]>
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', | |
2770590d GV |
12 | ) |
13 | ||
2c8d32de PH |
14 | __license__ = 'Public Domain' |
15 | __version__ = '2011.08.24-phihag' | |
2770590d | 16 | |
80066952 | 17 | import cookielib |
a1f03c7b | 18 | import datetime |
1987c232 | 19 | import gzip |
4fa74b52 RG |
20 | import htmlentitydefs |
21 | import httplib | |
2546e767 | 22 | import locale |
4fa74b52 RG |
23 | import math |
24 | import netrc | |
25 | import os | |
26 | import os.path | |
27 | import re | |
28 | import socket | |
29 | import string | |
0487b407 | 30 | import subprocess |
4fa74b52 RG |
31 | import sys |
32 | import time | |
33 | import urllib | |
34 | import urllib2 | |
c6b55a8d | 35 | import warnings |
1987c232 | 36 | import zlib |
a04e80a4 | 37 | |
0a3c8b62 PH |
38 | if os.name == 'nt': |
39 | import ctypes | |
40 | ||
41 | try: | |
42 | import email.utils | |
43 | except ImportError: # Python 2.4 | |
44 | import email.Utils | |
c6b55a8d PH |
45 | try: |
46 | import cStringIO as StringIO | |
47 | except ImportError: | |
48 | import StringIO | |
49 | ||
a04e80a4 RG |
50 | # parse_qs was moved from the cgi module to the urlparse module recently. |
51 | try: | |
52 | from urlparse import parse_qs | |
53 | except ImportError: | |
54 | from cgi import parse_qs | |
4fa74b52 | 55 | |
c6b55a8d PH |
56 | try: |
57 | import lxml.etree | |
2b70537d | 58 | except ImportError: |
c6b55a8d PH |
59 | pass # Handled below |
60 | ||
f995f712 | 61 | std_headers = { |
c44b9ee9 | 62 | 'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64; rv:5.0.1) Gecko/20100101 Firefox/5.0.1', |
4fa74b52 | 63 | 'Accept-Charset': 'ISO-8859-1,utf-8;q=0.7,*;q=0.7', |
96942e62 | 64 | 'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8', |
a57ed21f | 65 | 'Accept-Encoding': 'gzip, deflate', |
4fa74b52 RG |
66 | 'Accept-Language': 'en-us,en;q=0.5', |
67 | } | |
68 | ||
69 | simple_title_chars = string.ascii_letters.decode('ascii') + string.digits.decode('ascii') | |
70 | ||
437d76c1 PH |
71 | try: |
72 | import json | |
91e6a385 | 73 | except ImportError: # Python <2.6, use trivialjson (https://github.com/phihag/trivialjson): |
437d76c1 PH |
74 | import re |
75 | class json(object): | |
76 | @staticmethod | |
77 | def loads(s): | |
78 | s = s.decode('UTF-8') | |
79 | def raiseError(msg, i): | |
80 | raise ValueError(msg + ' at position ' + str(i) + ' of ' + repr(s) + ': ' + repr(s[i:])) | |
81 | def skipSpace(i, expectMore=True): | |
82 | while i < len(s) and s[i] in ' \t\r\n': | |
83 | i += 1 | |
84 | if expectMore: | |
85 | if i >= len(s): | |
86 | raiseError('Premature end', i) | |
87 | return i | |
88 | def decodeEscape(match): | |
89 | esc = match.group(1) | |
90 | _STATIC = { | |
91 | '"': '"', | |
92 | '\\': '\\', | |
93 | '/': '/', | |
94 | 'b': unichr(0x8), | |
95 | 'f': unichr(0xc), | |
96 | 'n': '\n', | |
97 | 'r': '\r', | |
98 | 't': '\t', | |
99 | } | |
100 | if esc in _STATIC: | |
101 | return _STATIC[esc] | |
102 | if esc[0] == 'u': | |
103 | if len(esc) == 1+4: | |
104 | return unichr(int(esc[1:5], 16)) | |
105 | if len(esc) == 5+6 and esc[5:7] == '\\u': | |
106 | hi = int(esc[1:5], 16) | |
107 | low = int(esc[7:11], 16) | |
108 | return unichr((hi - 0xd800) * 0x400 + low - 0xdc00 + 0x10000) | |
109 | raise ValueError('Unknown escape ' + str(esc)) | |
110 | def parseString(i): | |
111 | i += 1 | |
112 | e = i | |
113 | while True: | |
114 | e = s.index('"', e) | |
115 | bslashes = 0 | |
116 | while s[e-bslashes-1] == '\\': | |
117 | bslashes += 1 | |
118 | if bslashes % 2 == 1: | |
119 | e += 1 | |
120 | continue | |
121 | break | |
122 | rexp = re.compile(r'\\(u[dD][89aAbB][0-9a-fA-F]{2}\\u[0-9a-fA-F]{4}|u[0-9a-fA-F]{4}|.|$)') | |
123 | stri = rexp.sub(decodeEscape, s[i:e]) | |
124 | return (e+1,stri) | |
125 | def parseObj(i): | |
126 | i += 1 | |
127 | res = {} | |
128 | i = skipSpace(i) | |
129 | if s[i] == '}': # Empty dictionary | |
130 | return (i+1,res) | |
131 | while True: | |
