616ec0c | 831 | def _download_with_rtmpdump(self, filename, url, player_url): |
0487b407 | 832 | self.report_destination(filename) |
62cf7aaf | 833 | tmpfilename = self.temp_name(filename) |
0487b407 RG |
834 | |
835 | # Check for rtmpdump first | |
836 | try: | |
837 | subprocess.call(['rtmpdump', '-h'], stdout=(file(os.path.devnull, 'w')), stderr=subprocess.STDOUT) | |
838 | except (OSError, IOError): | |
839 | self.trouble(u'ERROR: RTMP download detected but "rtmpdump" could not be run') | |
840 | return False | |
841 | ||
842 | # Download using rtmpdump. rtmpdump returns exit code 2 when | |
843 | # the connection was interrumpted and resuming appears to be | |
844 | # possible. This is part of rtmpdump's normal usage, AFAIK. | |
b487ef08 | 845 | basic_args = ['rtmpdump', '-q'] + [[], ['-W', player_url]][player_url is not None] + ['-r', url, '-o', tmpfilename] |
1c1821f8 RG |
846 | retval = subprocess.call(basic_args + [[], ['-e', '-k', '1']][self.params.get('continuedl', False)]) |
847 | while retval == 2 or retval == 1: | |
62cf7aaf | 848 | prevsize = os.path.getsize(tmpfilename) |
331ce0a0 | 849 | self.to_screen(u'\r[rtmpdump] %s bytes' % prevsize, skip_eol=True) |
e616ec0c | 850 | time.sleep(5.0) # This seems to be needed |
1c1821f8 | 851 | retval = subprocess.call(basic_args + ['-e'] + [[], ['-k', '1']][retval == 1]) |
62cf7aaf | 852 | cursize = os.path.getsize(tmpfilename) |
e616ec0c RG |
853 | if prevsize == cursize and retval == 1: |
854 | break | |
b487ef08 PH |
855 | # Some rtmp streams seem abort after ~ 99.8%. Don't complain for those |
856 | if prevsize == cursize and retval == 2 and cursize > 1024: | |
857 | self.to_screen(u'\r[rtmpdump] Could not download the whole video. This can happen for some advertisements.') | |
858 | retval = 0 | |
859 | break | |
0487b407 | 860 | if retval == 0: |
62cf7aaf RG |
861 | self.to_screen(u'\r[rtmpdump] %s bytes' % os.path.getsize(tmpfilename)) |
862 | self.try_rename(tmpfilename, filename) | |
0487b407 RG |
863 | return True |
864 | else: | |
db7e31b8 | 865 | self.trouble(u'\nERROR: rtmpdump exited with code %d' % retval) |
0487b407 RG |
866 | return False |
867 | ||
366cbfb0 PH |
868 | def _do_download(self, filename, info_dict): |
869 | url = info_dict['url'] | |
870 | player_url = info_dict.get('player_url', None) | |
871 | ||
62cf7aaf | 872 | # Check file already present |
3fb2c487 | 873 | if self.params.get('continuedl', False) and os.path.isfile(filename) and not self.params.get('nopart', False): |
62cf7aaf RG |
874 | self.report_file_already_downloaded(filename) |
875 | return True | |
876 | ||
0487b407 RG |
877 | # Attempt to download using rtmpdump |
878 | if url.startswith('rtmp'): | |
e616ec0c | 879 | return self._download_with_rtmpdump(filename, url, player_url) |
0487b407 | 880 | |
62cf7aaf | 881 | tmpfilename = self.temp_name(filename) |
55e7c75e | 882 | stream = None |
1987c232 RG |
883 | |
884 | # Do not include the Accept-Encoding header | |
885 | headers = {'Youtubedl-no-compression': 'True'} | |
886 | basic_request = urllib2.Request(url, None, headers) | |
887 | request = urllib2.Request(url, None, headers) | |
7db85b2c | 888 | |
9c457d2a | 889 | # Establish possible resume length |
62cf7aaf RG |
890 | if os.path.isfile(tmpfilename): |
891 | resume_len = os.path.getsize(tmpfilename) | |
55e7c75e RG |
892 | else: |
893 | resume_len = 0 | |
9c457d2a | 894 | |
10e7194d MH |
895 | open_mode = 'wb' |
896 | if resume_len != 0: | |
897 | if self.params.get('continuedl', False): | |
898 | self.report_resuming_byte(resume_len) | |
899 | request.add_header('Range','bytes=%d-' % resume_len) | |
900 | open_mode = 'ab' | |
901 | else: | |
902 | resume_len = 0 | |
55e7c75e | 903 | |
7031008c RG |
904 | count = 0 |
905 | retries = self.params.get('retries', 0) | |
101e0d1e | 906 | while count <= retries: |
7031008c RG |
907 | # Establish connection |
908 | try: | |
54f329fe PH |
909 | if count == 0 and 'urlhandle' in info_dict: |
910 | data = info_dict['urlhandle'] | |
7031008c RG |
911 | data = urllib2.urlopen(request) |
912 | break | |
913 | except (urllib2.HTTPError, ), err: | |
ac249f42 | 914 | if (err.code < 500 or err.code >= 600) and err.code != 416: |
101e0d1e | 915 | # Unexpected HTTP error |
7031008c | 916 | raise |
101e0d1e RG |
917 | elif err.code == 416: |
918 | # Unable to resume (requested range not satisfiable) | |
919 | try: | |
920 | # Open the connection again without the range header | |
921 | data = urllib2.urlopen(basic_request) | |
922 | content_length = data.info()['Content-Length'] | |
923 | except (urllib2.HTTPError, ), err: | |
ac249f42 | 924 | if err.code < 500 or err.code >= 600: |
101e0d1e RG |
925 | raise |
926 | else: | |
927 | # Examine the reported length | |
268fb2bd | 928 | if (content_length is not None and |
c0a10ca8 | 929 | (resume_len - 100 < long(content_length) < resume_len + 100)): |
268fb2bd RG |
930 | # The file had already been fully downloaded. |
931 | # Explanation to the above condition: in issue #175 it was revealed that | |
932 | # YouTube sometimes adds or removes a few bytes from the end of the file, | |
933 | # changing the file size slightly and causing problems for some users. So | |
934 | # I decided to implement a suggested change and consider the file | |
935 | # completely downloaded if the file size differs less than 100 bytes from | |
936 | # the one in the hard drive. | |
101e0d1e | 937 | self.report_file_already_downloaded(filename) |
62cf7aaf | 938 | self.try_rename(tmpfilename, filename) |
101e0d1e RG |
939 | return True |
940 | else: | |
941 | # The length does not match, we start the download over | |
942 | self.report_unable_to_resume() | |
943 | open_mode = 'wb' | |
944 | break | |
945 | # Retry | |
946 | count += 1 | |
947 | if count <= retries: | |
948 | self.report_retry(count, retries) | |
949 | ||
950 | if count > retries: | |
951 | self.trouble(u'ERROR: giving up after %s retries' % retries) | |
952 | return False | |
7db85b2c | 953 | |
4fa74b52 | 954 | data_len = data.info().get('Content-length', None) |
106d091e RG |
955 | if data_len is not None: |
956 | data_len = long(data_len) + resume_len | |
4fa74b52 | 957 | data_len_str = self.format_bytes(data_len) |
106d091e | 958 | byte_counter = 0 + resume_len |
4fa74b52 RG |
959 | block_size = 1024 |
960 | start = time.time() | |
961 | while True: | |
bafa5cd9 | 962 | # Download and write |
4fa74b52 RG |
963 | before = time.time() |
964 | data_block = data.read(block_size) | |
965 | after = time.time() | |
975a91d0 | 966 | if len(data_block) == 0: |
4fa74b52 | 967 | break |
975a91d0 | 968 | byte_counter += len(data_block) |
55e7c75e RG |
969 | |
970 | # Open file just in time | |
971 | if stream is None: | |
972 | try: | |
62cf7aaf | 973 | (stream, tmpfilename) = sanitize_open(tmpfilename, open_mode) |
dbddab27 | 974 | assert stream is not None |
8cc42e7c | 975 | filename = self.undo_temp_name(tmpfilename) |
55e7c75e RG |
976 | self.report_destination(filename) |
977 | except (OSError, IOError), err: | |
db7e31b8 | 978 | self.trouble(u'ERROR: unable to open for writing: %s' % str(err)) |
55e7c75e | 979 | return False |
131efd1a RG |
980 | try: |
981 | stream.write(data_block) | |
982 | except (IOError, OSError), err: | |
d67e0974 RG |
983 | self.trouble(u'\nERROR: unable to write data: %s' % str(err)) |
984 | return False | |
975a91d0 | 985 | block_size = self.best_block_size(after - before, len(data_block)) |
4fa74b52 | 986 | |
55e7c75e | 987 | # Progress message |
975a91d0 | 988 | speed_str = self.calc_speed(start, time.time(), byte_counter - resume_len) |
67035ede PH |
989 | if data_len is None: |
990 | self.report_progress('Unknown %', data_len_str, speed_str, 'Unknown ETA') | |
991 | else: | |
992 | percent_str = self.calc_percent(byte_counter, data_len) | |
993 | eta_str = self.calc_eta(start, time.time(), data_len - resume_len, byte_counter - resume_len) | |
994 | self.report_progress(percent_str, data_len_str, speed_str, eta_str) | |
55e7c75e | 995 | |
acd3d842 | 996 | # Apply rate limit |
975a91d0 | 997 | self.slow_down(start, byte_counter - resume_len) |
acd3d842 | 998 | |
dbddab27 PH |
999 | if stream is None: |
1000 | self.trouble(u'\nERROR: Did not get any data blocks') | |
1001 | return False | |
6f0ff3ba | 1002 | stream.close() |
bafa5cd9 | 1003 | self.report_finish() |
b905e5f5 | 1004 | if data_len is not None and byte_counter != data_len: |
d69a1c91 | 1005 | raise ContentTooShortError(byte_counter, long(data_len)) |
62cf7aaf | 1006 | self.try_rename(tmpfilename, filename) |
e3018902 | 1007 | |
09bd408c | 1008 | # Update file modification time |
e3018902 | 1009 | if self.params.get('updatetime', True): |
366cbfb0 | 1010 | info_dict['filetime'] = self.try_utime(filename, data.info().get('last-modified', None)) |
e3018902 | 1011 | |
366cbfb0 | 1012 | return True |
4fa74b52 | 1013 | |
c0a10ca8 | 1014 | |
4fa74b52 RG |
1015 | class InfoExtractor(object): |
1016 | """Information Extractor class. | |
1017 | ||
1018 | Information extractors are the classes that, given a URL, extract | |
1019 | information from the video (or videos) the URL refers to. This | |
1020 | information includes the real video URL, the video title and simplified | |
2851b2ca RG |
1021 | title, author and others. The information is stored in a dictionary |
1022 | which is then passed to the FileDownloader. The FileDownloader | |
1023 | processes this information possibly downloading the video to the file | |
1024 | system, among other possible outcomes. The dictionaries must include | |
4fa74b52 RG |
1025 | the following fields: |
1026 | ||
1027 | id: Video identifier. | |
1028 | url: Final video URL. | |
1029 | uploader: Nickname of the video uploader. | |
1030 | title: Literal title. | |
1031 | stitle: Simplified title. | |
1032 | ext: Video filename extension. | |
6ba562b0 | 1033 | format: Video format. |
e616ec0c | 1034 | player_url: SWF Player URL (may be None). |
4fa74b52 | 1035 | |
7e58d568 RG |
1036 | The following fields are optional. Their primary purpose is to allow |
1037 | youtube-dl to serve as the backend for a video search function, such | |
1038 | as the one in youtube2mp3. They are only used when their respective | |
1039 | forced printing functions are called: | |
1040 | ||
1041 | thumbnail: Full URL to a video thumbnail image. | |
1042 | description: One-line video description. | |
1043 | ||
4fa74b52 | 1044 | Subclasses of this one should re-define the _real_initialize() and |
bdb3f7a7 PH |
1045 | _real_extract() methods and define a _VALID_URL regexp. |
1046 | Probably, they should also be added to the list of extractors. | |
4fa74b52 RG |
1047 | """ |
1048 | ||
1049 | _ready = False | |
1050 | _downloader = None | |
1051 | ||
1052 | def __init__(self, downloader=None): | |
1053 | """Constructor. Receives an optional downloader.""" | |
1054 | self._ready = False | |
1055 | self.set_downloader(downloader) | |
1056 | ||
bdb3f7a7 | 1057 | def suitable(self, url): |
4fa74b52 | 1058 | """Receives a URL and returns True if suitable for this IE.""" |
bdb3f7a7 | 1059 | return re.match(self._VALID_URL, url) is not None |
4fa74b52 RG |
1060 | |
1061 | def initialize(self): | |
1c5e2302 | 1062 | """Initializes an instance (authentication, etc).""" |
4fa74b52 RG |
1063 | if not self._ready: |
1064 | self._real_initialize() | |
1065 | self._ready = True | |
1066 | ||
1067 | def extract(self, url): | |
1068 | """Extracts URL information and returns it in list of dicts.""" | |
1069 | self.initialize() | |
1070 | return self._real_extract(url) | |
1071 | ||
1072 | def set_downloader(self, downloader): | |
1073 | """Sets the downloader for this IE.""" | |
1074 | self._downloader = downloader | |
d3975459 | 1075 | |
4fa74b52 RG |
1076 | def _real_initialize(self): |
1077 | """Real initialization process. Redefine in subclasses.""" | |
1078 | pass | |
1079 | ||
1080 | def _real_extract(self, url): | |
1081 | """Real extraction process. Redefine in subclasses.""" | |
1082 | pass | |
1083 | ||
c0a10ca8 | 1084 | |
4fa74b52 RG |
1085 | class YoutubeIE(InfoExtractor): |
1086 | """Information extractor for youtube.com.""" | |
1087 | ||
1cde6f1d | 1088 | _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).+)?$' |
9715661c | 1089 | _LANG_URL = r'http://www.youtube.com/?hl=en&persist_hl=1&gl=US&persist_gl=1&opt_out_ackd=1' |
7df4635f | 1090 | _LOGIN_URL = 'https://www.youtube.com/signup?next=/&gl=US&hl=en' |
72ac78b8 | 1091 | _AGE_URL = 'http://www.youtube.com/verify_age?next_url=/&gl=US&hl=en' |
4fa74b52 | 1092 | _NETRC_MACHINE = 'youtube' |
497cd3e6 | 1093 | # Listed in order of quality |
767414a2 | 1094 | _available_formats = ['38', '37', '22', '45', '35', '44', '34', '18', '43', '6', '5', '17', '13'] |
7b7759f5 | 1095 | _video_extensions = { |
1096 | '13': '3gp', | |
1097 | '17': 'mp4', | |
1098 | '18': 'mp4', | |
1099 | '22': 'mp4', | |
d9bc015b | 1100 | '37': 'mp4', |
9e9647d9 | 1101 | '38': 'video', # You actually don't know if this will be MOV, AVI or whatever |
0b59bf4a | 1102 | '43': 'webm', |
7b417b38 | 1103 | '44': 'webm', |
0b59bf4a | 1104 | '45': 'webm', |
7b7759f5 | 1105 | } |
3de2a1e6 FT |
1106 | _video_dimensions = { |
1107 | '5': '240x400', | |
1108 | '6': '???', | |
1109 | '13': '???', | |
1110 | '17': '144x176', | |
1111 | '18': '360x640', | |
1112 | '22': '720x1280', | |
1113 | '34': '360x640', | |
1114 | '35': '480x854', | |
1115 | '37': '1080x1920', | |
1116 | '38': '3072x4096', | |
1117 | '43': '360x640', | |
1118 | '44': '480x854', | |
1119 | '45': '720x1280', | |
1120 | } | |
f3098c4d | 1121 | IE_NAME = u'youtube' |
4fa74b52 | 1122 | |
72ac78b8 RG |
1123 | def report_lang(self): |
1124 | """Report attempt to set language.""" | |
331ce0a0 | 1125 | self._downloader.to_screen(u'[youtube] Setting language') |
72ac78b8 | 1126 | |
bafa5cd9 RG |
1127 | def report_login(self): |
1128 | """Report attempt to log in.""" | |
331ce0a0 | 1129 | self._downloader.to_screen(u'[youtube] Logging in') |
d3975459 | 1130 | |
bafa5cd9 RG |
1131 | def report_age_confirmation(self): |
1132 | """Report attempt to confirm age.""" | |
331ce0a0 | 1133 | self._downloader.to_screen(u'[youtube] Confirming age') |
d3975459 | 1134 | |
e616ec0c RG |
1135 | def report_video_webpage_download(self, video_id): |
1136 | """Report attempt to download video webpage.""" | |
331ce0a0 | 1137 | self._downloader.to_screen(u'[youtube] %s: Downloading video webpage' % video_id) |
d3975459 | 1138 | |
71b7300e RG |
1139 | def report_video_info_webpage_download(self, video_id): |
1140 | """Report attempt to download video info webpage.""" | |
331ce0a0 | 1141 | self._downloader.to_screen(u'[youtube] %s: Downloading video info webpage' % video_id) |
d3975459 | 1142 | |
bafa5cd9 RG |
1143 | def report_information_extraction(self, video_id): |
1144 | """Report attempt to extract video information.""" | |
331ce0a0 | 1145 | self._downloader.to_screen(u'[youtube] %s: Extracting video information' % video_id) |
d3975459 | 1146 | |
7b7759f5 | 1147 | def report_unavailable_format(self, video_id, format): |
1148 | """Report extracted video URL.""" | |
331ce0a0 | 1149 | self._downloader.to_screen(u'[youtube] %s: Format %s not available' % (video_id, format)) |
d3975459 | 1150 | |
0487b407 RG |
1151 | def report_rtmp_download(self): |
1152 | """Indicate the download will use the RTMP protocol.""" | |
331ce0a0 | 1153 | self._downloader.to_screen(u'[youtube] RTMP download detected') |
d3975459 | 1154 | |
3de2a1e6 FT |
1155 | def _print_formats(self, formats): |
1156 | print 'Available formats:' | |
1157 | for x in formats: | |
1158 | print '%s\t:\t%s\t[%s]' %(x, self._video_extensions.get(x, 'flv'), self._video_dimensions.get(x, '???')) | |
1159 | ||
4fa74b52 RG |
1160 | def _real_initialize(self): |
1161 | if self._downloader is None: | |
1162 | return | |
1163 | ||
1164 | username = None | |
1165 | password = None | |
d0a9affb | 1166 | downloader_params = self._downloader.params |
4fa74b52 RG |
1167 | |
1168 | # Attempt to use provided username and password or .netrc data | |
1169 | if downloader_params.get('username', None) is not None: | |
1170 | username = downloader_params['username'] | |
1171 | password = downloader_params['password'] | |
1172 | elif downloader_params.get('usenetrc', False): | |
1173 | try: | |
1174 | info = netrc.netrc().authenticators(self._NETRC_MACHINE) | |
1175 | if info is not None: | |
1176 | username = info[0] | |
1177 | password = info[2] | |
1178 | else: | |
1179 | raise netrc.NetrcParseError('No authenticators for %s' % self._NETRC_MACHINE) | |
1180 | except (IOError, netrc.NetrcParseError), err: | |
6f21f686 | 1181 | self._downloader.to_stderr(u'WARNING: parsing .netrc: %s' % str(err)) |
4fa74b52 RG |
1182 | return |
1183 | ||
72ac78b8 | 1184 | # Set language |
1987c232 | 1185 | request = urllib2.Request(self._LANG_URL) |
72ac78b8 RG |
1186 | try: |
1187 | self.report_lang() | |
1188 | urllib2.urlopen(request).read() | |
1189 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
6f21f686 | 1190 | self._downloader.to_stderr(u'WARNING: unable to set language: %s' % str(err)) |
72ac78b8 RG |
1191 | return |
1192 | ||
cc109403 RG |
1193 | # No authentication to be performed |
1194 | if username is None: | |
1195 | return | |
1196 | ||
4fa74b52 | 1197 | # Log in |
9fcd8355 RG |
1198 | login_form = { |
1199 | 'current_form': 'loginForm', | |
4fa74b52 RG |
1200 | 'next': '/', |
1201 | 'action_login': 'Log In', | |
1202 | 'username': username, | |
9fcd8355 RG |
1203 | 'password': password, |
1204 | } | |
1987c232 | 1205 | request = urllib2.Request(self._LOGIN_URL, urllib.urlencode(login_form)) |
4fa74b52 | 1206 | try: |
bafa5cd9 | 1207 | self.report_login() |
4fa74b52 RG |
1208 | login_results = urllib2.urlopen(request).read() |
1209 | if re.search(r'(?i)<form[^>]* name="loginForm"', login_results) is not None: | |
6f21f686 | 1210 | self._downloader.to_stderr(u'WARNING: unable to log in: bad username or password') |
4fa74b52 RG |
1211 | return |
1212 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
6f21f686 | 1213 | self._downloader.to_stderr(u'WARNING: unable to log in: %s' % str(err)) |
4fa74b52 | 1214 | return |
d3975459 | 1215 | |
4fa74b52 | 1216 | # Confirm age |
9fcd8355 RG |
1217 | age_form = { |
1218 | 'next_url': '/', | |
1219 | 'action_confirm': 'Confirm', | |
1220 | } | |
1987c232 | 1221 | request = urllib2.Request(self._AGE_URL, urllib.urlencode(age_form)) |
4fa74b52 | 1222 | try: |
bafa5cd9 | 1223 | self.report_age_confirmation() |
4fa74b52 RG |
1224 | age_results = urllib2.urlopen(request).read() |
1225 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
147753eb | 1226 | self._downloader.trouble(u'ERROR: unable to confirm age: %s' % str(err)) |
e5bf0f55 | 1227 | return |
4fa74b52 RG |
1228 | |
1229 | def _real_extract(self, url): | |
1230 | # Extract video id from URL | |
020f7150 | 1231 | mobj = re.match(self._VALID_URL, url) |
4fa74b52 | 1232 | if mobj is None: |
147753eb | 1233 | self._downloader.trouble(u'ERROR: invalid URL: %s' % url) |
6f21f686 | 1234 | return |
4fa74b52 RG |
1235 | video_id = mobj.group(2) |
1236 | ||
497cd3e6 RG |
1237 | # Get video webpage |
1238 | self.report_video_webpage_download(video_id) | |
8d89fbae | 1239 | request = urllib2.Request('http://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1' % video_id) |
497cd3e6 RG |
1240 | try: |
1241 | video_webpage = urllib2.urlopen(request).read() | |
1242 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
1243 | self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % str(err)) | |
1244 | return | |
968aa884 | 1245 | |
497cd3e6 | 1246 | # Attempt to extract SWF player URL |
b620a5f8 | 1247 | mobj = re.search(r'swfConfig.*?"(http:\\/\\/.*?watch.*?-.*?\.swf)"', video_webpage) |
497cd3e6 | 1248 | if mobj is not None: |
b620a5f8 | 1249 | player_url = re.sub(r'\\(.)', r'\1', mobj.group(1)) |
497cd3e6 RG |
1250 | else: |
1251 | player_url = None | |
1252 | ||
1253 | # Get video info | |
1254 | self.report_video_info_webpage_download(video_id) | |
1255 | for el_type in ['&el=embedded', '&el=detailpage', '&el=vevo', '']: | |
1256 | video_info_url = ('http://www.youtube.com/get_video_info?&video_id=%s%s&ps=default&eurl=&gl=US&hl=en' | |
c0a10ca8 | 1257 | % (video_id, el_type)) |
1987c232 | 1258 | request = urllib2.Request(video_info_url) |
e616ec0c | 1259 | try: |
497cd3e6 RG |
1260 | video_info_webpage = urllib2.urlopen(request).read() |
1261 | video_info = parse_qs(video_info_webpage) | |
1262 | if 'token' in video_info: | |
1263 | break | |
e616ec0c | 1264 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: |
497cd3e6 | 1265 | self._downloader.trouble(u'ERROR: unable to download video info webpage: %s' % str(err)) |
e616ec0c | 1266 | return |
f95f29fd RG |
1267 | if 'token' not in video_info: |
1268 | if 'reason' in video_info: | |
8e686771 | 1269 | self._downloader.trouble(u'ERROR: YouTube said: %s' % video_info['reason'][0].decode('utf-8')) |
f95f29fd RG |
1270 | else: |
1271 | self._downloader.trouble(u'ERROR: "token" parameter not in video info for unknown reason') | |
1272 | return | |
1273 | ||
1274 | # Start extracting information | |
497cd3e6 RG |
1275 | self.report_information_extraction(video_id) |
1276 | ||
1277 | # uploader | |
1278 | if 'author' not in video_info: | |
1279 | self._downloader.trouble(u'ERROR: unable to extract uploader nickname') | |
1280 | return | |
1281 | video_uploader = urllib.unquote_plus(video_info['author'][0]) | |
e616ec0c | 1282 | |
497cd3e6 RG |
1283 | # title |
1284 | if 'title' not in video_info: | |
1285 | self._downloader.trouble(u'ERROR: unable to extract video title') | |
1286 | return | |
1287 | video_title = urllib.unquote_plus(video_info['title'][0]) | |
1288 | video_title = video_title.decode('utf-8') | |
1289 | video_title = sanitize_title(video_title) | |
1290 | ||
1291 | # simplified title | |
1292 | simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title) | |
1293 | simple_title = simple_title.strip(ur'_') | |
1294 | ||
1295 | # thumbnail image | |
1296 | if 'thumbnail_url' not in video_info: | |
1297 | self._downloader.trouble(u'WARNING: unable to extract video thumbnail') | |
1298 | video_thumbnail = '' | |
1299 | else: # don't panic if we can't find it | |
1300 | video_thumbnail = urllib.unquote_plus(video_info['thumbnail_url'][0]) | |
1301 | ||
b3a27b52 NA |
1302 | # upload date |
1303 | upload_date = u'NA' | |
3efa45c3 | 1304 | mobj = re.search(r'id="eow-date.*?>(.*?)</span>', video_webpage, re.DOTALL) |
b3a27b52 | 1305 | if mobj is not None: |
a1f03c7b | 1306 | upload_date = ' '.join(re.sub(r'[/,-]', r' ', mobj.group(1)).split()) |
87cbd213 | 1307 | format_expressions = ['%d %B %Y', '%B %d %Y', '%b %d %Y'] |
a1f03c7b NA |
1308 | for expression in format_expressions: |
1309 | try: | |
1310 | upload_date = datetime.datetime.strptime(upload_date, expression).strftime('%Y%m%d') | |
1311 | except: | |
1312 | pass | |
b3a27b52 | 1313 | |
497cd3e6 | 1314 | # description |
c6b55a8d PH |
1315 | try: |
1316 | lxml.etree | |
1317 | except NameError: | |
1318 | video_description = u'No description available.' | |
8b95c387 | 1319 | if self._downloader.params.get('forcedescription', False) or self._downloader.params.get('writedescription', False): |
c6b55a8d PH |
1320 | mobj = re.search(r'<meta name="description" content="(.*)"(?:\s*/)?>', video_webpage) |
1321 | if mobj is not None: | |
1322 | video_description = mobj.group(1).decode('utf-8') | |
1323 | else: | |
1324 | html_parser = lxml.etree.HTMLParser(encoding='utf-8') | |
1325 | vwebpage_doc = lxml.etree.parse(StringIO.StringIO(video_webpage), html_parser) | |
1326 | video_description = u''.join(vwebpage_doc.xpath('id("eow-description")//text()')) | |
91e6a385 | 1327 | # TODO use another parser |
497cd3e6 | 1328 | |
5ce7d172 RG |
1329 | # token |
1330 | video_token = urllib.unquote_plus(video_info['token'][0]) | |
1331 | ||
497cd3e6 | 1332 | # Decide which formats to download |
f83ae781 | 1333 | req_format = self._downloader.params.get('format', None) |
2e3a32e4 | 1334 | |
f137bef9 PH |
1335 | if 'conn' in video_info and video_info['conn'][0].startswith('rtmp'): |
1336 | self.report_rtmp_download() | |
1337 | video_url_list = [(None, video_info['conn'][0])] | |
f137bef9 | 1338 | elif 'url_encoded_fmt_stream_map' in video_info and len(video_info['url_encoded_fmt_stream_map']) >= 1: |
0ac22e4f | 1339 | url_data_strs = video_info['url_encoded_fmt_stream_map'][0].split(',') |
8519c32d | 1340 | url_data = [parse_qs(uds) for uds in url_data_strs] |
f137bef9 | 1341 | url_data = filter(lambda ud: 'itag' in ud and 'url' in ud, url_data) |
8519c32d | 1342 | url_map = dict((ud['itag'][0], ud['url'][0]) for ud in url_data) |
2b70537d | 1343 | |
497cd3e6 RG |
1344 | format_limit = self._downloader.params.get('format_limit', None) |
1345 | if format_limit is not None and format_limit in self._available_formats: | |
1346 | format_list = self._available_formats[self._available_formats.index(format_limit):] | |
e616ec0c | 1347 | else: |
497cd3e6 RG |
1348 | format_list = self._available_formats |
1349 | existing_formats = [x for x in format_list if x in url_map] | |
1350 | if len(existing_formats) == 0: | |
1351 | self._downloader.trouble(u'ERROR: no known formats available for video') | |
968aa884 | 1352 | return |
3de2a1e6 FT |
1353 | if self._downloader.params.get('listformats', None): |
1354 | self._print_formats(existing_formats) | |
2761012f | 1355 | return |
5260e68f | 1356 | if req_format is None or req_format == 'best': |
d157d259 | 1357 | video_url_list = [(existing_formats[0], url_map[existing_formats[0]])] # Best quality |
c52b01f3 K |
1358 | elif req_format == 'worst': |
1359 | video_url_list = [(existing_formats[len(existing_formats)-1], url_map[existing_formats[len(existing_formats)-1]])] # worst quality | |
5260e68f | 1360 | elif req_format in ('-1', 'all'): |
d157d259 | 1361 | video_url_list = [(f, url_map[f]) for f in existing_formats] # All formats |
497cd3e6 | 1362 | else: |
5260e68f PH |
1363 | # Specific formats. We pick the first in a slash-delimeted sequence. |
1364 | # For example, if '1/2/3/4' is requested and '2' and '4' are available, we pick '2'. | |
1365 | req_formats = req_format.split('/') | |
1366 | video_url_list = None | |
1367 | for rf in req_formats: | |
1368 | if rf in url_map: | |
1369 | video_url_list = [(rf, url_map[rf])] | |
1370 | break | |
1371 | if video_url_list is None: | |
5c132793 RG |
1372 | self._downloader.trouble(u'ERROR: requested format not available') |
1373 | return | |
497cd3e6 | 1374 | else: |
f3dc18d8 | 1375 | self._downloader.trouble(u'ERROR: no conn or url_encoded_fmt_stream_map information found in video info') |
497cd3e6 | 1376 | return |
7b7759f5 | 1377 | |
497cd3e6 RG |
1378 | for format_param, video_real_url in video_url_list: |
1379 | # At this point we have a new video | |
1380 | self._downloader.increment_downloads() | |
1381 | ||
1382 | # Extension | |
1383 | video_extension = self._video_extensions.get(format_param, 'flv') | |
7e58d568 | 1384 | |
968aa884 | 1385 | try: |
7b7759f5 | 1386 | # Process video information |
1387 | self._downloader.process_info({ | |
1388 | 'id': video_id.decode('utf-8'), | |
1389 | 'url': video_real_url.decode('utf-8'), | |
1390 | 'uploader': video_uploader.decode('utf-8'), | |
138b11f3 | 1391 | 'upload_date': upload_date, |
7b7759f5 | 1392 | 'title': video_title, |
1393 | 'stitle': simple_title, | |
1394 | 'ext': video_extension.decode('utf-8'), | |
6ba562b0 | 1395 | 'format': (format_param is None and u'NA' or format_param.decode('utf-8')), |
7e58d568 | 1396 | 'thumbnail': video_thumbnail.decode('utf-8'), |
c6b55a8d | 1397 | 'description': video_description, |
e616ec0c | 1398 | 'player_url': player_url, |
7b7759f5 | 1399 | }) |
497cd3e6 | 1400 | except UnavailableVideoError, err: |
09cc744c | 1401 | self._downloader.trouble(u'\nERROR: unable to download video') |
42bcd27d | 1402 | |
4fa74b52 | 1403 | |
020f7150 RG |
1404 | class MetacafeIE(InfoExtractor): |
1405 | """Information Extractor for metacafe.com.""" | |
1406 | ||
1407 | _VALID_URL = r'(?:http://)?(?:www\.)?metacafe\.com/watch/([^/]+)/([^/]+)/.*' | |
2546e767 | 1408 | _DISCLAIMER = 'http://www.metacafe.com/family_filter/' |
dbccb6cd | 1409 | _FILTER_POST = 'http://www.metacafe.com/f/index.php?inputType=filter&controllerGroup=user' |
020f7150 | 1410 | _youtube_ie = None |
f3098c4d | 1411 | IE_NAME = u'metacafe' |
020f7150 RG |
1412 | |
1413 | def __init__(self, youtube_ie, downloader=None): | |
1414 | InfoExtractor.__init__(self, downloader) | |
1415 | self._youtube_ie = youtube_ie | |
1416 | ||
020f7150 RG |
1417 | def report_disclaimer(self): |
1418 | """Report disclaimer retrieval.""" | |
331ce0a0 | 1419 | self._downloader.to_screen(u'[metacafe] Retrieving disclaimer') |
020f7150 RG |
1420 | |
1421 | def report_age_confirmation(self): | |
1422 | """Report attempt to confirm age.""" | |
331ce0a0 | 1423 | self._downloader.to_screen(u'[metacafe] Confirming age') |
d3975459 | 1424 | |
020f7150 RG |
1425 | def report_download_webpage(self, video_id): |
1426 | """Report webpage download.""" | |
331ce0a0 | 1427 | self._downloader.to_screen(u'[metacafe] %s: Downloading webpage' % video_id) |
d3975459 | 1428 | |
020f7150 RG |
1429 | def report_extraction(self, video_id): |
1430 | """Report information extraction.""" | |
331ce0a0 | 1431 | self._downloader.to_screen(u'[metacafe] %s: Extracting information' % video_id) |
020f7150 RG |
1432 | |
1433 | def _real_initialize(self): | |
1434 | # Retrieve disclaimer | |
1987c232 | 1435 | request = urllib2.Request(self._DISCLAIMER) |
020f7150 RG |
1436 | try: |
1437 | self.report_disclaimer() | |
1438 | disclaimer = urllib2.urlopen(request).read() | |
1439 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
147753eb | 1440 | self._downloader.trouble(u'ERROR: unable to retrieve disclaimer: %s' % str(err)) |
020f7150 RG |
1441 | return |
1442 | ||
1443 | # Confirm age | |
1444 | disclaimer_form = { | |
2546e767 | 1445 | 'filters': '0', |
020f7150 RG |
1446 | 'submit': "Continue - I'm over 18", |
1447 | } | |
1987c232 | 1448 | request = urllib2.Request(self._FILTER_POST, urllib.urlencode(disclaimer_form)) |
020f7150 RG |
1449 | try: |
1450 | self.report_age_confirmation() | |
1451 | disclaimer = urllib2.urlopen(request).read() | |
1452 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
147753eb | 1453 | self._downloader.trouble(u'ERROR: unable to confirm age: %s' % str(err)) |
020f7150 | 1454 | return |
d3975459 | 1455 | |
020f7150 RG |
1456 | def _real_extract(self, url): |
1457 | # Extract id and simplified title from URL | |
1458 | mobj = re.match(self._VALID_URL, url) | |
1459 | if mobj is None: | |
147753eb | 1460 | self._downloader.trouble(u'ERROR: invalid URL: %s' % url) |
6f21f686 | 1461 | return |
020f7150 RG |
1462 | |
1463 | video_id = mobj.group(1) | |
1464 | ||
1465 | # Check if video comes from YouTube | |
1466 | mobj2 = re.match(r'^yt-(.*)$', video_id) | |
1467 | if mobj2 is not None: | |
6f21f686 RG |
1468 | self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % mobj2.group(1)) |
1469 | return | |
020f7150 | 1470 | |
df372a65 | 1471 | # At this point we have a new video |
9bf7fa52 | 1472 | self._downloader.increment_downloads() |
df372a65 | 1473 | |
020f7150 | 1474 | simple_title = mobj.group(2).decode('utf-8') |
020f7150 RG |
1475 | |
1476 | # Retrieve video webpage to extract further information | |
1477 | request = urllib2.Request('http://www.metacafe.com/watch/%s/' % video_id) | |
1478 | try: | |
1479 | self.report_download_webpage(video_id) | |
1480 | webpage = urllib2.urlopen(request).read() | |
1481 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
147753eb | 1482 | self._downloader.trouble(u'ERROR: unable retrieve video webpage: %s' % str(err)) |
6f21f686 | 1483 | return |
020f7150 RG |
1484 | |
1485 | # Extract URL, uploader and title from webpage | |
1486 | self.report_extraction(video_id) | |
18963a36 | 1487 | mobj = re.search(r'(?m)&mediaURL=([^&]+)', webpage) |
c6c555cf RG |
1488 | if mobj is not None: |
1489 | mediaURL = urllib.unquote(mobj.group(1)) | |
6b57e8c5 | 1490 | video_extension = mediaURL[-3:] |
d3975459 | 1491 | |
c6c555cf RG |
1492 | # Extract gdaKey if available |
1493 | mobj = re.search(r'(?m)&gdaKey=(.*?)&', webpage) | |
1494 | if mobj is None: | |
1495 | video_url = mediaURL | |
1496 | else: | |
1497 | gdaKey = mobj.group(1) | |
1498 | video_url = '%s?__gda__=%s' % (mediaURL, gdaKey) | |
109626fc | 1499 | else: |
c6c555cf RG |
1500 | mobj = re.search(r' name="flashvars" value="(.*?)"', webpage) |
1501 | if mobj is None: | |
1502 | self._downloader.trouble(u'ERROR: unable to extract media URL') | |
1503 | return | |
1504 | vardict = parse_qs(mobj.group(1)) | |
1505 | if 'mediaData' not in vardict: | |
1506 | self._downloader.trouble(u'ERROR: unable to extract media URL') | |
1507 | return | |
1508 | mobj = re.search(r'"mediaURL":"(http.*?)","key":"(.*?)"', vardict['mediaData'][0]) | |
1509 | if mobj is None: | |
1510 | self._downloader.trouble(u'ERROR: unable to extract media URL') | |
1511 | return | |
6b57e8c5 RG |
1512 | mediaURL = mobj.group(1).replace('\\/', '/') |
1513 | video_extension = mediaURL[-3:] | |
1514 | video_url = '%s?__gda__=%s' % (mediaURL, mobj.group(2)) | |
020f7150 | 1515 | |
2546e767 | 1516 | mobj = re.search(r'(?im)<title>(.*) - Video</title>', webpage) |
020f7150 | 1517 | if mobj is None: |
147753eb | 1518 | self._downloader.trouble(u'ERROR: unable to extract title') |
6f21f686 | 1519 | return |
020f7150 | 1520 | video_title = mobj.group(1).decode('utf-8') |
490fd7ae | 1521 | video_title = sanitize_title(video_title) |
020f7150 | 1522 | |
29f07568 | 1523 | mobj = re.search(r'(?ms)By:\s*<a .*?>(.+?)<', webpage) |
020f7150 | 1524 | if mobj is None: |
147753eb | 1525 | self._downloader.trouble(u'ERROR: unable to extract uploader nickname') |
6f21f686 | 1526 | return |
dbccb6cd | 1527 | video_uploader = mobj.group(1) |
020f7150 | 1528 | |
42bcd27d | 1529 | try: |
1530 | # Process video information | |
1531 | self._downloader.process_info({ | |
1532 | 'id': video_id.decode('utf-8'), | |
1533 | 'url': video_url.decode('utf-8'), | |
1534 | 'uploader': video_uploader.decode('utf-8'), | |
138b11f3 | 1535 | 'upload_date': u'NA', |
42bcd27d | 1536 | 'title': video_title, |
1537 | 'stitle': simple_title, | |
1538 | 'ext': video_extension.decode('utf-8'), | |
6ba562b0 | 1539 | 'format': u'NA', |
e616ec0c | 1540 | 'player_url': None, |
42bcd27d | 1541 | }) |
73f4e7af | 1542 | except UnavailableVideoError: |
09cc744c | 1543 | self._downloader.trouble(u'\nERROR: unable to download video') |
020f7150 | 1544 | |
25af2bce | 1545 | |
4135fa45 WB |
1546 | class DailymotionIE(InfoExtractor): |
1547 | """Information Extractor for Dailymotion""" | |
1548 | ||
1549 | _VALID_URL = r'(?i)(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/video/([^_/]+)_([^/]+)' | |
f3098c4d | 1550 | IE_NAME = u'dailymotion' |
4135fa45 WB |
1551 | |
1552 | def __init__(self, downloader=None): | |
1553 | InfoExtractor.__init__(self, downloader) | |
1554 | ||
4135fa45 WB |
1555 | def report_download_webpage(self, video_id): |
1556 | """Report webpage download.""" | |
331ce0a0 | 1557 | self._downloader.to_screen(u'[dailymotion] %s: Downloading webpage' % video_id) |
d3975459 | 1558 | |
4135fa45 WB |
1559 | def report_extraction(self, video_id): |
1560 | """Report information extraction.""" | |
331ce0a0 | 1561 | self._downloader.to_screen(u'[dailymotion] %s: Extracting information' % video_id) |
4135fa45 WB |
1562 | |
1563 | def _real_initialize(self): | |
1564 | return | |
1565 | ||
4135fa45 WB |
1566 | def _real_extract(self, url): |
1567 | # Extract id and simplified title from URL | |
1568 | mobj = re.match(self._VALID_URL, url) | |
1569 | if mobj is None: | |
1570 | self._downloader.trouble(u'ERROR: invalid URL: %s' % url) | |
1571 | return | |
1572 | ||
df372a65 | 1573 | # At this point we have a new video |
9bf7fa52 | 1574 | self._downloader.increment_downloads() |
4135fa45 WB |
1575 | video_id = mobj.group(1) |
1576 | ||
1577 | simple_title = mobj.group(2).decode('utf-8') | |
1578 | video_extension = 'flv' | |
1579 | ||
1580 | # Retrieve video webpage to extract further information | |
1581 | request = urllib2.Request(url) | |
62a29bbf | 1582 | request.add_header('Cookie', 'family_filter=off') |
4135fa45 WB |
1583 | try: |
1584 | self.report_download_webpage(video_id) | |
1585 | webpage = urllib2.urlopen(request).read() | |
1586 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
1587 | self._downloader.trouble(u'ERROR: unable retrieve video webpage: %s' % str(err)) | |
1588 | return | |
1589 | ||
1590 | # Extract URL, uploader and title from webpage | |
1591 | self.report_extraction(video_id) | |
62a29bbf | 1592 | mobj = re.search(r'(?i)addVariable\(\"sequence\"\s*,\s*\"([^\"]+?)\"\)', webpage) |
4135fa45 WB |
1593 | if mobj is None: |
1594 | self._downloader.trouble(u'ERROR: unable to extract media URL') | |