132 | if s[i] != '"': | |
133 | raiseError('Expected a string object key', i) | |
134 | i,key = parseString(i) | |
135 | i = skipSpace(i) | |
136 | if i >= len(s) or s[i] != ':': | |
137 | raiseError('Expected a colon', i) | |
138 | i,val = parse(i+1) | |
139 | res[key] = val | |
140 | i = skipSpace(i) | |
141 | if s[i] == '}': | |
142 | return (i+1, res) | |
143 | if s[i] != ',': | |
144 | raiseError('Expected comma or closing curly brace', i) | |
145 | i = skipSpace(i+1) | |
146 | def parseArray(i): | |
147 | res = [] | |
148 | i = skipSpace(i+1) | |
149 | if s[i] == ']': # Empty array | |
150 | return (i+1,res) | |
151 | while True: | |
152 | i,val = parse(i) | |
153 | res.append(val) | |
154 | i = skipSpace(i) # Raise exception if premature end | |
155 | if s[i] == ']': | |
156 | return (i+1, res) | |
157 | if s[i] != ',': | |
158 | raiseError('Expected a comma or closing bracket', i) | |
159 | i = skipSpace(i+1) | |
160 | def parseDiscrete(i): | |
161 | for k,v in {'true': True, 'false': False, 'null': None}.items(): | |
162 | if s.startswith(k, i): | |
163 | return (i+len(k), v) | |
164 | raiseError('Not a boolean (or null)', i) | |
165 | def parseNumber(i): | |
166 | mobj = re.match('^(-?(0|[1-9][0-9]*)(\.[0-9]*)?([eE][+-]?[0-9]+)?)', s[i:]) | |
167 | if mobj is None: | |
168 | raiseError('Not a number', i) | |
169 | nums = mobj.group(1) | |
170 | if '.' in nums or 'e' in nums or 'E' in nums: | |
171 | return (i+len(nums), float(nums)) | |
172 | return (i+len(nums), int(nums)) | |
173 | CHARMAP = {'{': parseObj, '[': parseArray, '"': parseString, 't': parseDiscrete, 'f': parseDiscrete, 'n': parseDiscrete} | |
174 | def parse(i): | |
175 | i = skipSpace(i) | |
176 | i,res = CHARMAP.get(s[i], parseNumber)(i) | |
177 | i = skipSpace(i, False) | |
178 | return (i,res) | |
179 | i,res = parse(0) | |
180 | if i < len(s): | |
181 | raise ValueError('Extra data at end of input (index ' + str(i) + ' of ' + repr(s) + ': ' + repr(s[i:]) + ')') | |
182 | return res | |
183 | ||
eae2666c RG |
184 | def preferredencoding(): |
185 | """Get preferred encoding. | |
186 | ||
187 | Returns the best encoding scheme for the system, based on | |
188 | locale.getpreferredencoding() and some further tweaks. | |
189 | """ | |
f94b636c RG |
190 | def yield_preferredencoding(): |
191 | try: | |
192 | pref = locale.getpreferredencoding() | |
193 | u'TEST'.encode(pref) | |
194 | except: | |
195 | pref = 'UTF-8' | |
196 | while True: | |
197 | yield pref | |
198 | return yield_preferredencoding().next() | |
eae2666c | 199 | |
490fd7ae RG |
200 | def htmlentity_transform(matchobj): |
201 | """Transforms an HTML entity to a Unicode character. | |
d3975459 | 202 | |
490fd7ae RG |
203 | This function receives a match object and is intended to be used with |
204 | the re.sub() function. | |
205 | """ | |
206 | entity = matchobj.group(1) | |
207 | ||
208 | # Known non-numeric HTML entity | |
209 | if entity in htmlentitydefs.name2codepoint: | |
210 | return unichr(htmlentitydefs.name2codepoint[entity]) | |
211 | ||
212 | # Unicode character | |
213 | mobj = re.match(ur'(?u)#(x?\d+)', entity) | |
214 | if mobj is not None: | |
215 | numstr = mobj.group(1) | |
216 | if numstr.startswith(u'x'): | |
217 | base = 16 | |
218 | numstr = u'0%s' % numstr | |
219 | else: | |
220 | base = 10 | |
221 | return unichr(long(numstr, base)) | |
222 | ||
223 | # Unknown entity in name, return its literal representation | |
224 | return (u'&%s;' % entity) | |
225 | ||
226 | def sanitize_title(utitle): | |
31bcb480 | 227 | """Sanitizes a video title so it could be used as part of a filename.""" |
490fd7ae | 228 | utitle = re.sub(ur'(?u)&(.+?);', htmlentity_transform, utitle) |
490fd7ae RG |
229 | return utitle.replace(unicode(os.sep), u'%') |
230 | ||
31bcb480 RG |
231 | def sanitize_open(filename, open_mode): |
232 | """Try to open the given filename, and slightly tweak it if this fails. | |
233 | ||
234 | Attempts to open the given filename. If this fails, it tries to change | |