1595 | return | |
62a29bbf | 1596 | sequence = urllib.unquote(mobj.group(1)) |
1597 | mobj = re.search(r',\"sdURL\"\:\"([^\"]+?)\",', sequence) | |
1598 | if mobj is None: | |
1599 | self._downloader.trouble(u'ERROR: unable to extract media URL') | |
1600 | return | |
1601 | mediaURL = urllib.unquote(mobj.group(1)).replace('\\', '') | |
4135fa45 WB |
1602 | |
1603 | # if needed add http://www.dailymotion.com/ if relative URL | |
1604 | ||
1605 | video_url = mediaURL | |
1606 | ||
62a29bbf | 1607 | mobj = re.search(r'(?im)<title>Dailymotion\s*-\s*(.+)\s*-\s*[^<]+?</title>', webpage) |
4135fa45 WB |
1608 | if mobj is None: |
1609 | self._downloader.trouble(u'ERROR: unable to extract title') | |
1610 | return | |
1611 | video_title = mobj.group(1).decode('utf-8') | |
1612 | video_title = sanitize_title(video_title) | |
1613 | ||
62a29bbf | 1614 | mobj = re.search(r'(?im)<span class="owner[^\"]+?">[^<]+?<a [^>]+?>([^<]+?)</a></span>', webpage) |
4135fa45 WB |
1615 | if mobj is None: |
1616 | self._downloader.trouble(u'ERROR: unable to extract uploader nickname') | |
1617 | return | |
1618 | video_uploader = mobj.group(1) | |
1619 | ||
1620 | try: | |
1621 | # Process video information | |
1622 | self._downloader.process_info({ | |
1623 | 'id': video_id.decode('utf-8'), | |
1624 | 'url': video_url.decode('utf-8'), | |
1625 | 'uploader': video_uploader.decode('utf-8'), | |
138b11f3 | 1626 | 'upload_date': u'NA', |
4135fa45 WB |
1627 | 'title': video_title, |
1628 | 'stitle': simple_title, | |
1629 | 'ext': video_extension.decode('utf-8'), | |
1630 | 'format': u'NA', | |
1631 | 'player_url': None, | |
1632 | }) | |
73f4e7af | 1633 | except UnavailableVideoError: |
09cc744c | 1634 | self._downloader.trouble(u'\nERROR: unable to download video') |
4135fa45 | 1635 | |
c0a10ca8 | 1636 | |
49c0028a | 1637 | class GoogleIE(InfoExtractor): |
1638 | """Information extractor for video.google.com.""" | |
1639 | ||
490fd7ae | 1640 | _VALID_URL = r'(?:http://)?video\.google\.(?:com(?:\.au)?|co\.(?:uk|jp|kr|cr)|ca|de|es|fr|it|nl|pl)/videoplay\?docid=([^\&]+).*' |
f3098c4d | 1641 | IE_NAME = u'video.google' |
49c0028a | 1642 | |
1643 | def __init__(self, downloader=None): | |
1644 | InfoExtractor.__init__(self, downloader) | |
1645 | ||
49c0028a | 1646 | def report_download_webpage(self, video_id): |
1647 | """Report webpage download.""" | |
331ce0a0 | 1648 | self._downloader.to_screen(u'[video.google] %s: Downloading webpage' % video_id) |
49c0028a | 1649 | |
1650 | def report_extraction(self, video_id): | |
1651 | """Report information extraction.""" | |
331ce0a0 | 1652 | self._downloader.to_screen(u'[video.google] %s: Extracting information' % video_id) |
49c0028a | 1653 | |
1654 | def _real_initialize(self): | |
1655 | return | |
1656 | ||
1657 | def _real_extract(self, url): | |
1658 | # Extract id from URL | |
1659 | mobj = re.match(self._VALID_URL, url) | |
1660 | if mobj is None: | |
1661 | self._downloader.trouble(u'ERROR: Invalid URL: %s' % url) | |
1662 | return | |
1663 | ||
df372a65 | 1664 | # At this point we have a new video |
9bf7fa52 | 1665 | self._downloader.increment_downloads() |
49c0028a | 1666 | video_id = mobj.group(1) |
1667 | ||
1668 | video_extension = 'mp4' | |
1669 | ||
1670 | # Retrieve video webpage to extract further information | |
490fd7ae | 1671 | request = urllib2.Request('http://video.google.com/videoplay?docid=%s&hl=en&oe=utf-8' % video_id) |
49c0028a | 1672 | try: |
1673 | self.report_download_webpage(video_id) | |
1674 | webpage = urllib2.urlopen(request).read() | |
1675 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
1676 | self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err)) | |
1677 | return | |
1678 | ||
1679 | # Extract URL, uploader, and title from webpage | |
1680 | self.report_extraction(video_id) | |
490fd7ae RG |
1681 | mobj = re.search(r"download_url:'([^']+)'", webpage) |
1682 | if mobj is None: | |
1683 | video_extension = 'flv' | |
1684 | mobj = re.search(r"(?i)videoUrl\\x3d(.+?)\\x26", webpage) | |
49c0028a | 1685 | if mobj is None: |
1686 | self._downloader.trouble(u'ERROR: unable to extract media URL') | |
1687 | return | |
1688 | mediaURL = urllib.unquote(mobj.group(1)) | |
1689 | mediaURL = mediaURL.replace('\\x3d', '\x3d') | |
1690 | mediaURL = mediaURL.replace('\\x26', '\x26') | |
1691 | ||
1692 | video_url = mediaURL | |
1693 | ||
1694 | mobj = re.search(r'<title>(.*)</title>', webpage) | |
1695 | if mobj is None: | |
1696 | self._downloader.trouble(u'ERROR: unable to extract title') | |
1697 | return | |
1698 | video_title = mobj.group(1).decode('utf-8') | |
490fd7ae | 1699 | video_title = sanitize_title(video_title) |
31cbdaaf | 1700 | simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title) |
49c0028a | 1701 | |
7e58d568 RG |
1702 | # Extract video description |
1703 | mobj = re.search(r'<span id=short-desc-content>([^<]*)</span>', webpage) | |
1704 | if mobj is None: | |
1705 | self._downloader.trouble(u'ERROR: unable to extract video description') | |
1706 | return | |
1707 | video_description = mobj.group(1).decode('utf-8') | |
1708 | if not video_description: | |
1709 | video_description = 'No description available.' | |
1710 | ||
1711 | # Extract video thumbnail | |
1712 | if self._downloader.params.get('forcethumbnail', False): | |
1713 | request = urllib2.Request('http://video.google.com/videosearch?q=%s+site:video.google.com&hl=en' % abs(int(video_id))) | |
1714 | try: | |
1715 | webpage = urllib2.urlopen(request).read() | |
1716 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
1717 | self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err)) | |
1718 | return | |
1719 | mobj = re.search(r'<img class=thumbnail-img (?:.* )?src=(http.*)>', webpage) | |
1720 | if mobj is None: | |
1721 | self._downloader.trouble(u'ERROR: unable to extract video thumbnail') | |
1722 | return | |
1723 | video_thumbnail = mobj.group(1) | |
1724 | else: # we need something to pass to process_info | |
1725 | video_thumbnail = '' | |
1726 | ||
49c0028a | 1727 | try: |
1728 | # Process video information | |
1729 | self._downloader.process_info({ | |
1730 | 'id': video_id.decode('utf-8'), | |
1731 | 'url': video_url.decode('utf-8'), | |
6ba562b0 | 1732 | 'uploader': u'NA', |
138b11f3 | 1733 | 'upload_date': u'NA', |
490fd7ae | 1734 | 'title': video_title, |
31cbdaaf | 1735 | 'stitle': simple_title, |
49c0028a | 1736 | 'ext': video_extension.decode('utf-8'), |
6ba562b0 | 1737 | 'format': u'NA', |
e616ec0c | 1738 | 'player_url': None, |
49c0028a | 1739 | }) |
73f4e7af | 1740 | except UnavailableVideoError: |
09cc744c | 1741 | self._downloader.trouble(u'\nERROR: unable to download video') |
49c0028a | 1742 | |
1743 | ||
1744 | class PhotobucketIE(InfoExtractor): | |
1745 | """Information extractor for photobucket.com.""" | |
1746 | ||
1747 | _VALID_URL = r'(?:http://)?(?:[a-z0-9]+\.)?photobucket\.com/.*[\?\&]current=(.*\.flv)' | |
f3098c4d | 1748 | IE_NAME = u'photobucket' |
49c0028a | 1749 | |
1750 | def __init__(self, downloader=None): | |
1751 | InfoExtractor.__init__(self, downloader) | |
1752 | ||
49c0028a | 1753 | def report_download_webpage(self, video_id): |
1754 | """Report webpage download.""" | |
331ce0a0 | 1755 | self._downloader.to_screen(u'[photobucket] %s: Downloading webpage' % video_id) |
49c0028a | 1756 | |
1757 | def report_extraction(self, video_id): | |
1758 | """Report information extraction.""" | |
331ce0a0 | 1759 | self._downloader.to_screen(u'[photobucket] %s: Extracting information' % video_id) |
49c0028a | 1760 | |
1761 | def _real_initialize(self): | |
1762 | return | |
1763 | ||
1764 | def _real_extract(self, url): | |
1765 | # Extract id from URL | |
1766 | mobj = re.match(self._VALID_URL, url) | |
1767 | if mobj is None: | |
1768 | self._downloader.trouble(u'ERROR: Invalid URL: %s' % url) | |
1769 | return | |
1770 | ||
df372a65 | 1771 | # At this point we have a new video |
9bf7fa52 | 1772 | self._downloader.increment_downloads() |
49c0028a | 1773 | video_id = mobj.group(1) |
1774 | ||
1775 | video_extension = 'flv' | |
1776 | ||
1777 | # Retrieve video webpage to extract further information | |
1778 | request = urllib2.Request(url) | |
1779 | try: | |
1780 | self.report_download_webpage(video_id) | |
1781 | webpage = urllib2.urlopen(request).read() | |
1782 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
1783 | self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err)) | |
1784 | return | |
1785 | ||
1786 | # Extract URL, uploader, and title from webpage | |
1787 | self.report_extraction(video_id) | |
1788 | mobj = re.search(r'<link rel="video_src" href=".*\?file=([^"]+)" />', webpage) | |
1789 | if mobj is None: | |
1790 | self._downloader.trouble(u'ERROR: unable to extract media URL') | |
1791 | return | |
1792 | mediaURL = urllib.unquote(mobj.group(1)) | |
1793 | ||
1794 | video_url = mediaURL | |
1795 | ||
1796 | mobj = re.search(r'<title>(.*) video by (.*) - Photobucket</title>', webpage) | |
1797 | if mobj is None: | |
1798 | self._downloader.trouble(u'ERROR: unable to extract title') | |
1799 | return | |
1800 | video_title = mobj.group(1).decode('utf-8') | |
490fd7ae | 1801 | video_title = sanitize_title(video_title) |
31cbdaaf | 1802 | simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title) |
49c0028a | 1803 | |
1804 | video_uploader = mobj.group(2).decode('utf-8') | |
1805 | ||
1806 | try: | |
1807 | # Process video information | |
1808 | self._downloader.process_info({ | |
1809 | 'id': video_id.decode('utf-8'), | |
1810 | 'url': video_url.decode('utf-8'), | |
490fd7ae | 1811 | 'uploader': video_uploader, |
138b11f3 | 1812 | 'upload_date': u'NA', |
490fd7ae | 1813 | 'title': video_title, |
31cbdaaf | 1814 | 'stitle': simple_title, |
490fd7ae | 1815 | 'ext': video_extension.decode('utf-8'), |
6ba562b0 | 1816 | 'format': u'NA', |
e616ec0c | 1817 | 'player_url': None, |
490fd7ae | 1818 | }) |
73f4e7af | 1819 | except UnavailableVideoError: |
09cc744c | 1820 | self._downloader.trouble(u'\nERROR: unable to download video') |
490fd7ae RG |
1821 | |
1822 | ||
61945318 RG |
1823 | class YahooIE(InfoExtractor): |
1824 | """Information extractor for video.yahoo.com.""" | |
1825 | ||
1826 | # _VALID_URL matches all Yahoo! Video URLs | |
1827 | # _VPAGE_URL matches only the extractable '/watch/' URLs | |
1828 | _VALID_URL = r'(?:http://)?(?:[a-z]+\.)?video\.yahoo\.com/(?:watch|network)/([0-9]+)(?:/|\?v=)([0-9]+)(?:[#\?].*)?' | |
1829 | _VPAGE_URL = r'(?:http://)?video\.yahoo\.com/watch/([0-9]+)/([0-9]+)(?:[#\?].*)?' | |
f3098c4d | 1830 | IE_NAME = u'video.yahoo' |
61945318 RG |
1831 | |
1832 | def __init__(self, downloader=None): | |
1833 | InfoExtractor.__init__(self, downloader) | |
1834 | ||
61945318 RG |
1835 | def report_download_webpage(self, video_id): |
1836 | """Report webpage download.""" | |
331ce0a0 | 1837 | self._downloader.to_screen(u'[video.yahoo] %s: Downloading webpage' % video_id) |
61945318 RG |
1838 | |
1839 | def report_extraction(self, video_id): | |
1840 | """Report information extraction.""" | |
331ce0a0 | 1841 | self._downloader.to_screen(u'[video.yahoo] %s: Extracting information' % video_id) |
61945318 RG |
1842 | |
1843 | def _real_initialize(self): | |
1844 | return | |
1845 | ||
df372a65 | 1846 | def _real_extract(self, url, new_video=True): |
61945318 RG |
1847 | # Extract ID from URL |
1848 | mobj = re.match(self._VALID_URL, url) | |
1849 | if mobj is None: | |
1850 | self._downloader.trouble(u'ERROR: Invalid URL: %s' % url) | |
1851 | return | |
1852 | ||
df372a65 | 1853 | # At this point we have a new video |
9bf7fa52 | 1854 | self._downloader.increment_downloads() |
61945318 RG |
1855 | video_id = mobj.group(2) |
1856 | video_extension = 'flv' | |
1857 | ||
1858 | # Rewrite valid but non-extractable URLs as | |
1859 | # extractable English language /watch/ URLs | |
1860 | if re.match(self._VPAGE_URL, url) is None: | |
1861 | request = urllib2.Request(url) | |
1862 | try: | |
1863 | webpage = urllib2.urlopen(request).read() | |
1864 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
1865 | self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err)) | |
1866 | return | |
1867 | ||
1868 | mobj = re.search(r'\("id", "([0-9]+)"\);', webpage) | |
1869 | if mobj is None: | |
1870 | self._downloader.trouble(u'ERROR: Unable to extract id field') | |
1871 | return | |
1872 | yahoo_id = mobj.group(1) | |
1873 | ||
1874 | mobj = re.search(r'\("vid", "([0-9]+)"\);', webpage) | |
1875 | if mobj is None: | |
1876 | self._downloader.trouble(u'ERROR: Unable to extract vid field') | |
1877 | return | |
1878 | yahoo_vid = mobj.group(1) | |
1879 | ||
1880 | url = 'http://video.yahoo.com/watch/%s/%s' % (yahoo_vid, yahoo_id) | |
df372a65 | 1881 | return self._real_extract(url, new_video=False) |
61945318 RG |
1882 | |
1883 | # Retrieve video webpage to extract further information | |
1884 | request = urllib2.Request(url) | |
1885 | try: | |
1886 | self.report_download_webpage(video_id) | |
1887 | webpage = urllib2.urlopen(request).read() | |
1888 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
1889 | self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err)) | |
1890 | return | |
1891 | ||
1892 | # Extract uploader and title from webpage | |
1893 | self.report_extraction(video_id) | |
1894 | mobj = re.search(r'<meta name="title" content="(.*)" />', webpage) | |
1895 | if mobj is None: | |
1896 | self._downloader.trouble(u'ERROR: unable to extract video title') | |
1897 | return | |
1898 | video_title = mobj.group(1).decode('utf-8') | |
1899 | simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title) | |
1900 | ||
1901 | mobj = re.search(r'<h2 class="ti-5"><a href="http://video\.yahoo\.com/(people|profile)/[0-9]+" beacon=".*">(.*)</a></h2>', webpage) | |
1902 | if mobj is None: | |
1903 | self._downloader.trouble(u'ERROR: unable to extract video uploader') | |
1904 | return | |
1905 | video_uploader = mobj.group(1).decode('utf-8') | |
1906 | ||
7e58d568 RG |
1907 | # Extract video thumbnail |
1908 | mobj = re.search(r'<link rel="image_src" href="(.*)" />', webpage) | |
1909 | if mobj is None: | |
1910 | self._downloader.trouble(u'ERROR: unable to extract video thumbnail') | |
1911 | return | |
1912 | video_thumbnail = mobj.group(1).decode('utf-8') | |
1913 | ||
1914 | # Extract video description | |
1915 | mobj = re.search(r'<meta name="description" content="(.*)" />', webpage) | |
1916 | if mobj is None: | |
1917 | self._downloader.trouble(u'ERROR: unable to extract video description') | |
1918 | return | |
1919 | video_description = mobj.group(1).decode('utf-8') | |
c0a10ca8 F |
1920 | if not video_description: |
1921 | video_description = 'No description available.' | |
7e58d568 | 1922 | |
61945318 RG |
1923 | # Extract video height and width |
1924 | mobj = re.search(r'<meta name="video_height" content="([0-9]+)" />', webpage) | |
1925 | if mobj is None: | |
1926 | self._downloader.trouble(u'ERROR: unable to extract video height') | |
1927 | return | |
1928 | yv_video_height = mobj.group(1) | |
1929 | ||
1930 | mobj = re.search(r'<meta name="video_width" content="([0-9]+)" />', webpage) | |
1931 | if mobj is None: | |
1932 | self._downloader.trouble(u'ERROR: unable to extract video width') | |
1933 | return | |
1934 | yv_video_width = mobj.group(1) | |
1935 | ||
1936 | # Retrieve video playlist to extract media URL | |
1937 | # I'm not completely sure what all these options are, but we | |
1938 | # seem to need most of them, otherwise the server sends a 401. | |
1939 | yv_lg = 'R0xx6idZnW2zlrKP8xxAIR' # not sure what this represents | |
1940 | yv_bitrate = '700' # according to Wikipedia this is hard-coded | |
1941 | request = urllib2.Request('http://cosmos.bcst.yahoo.com/up/yep/process/getPlaylistFOP.php?node_id=' + video_id + | |
c0a10ca8 F |
1942 | '&tech=flash&mode=playlist&lg=' + yv_lg + '&bitrate=' + yv_bitrate + '&vidH=' + yv_video_height + |
1943 | '&vidW=' + yv_video_width + '&swf=as3&rd=video.yahoo.com&tk=null&adsupported=v1,v2,&eventid=1301797') | |
61945318 RG |
1944 | try: |
1945 | self.report_download_webpage(video_id) | |
1946 | webpage = urllib2.urlopen(request).read() | |
1947 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
1948 | self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err)) | |
1949 | return | |
1950 | ||
1951 | # Extract media URL from playlist XML | |
1952 | mobj = re.search(r'<STREAM APP="(http://.*)" FULLPATH="/?(/.*\.flv\?[^"]*)"', webpage) | |
1953 | if mobj is None: | |
1954 | self._downloader.trouble(u'ERROR: Unable to extract media URL') | |
1955 | return | |
1956 | video_url = urllib.unquote(mobj.group(1) + mobj.group(2)).decode('utf-8') | |
1957 | video_url = re.sub(r'(?u)&(.+?);', htmlentity_transform, video_url) | |
1958 | ||
1959 | try: | |
1960 | # Process video information | |
1961 | self._downloader.process_info({ | |
1962 | 'id': video_id.decode('utf-8'), | |
1963 | 'url': video_url, | |
1964 | 'uploader': video_uploader, | |
138b11f3 | 1965 | 'upload_date': u'NA', |
61945318 RG |
1966 | 'title': video_title, |
1967 | 'stitle': simple_title, | |
1968 | 'ext': video_extension.decode('utf-8'), | |
7e58d568 RG |
1969 | 'thumbnail': video_thumbnail.decode('utf-8'), |
1970 | 'description': video_description, | |
1971 | 'thumbnail': video_thumbnail, | |
e616ec0c | 1972 | 'player_url': None, |
61945318 | 1973 | }) |
73f4e7af | 1974 | except UnavailableVideoError: |
09cc744c | 1975 | self._downloader.trouble(u'\nERROR: unable to download video') |
61945318 RG |
1976 | |
1977 | ||
92743d42 RB |
1978 | class VimeoIE(InfoExtractor): |
1979 | """Information extractor for vimeo.com.""" | |
1980 | ||
1981 | # _VALID_URL matches Vimeo URLs | |
44c636df | 1982 | _VALID_URL = r'(?:https?://)?(?:(?:www|player).)?vimeo\.com/(?:groups/[^/]+/)?(?:videos?/)?([0-9]+)' |
f3098c4d | 1983 | IE_NAME = u'vimeo' |
92743d42 RB |
1984 | |
1985 | def __init__(self, downloader=None): | |
1986 | InfoExtractor.__init__(self, downloader) | |
1987 | ||
92743d42 RB |
1988 | def report_download_webpage(self, video_id): |
1989 | """Report webpage download.""" | |
0ecedbdb | 1990 | self._downloader.to_screen(u'[vimeo] %s: Downloading webpage' % video_id) |
92743d42 RB |
1991 | |
1992 | def report_extraction(self, video_id): | |
1993 | """Report information extraction.""" | |
0ecedbdb | 1994 | self._downloader.to_screen(u'[vimeo] %s: Extracting information' % video_id) |
92743d42 RB |
1995 | |
1996 | def _real_initialize(self): | |
1997 | return | |
1998 | ||
1999 | def _real_extract(self, url, new_video=True): | |
2000 | # Extract ID from URL | |
2001 | mobj = re.match(self._VALID_URL, url) | |
2002 | if mobj is None: | |
2003 | self._downloader.trouble(u'ERROR: Invalid URL: %s' % url) | |
2004 | return | |
2005 | ||
2006 | # At this point we have a new video | |
2007 | self._downloader.increment_downloads() | |
2008 | video_id = mobj.group(1) | |
92743d42 RB |
2009 | |
2010 | # Retrieve video webpage to extract further information | |
2011 | request = urllib2.Request("http://vimeo.com/moogaloop/load/clip:%s" % video_id, None, std_headers) | |
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 | ||
f24c674b RB |
2019 | # Now we begin extracting as much information as we can from what we |
2020 | # retrieved. First we extract the information common to all extractors, | |
2021 | # and latter we extract those that are Vimeo specific. | |
92743d42 | 2022 | self.report_extraction(video_id) |
f24c674b RB |
2023 | |
2024 | # Extract title | |
c5a088d3 | 2025 | mobj = re.search(r'<caption>(.*?)</caption>', webpage) |
92743d42 RB |
2026 | if mobj is None: |
2027 | self._downloader.trouble(u'ERROR: unable to extract video title') | |
2028 | return | |
2029 | video_title = mobj.group(1).decode('utf-8') | |
2030 | simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title) | |
2031 | ||
f24c674b | 2032 | # Extract uploader |
c5a088d3 | 2033 | mobj = re.search(r'<uploader_url>http://vimeo.com/(.*?)</uploader_url>', webpage) |
92743d42 RB |
2034 | if mobj is None: |
2035 | self._downloader.trouble(u'ERROR: unable to extract video uploader') | |
2036 | return | |
2037 | video_uploader = mobj.group(1).decode('utf-8') | |
2038 | ||
2039 | # Extract video thumbnail | |
c5a088d3 | 2040 | mobj = re.search(r'<thumbnail>(.*?)</thumbnail>', webpage) |
92743d42 RB |
2041 | if mobj is None: |
2042 | self._downloader.trouble(u'ERROR: unable to extract video thumbnail') | |
2043 | return | |
2044 | video_thumbnail = mobj.group(1).decode('utf-8') | |
2045 | ||
2046 | # # Extract video description | |
2047 | # mobj = re.search(r'<meta property="og:description" content="(.*)" />', webpage) | |
2048 | # if mobj is None: | |
2049 | # self._downloader.trouble(u'ERROR: unable to extract video description') | |
2050 | # return | |
2051 | # video_description = mobj.group(1).decode('utf-8') | |
2052 | # if not video_description: video_description = 'No description available.' | |
2053 | video_description = 'Foo.' | |
2054 | ||
f24c674b | 2055 | # Vimeo specific: extract request signature |
c5a088d3 | 2056 | mobj = re.search(r'<request_signature>(.*?)</request_signature>', webpage) |
92743d42 RB |
2057 | if mobj is None: |
2058 | self._downloader.trouble(u'ERROR: unable to extract request signature') | |
2059 | return | |
2060 | sig = mobj.group(1).decode('utf-8') | |
2061 | ||
f24c674b | 2062 | # Vimeo specific: Extract request signature expiration |
c5a088d3 | 2063 | mobj = re.search(r'<request_signature_expires>(.*?)</request_signature_expires>', webpage) |
92743d42 RB |
2064 | if mobj is None: |
2065 | self._downloader.trouble(u'ERROR: unable to extract request signature expiration') | |
2066 | return | |
2067 | sig_exp = mobj.group(1).decode('utf-8') | |
2068 | ||
2069 | video_url = "http://vimeo.com/moogaloop/play/clip:%s/%s/%s" % (video_id, sig, sig_exp) | |
2070 | ||
2071 | try: | |
2072 | # Process video information | |
2073 | self._downloader.process_info({ | |
2074 | 'id': video_id.decode('utf-8'), | |
2075 | 'url': video_url, | |
2076 | 'uploader': video_uploader, | |
2077 | 'upload_date': u'NA', | |
2078 | 'title': video_title, | |
2079 | 'stitle': simple_title, | |
2fc31a48 | 2080 | 'ext': u'mp4', |
92743d42 RB |
2081 | 'thumbnail': video_thumbnail.decode('utf-8'), |
2082 | 'description': video_description, | |
2083 | 'thumbnail': video_thumbnail, | |
2084 | 'description': video_description, | |
2085 | 'player_url': None, | |
2086 | }) | |
2087 | except UnavailableVideoError: | |
2088 | self._downloader.trouble(u'ERROR: unable to download video') | |
2089 | ||
2090 | ||
490fd7ae RG |
2091 | class GenericIE(InfoExtractor): |
2092 | """Generic last-resort information extractor.""" | |
2093 | ||
f3098c4d PH |
2094 | _VALID_URL = r'.*' |
2095 | IE_NAME = u'generic' | |
bdb3f7a7 | 2096 | |
490fd7ae RG |
2097 | def __init__(self, downloader=None): |
2098 | InfoExtractor.__init__(self, downloader) | |
2099 | ||
490fd7ae RG |
2100 | def report_download_webpage(self, video_id): |
2101 | """Report webpage download.""" | |
331ce0a0 RG |
2102 | self._downloader.to_screen(u'WARNING: Falling back on generic information extractor.') |
2103 | self._downloader.to_screen(u'[generic] %s: Downloading webpage' % video_id) | |
490fd7ae RG |
2104 | |
2105 | def report_extraction(self, video_id): | |
2106 | """Report information extraction.""" | |
331ce0a0 | 2107 | self._downloader.to_screen(u'[generic] %s: Extracting information' % video_id) |
490fd7ae RG |
2108 | |
2109 | def _real_initialize(self): | |
2110 | return | |
2111 | ||
2112 | def _real_extract(self, url): | |
df372a65 | 2113 | # At this point we have a new video |
9bf7fa52 | 2114 | self._downloader.increment_downloads() |
df372a65 | 2115 | |
490fd7ae RG |
2116 | video_id = url.split('/')[-1] |
2117 | request = urllib2.Request(url) | |
2118 | try: | |
2119 | self.report_download_webpage(video_id) | |
2120 | webpage = urllib2.urlopen(request).read() | |
2121 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
2122 | self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err)) | |
2123 | return | |
2124 | except ValueError, err: | |
2125 | # since this is the last-resort InfoExtractor, if | |
2126 | # this error is thrown, it'll be thrown here | |
2127 | self._downloader.trouble(u'ERROR: Invalid URL: %s' % url) | |
2128 | return | |
2129 | ||
a9806fd8 | 2130 | self.report_extraction(video_id) |
490fd7ae RG |
2131 | # Start with something easy: JW Player in SWFObject |
2132 | mobj = re.search(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage) | |
2133 | if mobj is None: | |
2134 | # Broaden the search a little bit | |
2135 | mobj = re.search(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage) | |
2136 | if mobj is None: | |
2137 | self._downloader.trouble(u'ERROR: Invalid URL: %s' % url) | |
2138 | return | |
2139 | ||
2140 | # It's possible that one of the regexes | |
2141 | # matched, but returned an empty group: | |
2142 | if mobj.group(1) is None: | |
2143 | self._downloader.trouble(u'ERROR: Invalid URL: %s' % url) | |
2144 | return | |
2145 | ||
2146 | video_url = urllib.unquote(mobj.group(1)) | |
c0a10ca8 | 2147 | video_id = os.path.basename(video_url) |
490fd7ae RG |
2148 | |
2149 | # here's a fun little line of code for you: | |
2150 | video_extension = os.path.splitext(video_id)[1][1:] | |
c0a10ca8 | 2151 | video_id = os.path.splitext(video_id)[0] |
490fd7ae RG |
2152 | |
2153 | # it's tempting to parse this further, but you would | |
2154 | # have to take into account all the variations like | |
2155 | # Video Title - Site Name | |
2156 | # Site Name | Video Title | |
2157 | # Video Title - Tagline | Site Name | |
2158 | # and so on and so forth; it's just not practical | |
2159 | mobj = re.search(r'<title>(.*)</title>', webpage) | |
2160 | if mobj is None: | |
2161 | self._downloader.trouble(u'ERROR: unable to extract title') | |
2162 | return | |
2163 | video_title = mobj.group(1).decode('utf-8') | |
2164 | video_title = sanitize_title(video_title) | |
31cbdaaf | 2165 | simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title) |
490fd7ae RG |
2166 | |
2167 | # video uploader is domain name | |
2168 | mobj = re.match(r'(?:https?://)?([^/]*)/.*', url) | |
2169 | if mobj is None: | |
2170 | self._downloader.trouble(u'ERROR: unable to extract title') | |
2171 | return | |
2172 | video_uploader = mobj.group(1).decode('utf-8') | |
2173 | ||
2174 | try: | |
2175 | # Process video information | |
2176 | self._downloader.process_info({ | |
2177 | 'id': video_id.decode('utf-8'), | |
2178 | 'url': video_url.decode('utf-8'), | |
2179 | 'uploader': video_uploader, | |
138b11f3 | 2180 | 'upload_date': u'NA', |
490fd7ae | 2181 | 'title': video_title, |
31cbdaaf | 2182 | 'stitle': simple_title, |
49c0028a | 2183 | 'ext': video_extension.decode('utf-8'), |
6ba562b0 | 2184 | 'format': u'NA', |
e616ec0c | 2185 | 'player_url': None, |
49c0028a | 2186 | }) |
73f4e7af | 2187 | except UnavailableVideoError, err: |
09cc744c | 2188 | self._downloader.trouble(u'\nERROR: unable to download video') |
49c0028a | 2189 | |
2190 | ||
25af2bce RG |
2191 | class YoutubeSearchIE(InfoExtractor): |
2192 | """Information Extractor for YouTube search queries.""" | |
bdb3f7a7 | 2193 | _VALID_URL = r'ytsearch(\d+|all)?:[\s\S]+' |
25af2bce RG |
2194 | _TEMPLATE_URL = 'http://www.youtube.com/results?search_query=%s&page=%s&gl=US&hl=en' |
2195 | _VIDEO_INDICATOR = r'href="/watch\?v=.+?"' | |
304a4d85 | 2196 | _MORE_PAGES_INDICATOR = r'(?m)>\s*Next\s*</a>' |
25af2bce | 2197 | _youtube_ie = None |
fd9288c3 | 2198 | _max_youtube_results = 1000 |
f3098c4d | 2199 | IE_NAME = u'youtube:search' |
25af2bce | 2200 | |
f995f712 | 2201 | def __init__(self, youtube_ie, downloader=None): |
25af2bce RG |
2202 | InfoExtractor.__init__(self, downloader) |
2203 | self._youtube_ie = youtube_ie | |
d3975459 | 2204 | |
25af2bce RG |
2205 | def report_download_page(self, query, pagenum): |
2206 | """Report attempt to download playlist page with given number.""" | |
490fd7ae | 2207 | query = query.decode(preferredencoding()) |
331ce0a0 | 2208 | self._downloader.to_screen(u'[youtube] query "%s": Downloading page %s' % (query, pagenum)) |
25af2bce RG |
2209 | |
2210 | def _real_initialize(self): | |
2211 | self._youtube_ie.initialize() | |
d3975459 | 2212 | |
25af2bce | 2213 | def _real_extract(self, query): |
bdb3f7a7 | 2214 | mobj = re.match(self._VALID_URL, query) |
25af2bce | 2215 | if mobj is None: |
147753eb | 2216 | self._downloader.trouble(u'ERROR: invalid search query "%s"' % query) |
6f21f686 | 2217 | return |
25af2bce RG |
2218 | |
2219 | prefix, query = query.split(':') | |
2220 | prefix = prefix[8:] | |
c0a10ca8 | 2221 | query = query.encode('utf-8') |
f995f712 | 2222 | if prefix == '': |
6f21f686 RG |
2223 | self._download_n_results(query, 1) |
2224 | return | |
f995f712 | 2225 | elif prefix == 'all': |
6f21f686 RG |
2226 | self._download_n_results(query, self._max_youtube_results) |
2227 | return | |
f995f712 | 2228 | else: |
25af2bce | 2229 | try: |
e1f18b8a | 2230 | n = long(prefix) |
25af2bce | 2231 | if n <= 0: |
147753eb | 2232 | self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query)) |
6f21f686 | 2233 | return |
257453b9 | 2234 | elif n > self._max_youtube_results: |
c0a10ca8 | 2235 | self._downloader.to_stderr(u'WARNING: ytsearch returns max %i results (you requested %i)' % (self._max_youtube_results, n)) |
257453b9 | 2236 | n = self._max_youtube_results |
6f21f686 RG |
2237 | self._download_n_results(query, n) |
2238 | return | |
e1f18b8a | 2239 | except ValueError: # parsing prefix as integer fails |
6f21f686 RG |
2240 | self._download_n_results(query, 1) |
2241 | return | |
25af2bce RG |
2242 | |
2243 | def _download_n_results(self, query, n): | |
2244 | """Downloads a specified number of results for a query""" | |
2245 | ||
2246 | video_ids = [] | |
2247 | already_seen = set() | |
2248 | pagenum = 1 | |
2249 | ||
2250 | while True: | |
2251 | self.report_download_page(query, pagenum) | |
a9633f14 | 2252 | result_url = self._TEMPLATE_URL % (urllib.quote_plus(query), pagenum) |
1987c232 | 2253 | request = urllib2.Request(result_url) |
25af2bce RG |
2254 | try: |
2255 | page = urllib2.urlopen(request).read() | |
2256 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
147753eb | 2257 | self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err)) |
6f21f686 | 2258 | return |
25af2bce RG |
2259 | |
2260 | # Extract video identifiers | |
2261 | for mobj in re.finditer(self._VIDEO_INDICATOR, page): | |
2262 | video_id = page[mobj.span()[0]:mobj.span()[1]].split('=')[2][:-1] | |
2263 | if video_id not in already_seen: | |
2264 | video_ids.append(video_id) | |
2265 | already_seen.add(video_id) | |
2266 | if len(video_ids) == n: | |
2267 | # Specified n videos reached | |
25af2bce | 2268 | for id in video_ids: |
6f21f686 RG |
2269 | self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id) |
2270 | return | |
25af2bce | 2271 | |
304a4d85 | 2272 | if re.search(self._MORE_PAGES_INDICATOR, page) is None: |
25af2bce | 2273 | for id in video_ids: |
6f21f686 RG |
2274 | self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id) |
2275 | return | |
25af2bce RG |
2276 | |
2277 | pagenum = pagenum + 1 | |
2278 | ||
c0a10ca8 | 2279 | |
7e58d568 RG |
2280 | class GoogleSearchIE(InfoExtractor): |
2281 | """Information Extractor for Google Video search queries.""" | |
bdb3f7a7 | 2282 | _VALID_URL = r'gvsearch(\d+|all)?:[\s\S]+' |
7e58d568 RG |
2283 | _TEMPLATE_URL = 'http://video.google.com/videosearch?q=%s+site:video.google.com&start=%s&hl=en' |
2284 | _VIDEO_INDICATOR = r'videoplay\?docid=([^\&>]+)\&' | |
2285 | _MORE_PAGES_INDICATOR = r'<span>Next</span>' | |
2286 | _google_ie = None | |
2287 | _max_google_results = 1000 | |
f3098c4d | 2288 | IE_NAME = u'video.google:search' |
7e58d568 RG |
2289 | |
2290 | def __init__(self, google_ie, downloader=None): | |
2291 | InfoExtractor.__init__(self, downloader) | |
2292 | self._google_ie = google_ie | |
d3975459 | 2293 | |
7e58d568 RG |
2294 | def report_download_page(self, query, pagenum): |
2295 | """Report attempt to download playlist page with given number.""" | |
2296 | query = query.decode(preferredencoding()) | |
331ce0a0 | 2297 | self._downloader.to_screen(u'[video.google] query "%s": Downloading page %s' % (query, pagenum)) |
7e58d568 RG |
2298 | |
2299 | def _real_initialize(self): | |
2300 | self._google_ie.initialize() | |
d3975459 | 2301 | |
7e58d568 | 2302 | def _real_extract(self, query): |
bdb3f7a7 | 2303 | mobj = re.match(self._VALID_URL, query) |
7e58d568 RG |
2304 | if mobj is None: |
2305 | self._downloader.trouble(u'ERROR: invalid search query "%s"' % query) | |
2306 | return | |
2307 | ||
2308 | prefix, query = query.split(':') | |
2309 | prefix = prefix[8:] | |
c0a10ca8 | 2310 | query = query.encode('utf-8') |
7e58d568 RG |
2311 | if prefix == '': |
2312 | self._download_n_results(query, 1) | |
2313 | return | |
2314 | elif prefix == 'all': | |
2315 | self._download_n_results(query, self._max_google_results) | |
2316 | return | |
2317 | else: | |
2318 | try: | |
2319 | n = long(prefix) | |
2320 | if n <= 0: | |
2321 | self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query)) | |
2322 | return | |
2323 | elif n > self._max_google_results: | |
c0a10ca8 | 2324 | self._downloader.to_stderr(u'WARNING: gvsearch returns max %i results (you requested %i)' % (self._max_google_results, n)) |
7e58d568 RG |
2325 | n = self._max_google_results |
2326 | self._download_n_results(query, n) | |
2327 | return | |
2328 | except ValueError: # parsing prefix as integer fails | |
2329 | self._download_n_results(query, 1) | |
2330 | return | |
2331 | ||
2332 | def _download_n_results(self, query, n): | |
2333 | """Downloads a specified number of results for a query""" | |
2334 | ||
2335 | video_ids = [] | |
2336 | already_seen = set() | |
2337 | pagenum = 1 | |
2338 | ||
2339 | while True: | |
2340 | self.report_download_page(query, pagenum) | |
2341 | result_url = self._TEMPLATE_URL % (urllib.quote_plus(query), pagenum) | |
1987c232 | 2342 | request = urllib2.Request(result_url) |
7e58d568 RG |
2343 | try: |
2344 | page = urllib2.urlopen(request).read() | |
2345 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
2346 | self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err)) | |
2347 | return | |
2348 | ||
2349 | # Extract video identifiers | |
2350 | for mobj in re.finditer(self._VIDEO_INDICATOR, page): | |
2351 | video_id = mobj.group(1) | |
2352 | if video_id not in already_seen: | |
2353 | video_ids.append(video_id) | |
2354 | already_seen.add(video_id) | |
2355 | if len(video_ids) == n: | |
2356 | # Specified n videos reached | |
2357 | for id in video_ids: | |
2358 | self._google_ie.extract('http://video.google.com/videoplay?docid=%s' % id) | |
2359 | return | |
2360 | ||
2361 | if re.search(self._MORE_PAGES_INDICATOR, page) is None: | |
2362 | for id in video_ids: | |
2363 | self._google_ie.extract('http://video.google.com/videoplay?docid=%s' % id) | |
2364 | return | |
2365 | ||
2366 | pagenum = pagenum + 1 | |
2367 | ||
c0a10ca8 | 2368 | |
7e58d568 RG |
2369 | class YahooSearchIE(InfoExtractor): |
2370 | """Information Extractor for Yahoo! Video search queries.""" | |
bdb3f7a7 | 2371 | _VALID_URL = r'yvsearch(\d+|all)?:[\s\S]+' |
7e58d568 RG |
2372 | _TEMPLATE_URL = 'http://video.yahoo.com/search/?p=%s&o=%s' |
2373 | _VIDEO_INDICATOR = r'href="http://video\.yahoo\.com/watch/([0-9]+/[0-9]+)"' | |
2374 | _MORE_PAGES_INDICATOR = r'\s*Next' | |
2375 | _yahoo_ie = None | |
2376 | _max_yahoo_results = 1000 | |
f3098c4d | 2377 | IE_NAME = u'video.yahoo:search' |
7e58d568 RG |
2378 | |
2379 | def __init__(self, yahoo_ie, downloader=None): | |
2380 | InfoExtractor.__init__(self, downloader) | |
2381 | self._yahoo_ie = yahoo_ie | |
d3975459 | 2382 | |
7e58d568 RG |
2383 | def report_download_page(self, query, pagenum): |
2384 | """Report attempt to download playlist page with given number.""" | |
2385 | query = query.decode(preferredencoding()) | |
331ce0a0 | 2386 | self._downloader.to_screen(u'[video.yahoo] query "%s": Downloading page %s' % (query, pagenum)) |
7e58d568 RG |
2387 | |
2388 | def _real_initialize(self): | |
2389 | self._yahoo_ie.initialize() | |
d3975459 | 2390 | |
7e58d568 | 2391 | def _real_extract(self, query): |
bdb3f7a7 | 2392 | mobj = re.match(self._VALID_URL, query) |
7e58d568 RG |
2393 | if mobj is None: |
2394 | self._downloader.trouble(u'ERROR: invalid search query "%s"' % query) | |
2395 | return | |
2396 | ||
2397 | prefix, query = query.split(':') | |
2398 | prefix = prefix[8:] | |
c0a10ca8 | 2399 | query = query.encode('utf-8') |
7e58d568 RG |
2400 | if prefix == '': |
2401 | self._download_n_results(query, 1) | |
2402 | return | |
2403 | elif prefix == 'all': | |
2404 | self._download_n_results(query, self._max_yahoo_results) | |
2405 | return | |
2406 | else: | |
2407 | try: | |
2408 | n = long(prefix) | |
2409 | if n <= 0: | |