235 | the filename slightly, step by step, until it's either able to open it | |
236 | or it fails and raises a final exception, like the standard open() | |
237 | function. | |
238 | ||
239 | It returns the tuple (stream, definitive_file_name). | |
240 | """ | |
241 | try: | |
131bc765 | 242 | if filename == u'-': |
e08878f4 RG |
243 | if sys.platform == 'win32': |
244 | import msvcrt | |
245 | msvcrt.setmode(sys.stdout.fileno(), os.O_BINARY) | |
131bc765 | 246 | return (sys.stdout, filename) |
31bcb480 RG |
247 | stream = open(filename, open_mode) |
248 | return (stream, filename) | |
249 | except (IOError, OSError), err: | |
250 | # In case of error, try to remove win32 forbidden chars | |
ca6a11fa | 251 | filename = re.sub(ur'[/<>:"\|\?\*]', u'#', filename) |
31bcb480 RG |
252 | |
253 | # An exception here should be caught in the caller | |
254 | stream = open(filename, open_mode) | |
255 | return (stream, filename) | |
256 | ||
09bd408c GI |
257 | def timeconvert(timestr): |
258 | """Convert RFC 2822 defined time string into system timestamp""" | |
259 | timestamp = None | |
260 | timetuple = email.utils.parsedate_tz(timestr) | |
261 | if timetuple is not None: | |
262 | timestamp = email.utils.mktime_tz(timetuple) | |
263 | return timestamp | |
264 | ||
e5bf0f55 RG |
265 | class DownloadError(Exception): |
266 | """Download Error exception. | |
d3975459 | 267 | |
e5bf0f55 RG |
268 | This exception may be thrown by FileDownloader objects if they are not |
269 | configured to continue on errors. They will contain the appropriate | |
270 | error message. | |
271 | """ | |
272 | pass | |
273 | ||
274 | class SameFileError(Exception): | |
275 | """Same File exception. | |
276 | ||
277 | This exception will be thrown by FileDownloader objects if they detect | |
278 | multiple files would have to be downloaded to the same file on disk. | |
279 | """ | |
280 | pass | |
281 | ||
65cd34c5 RG |
282 | class PostProcessingError(Exception): |
283 | """Post Processing exception. | |
284 | ||
285 | This exception may be raised by PostProcessor's .run() method to | |
286 | indicate an error in the postprocessing task. | |
287 | """ | |
288 | pass | |
289 | ||
73f4e7af | 290 | class UnavailableVideoError(Exception): |
7b7759f5 | 291 | """Unavailable Format exception. |
292 | ||
293 | This exception will be thrown when a video is requested | |
294 | in a format that is not available for that video. | |
295 | """ | |
d69a1c91 RG |
296 | pass |
297 | ||
298 | class ContentTooShortError(Exception): | |
299 | """Content Too Short exception. | |
300 | ||
301 | This exception may be raised by FileDownloader objects when a file they | |
302 | download is too small for what the server announced first, indicating | |
303 | the connection was probably interrupted. | |
304 | """ | |
305 | # Both in bytes | |
306 | downloaded = None | |
307 | expected = None | |
308 | ||
309 | def __init__(self, downloaded, expected): | |
310 | self.downloaded = downloaded | |
311 | self.expected = expected | |
7b7759f5 | 312 | |
1987c232 RG |
313 | class YoutubeDLHandler(urllib2.HTTPHandler): |
314 | """Handler for HTTP requests and responses. | |
315 | ||
316 | This class, when installed with an OpenerDirector, automatically adds | |
317 | the standard headers to every HTTP request and handles gzipped and | |
318 | deflated responses from web servers. If compression is to be avoided in | |
319 | a particular request, the original request in the program code only has | |
320 | to include the HTTP header "Youtubedl-No-Compression", which will be | |
321 | removed before making the real request. | |
322 | ||
323 | Part of this code was copied from: | |
324 | ||
325 | http://techknack.net/python-urllib2-handlers/ | |
326 | ||
327 | Andrew Rowls, the author of that code, agreed to release it to the | |
328 | public domain. | |
329 | """ | |
330 | ||
331 | @staticmethod | |
332 | def deflate(data): | |
333 | try: | |