2410 | self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query)) | |
2411 | return | |
2412 | elif n > self._max_yahoo_results: | |
c0a10ca8 | 2413 | self._downloader.to_stderr(u'WARNING: yvsearch returns max %i results (you requested %i)' % (self._max_yahoo_results, n)) |
7e58d568 RG |
2414 | n = self._max_yahoo_results |
2415 | self._download_n_results(query, n) | |
2416 | return | |
2417 | except ValueError: # parsing prefix as integer fails | |
2418 | self._download_n_results(query, 1) | |
2419 | return | |
2420 | ||
2421 | def _download_n_results(self, query, n): | |
2422 | """Downloads a specified number of results for a query""" | |
2423 | ||
2424 | video_ids = [] | |
2425 | already_seen = set() | |
2426 | pagenum = 1 | |
2427 | ||
2428 | while True: | |
2429 | self.report_download_page(query, pagenum) | |
2430 | result_url = self._TEMPLATE_URL % (urllib.quote_plus(query), pagenum) | |
1987c232 | 2431 | request = urllib2.Request(result_url) |
7e58d568 RG |
2432 | try: |
2433 | page = urllib2.urlopen(request).read() | |
2434 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
2435 | self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err)) | |
2436 | return | |
2437 | ||
2438 | # Extract video identifiers | |
2439 | for mobj in re.finditer(self._VIDEO_INDICATOR, page): | |
2440 | video_id = mobj.group(1) | |
2441 | if video_id not in already_seen: | |
2442 | video_ids.append(video_id) | |
2443 | already_seen.add(video_id) | |
2444 | if len(video_ids) == n: | |
2445 | # Specified n videos reached | |
2446 | for id in video_ids: | |
2447 | self._yahoo_ie.extract('http://video.yahoo.com/watch/%s' % id) | |
2448 | return | |
2449 | ||
2450 | if re.search(self._MORE_PAGES_INDICATOR, page) is None: | |
2451 | for id in video_ids: | |
2452 | self._yahoo_ie.extract('http://video.yahoo.com/watch/%s' % id) | |
2453 | return | |
2454 | ||
2455 | pagenum = pagenum + 1 | |
2456 | ||
c0a10ca8 | 2457 | |
0c2dc87d RG |
2458 | class YoutubePlaylistIE(InfoExtractor): |
2459 | """Information Extractor for YouTube playlists.""" | |
2460 | ||
7a2cf545 | 2461 | _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_-]+))?.*' |
f74e22ae | 2462 | _TEMPLATE_URL = 'http://www.youtube.com/%s?%s=%s&page=%s&gl=US&hl=en' |
0c2dc87d | 2463 | _VIDEO_INDICATOR = r'/watch\?v=(.+?)&' |
ce5cafea | 2464 | _MORE_PAGES_INDICATOR = r'(?m)>\s*Next\s*</a>' |
0c2dc87d | 2465 | _youtube_ie = None |
f3098c4d | 2466 | IE_NAME = u'youtube:playlist' |
0c2dc87d RG |
2467 | |
2468 | def __init__(self, youtube_ie, downloader=None): | |
2469 | InfoExtractor.__init__(self, downloader) | |
2470 | self._youtube_ie = youtube_ie | |
d3975459 | 2471 | |
0c2dc87d RG |
2472 | def report_download_page(self, playlist_id, pagenum): |
2473 | """Report attempt to download playlist page with given number.""" | |
331ce0a0 | 2474 | self._downloader.to_screen(u'[youtube] PL %s: Downloading page #%s' % (playlist_id, pagenum)) |
0c2dc87d RG |
2475 | |
2476 | def _real_initialize(self): | |
2477 | self._youtube_ie.initialize() | |
d3975459 | 2478 | |
0c2dc87d RG |
2479 | def _real_extract(self, url): |
2480 | # Extract playlist id | |
2481 | mobj = re.match(self._VALID_URL, url) | |
2482 | if mobj is None: | |
147753eb | 2483 | self._downloader.trouble(u'ERROR: invalid url: %s' % url) |
6f21f686 | 2484 | return |
0c2dc87d | 2485 | |
d119b54d RG |
2486 | # Single video case |
2487 | if mobj.group(3) is not None: | |
2488 | self._youtube_ie.extract(mobj.group(3)) | |
2489 | return | |
2490 | ||
0c2dc87d | 2491 | # Download playlist pages |
f74e22ae GI |
2492 | # prefix is 'p' as default for playlists but there are other types that need extra care |
2493 | playlist_prefix = mobj.group(1) | |
2494 | if playlist_prefix == 'a': | |
2495 | playlist_access = 'artist' | |
2496 | else: | |
7cc3c6fd | 2497 | playlist_prefix = 'p' |
f74e22ae GI |
2498 | playlist_access = 'view_play_list' |
2499 | playlist_id = mobj.group(2) | |
0c2dc87d RG |
2500 | video_ids = [] |
2501 | pagenum = 1 | |
2502 | ||
2503 | while True: | |
2504 | self.report_download_page(playlist_id, pagenum) | |
f74e22ae | 2505 | request = urllib2.Request(self._TEMPLATE_URL % (playlist_access, playlist_prefix, playlist_id, pagenum)) |
0c2dc87d RG |
2506 | try: |
2507 | page = urllib2.urlopen(request).read() | |
2508 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
147753eb | 2509 | self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err)) |
6f21f686 | 2510 | return |
0c2dc87d RG |
2511 | |
2512 | # Extract video identifiers | |
27d98b6e | 2513 | ids_in_page = [] |
0c2dc87d | 2514 | for mobj in re.finditer(self._VIDEO_INDICATOR, page): |
27d98b6e RG |
2515 | if mobj.group(1) not in ids_in_page: |
2516 | ids_in_page.append(mobj.group(1)) | |
2517 | video_ids.extend(ids_in_page) | |
0c2dc87d | 2518 | |
ce5cafea | 2519 | if re.search(self._MORE_PAGES_INDICATOR, page) is None: |
0c2dc87d RG |
2520 | break |
2521 | pagenum = pagenum + 1 | |
2522 | ||
8cc44341 RG |
2523 | playliststart = self._downloader.params.get('playliststart', 1) - 1 |
2524 | playlistend = self._downloader.params.get('playlistend', -1) | |
2525 | video_ids = video_ids[playliststart:playlistend] | |
2526 | ||
0c2dc87d | 2527 | for id in video_ids: |
6f21f686 RG |
2528 | self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id) |
2529 | return | |
0c2dc87d | 2530 | |
c0a10ca8 | 2531 | |
c39c05cd A |
2532 | class YoutubeUserIE(InfoExtractor): |
2533 | """Information Extractor for YouTube users.""" | |
2534 | ||
b845d58b | 2535 | _VALID_URL = r'(?:(?:(?:https?://)?(?:\w+\.)?youtube\.com/user/)|ytuser:)([A-Za-z0-9_-]+)' |
c39c05cd | 2536 | _TEMPLATE_URL = 'http://gdata.youtube.com/feeds/api/users/%s' |
5aba6ea4 RG |
2537 | _GDATA_PAGE_SIZE = 50 |
2538 | _GDATA_URL = 'http://gdata.youtube.com/feeds/api/users/%s/uploads?max-results=%d&start-index=%d' | |
2539 | _VIDEO_INDICATOR = r'/watch\?v=(.+?)&' | |
c39c05cd | 2540 | _youtube_ie = None |
f3098c4d | 2541 | IE_NAME = u'youtube:user' |
c39c05cd A |
2542 | |
2543 | def __init__(self, youtube_ie, downloader=None): | |
2544 | InfoExtractor.__init__(self, downloader) | |
2545 | self._youtube_ie = youtube_ie | |
d3975459 | 2546 | |
5aba6ea4 | 2547 | def report_download_page(self, username, start_index): |
c39c05cd | 2548 | """Report attempt to download user page.""" |
5aba6ea4 | 2549 | self._downloader.to_screen(u'[youtube] user %s: Downloading video ids from %d to %d' % |
c0a10ca8 | 2550 | (username, start_index, start_index + self._GDATA_PAGE_SIZE)) |
c39c05cd A |
2551 | |
2552 | def _real_initialize(self): | |
2553 | self._youtube_ie.initialize() | |
d3975459 | 2554 | |
c39c05cd A |
2555 | def _real_extract(self, url): |
2556 | # Extract username | |
2557 | mobj = re.match(self._VALID_URL, url) | |
2558 | if mobj is None: | |
2559 | self._downloader.trouble(u'ERROR: invalid url: %s' % url) | |
2560 | return | |
2561 | ||
c39c05cd | 2562 | username = mobj.group(1) |
5aba6ea4 RG |
2563 | |
2564 | # Download video ids using YouTube Data API. Result size per | |
2565 | # query is limited (currently to 50 videos) so we need to query | |
2566 | # page by page until there are no video ids - it means we got | |
2567 | # all of them. | |
2568 | ||
c39c05cd | 2569 | video_ids = [] |
5aba6ea4 | 2570 | pagenum = 0 |
c39c05cd | 2571 | |
5aba6ea4 RG |
2572 | while True: |
2573 | start_index = pagenum * self._GDATA_PAGE_SIZE + 1 | |
2574 | self.report_download_page(username, start_index) | |
c39c05cd | 2575 | |
5aba6ea4 | 2576 | request = urllib2.Request(self._GDATA_URL % (username, self._GDATA_PAGE_SIZE, start_index)) |
c39c05cd | 2577 | |
5aba6ea4 RG |
2578 | try: |
2579 | page = urllib2.urlopen(request).read() | |
2580 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
2581 | self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err)) | |
2582 | return | |
c39c05cd | 2583 | |
5aba6ea4 RG |
2584 | # Extract video identifiers |
2585 | ids_in_page = [] | |
2586 | ||
2587 | for mobj in re.finditer(self._VIDEO_INDICATOR, page): | |
2588 | if mobj.group(1) not in ids_in_page: | |
2589 | ids_in_page.append(mobj.group(1)) | |
2590 | ||
2591 | video_ids.extend(ids_in_page) | |
2592 | ||
2593 | # A little optimization - if current page is not | |
2594 | # "full", ie. does not contain PAGE_SIZE video ids then | |
2595 | # we can assume that this page is the last one - there | |
2596 | # are no more ids on further pages - no need to query | |
2597 | # again. | |
2598 | ||
2599 | if len(ids_in_page) < self._GDATA_PAGE_SIZE: | |
2600 | break | |
2601 | ||
2602 | pagenum += 1 | |
2603 | ||
2604 | all_ids_count = len(video_ids) | |
8cc44341 RG |
2605 | playliststart = self._downloader.params.get('playliststart', 1) - 1 |
2606 | playlistend = self._downloader.params.get('playlistend', -1) | |
204c9398 | 2607 | |
5aba6ea4 RG |
2608 | if playlistend == -1: |
2609 | video_ids = video_ids[playliststart:] | |
2610 | else: | |
2611 | video_ids = video_ids[playliststart:playlistend] | |
7a9054ec | 2612 | |
5aba6ea4 | 2613 | self._downloader.to_screen("[youtube] user %s: Collected %d video ids (downloading %d of them)" % |
c0a10ca8 | 2614 | (username, all_ids_count, len(video_ids))) |
5aba6ea4 RG |
2615 | |
2616 | for video_id in video_ids: | |
2617 | self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % video_id) | |
2618 | ||
c39c05cd | 2619 | |
27179cfd VV |
2620 | class DepositFilesIE(InfoExtractor): |
2621 | """Information extractor for depositfiles.com""" | |
2622 | ||
b845d58b | 2623 | _VALID_URL = r'(?:http://)?(?:\w+\.)?depositfiles\.com/(?:../(?#locale))?files/(.+)' |
f3098c4d | 2624 | IE_NAME = u'DepositFiles' |
27179cfd VV |
2625 | |
2626 | def __init__(self, downloader=None): | |
2627 | InfoExtractor.__init__(self, downloader) | |
2628 | ||
27179cfd VV |
2629 | def report_download_webpage(self, file_id): |
2630 | """Report webpage download.""" | |
2631 | self._downloader.to_screen(u'[DepositFiles] %s: Downloading webpage' % file_id) | |
2632 | ||
2633 | def report_extraction(self, file_id): | |
2634 | """Report information extraction.""" | |
2635 | self._downloader.to_screen(u'[DepositFiles] %s: Extracting information' % file_id) | |
2636 | ||
2637 | def _real_initialize(self): | |
2638 | return | |
2639 | ||
2640 | def _real_extract(self, url): | |
2641 | # At this point we have a new file | |
2642 | self._downloader.increment_downloads() | |
2643 | ||
2644 | file_id = url.split('/')[-1] | |
2645 | # Rebuild url in english locale | |
2646 | url = 'http://depositfiles.com/en/files/' + file_id | |
2647 | ||
2648 | # Retrieve file webpage with 'Free download' button pressed | |
2649 | free_download_indication = { 'gateway_result' : '1' } | |
1987c232 | 2650 | request = urllib2.Request(url, urllib.urlencode(free_download_indication)) |
27179cfd VV |
2651 | try: |
2652 | self.report_download_webpage(file_id) | |
2653 | webpage = urllib2.urlopen(request).read() | |
2654 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
2655 | self._downloader.trouble(u'ERROR: Unable to retrieve file webpage: %s' % str(err)) | |
2656 | return | |
2657 | ||
2658 | # Search for the real file URL | |
2659 | mobj = re.search(r'<form action="(http://fileshare.+?)"', webpage) | |
2660 | if (mobj is None) or (mobj.group(1) is None): | |
2661 | # Try to figure out reason of the error. | |
2662 | mobj = re.search(r'<strong>(Attention.*?)</strong>', webpage, re.DOTALL) | |
2663 | if (mobj is not None) and (mobj.group(1) is not None): | |
2664 | restriction_message = re.sub('\s+', ' ', mobj.group(1)).strip() | |
2665 | self._downloader.trouble(u'ERROR: %s' % restriction_message) | |
2666 | else: | |
2667 | self._downloader.trouble(u'ERROR: unable to extract download URL from: %s' % url) | |
2668 | return | |
2669 | ||
2670 | file_url = mobj.group(1) | |
2671 | file_extension = os.path.splitext(file_url)[1][1:] | |
2672 | ||
2673 | # Search for file title | |
2674 | mobj = re.search(r'<b title="(.*?)">', webpage) | |
2675 | if mobj is None: | |
2676 | self._downloader.trouble(u'ERROR: unable to extract title') | |
2677 | return | |
2678 | file_title = mobj.group(1).decode('utf-8') | |
2679 | ||
2680 | try: | |
2681 | # Process file information | |
2682 | self._downloader.process_info({ | |
2683 | 'id': file_id.decode('utf-8'), | |
2684 | 'url': file_url.decode('utf-8'), | |
2685 | 'uploader': u'NA', | |
2686 | 'upload_date': u'NA', | |
2687 | 'title': file_title, | |
2688 | 'stitle': file_title, | |
2689 | 'ext': file_extension.decode('utf-8'), | |
2690 | 'format': u'NA', | |
2691 | 'player_url': None, | |
2692 | }) | |
2693 | except UnavailableVideoError, err: | |
2694 | self._downloader.trouble(u'ERROR: unable to download file') | |
2695 | ||
c0a10ca8 | 2696 | |
9f5f9602 GI |
2697 | class FacebookIE(InfoExtractor): |
2698 | """Information Extractor for Facebook""" | |
2699 | ||
b845d58b | 2700 | _VALID_URL = r'^(?:https?://)?(?:\w+\.)?facebook\.com/video/video\.php\?(?:.*?)v=(?P<ID>\d+)(?:.*)' |
9f5f9602 GI |
2701 | _LOGIN_URL = 'https://login.facebook.com/login.php?m&next=http%3A%2F%2Fm.facebook.com%2Fhome.php&' |
2702 | _NETRC_MACHINE = 'facebook' | |
2703 | _available_formats = ['highqual', 'lowqual'] | |
2704 | _video_extensions = { | |
2705 | 'highqual': 'mp4', | |
2706 | 'lowqual': 'mp4', | |
2707 | } | |
f3098c4d | 2708 | IE_NAME = u'facebook' |
9f5f9602 GI |
2709 | |
2710 | def __init__(self, downloader=None): | |
2711 | InfoExtractor.__init__(self, downloader) | |
2712 | ||
9f5f9602 GI |
2713 | def _reporter(self, message): |
2714 | """Add header and report message.""" | |
2715 | self._downloader.to_screen(u'[facebook] %s' % message) | |
2716 | ||
2717 | def report_login(self): | |
2718 | """Report attempt to log in.""" | |
2719 | self._reporter(u'Logging in') | |
2720 | ||
2721 | def report_video_webpage_download(self, video_id): | |
2722 | """Report attempt to download video webpage.""" | |
2723 | self._reporter(u'%s: Downloading video webpage' % video_id) | |
2724 | ||
2725 | def report_information_extraction(self, video_id): | |
2726 | """Report attempt to extract video information.""" | |
2727 | self._reporter(u'%s: Extracting video information' % video_id) | |
2728 | ||
2729 | def _parse_page(self, video_webpage): | |
2730 | """Extract video information from page""" | |
2731 | # General data | |
2732 | data = {'title': r'class="video_title datawrap">(.*?)</', | |
2733 | 'description': r'<div class="datawrap">(.*?)</div>', | |
2734 | 'owner': r'\("video_owner_name", "(.*?)"\)', | |
2735 | 'upload_date': r'data-date="(.*?)"', | |
2736 | 'thumbnail': r'\("thumb_url", "(?P<THUMB>.*?)"\)', | |
2737 | } | |
2738 | video_info = {} | |
2739 | for piece in data.keys(): | |
2740 | mobj = re.search(data[piece], video_webpage) | |
2741 | if mobj is not None: | |
2742 | video_info[piece] = urllib.unquote_plus(mobj.group(1).decode("unicode_escape")) | |
2743 | ||
2744 | # Video urls | |
2745 | video_urls = {} | |
2746 | for fmt in self._available_formats: | |
2747 | mobj = re.search(r'\("%s_src\", "(.+?)"\)' % fmt, video_webpage) | |
2748 | if mobj is not None: | |
2749 | # URL is in a Javascript segment inside an escaped Unicode format within | |
2750 | # the generally utf-8 page | |
2751 | video_urls[fmt] = urllib.unquote_plus(mobj.group(1).decode("unicode_escape")) | |
2752 | video_info['video_urls'] = video_urls | |
2753 | ||
2754 | return video_info | |
2755 | ||
2756 | def _real_initialize(self): | |
2757 | if self._downloader is None: | |
2758 | return | |
2759 | ||
2760 | useremail = None | |
2761 | password = None | |
2762 | downloader_params = self._downloader.params | |
2763 | ||
2764 | # Attempt to use provided username and password or .netrc data | |
2765 | if downloader_params.get('username', None) is not None: | |
2766 | useremail = downloader_params['username'] | |
2767 | password = downloader_params['password'] | |
2768 | elif downloader_params.get('usenetrc', False): | |
2769 | try: | |
2770 | info = netrc.netrc().authenticators(self._NETRC_MACHINE) | |
2771 | if info is not None: | |
2772 | useremail = info[0] | |
2773 | password = info[2] | |
2774 | else: | |
2775 | raise netrc.NetrcParseError('No authenticators for %s' % self._NETRC_MACHINE) | |
2776 | except (IOError, netrc.NetrcParseError), err: | |
2777 | self._downloader.to_stderr(u'WARNING: parsing .netrc: %s' % str(err)) | |
2778 | return | |
2779 | ||
2780 | if useremail is None: | |
2781 | return | |
2782 | ||
2783 | # Log in | |
2784 | login_form = { | |
2785 | 'email': useremail, | |
2786 | 'pass': password, | |
2787 | 'login': 'Log+In' | |
2788 | } | |
2789 | request = urllib2.Request(self._LOGIN_URL, urllib.urlencode(login_form)) | |
2790 | try: | |
2791 | self.report_login() | |
2792 | login_results = urllib2.urlopen(request).read() | |
2793 | if re.search(r'<form(.*)name="login"(.*)</form>', login_results) is not None: | |
2794 | self._downloader.to_stderr(u'WARNING: unable to log in: bad username/password, or exceded login rate limit (~3/min). Check credentials or wait.') | |
2795 | return | |
2796 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
2797 | self._downloader.to_stderr(u'WARNING: unable to log in: %s' % str(err)) | |
2798 | return | |
2799 | ||
2800 | def _real_extract(self, url): | |
2801 | mobj = re.match(self._VALID_URL, url) | |
2802 | if mobj is None: | |
2803 | self._downloader.trouble(u'ERROR: invalid URL: %s' % url) | |
2804 | return | |
2805 | video_id = mobj.group('ID') | |
2806 | ||
2807 | # Get video webpage | |
2808 | self.report_video_webpage_download(video_id) | |
2809 | request = urllib2.Request('https://www.facebook.com/video/video.php?v=%s' % video_id) | |
2810 | try: | |
2811 | page = urllib2.urlopen(request) | |
2812 | video_webpage = page.read() | |
2813 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
2814 | self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % str(err)) | |
2815 | return | |
2816 | ||
2817 | # Start extracting information | |
2818 | self.report_information_extraction(video_id) | |
2819 | ||
2820 | # Extract information | |
2821 | video_info = self._parse_page(video_webpage) | |
2822 | ||
2823 | # uploader | |
2824 | if 'owner' not in video_info: | |
2825 | self._downloader.trouble(u'ERROR: unable to extract uploader nickname') | |
2826 | return | |
2827 | video_uploader = video_info['owner'] | |
2828 | ||
2829 | # title | |
2830 | if 'title' not in video_info: | |
2831 | self._downloader.trouble(u'ERROR: unable to extract video title') | |
2832 | return | |
2833 | video_title = video_info['title'] | |
2834 | video_title = video_title.decode('utf-8') | |
2835 | video_title = sanitize_title(video_title) | |
2836 | ||
2837 | # simplified title | |
2838 | simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title) | |
2839 | simple_title = simple_title.strip(ur'_') | |
2840 | ||
2841 | # thumbnail image | |
2842 | if 'thumbnail' not in video_info: | |
2843 | self._downloader.trouble(u'WARNING: unable to extract video thumbnail') | |
2844 | video_thumbnail = '' | |
2845 | else: | |
2846 | video_thumbnail = video_info['thumbnail'] | |
2847 | ||
2848 | # upload date | |
2849 | upload_date = u'NA' | |
2850 | if 'upload_date' in video_info: | |
2851 | upload_time = video_info['upload_date'] | |
2852 | timetuple = email.utils.parsedate_tz(upload_time) | |
2853 | if timetuple is not None: | |
2854 | try: | |
2855 | upload_date = time.strftime('%Y%m%d', timetuple[0:9]) | |
2856 | except: | |
2857 | pass | |
2858 | ||
2859 | # description | |
8b95c387 | 2860 | video_description = video_info.get('description', 'No description available.') |
9f5f9602 GI |
2861 | |
2862 | url_map = video_info['video_urls'] | |
2863 | if len(url_map.keys()) > 0: | |
2864 | # Decide which formats to download | |
2865 | req_format = self._downloader.params.get('format', None) | |
2866 | format_limit = self._downloader.params.get('format_limit', None) | |
2867 | ||
2868 | if format_limit is not None and format_limit in self._available_formats: | |
2869 | format_list = self._available_formats[self._available_formats.index(format_limit):] | |
2870 | else: | |
2871 | format_list = self._available_formats | |
2872 | existing_formats = [x for x in format_list if x in url_map] | |
2873 | if len(existing_formats) == 0: | |
2874 | self._downloader.trouble(u'ERROR: no known formats available for video') | |
2875 | return | |
2876 | if req_format is None: | |
2877 | video_url_list = [(existing_formats[0], url_map[existing_formats[0]])] # Best quality | |
c52b01f3 K |
2878 | elif req_format == 'worst': |
2879 | video_url_list = [(existing_formats[len(existing_formats)-1], url_map[existing_formats[len(existing_formats)-1]])] # worst quality | |
9f5f9602 GI |
2880 | elif req_format == '-1': |
2881 | video_url_list = [(f, url_map[f]) for f in existing_formats] # All formats | |
2882 | else: | |
2883 | # Specific format | |
2884 | if req_format not in url_map: | |
2885 | self._downloader.trouble(u'ERROR: requested format not available') | |
2886 | return | |
2887 | video_url_list = [(req_format, url_map[req_format])] # Specific format | |
2888 | ||
2889 | for format_param, video_real_url in video_url_list: | |
2890 | ||
2891 | # At this point we have a new video | |
2892 | self._downloader.increment_downloads() | |
2893 | ||
2894 | # Extension | |
2895 | video_extension = self._video_extensions.get(format_param, 'mp4') | |
2896 | ||
9f5f9602 GI |
2897 | try: |
2898 | # Process video information | |
2899 | self._downloader.process_info({ | |
2900 | 'id': video_id.decode('utf-8'), | |
2901 | 'url': video_real_url.decode('utf-8'), | |
2902 | 'uploader': video_uploader.decode('utf-8'), | |
2903 | 'upload_date': upload_date, | |
2904 | 'title': video_title, | |
2905 | 'stitle': simple_title, | |
2906 | 'ext': video_extension.decode('utf-8'), | |
2907 | 'format': (format_param is None and u'NA' or format_param.decode('utf-8')), | |
2908 | 'thumbnail': video_thumbnail.decode('utf-8'), | |
2909 | 'description': video_description.decode('utf-8'), | |
2910 | 'player_url': None, | |
2911 | }) | |
2912 | except UnavailableVideoError, err: | |
2913 | self._downloader.trouble(u'\nERROR: unable to download video') | |
2914 | ||
7745f5d8 PH |
2915 | class BlipTVIE(InfoExtractor): |
2916 | """Information extractor for blip.tv""" | |
2917 | ||
1cab2c6d | 2918 | _VALID_URL = r'^(?:https?://)?(?:\w+\.)?blip\.tv(/.+)$' |
7745f5d8 | 2919 | _URL_EXT = r'^.*\.([a-z0-9]+)$' |
f3098c4d | 2920 | IE_NAME = u'blip.tv' |
7745f5d8 | 2921 | |
7745f5d8 PH |
2922 | def report_extraction(self, file_id): |
2923 | """Report information extraction.""" | |
54f329fe PH |
2924 | self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, file_id)) |
2925 | ||
2926 | def report_direct_download(self, title): | |
2927 | """Report information extraction.""" | |
2928 | self._downloader.to_screen(u'[%s] %s: Direct download detected' % (self.IE_NAME, title)) | |
7745f5d8 PH |
2929 | |
2930 | def _simplify_title(self, title): | |
2931 | res = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', title) | |
2932 | res = res.strip(ur'_') | |
2933 | return res | |
2934 | ||
2935 | def _real_extract(self, url): | |
2936 | mobj = re.match(self._VALID_URL, url) | |
2937 | if mobj is None: | |
2938 | self._downloader.trouble(u'ERROR: invalid URL: %s' % url) | |
2939 | return | |
2940 | ||
1293ce58 PH |
2941 | if '?' in url: |
2942 | cchar = '&' | |
2943 | else: | |
2944 | cchar = '?' | |
2945 | json_url = url + cchar + 'skin=json&version=2&no_wrap=1' | |
7745f5d8 | 2946 | request = urllib2.Request(json_url) |
aded78d9 | 2947 | self.report_extraction(mobj.group(1)) |
54f329fe | 2948 | info = None |
7745f5d8 | 2949 | try: |
54f329fe PH |
2950 | urlh = urllib2.urlopen(request) |
2951 | if urlh.headers.get('Content-Type', '').startswith('video/'): # Direct download | |
2952 | basename = url.split('/')[-1] | |
2953 | title,ext = os.path.splitext(basename) | |
2954 | ext = ext.replace('.', '') | |
2955 | self.report_direct_download(title) | |
2956 | info = { | |
2957 | 'id': title, | |
2958 | 'url': url, | |
2959 | 'title': title, | |
2960 | 'stitle': self._simplify_title(title), | |
2961 | 'ext': ext, | |
2962 | 'urlhandle': urlh | |
2963 | } | |
7745f5d8 PH |
2964 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: |
2965 | self._downloader.trouble(u'ERROR: unable to download video info webpage: %s' % str(err)) | |
2966 | return | |
54f329fe PH |
2967 | if info is None: # Regular URL |
2968 | try: | |
2969 | json_code = urlh.read() | |
2970 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
2971 | self._downloader.trouble(u'ERROR: unable to read video info webpage: %s' % str(err)) | |
2972 | return | |
7745f5d8 | 2973 | |
54f329fe PH |
2974 | try: |
2975 | json_data = json.loads(json_code) | |
2976 | if 'Post' in json_data: | |
2977 | data = json_data['Post'] | |
2978 | else: | |
2979 | data = json_data | |
2980 | ||
2981 | upload_date = datetime.datetime.strptime(data['datestamp'], '%m-%d-%y %H:%M%p').strftime('%Y%m%d') | |
2982 | video_url = data['media']['url'] | |
2983 | umobj = re.match(self._URL_EXT, video_url) | |
2984 | if umobj is None: | |
2985 | raise ValueError('Can not determine filename extension') | |
2986 | ext = umobj.group(1) | |
2987 | ||
2988 | info = { | |
2989 | 'id': data['item_id'], | |
2990 | 'url': video_url, | |
2991 | 'uploader': data['display_name'], | |
2992 | 'upload_date': upload_date, | |
2993 | 'title': data['title'], | |
2994 | 'stitle': self._simplify_title(data['title']), | |
2995 | 'ext': ext, | |
2996 | 'format': data['media']['mimeType'], | |
2997 | 'thumbnail': data['thumbnailUrl'], | |
2998 | 'description': data['description'], | |
2999 | 'player_url': data['embedUrl'] | |
3000 | } | |
3001 | except (ValueError,KeyError), err: | |
3002 | self._downloader.trouble(u'ERROR: unable to parse video information: %s' % repr(err)) | |
3003 | return | |
a1cab7ce | 3004 | |
54f329fe | 3005 | self._downloader.increment_downloads() |
7745f5d8 PH |
3006 | |
3007 | try: | |
3008 | self._downloader.process_info(info) | |
3009 | except UnavailableVideoError, err: | |
3010 | self._downloader.trouble(u'\nERROR: unable to download video') | |
3011 | ||
3012 | ||
9b0a8bc1 PH |
3013 | class MyVideoIE(InfoExtractor): |
3014 | """Information Extractor for myvideo.de.""" | |
3015 | ||
3016 | _VALID_URL = r'(?:http://)?(?:www\.)?myvideo\.de/watch/([0-9]+)/([^?/]+).*' | |
f3098c4d | 3017 | IE_NAME = u'myvideo' |
9b0a8bc1 PH |
3018 | |
3019 | def __init__(self, downloader=None): | |
3020 | InfoExtractor.__init__(self, downloader) | |
3021 | ||
9b0a8bc1 PH |
3022 | def report_download_webpage(self, video_id): |
3023 | """Report webpage download.""" | |
3024 | self._downloader.to_screen(u'[myvideo] %s: Downloading webpage' % video_id) | |
3025 | ||
3026 | def report_extraction(self, video_id): | |
3027 | """Report information extraction.""" | |
3028 | self._downloader.to_screen(u'[myvideo] %s: Extracting information' % video_id) | |
3029 | ||
3030 | def _real_initialize(self): | |
3031 | return | |
3032 | ||
3033 | def _real_extract(self,url): | |
3034 | mobj = re.match(self._VALID_URL, url) | |
3035 | if mobj is None: | |
3036 | self._download.trouble(u'ERROR: invalid URL: %s' % url) | |
3037 | return | |
3038 | ||
3039 | video_id = mobj.group(1) | |
3040 | simple_title = mobj.group(2).decode('utf-8') | |
3041 | # should actually not be necessary | |
3042 | simple_title = sanitize_title(simple_title) | |
3043 | simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', simple_title) | |
3044 | ||
3045 | # Get video webpage | |
3046 | request = urllib2.Request('http://www.myvideo.de/watch/%s' % video_id) | |
3047 | try: | |
3048 | self.report_download_webpage(video_id) | |
3049 | webpage = urllib2.urlopen(request).read() | |
3050 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
3051 | self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err)) | |
3052 | return | |
3053 | ||
3054 | self.report_extraction(video_id) | |
3055 | mobj = re.search(r'<link rel=\'image_src\' href=\'(http://is[0-9].myvideo\.de/de/movie[0-9]+/[a-f0-9]+)/thumbs/[^.]+\.jpg\' />', | |
3056 | webpage) | |
3057 | if mobj is None: | |
3058 | self._downloader.trouble(u'ERROR: unable to extract media URL') | |
3059 | return | |
3060 | video_url = mobj.group(1) + ('/%s.flv' % video_id) | |
3061 | ||
3062 | mobj = re.search('<title>([^<]+)</title>', webpage) | |
3063 | if mobj is None: | |
3064 | self._downloader.trouble(u'ERROR: unable to extract title') | |
3065 | return | |
3066 | ||
3067 | video_title = mobj.group(1) | |
3068 | video_title = sanitize_title(video_title) | |
3069 | ||
3070 | try: | |
9b0a8bc1 PH |
3071 | self._downloader.process_info({ |
3072 | 'id': video_id, | |
3073 | 'url': video_url, | |
3074 | 'uploader': u'NA', | |
3075 | 'upload_date': u'NA', | |
3076 | 'title': video_title, | |
3077 | 'stitle': simple_title, | |
3078 | 'ext': u'flv', | |
3079 | 'format': u'NA', | |
3080 | 'player_url': None, | |
3081 | }) | |
3082 | except UnavailableVideoError: | |
3083 | self._downloader.trouble(u'\nERROR: Unable to download video') | |
3084 | ||
c8e30044 | 3085 | class ComedyCentralIE(InfoExtractor): |
f166bccc | 3086 | """Information extractor for The Daily Show and Colbert Report """ |
c8e30044 | 3087 | |
f3098c4d PH |
3088 | _VALID_URL = r'^(:(?P<shortname>tds|thedailyshow|cr|colbert|colbertnation|colbertreport))|(https?://)?(www\.)?(?P<showname>thedailyshow|colbertnation)\.com/full-episodes/(?P<episode>.*)$' |
3089 | IE_NAME = u'comedycentral' | |
c8e30044 | 3090 | |
c8e30044 PH |
3091 | def report_extraction(self, episode_id): |
3092 | self._downloader.to_screen(u'[comedycentral] %s: Extracting information' % episode_id) | |
3093 | ||
3094 | def report_config_download(self, episode_id): | |
3095 | self._downloader.to_screen(u'[comedycentral] %s: Downloading configuration' % episode_id) | |
3096 | ||
b487ef08 PH |
3097 | def report_index_download(self, episode_id): |
3098 | self._downloader.to_screen(u'[comedycentral] %s: Downloading show index' % episode_id) | |
3099 | ||
fedf9f39 PH |
3100 | def report_player_url(self, episode_id): |
3101 | self._downloader.to_screen(u'[comedycentral] %s: Determining player URL' % episode_id) | |
3102 | ||
c8e30044 PH |
3103 | def _simplify_title(self, title): |
3104 | res = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', title) | |
3105 | res = res.strip(ur'_') | |
3106 | return res | |
3107 | ||
3108 | def _real_extract(self, url): | |
3109 | mobj = re.match(self._VALID_URL, url) | |
3110 | if mobj is None: | |
3111 | self._downloader.trouble(u'ERROR: invalid URL: %s' % url) | |
3112 | return | |
f166bccc PH |
3113 | |
3114 | if mobj.group('shortname'): | |
3115 | if mobj.group('shortname') in ('tds', 'thedailyshow'): | |
3116 | url = 'http://www.thedailyshow.com/full-episodes/' | |
3117 | else: | |
3118 | url = 'http://www.colbertnation.com/full-episodes/' | |
3119 | mobj = re.match(self._VALID_URL, url) | |
3120 | assert mobj is not None | |
3121 | ||
3122 | dlNewest = not mobj.group('episode') | |
3123 | if dlNewest: | |
3124 | epTitle = mobj.group('showname') | |
3125 | else: | |
3126 | epTitle = mobj.group('episode') | |
c8e30044 PH |
3127 | |
3128 | req = urllib2.Request(url) | |
3129 | self.report_extraction(epTitle) | |
3130 | try: | |
f166bccc PH |
3131 | htmlHandle = urllib2.urlopen(req) |
3132 | html = htmlHandle.read() | |
c8e30044 PH |
3133 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: |
3134 | self._downloader.trouble(u'ERROR: unable to download webpage: %s' % unicode(err)) | |
3135 | return | |
f166bccc PH |
3136 | if dlNewest: |
3137 | url = htmlHandle.geturl() | |
3138 | mobj = re.match(self._VALID_URL, url) | |
3139 | if mobj is None: | |
3140 | self._downloader.trouble(u'ERROR: Invalid redirected URL: ' + url) | |
3141 | return | |
3142 | if mobj.group('episode') == '': | |
3143 | self._downloader.trouble(u'ERROR: Redirected URL is still not specific: ' + url) | |
3144 | return | |
3145 | epTitle = mobj.group('episode') | |
c8e30044 | 3146 | |
b487ef08 | 3147 | mMovieParams = re.findall('<param name="movie" value="(http://media.mtvnservices.com/([^"]*episode.*?:.*?))"/>', html) |
c8e30044 PH |
3148 | if len(mMovieParams) == 0: |
3149 | self._downloader.trouble(u'ERROR: unable to find Flash URL in webpage ' + url) | |
3150 | return | |
b487ef08 PH |
3151 | |
3152 | playerUrl_raw = mMovieParams[0][0] | |
fedf9f39 PH |
3153 | self.report_player_url(epTitle) |
3154 | try: | |
b487ef08 PH |
3155 | urlHandle = urllib2.urlopen(playerUrl_raw) |
3156 | playerUrl = urlHandle.geturl() | |
3157 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
3158 | self._downloader.trouble(u'ERROR: unable to find out player URL: ' + unicode(err)) | |
3159 | return | |
3160 | ||
3161 | uri = mMovieParams[0][1] | |
3162 | indexUrl = 'http://shadow.comedycentral.com/feeds/video_player/mrss/?' + urllib.urlencode({'uri': uri}) | |
3163 | self.report_index_download(epTitle) | |
3164 | try: | |
3165 | indexXml = urllib2.urlopen(indexUrl).read() | |
fedf9f39 | 3166 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: |
b487ef08 | 3167 | self._downloader.trouble(u'ERROR: unable to download episode index: ' + unicode(err)) |
fedf9f39 | 3168 | return |
fedf9f39 | 3169 | |
b487ef08 PH |
3170 | idoc = xml.etree.ElementTree.fromstring(indexXml) |
3171 | itemEls = idoc.findall('.//item') | |
3172 | for itemEl in itemEls: | |
3173 | mediaId = itemEl.findall('./guid')[0].text | |
3174 | shortMediaId = mediaId.split(':')[-1] | |
3175 | showId = mediaId.split(':')[-2].replace('.com', '') | |
3176 | officialTitle = itemEl.findall('./title')[0].text | |
3177 | officialDate = itemEl.findall('./pubDate')[0].text | |
3178 | ||
c8e30044 PH |
3179 | configUrl = ('http://www.comedycentral.com/global/feeds/entertainment/media/mediaGenEntertainment.jhtml?' + |
3180 | urllib.urlencode({'uri': mediaId})) | |
3181 | configReq = urllib2.Request(configUrl) | |
3182 | self.report_config_download(epTitle) | |
3183 | try: | |
3184 | configXml = urllib2.urlopen(configReq).read() | |
3185 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
3186 | self._downloader.trouble(u'ERROR: unable to download webpage: %s' % unicode(err)) | |
3187 | return | |
46c8c432 | 3188 | |
c8e30044 PH |
3189 | cdoc = xml.etree.ElementTree.fromstring(configXml) |
3190 | turls = [] | |
3191 | for rendition in cdoc.findall('.//rendition'): | |
3192 | finfo = (rendition.attrib['bitrate'], rendition.findall('./src')[0].text) | |
3193 | turls.append(finfo) | |
3194 | ||
a88bc6bb | 3195 | if len(turls) == 0: |
b487ef08 | 3196 | self._downloader.trouble(u'\nERROR: unable to download ' + mediaId + ': No videos found') |
a88bc6bb PH |
3197 | continue |
3198 | ||
c8e30044 PH |
3199 | # For now, just pick the highest bitrate |
3200 | format,video_url = turls[-1] | |
3201 | ||
3202 | self._downloader.increment_downloads() | |
a88bc6bb | 3203 | |
b487ef08 | 3204 | effTitle = showId + '-' + epTitle |
c8e30044 | 3205 | info = { |
b487ef08 | 3206 | 'id': shortMediaId, |
c8e30044 | 3207 | 'url': video_url, |
b487ef08 PH |
3208 | 'uploader': showId, |
3209 | 'upload_date': officialDate, | |
a88bc6bb PH |
3210 | 'title': effTitle, |
3211 | 'stitle': self._simplify_title(effTitle), | |
c8e30044 PH |
3212 | 'ext': 'mp4', |
3213 | 'format': format, | |
3214 | 'thumbnail': None, | |
b487ef08 PH |
3215 | 'description': officialTitle, |
3216 | 'player_url': playerUrl | |
c8e30044 | 3217 | } |
46c8c432 | 3218 | |
c8e30044 PH |
3219 | try: |
3220 | self._downloader.process_info(info) | |
3221 | except UnavailableVideoError, err: | |
b487ef08 | 3222 | self._downloader.trouble(u'\nERROR: unable to download ' + mediaId) |
a88bc6bb | 3223 | continue |
c8e30044 PH |
3224 | |
3225 | ||
f9c68787 PH |
3226 | class EscapistIE(InfoExtractor): |
3227 | """Information extractor for The Escapist """ | |
3228 | ||
b845d58b | 3229 | _VALID_URL = r'^(https?://)?(www\.)?escapistmagazine\.com/videos/view/(?P<showname>[^/]+)/(?P<episode>[^/?]+)[/?]?.*$' |
f3098c4d | 3230 | IE_NAME = u'escapist' |
f9c68787 | 3231 | |
f9c68787 PH |
3232 | def report_extraction(self, showName): |
3233 | self._downloader.to_screen(u'[escapist] %s: Extracting information' % showName) | |
3234 | ||
3235 | def report_config_download(self, showName): | |
3236 | self._downloader.to_screen(u'[escapist] %s: Downloading configuration' % showName) | |
3237 | ||
3238 | def _simplify_title(self, title): | |
3239 | res = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', title) | |
3240 | res = res.strip(ur'_') | |
3241 | return res | |
3242 | ||
3243 | def _real_extract(self, url): | |
3244 | htmlParser = HTMLParser.HTMLParser() | |
3245 | ||
3246 | mobj = re.match(self._VALID_URL, url) | |
3247 | if mobj is None: | |
3248 | self._downloader.trouble(u'ERROR: invalid URL: %s' % url) | |
3249 | return | |
3250 | showName = mobj.group('showname') | |
3251 | videoId = mobj.group('episode') | |
3252 | ||
3253 | self.report_extraction(showName) | |
3254 | try: | |
3255 | webPage = urllib2.urlopen(url).read() | |
3256 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
3257 | self._downloader.trouble(u'ERROR: unable to download webpage: ' + unicode(err)) | |
3258 | return | |
3259 | ||
3260 | descMatch = re.search('<meta name="description" content="([^"]*)"', webPage) | |
3261 | description = htmlParser.unescape(descMatch.group(1)) | |
3262 | imgMatch = re.search('<meta property="og:image" content="([^"]*)"', webPage) | |
3263 | imgUrl = htmlParser.unescape(imgMatch.group(1)) | |
3264 | playerUrlMatch = re.search('<meta property="og:video" content="([^"]*)"', webPage) | |
3265 | playerUrl = htmlParser.unescape(playerUrlMatch.group(1)) | |
3266 | configUrlMatch = re.search('config=(.*)$', playerUrl) | |
3267 | configUrl = urllib2.unquote(configUrlMatch.group(1)) | |
3268 | ||
3269 | self.report_config_download(showName) | |
3270 | try: | |
3271 | configJSON = urllib2.urlopen(configUrl).read() | |
3272 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
3273 | self._downloader.trouble(u'ERROR: unable to download configuration: ' + unicode(err)) | |
3274 | return | |
3275 | ||
3276 | # Technically, it's JavaScript, not JSON | |
3277 | configJSON = configJSON.replace("'", '"') | |
3278 | ||
3279 | try: | |
3280 | config = json.loads(configJSON) | |
3281 | except (ValueError,), err: | |
3282 | self._downloader.trouble(u'ERROR: Invalid JSON in configuration file: ' + unicode(err)) | |
3283 | return | |
3284 | ||
3285 | playlist = config['playlist'] | |
3286 | videoUrl = playlist[1]['url'] | |
3287 | ||
3288 | self._downloader.increment_downloads() | |
3289 | info = { | |
3290 | 'id': videoId, | |
3291 | 'url': videoUrl, | |
3292 | 'uploader': showName, | |
3293 | 'upload_date': None, | |
3294 | 'title': showName, | |
3295 | 'stitle': self._simplify_title(showName), | |
3296 | 'ext': 'flv', | |
3297 | 'format': 'flv', | |
3298 | 'thumbnail': imgUrl, | |
3299 | 'description': description, | |
3300 | 'player_url': playerUrl, | |
3301 | } | |
3302 | ||
3303 | try: | |
3304 | self._downloader.process_info(info) | |
3305 | except UnavailableVideoError, err: | |
3306 | self._downloader.trouble(u'\nERROR: unable to download ' + videoId) | |
3307 | ||
3308 | ||
8d89fbae PH |
3309 | class CollegeHumorIE(InfoExtractor): |
3310 | """Information extractor for collegehumor.com""" | |
3311 | ||
3312 | _VALID_URL = r'^(?:https?://)?(?:www\.)?collegehumor\.com/video/(?P<videoid>[0-9]+)/(?P<shorttitle>.*)$' | |
3313 | IE_NAME = u'collegehumor' | |
3314 | ||
3315 | def report_webpage(self, video_id): | |
3316 | """Report information extraction.""" | |
3317 | self._downloader.to_screen(u'[%s] %s: Downloading webpage' % (self.IE_NAME, video_id)) | |
3318 | ||
3319 | def report_extraction(self, video_id): | |
3320 | """Report information extraction.""" | |
3321 | self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id)) | |
3322 | ||
3323 | def _simplify_title(self, title): | |
3324 | res = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', title) | |
3325 | res = res.strip(ur'_') | |
3326 | return res | |
3327 | ||
3328 | def _real_extract(self, url): | |
3329 | htmlParser = HTMLParser.HTMLParser() | |
3330 | ||
3331 | mobj = re.match(self._VALID_URL, url) | |
3332 | if mobj is None: | |
3333 | self._downloader.trouble(u'ERROR: invalid URL: %s' % url) | |
3334 | return | |
3335 | video_id = mobj.group('videoid') | |
3336 | ||
3337 | self.report_webpage(video_id) | |
3338 | request = urllib2.Request(url) | |
3339 | try: | |
3340 | webpage = urllib2.urlopen(request).read() | |
3341 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
3342 | self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % str(err)) | |
3343 | return | |
3344 | ||
3345 | m = re.search(r'id="video:(?P<internalvideoid>[0-9]+)"', webpage) | |
3346 | if m is None: | |
3347 | self._downloader.trouble(u'ERROR: Cannot extract internal video ID') | |
3348 | return | |
3349 | internal_video_id = m.group('internalvideoid') | |
3350 | ||
3351 | info = { | |
3352 | 'id': video_id, | |
3353 | 'internal_id': internal_video_id, | |
3354 | } | |
3355 | ||
3356 | self.report_extraction(video_id) | |
3357 | xmlUrl = 'http://www.collegehumor.com/moogaloop/video:' + internal_video_id | |
3358 | try: | |
3359 | metaXml = urllib2.urlopen(xmlUrl).read() | |
3360 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
3361 | self._downloader.trouble(u'ERROR: unable to download video info XML: %s' % str(err)) | |
3362 | return | |
3363 | ||
3364 | mdoc = xml.etree.ElementTree.fromstring(metaXml) | |
3365 | try: | |
3366 | videoNode = mdoc.findall('./video')[0] | |
3367 | info['description'] = videoNode.findall('./description')[0].text | |
3368 | info['title'] = videoNode.findall('./caption')[0].text | |
3369 | info['stitle'] = self._simplify_title(info['title']) | |
3370 | info['url'] = videoNode.findall('./file')[0].text | |
3371 | info['thumbnail'] = videoNode.findall('./thumbnail')[0].text | |
3372 | info['ext'] = info['url'].rpartition('.')[2] | |
3373 | info['format'] = info['ext'] | |
3374 | except IndexError: | |
3375 | self._downloader.trouble(u'\nERROR: Invalid metadata XML file') | |
3376 | return | |
3377 | ||
3378 | self._downloader.increment_downloads() | |
3379 | ||
3380 | try: | |
3381 | self._downloader.process_info(info) | |
3382 | except UnavailableVideoError, err: | |
3383 | self._downloader.trouble(u'\nERROR: unable to download video') | |
3384 | ||
f9c68787 | 3385 | |
6501a06d RB |
3386 | class XVideosIE(InfoExtractor): |
3387 | """Information extractor for xvideos.com""" | |
3388 | ||
3389 | _VALID_URL = r'^(?:https?://)?(?:www\.)?xvideos\.com/video([0-9]+)(?:.*)' | |
3390 | IE_NAME = u'xvideos' | |
3391 | ||
3392 | def report_webpage(self, video_id): | |
3393 | """Report information extraction.""" | |
3394 | self._downloader.to_screen(u'[%s] %s: Downloading webpage' % (self.IE_NAME, video_id)) | |
3395 | ||
3396 | def report_extraction(self, video_id): | |
3397 | """Report information extraction.""" | |
3398 | self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id)) | |
3399 | ||
3400 | def _simplify_title(self, title): | |
3401 | res = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', title) | |
3402 | res = res.strip(ur'_') | |
3403 | return res | |
3404 | ||
3405 | def _real_extract(self, url): | |
3406 | htmlParser = HTMLParser.HTMLParser() | |
3407 | ||
3408 | mobj = re.match(self._VALID_URL, url) | |
3409 | if mobj is None: | |
3410 | self._downloader.trouble(u'ERROR: invalid URL: %s' % url) | |
3411 | return | |
3412 | video_id = mobj.group(1).decode('utf-8') | |
3413 | ||
3414 | self.report_webpage(video_id) | |
3415 | ||
3416 | request = urllib2.Request(url) | |
3417 | try: | |
3418 | webpage = urllib2.urlopen(request).read() | |
3419 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
3420 | self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % str(err)) | |
3421 | return | |
3422 | ||
3423 | self.report_extraction(video_id) | |
3424 | ||
3425 | ||
3426 | # Extract video URL | |
3427 | mobj = re.search(r'flv_url=(.+?)&', webpage) | |
3428 | if mobj is None: | |
3429 | self._downloader.trouble(u'ERROR: unable to extract video title') | |
3430 | return | |
3431 | video_url = urllib2.unquote(mobj.group(1).decode('utf-8')) | |
3432 | ||
3433 | ||
3434 | # Extract title | |
3435 | mobj = re.search(r'<title>(.*?)</title>', webpage) | |
3436 | if mobj is None: | |
3437 | self._downloader.trouble(u'ERROR: unable to extract video title') | |
3438 | return | |
3439 | video_title = mobj.group(1).decode('utf-8') | |
3440 | ||
3441 | ||
3442 | # Extract video thumbnail | |
3443 | 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) | |
3444 | if mobj is None: | |
3445 | self._downloader.trouble(u'ERROR: unable to extract video thumbnail') | |
3446 | return | |
3447 | video_thumbnail = mobj.group(1).decode('utf-8') | |
3448 | ||
3449 | ||
3450 | ||
3451 | self._downloader.increment_downloads() | |
3452 | info = { | |
3453 | 'id': video_id, | |
3454 | 'url': video_url, | |
3455 | 'uploader': None, | |
3456 | 'upload_date': None, | |
3457 | 'title': video_title, | |
3458 | 'stitle': self._simplify_title(video_title), | |
3459 | 'ext': 'flv', | |
3460 | 'format': 'flv', | |
3461 | 'thumbnail': video_thumbnail, | |
3462 | 'description': None, | |
3463 | 'player_url': None, | |
3464 | } | |
3465 | ||
3466 | try: | |
3467 | self._downloader.process_info(info) | |
3468 | except UnavailableVideoError, err: | |
3469 | self._downloader.trouble(u'\nERROR: unable to download ' + video_id) | |
3470 | ||
3471 | ||
65cd34c5 RG |
3472 | class PostProcessor(object): |
3473 | """Post Processor class. | |
3474 | ||
3475 | PostProcessor objects can be added to downloaders with their | |
3476 | add_post_processor() method. When the downloader has finished a | |
3477 | successful download, it will take its internal chain of PostProcessors | |
3478 | and start calling the run() method on each one of them, first with | |
3479 | an initial argument and then with the returned value of the previous | |
3480 | PostProcessor. | |
3481 | ||
3482 | The chain will be stopped if one of them ever returns None or the end | |
3483 | of the chain is reached. | |
3484 | ||
3485 | PostProcessor objects follow a "mutual registration" process similar | |
3486 | to InfoExtractor objects. | |
3487 | """ | |
3488 | ||
3489 | _downloader = None | |
3490 | ||
3491 | def __init__(self, downloader=None): | |
3492 | self._downloader = downloader | |
3493 | ||
65cd34c5 RG |
3494 | def set_downloader(self, downloader): |
3495 | """Sets the downloader for this PP.""" | |
3496 | self._downloader = downloader | |
d3975459 | 3497 | |
65cd34c5 RG |
3498 | def run(self, information): |
3499 | """Run the PostProcessor. | |
3500 | ||
3501 | The "information" argument is a dictionary like the ones | |
2f11508a | 3502 | composed by InfoExtractors. The only difference is that this |
65cd34c5 RG |
3503 | one has an extra field called "filepath" that points to the |
3504 | downloaded file. | |
3505 | ||
3506 | When this method returns None, the postprocessing chain is | |
3507 | stopped. However, this method may return an information | |
3508 | dictionary that will be passed to the next postprocessing | |
3509 | object in the chain. It can be the one it received after | |
3510 | changing some fields. | |
3511 | ||
3512 | In addition, this method may raise a PostProcessingError | |
3513 | exception that will be taken into account by the downloader | |
3514 | it was called from. | |
3515 | """ | |
3516 | return information # by default, do nothing | |
d3975459 | 3517 | |
c0a10ca8 | 3518 | |
3072fab1 RG |
3519 | class FFmpegExtractAudioPP(PostProcessor): |
3520 | ||
c99dcbd2 | 3521 | def __init__(self, downloader=None, preferredcodec=None, preferredquality=None, keepvideo=False): |
3072fab1 RG |
3522 | PostProcessor.__init__(self, downloader) |
3523 | if preferredcodec is None: | |
3524 | preferredcodec = 'best' | |
3525 | self._preferredcodec = preferredcodec | |
18b7f874 | 3526 | self._preferredquality = preferredquality |
3527 | self._keepvideo = keepvideo | |
3072fab1 RG |
3528 | |
3529 | @staticmethod | |
3530 | def get_audio_codec(path): | |
da273188 | 3531 | try: |
2727dbf7 RG |
3532 | cmd = ['ffprobe', '-show_streams', '--', path] |
3533 | handle = subprocess.Popen(cmd, stderr=file(os.path.devnull, 'w'), stdout=subprocess.PIPE) | |
da273188 RG |
3534 | output = handle.communicate()[0] |
3535 | if handle.wait() != 0: | |
3536 | return None | |
3537 | except (IOError, OSError): | |
3072fab1 RG |
3538 | return None |
3539 | audio_codec = None | |
3540 | for line in output.split('\n'): | |
3541 | if line.startswith('codec_name='): | |
3542 | audio_codec = line.split('=')[1].strip() | |
3543 | elif line.strip() == 'codec_type=audio' and audio_codec is not None: | |
3544 | return audio_codec | |
3545 | return None | |
3546 | ||
3547 | @staticmethod | |
3548 | def run_ffmpeg(path, out_path, codec, more_opts): | |
3549 | try: | |
2727dbf7 RG |
3550 | cmd = ['ffmpeg', '-y', '-i', path, '-vn', '-acodec', codec] + more_opts + ['--', out_path] |
3551 | ret = subprocess.call(cmd, stdout=file(os.path.devnull, 'w'), stderr=subprocess.STDOUT) | |
3072fab1 RG |
3552 | return (ret == 0) |
3553 | except (IOError, OSError): | |
3554 | return False | |
3555 | ||
3556 | def run(self, information): | |
3557 | path = information['filepath'] | |
3558 | ||
3559 | filecodec = self.get_audio_codec(path) | |
3560 | if filecodec is None: | |
da273188 | 3561 | self._downloader.to_stderr(u'WARNING: unable to obtain file audio codec with ffprobe') |
3072fab1 RG |
3562 | return None |
3563 | ||
3564 | more_opts = [] | |
3565 | if self._preferredcodec == 'best' or self._preferredcodec == filecodec: | |
efb113c7 | 3566 | if filecodec in ['aac', 'mp3', 'vorbis']: |
3072fab1 RG |
3567 | # Lossless if possible |
3568 | acodec = 'copy' | |
3569 | extension = filecodec | |
3570 | if filecodec == 'aac': | |
3571 | more_opts = ['-f', 'adts'] | |
58384838 RC |
3572 | if filecodec == 'vorbis': |
3573 | extension = 'ogg' | |
3072fab1 RG |
3574 | else: |
3575 | # MP3 otherwise. | |
3576 | acodec = 'libmp3lame' | |
3577 | extension = 'mp3' | |
c99dcbd2 PH |
3578 | more_opts = [] |
3579 | if self._preferredquality is not None: | |
3580 | more_opts += ['-ab', self._preferredquality] | |
3072fab1 RG |
3581 | else: |
3582 | # We convert the audio (lossy) | |
58384838 | 3583 | acodec = {'mp3': 'libmp3lame', 'aac': 'aac', 'vorbis': 'libvorbis'}[self._preferredcodec] |
3072fab1 | 3584 | extension = self._preferredcodec |
c99dcbd2 PH |
3585 | more_opts = [] |
3586 | if self._preferredquality is not None: | |
3587 | more_opts += ['-ab', self._preferredquality] | |
3072fab1 RG |
3588 | if self._preferredcodec == 'aac': |
3589 | more_opts += ['-f', 'adts'] | |
58384838 RC |
3590 | if self._preferredcodec == 'vorbis': |
3591 | extension = 'ogg' | |
3072fab1 RG |
3592 | |
3593 | (prefix, ext) = os.path.splitext(path) | |
3594 | new_path = prefix + '.' + extension | |
3595 | self._downloader.to_screen(u'[ffmpeg] Destination: %s' % new_path) | |
3596 | status = self.run_ffmpeg(path, new_path, acodec, more_opts) | |
3597 | ||
3598 | if not status: | |
1bd92582 | 3599 | self._downloader.to_stderr(u'WARNING: error running ffmpeg') |
3072fab1 RG |
3600 | return None |
3601 | ||
36597dc4 K |
3602 | # Try to update the date time for extracted audio file. |
3603 | if information.get('filetime') is not None: | |
3604 | try: | |
3605 | os.utime(new_path, (time.time(), information['filetime'])) | |
3606 | except: | |
3607 | self._downloader.to_stderr(u'WARNING: Cannot update utime of audio file') | |
3608 | ||
18b7f874 | 3609 | if not self._keepvideo: |
3610 | try: | |
3611 | os.remove(path) | |
3612 | except (IOError, OSError): | |
3613 | self._downloader.to_stderr(u'WARNING: Unable to remove downloaded video file') | |
3614 | return None | |
3072fab1 RG |
3615 | |
3616 | information['filepath'] = new_path | |
3617 | return information | |
3618 | ||
5fb3df4a GV |
3619 | |
3620 | def updateSelf(downloader, filename): | |
3621 | ''' Update the program file with the latest version from the repository ''' | |
3622 | # Note: downloader only used for options | |
3623 | if not os.access(filename, os.W_OK): | |
3624 | sys.exit('ERROR: no write permissions on %s' % filename) | |
3625 | ||
d207e7cf | 3626 | downloader.to_screen('Updating to latest version...') |
5fb3df4a | 3627 | |
4fa74b52 | 3628 | try: |
d207e7cf PH |
3629 | try: |
3630 | urlh = urllib.urlopen(UPDATE_URL) | |
3631 | newcontent = urlh.read() | |
27365956 PH |
3632 | |
3633 | vmatch = re.search("__version__ = '([^']+)'", newcontent) | |
3634 | if vmatch is not None and vmatch.group(1) == __version__: | |
3635 | downloader.to_screen('youtube-dl is up-to-date (' + __version__ + ')') | |
3636 | return | |
d207e7cf PH |
3637 | finally: |
3638 | urlh.close() | |
5fb3df4a GV |
3639 | except (IOError, OSError), err: |
3640 | sys.exit('ERROR: unable to download latest version') | |
f9f1e798 | 3641 | |
5fb3df4a | 3642 | try: |
d207e7cf PH |
3643 | outf = open(filename, 'wb') |
3644 | try: | |
3645 | outf.write(newcontent) | |
3646 | finally: | |
3647 | outf.close() | |
5fb3df4a GV |
3648 | except (IOError, OSError), err: |
3649 | sys.exit('ERROR: unable to overwrite current version') | |
4bec29ef | 3650 | |
eb6c37da | 3651 | downloader.to_screen('Updated youtube-dl. Restart youtube-dl to use the new version.') |
80066952 | 3652 | |
4f9f96f6 GV |
3653 | def parseOpts(): |
3654 | # Deferred imports | |
3655 | import getpass | |
3656 | import optparse | |
e7cf18cb | 3657 | |
4f9f96f6 GV |
3658 | def _format_option_string(option): |
3659 | ''' ('-o', '--option') -> -o, --format METAVAR''' | |
80066952 | 3660 | |
4f9f96f6 GV |
3661 | opts = [] |
3662 | ||
3663 | if option._short_opts: opts.append(option._short_opts[0]) | |
3664 | if option._long_opts: opts.append(option._long_opts[0]) | |
3665 | if len(opts) > 1: opts.insert(1, ', ') | |
3666 | ||
3667 | if option.takes_value(): opts.append(' %s' % option.metavar) | |
3668 | ||
3669 | return "".join(opts) | |
3670 | ||
6a4f0a11 GV |
3671 | def _find_term_columns(): |
3672 | columns = os.environ.get('COLUMNS', None) | |
2c8d32de PH |
3673 | if columns: |
3674 | return int(columns) | |
3675 | ||
4f2a5e06 PH |
3676 | try: |
3677 | sp = subprocess.Popen(['stty', 'size'], stdout=subprocess.PIPE, stderr=subprocess.PIPE) | |
3678 | out,err = sp.communicate() | |
eb0387a8 | 3679 | return int(out.split()[1]) |
4f2a5e06 PH |
3680 | except: |
3681 | pass | |
2c8d32de | 3682 | return None |
6a4f0a11 | 3683 | |
51c8e53f GV |
3684 | max_width = 80 |
3685 | max_help_position = 80 | |
3686 | ||
3687 | # No need to wrap help messages if we're on a wide console | |
6a4f0a11 | 3688 | columns = _find_term_columns() |
51c8e53f GV |
3689 | if columns: max_width = columns |
3690 | ||
3691 | fmt = optparse.IndentedHelpFormatter(width=max_width, max_help_position=max_help_position) | |
4f9f96f6 GV |
3692 | fmt.format_option_strings = _format_option_string |
3693 | ||
3694 | kw = { | |
3695 | 'version' : __version__, | |
3696 | 'formatter' : fmt, | |
a2f7e3a5 | 3697 | 'usage' : '%prog [options] url [url...]', |
4f9f96f6 GV |
3698 | 'conflict_handler' : 'resolve', |
3699 | } | |
3700 | ||
3701 | parser = optparse.OptionParser(**kw) | |
3702 | ||
3703 | # option groups | |
3704 | general = optparse.OptionGroup(parser, 'General Options') | |
20e91e83 | 3705 | selection = optparse.OptionGroup(parser, 'Video Selection') |
4f9f96f6 GV |
3706 | authentication = optparse.OptionGroup(parser, 'Authentication Options') |
3707 | video_format = optparse.OptionGroup(parser, 'Video Format Options') | |
3708 | postproc = optparse.OptionGroup(parser, 'Post-processing Options') | |
3709 | filesystem = optparse.OptionGroup(parser, 'Filesystem Options') | |
3710 | verbosity = optparse.OptionGroup(parser, 'Verbosity / Simulation Options') | |
3711 | ||
3712 | general.add_option('-h', '--help', | |
3713 | action='help', help='print this help text and exit') | |
3714 | general.add_option('-v', '--version', | |
3715 | action='version', help='print program version and exit') | |
3716 | general.add_option('-U', '--update', | |
e0e56865 | 3717 | action='store_true', dest='update_self', help='update this program to latest version') |
4f9f96f6 GV |
3718 | general.add_option('-i', '--ignore-errors', |
3719 | action='store_true', dest='ignoreerrors', help='continue on download errors', default=False) | |
3720 | general.add_option('-r', '--rate-limit', | |
3721 | dest='ratelimit', metavar='LIMIT', help='download rate limit (e.g. 50k or 44.6m)') | |
3722 | general.add_option('-R', '--retries', | |
3723 | dest='retries', metavar='RETRIES', help='number of retries (default is 10)', default=10) | |
4f9f96f6 GV |
3724 | general.add_option('--dump-user-agent', |
3725 | action='store_true', dest='dump_user_agent', | |
3726 | help='display the current browser identification', default=False) | |
f3098c4d PH |
3727 | general.add_option('--list-extractors', |
3728 | action='store_true', dest='list_extractors', | |
3729 | help='List all supported extractors and the URLs they would handle', default=False) | |
4f9f96f6 | 3730 | |
20e91e83 ABP |
3731 | selection.add_option('--playlist-start', |
3732 | dest='playliststart', metavar='NUMBER', help='playlist video to start at (default is 1)', default=1) | |
3733 | selection.add_option('--playlist-end', | |
3734 | dest='playlistend', metavar='NUMBER', help='playlist video to end at (default is last)', default=-1) | |
3735 | selection.add_option('--match-title', dest='matchtitle', metavar='REGEX',help='download only matching titles (regex or caseless sub-string)') | |
3736 | selection.add_option('--reject-title', dest='rejecttitle', metavar='REGEX',help='skip download for matching titles (regex or caseless sub-string)') | |
3737 | ||
4f9f96f6 GV |
3738 | authentication.add_option('-u', '--username', |
3739 | dest='username', metavar='USERNAME', help='account username') | |
3740 | authentication.add_option('-p', '--password', | |
3741 | dest='password', metavar='PASSWORD', help='account password') | |
3742 | authentication.add_option('-n', '--netrc', | |
3743 | action='store_true', dest='usenetrc', help='use .netrc authentication data', default=False) | |
3744 | ||
3745 | ||
3746 | video_format.add_option('-f', '--format', | |
3747 | action='store', dest='format', metavar='FORMAT', help='video format code') | |
3748 | video_format.add_option('--all-formats', | |
5260e68f | 3749 | action='store_const', dest='format', help='download all available video formats', const='all') |
4f9f96f6 GV |
3750 | video_format.add_option('--max-quality', |
3751 | action='store', dest='format_limit', metavar='FORMAT', help='highest quality format to download') | |
2761012f PH |
3752 | video_format.add_option('-F', '--list-formats', |
3753 | action='store_true', dest='listformats', help='list all available formats (currently youtube only)') | |
4f9f96f6 GV |
3754 | |
3755 | ||
3756 | verbosity.add_option('-q', '--quiet', | |
3757 | action='store_true', dest='quiet', help='activates quiet mode', default=False) | |
3758 | verbosity.add_option('-s', '--simulate', | |
9b4556c4 PH |
3759 | action='store_true', dest='simulate', help='do not download the video and do not write anything to disk', default=False) |
3760 | verbosity.add_option('--skip-download', | |
3761 | action='store_true', dest='skip_download', help='do not download the video', default=False) | |
4f9f96f6 GV |
3762 | verbosity.add_option('-g', '--get-url', |
3763 | action='store_true', dest='geturl', help='simulate, quiet but print URL', default=False) | |
3764 | verbosity.add_option('-e', '--get-title', | |
3765 | action='store_true', dest='gettitle', help='simulate, quiet but print title', default=False) | |
3766 | verbosity.add_option('--get-thumbnail', | |
3767 | action='store_true', dest='getthumbnail', | |
3768 | help='simulate, quiet but print thumbnail URL', default=False) | |
3769 | verbosity.add_option('--get-description', | |
3770 | action='store_true', dest='getdescription', | |
3771 | help='simulate, quiet but print video description', default=False) | |
3772 | verbosity.add_option('--get-filename', | |
3773 | action='store_true', dest='getfilename', | |
3774 | help='simulate, quiet but print output filename', default=False) | |
da0db53a DH |
3775 | verbosity.add_option('--get-format', |
3776 | action='store_true', dest='getformat', | |
3777 | help='simulate, quiet but print output format', default=False) | |
4f9f96f6 GV |
3778 | verbosity.add_option('--no-progress', |
3779 | action='store_true', dest='noprogress', help='do not print progress bar', default=False) | |
3780 | verbosity.add_option('--console-title', | |
3781 | action='store_true', dest='consoletitle', | |
3782 | help='display progress in console titlebar', default=False) | |
3783 | ||
3784 | ||
3785 | filesystem.add_option('-t', '--title', | |
3786 | action='store_true', dest='usetitle', help='use title in file name', default=False) | |
3787 | filesystem.add_option('-l', '--literal', | |
3788 | action='store_true', dest='useliteral', help='use literal title in file name', default=False) | |
3789 | filesystem.add_option('-A', '--auto-number', | |
3790 | action='store_true', dest='autonumber', | |
3791 | help='number downloaded files starting from 00000', default=False) | |
3792 | filesystem.add_option('-o', '--output', | |
6bde5972 | 3793 | 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, and %% for a literal percent') |
4f9f96f6 GV |
3794 | filesystem.add_option('-a', '--batch-file', |
3795 | dest='batchfile', metavar='FILE', help='file containing URLs to download (\'-\' for stdin)') | |
3796 | filesystem.add_option('-w', '--no-overwrites', | |
3797 | action='store_true', dest='nooverwrites', help='do not overwrite files', default=False) | |
3798 | filesystem.add_option('-c', '--continue', | |
c25303c3 | 3799 | action='store_true', dest='continue_dl', help='resume partially downloaded files', default=False) |
18bb3d1e PH |
3800 | filesystem.add_option('--no-continue', |
3801 | action='store_false', dest='continue_dl', | |
3802 | help='do not resume partially downloaded files (restart from beginning)') | |
4f9f96f6 | 3803 | filesystem.add_option('--cookies', |
abb870d1 | 3804 | dest='cookiefile', metavar='FILE', help='file to read cookies from and dump cookie jar in') |
4f9f96f6 GV |
3805 | filesystem.add_option('--no-part', |
3806 | action='store_true', dest='nopart', help='do not use .part files', default=False) | |
3807 | filesystem.add_option('--no-mtime', | |
3808 | action='store_false', dest='updatetime', | |
3809 | help='do not use the Last-modified header to set the file modification time', default=True) | |
2c8d32de PH |
3810 | filesystem.add_option('--write-description', |
3811 | action='store_true', dest='writedescription', | |
3812 | help='write video description to a .description file', default=False) | |
3813 | filesystem.add_option('--write-info-json', | |
3814 | action='store_true', dest='writeinfojson', | |
3815 | help='write video metadata to a .info.json file', default=False) | |
4f9f96f6 GV |
3816 | |
3817 | ||
3818 | postproc.add_option('--extract-audio', action='store_true', dest='extractaudio', default=False, | |
3819 | help='convert video files to audio-only files (requires ffmpeg and ffprobe)') | |
3820 | postproc.add_option('--audio-format', metavar='FORMAT', dest='audioformat', default='best', | |
58384838 | 3821 | help='"best", "aac", "vorbis" or "mp3"; best by default') |
c99dcbd2 PH |
3822 | postproc.add_option('--audio-quality', metavar='QUALITY', dest='audioquality', default='128K', |
3823 | help='ffmpeg audio bitrate specification, 128k by default') | |
3824 | postproc.add_option('-k', '--keep-video', action='store_true', dest='keepvideo', default=False, | |
3825 | help='keeps the video file on disk after the post-processing; the video is erased by default') | |
4f9f96f6 GV |
3826 | |
3827 | ||
3828 | parser.add_option_group(general) | |
20e91e83 | 3829 | parser.add_option_group(selection) |
4f9f96f6 GV |
3830 | parser.add_option_group(filesystem) |
3831 | parser.add_option_group(verbosity) | |
3832 | parser.add_option_group(video_format) | |
3833 | parser.add_option_group(authentication) | |
3834 | parser.add_option_group(postproc) | |
3835 | ||
3836 | opts, args = parser.parse_args() | |
3837 | ||
3838 | return parser, opts, args | |
3839 | ||
f3098c4d PH |
3840 | def gen_extractors(): |
3841 | """ Return a list of an instance of every supported extractor. | |
3842 | The order does matter; the first extractor matched is the one handling the URL. | |
3843 | """ | |
3844 | youtube_ie = YoutubeIE() | |
3845 | google_ie = GoogleIE() | |
3846 | yahoo_ie = YahooIE() | |
3847 | return [ | |
f3098c4d PH |
3848 | YoutubePlaylistIE(youtube_ie), |
3849 | YoutubeUserIE(youtube_ie), | |
3850 | YoutubeSearchIE(youtube_ie), | |
1cde6f1d PH |
3851 | youtube_ie, |
3852 | MetacafeIE(youtube_ie), | |
3853 | DailymotionIE(), | |
f3098c4d PH |
3854 | google_ie, |
3855 | GoogleSearchIE(google_ie), | |
3856 | PhotobucketIE(), | |
3857 | yahoo_ie, | |
3858 | YahooSearchIE(yahoo_ie), | |
3859 | DepositFilesIE(), | |
3860 | FacebookIE(), | |
3861 | BlipTVIE(), | |
3862 | VimeoIE(), | |
3863 | MyVideoIE(), | |
3864 | ComedyCentralIE(), | |
3865 | EscapistIE(), | |
8d89fbae | 3866 | CollegeHumorIE(), |
6501a06d | 3867 | XVideosIE(), |
f3098c4d PH |
3868 | |
3869 | GenericIE() | |
3870 | ] | |
3871 | ||
5adcaa43 GV |
3872 | def main(): |
3873 | parser, opts, args = parseOpts() | |
4f9f96f6 | 3874 | |
5adcaa43 GV |
3875 | # Open appropriate CookieJar |
3876 | if opts.cookiefile is None: | |
3877 | jar = cookielib.CookieJar() | |
3878 | else: | |
8cc44341 | 3879 | try: |
5adcaa43 GV |
3880 | jar = cookielib.MozillaCookieJar(opts.cookiefile) |
3881 | if os.path.isfile(opts.cookiefile) and os.access(opts.cookiefile, os.R_OK): | |
3882 | jar.load() | |
3883 | except (IOError, OSError), err: | |
3884 | sys.exit(u'ERROR: unable to open cookie file') | |
80066952 | 3885 | |
5adcaa43 GV |
3886 | # Dump user agent |
3887 | if opts.dump_user_agent: | |
3888 | print std_headers['User-Agent'] | |
3889 | sys.exit(0) | |
e7cf18cb | 3890 | |
5adcaa43 GV |
3891 | # Batch file verification |
3892 | batchurls = [] | |
3893 | if opts.batchfile is not None: | |
8cc44341 | 3894 | try: |
5adcaa43 GV |
3895 | if opts.batchfile == '-': |
3896 | batchfd = sys.stdin | |
4bec29ef | 3897 | else: |
5adcaa43 GV |
3898 | batchfd = open(opts.batchfile, 'r') |
3899 | batchurls = batchfd.readlines() | |
3900 | batchurls = [x.strip() for x in batchurls] | |
3901 | batchurls = [x for x in batchurls if len(x) > 0 and not re.search(r'^[#/;]', x)] | |
3902 | except IOError: | |
3903 | sys.exit(u'ERROR: batch file could not be read') | |
3904 | all_urls = batchurls + args | |
3905 | ||
f3098c4d PH |
3906 | # General configuration |
3907 | cookie_processor = urllib2.HTTPCookieProcessor(jar) | |
3908 | opener = urllib2.build_opener(urllib2.ProxyHandler(), cookie_processor, YoutubeDLHandler()) | |
3909 | urllib2.install_opener(opener) | |
3910 | socket.setdefaulttimeout(300) # 5 minutes should be enough (famous last words) | |
3911 | ||
3912 | extractors = gen_extractors() | |
3913 | ||
3914 | if opts.list_extractors: | |
3915 | for ie in extractors: | |
3916 | print(ie.IE_NAME) | |
3917 | matchedUrls = filter(lambda url: ie.suitable(url), all_urls) | |
3918 | all_urls = filter(lambda url: url not in matchedUrls, all_urls) | |
3919 | for mu in matchedUrls: | |
3920 | print(u' ' + mu) | |
3921 | sys.exit(0) | |
3922 | ||
5adcaa43 GV |
3923 | # Conflicting, missing and erroneous options |
3924 | if opts.usenetrc and (opts.username is not None or opts.password is not None): | |
3925 | parser.error(u'using .netrc conflicts with giving username/password') | |
3926 | if opts.password is not None and opts.username is None: | |
3927 | parser.error(u'account username missing') | |
3928 | if opts.outtmpl is not None and (opts.useliteral or opts.usetitle or opts.autonumber): | |
3929 | parser.error(u'using output template conflicts with using title, literal title or auto number') | |
3930 | if opts.usetitle and opts.useliteral: | |
3931 | parser.error(u'using title conflicts with using literal title') | |
3932 | if opts.username is not None and opts.password is None: | |
3933 | opts.password = getpass.getpass(u'Type account password and press return:') | |
3934 | if opts.ratelimit is not None: | |
3935 | numeric_limit = FileDownloader.parse_bytes(opts.ratelimit) | |
3936 | if numeric_limit is None: | |
3937 | parser.error(u'invalid rate limit specified') | |
3938 | opts.ratelimit = numeric_limit | |
3939 | if opts.retries is not None: | |
8cc44341 | 3940 | try: |
5adcaa43 | 3941 | opts.retries = long(opts.retries) |
8cc44341 | 3942 | except (TypeError, ValueError), err: |
5adcaa43 GV |
3943 | parser.error(u'invalid retry count specified') |
3944 | try: | |
2c8d32de | 3945 | opts.playliststart = int(opts.playliststart) |
5adcaa43 | 3946 | if opts.playliststart <= 0: |
2c8d32de | 3947 | raise ValueError(u'Playlist start must be positive') |
5adcaa43 GV |
3948 | except (TypeError, ValueError), err: |
3949 | parser.error(u'invalid playlist start number specified') | |
3950 | try: | |
2c8d32de | 3951 | opts.playlistend = int(opts.playlistend) |
5adcaa43 | 3952 | if opts.playlistend != -1 and (opts.playlistend <= 0 or opts.playlistend < opts.playliststart): |
2c8d32de | 3953 | raise ValueError(u'Playlist end must be greater than playlist start') |
5adcaa43 GV |
3954 | except (TypeError, ValueError), err: |
3955 | parser.error(u'invalid playlist end number specified') | |
3956 | if opts.extractaudio: | |
58384838 | 3957 | if opts.audioformat not in ['best', 'aac', 'mp3', 'vorbis']: |
5adcaa43 GV |
3958 | parser.error(u'invalid audio format specified') |
3959 | ||
5adcaa43 GV |
3960 | # File downloader |
3961 | fd = FileDownloader({ | |
3962 | 'usenetrc': opts.usenetrc, | |
3963 | 'username': opts.username, | |
3964 | 'password': opts.password, | |
da0db53a | 3965 | 'quiet': (opts.quiet or opts.geturl or opts.gettitle or opts.getthumbnail or opts.getdescription or opts.getfilename or opts.getformat), |
5adcaa43 GV |
3966 | 'forceurl': opts.geturl, |
3967 | 'forcetitle': opts.gettitle, | |
3968 | 'forcethumbnail': opts.getthumbnail, | |
3969 | 'forcedescription': opts.getdescription, | |
3970 | 'forcefilename': opts.getfilename, | |
da0db53a | 3971 | 'forceformat': opts.getformat, |
9b4556c4 | 3972 | 'simulate': opts.simulate, |
da0db53a | 3973 | '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), |
5adcaa43 GV |
3974 | 'format': opts.format, |
3975 | 'format_limit': opts.format_limit, | |
3de2a1e6 | 3976 | 'listformats': opts.listformats, |
5adcaa43 GV |
3977 | 'outtmpl': ((opts.outtmpl is not None and opts.outtmpl.decode(preferredencoding())) |
3978 | or (opts.format == '-1' and opts.usetitle and u'%(stitle)s-%(id)s-%(format)s.%(ext)s') | |
3979 | or (opts.format == '-1' and opts.useliteral and u'%(title)s-%(id)s-%(format)s.%(ext)s') | |
3980 | or (opts.format == '-1' and u'%(id)s-%(format)s.%(ext)s') | |
3981 | or (opts.usetitle and opts.autonumber and u'%(autonumber)s-%(stitle)s-%(id)s.%(ext)s') | |
3982 | or (opts.useliteral and opts.autonumber and u'%(autonumber)s-%(title)s-%(id)s.%(ext)s') | |
3983 | or (opts.usetitle and u'%(stitle)s-%(id)s.%(ext)s') | |
3984 | or (opts.useliteral and u'%(title)s-%(id)s.%(ext)s') | |
3985 | or (opts.autonumber and u'%(autonumber)s-%(id)s.%(ext)s') | |
3986 | or u'%(id)s.%(ext)s'), | |
3987 | 'ignoreerrors': opts.ignoreerrors, | |
3988 | 'ratelimit': opts.ratelimit, | |
3989 | 'nooverwrites': opts.nooverwrites, | |
3990 | 'retries': opts.retries, | |
3991 | 'continuedl': opts.continue_dl, | |
3992 | 'noprogress': opts.noprogress, | |
3993 | 'playliststart': opts.playliststart, | |
3994 | 'playlistend': opts.playlistend, | |
3995 | 'logtostderr': opts.outtmpl == '-', | |
3996 | 'consoletitle': opts.consoletitle, | |
3997 | 'nopart': opts.nopart, | |
3998 | 'updatetime': opts.updatetime, | |
2c8d32de PH |
3999 | 'writedescription': opts.writedescription, |
4000 | 'writeinfojson': opts.writeinfojson, | |
20e91e83 ABP |
4001 | 'matchtitle': opts.matchtitle, |
4002 | 'rejecttitle': opts.rejecttitle, | |
5adcaa43 | 4003 | }) |
8c5dc3ad PH |
4004 | for extractor in extractors: |
4005 | fd.add_info_extractor(extractor) | |
5adcaa43 GV |
4006 | |
4007 | # PostProcessors | |
4008 | if opts.extractaudio: | |
c99dcbd2 | 4009 | fd.add_post_processor(FFmpegExtractAudioPP(preferredcodec=opts.audioformat, preferredquality=opts.audioquality, keepvideo=opts.keepvideo)) |
5adcaa43 GV |
4010 | |
4011 | # Update version | |
4012 | if opts.update_self: | |
4013 | updateSelf(fd, sys.argv[0]) | |
4014 | ||
4015 | # Maybe do nothing | |
4016 | if len(all_urls) < 1: | |
4017 | if not opts.update_self: | |
4018 | parser.error(u'you must provide at least one URL') | |
4019 | else: | |
4020 | sys.exit() | |
4021 | retcode = fd.download(all_urls) | |
80066952 | 4022 | |
5adcaa43 GV |
4023 | # Dump cookie jar if requested |
4024 | if opts.cookiefile is not None: | |
4025 | try: | |
4026 | jar.save() | |
4027 | except (IOError, OSError), err: | |
4028 | sys.exit(u'ERROR: unable to save cookie jar') | |
80066952 | 4029 | |
5adcaa43 | 4030 | sys.exit(retcode) |
80066952 | 4031 | |
4fa74b52 | 4032 | |
5adcaa43 GV |
4033 | if __name__ == '__main__': |
4034 | try: | |
4035 | main() | |
e5bf0f55 RG |
4036 | except DownloadError: |
4037 | sys.exit(1) | |
4038 | except SameFileError: | |
76a7f364 | 4039 | sys.exit(u'ERROR: fixed output name but more than one file to download') |
4fa74b52 | 4040 | except KeyboardInterrupt: |
76a7f364 | 4041 | sys.exit(u'\nERROR: Interrupted by user') |
e9cb9c28 GV |
4042 | |
4043 | # vim: set ts=4 sw=4 sts=4 noet ai si filetype=python: |