334 | return zlib.decompress(data, -zlib.MAX_WBITS) | |
335 | except zlib.error: | |
336 | return zlib.decompress(data) | |
337 | ||
7b531c0b RG |
338 | @staticmethod |
339 | def addinfourl_wrapper(stream, headers, url, code): | |
340 | if hasattr(urllib2.addinfourl, 'getcode'): | |
341 | return urllib2.addinfourl(stream, headers, url, code) | |
0f6b00b5 RG |
342 | ret = urllib2.addinfourl(stream, headers, url) |
343 | ret.code = code | |
344 | return ret | |
7b531c0b | 345 | |
1987c232 RG |
346 | def http_request(self, req): |
347 | for h in std_headers: | |
348 | if h in req.headers: | |
349 | del req.headers[h] | |
350 | req.add_header(h, std_headers[h]) | |
351 | if 'Youtubedl-no-compression' in req.headers: | |
352 | if 'Accept-encoding' in req.headers: | |
353 | del req.headers['Accept-encoding'] | |
354 | del req.headers['Youtubedl-no-compression'] | |
355 | return req | |
356 | ||
357 | def http_response(self, req, resp): | |
358 | old_resp = resp | |
359 | # gzip | |
360 | if resp.headers.get('Content-encoding', '') == 'gzip': | |
361 | gz = gzip.GzipFile(fileobj=StringIO.StringIO(resp.read()), mode='r') | |
7b531c0b | 362 | resp = self.addinfourl_wrapper(gz, old_resp.headers, old_resp.url, old_resp.code) |
1987c232 RG |
363 | resp.msg = old_resp.msg |
364 | # deflate | |
365 | if resp.headers.get('Content-encoding', '') == 'deflate': | |
366 | gz = StringIO.StringIO(self.deflate(resp.read())) | |
7b531c0b | 367 | resp = self.addinfourl_wrapper(gz, old_resp.headers, old_resp.url, old_resp.code) |
1987c232 RG |
368 | resp.msg = old_resp.msg |
369 | return resp | |
370 | ||
4fa74b52 RG |
371 | class FileDownloader(object): |
372 | """File Downloader class. | |
373 | ||
374 | File downloader objects are the ones responsible of downloading the | |
375 | actual video file and writing it to disk if the user has requested | |
376 | it, among some other tasks. In most cases there should be one per | |
377 | program. As, given a video URL, the downloader doesn't know how to | |
378 | extract all the needed information, task that InfoExtractors do, it | |
379 | has to pass the URL to one of them. | |
380 | ||
381 | For this, file downloader objects have a method that allows | |
382 | InfoExtractors to be registered in a given order. When it is passed | |
383 | a URL, the file downloader handles it to the first InfoExtractor it | |
2851b2ca RG |
384 | finds that reports being able to handle it. The InfoExtractor extracts |
385 | all the information about the video or videos the URL refers to, and | |
386 | asks the FileDownloader to process the video information, possibly | |
387 | downloading the video. | |
4fa74b52 RG |
388 | |
389 | File downloaders accept a lot of parameters. In order not to saturate | |
390 | the object constructor with arguments, it receives a dictionary of | |
d0a9affb RG |
391 | options instead. These options are available through the params |
392 | attribute for the InfoExtractors to use. The FileDownloader also | |
393 | registers itself as the downloader in charge for the InfoExtractors | |
394 | that are added to it, so this is a "mutual registration". | |
4fa74b52 RG |
395 | |
396 | Available options: | |
397 | ||
80066952 RG |
398 | username: Username for authentication purposes. |
399 | password: Password for authentication purposes. | |
400 | usenetrc: Use netrc for authentication instead. | |
401 | quiet: Do not print messages to stdout. | |
402 | forceurl: Force printing final URL. | |
403 | forcetitle: Force printing title. | |
404 | forcethumbnail: Force printing thumbnail URL. | |
405 | forcedescription: Force printing description. | |
9f796346 | 406 | forcefilename: Force printing final filename. |
80066952 RG |
407 | simulate: Do not download the video files. |
408 | format: Video format code. | |
409 | format_limit: Highest quality format to try. | |
410 | outtmpl: Template for output names. | |
411 | ignoreerrors: Do not stop on download errors. | |
412 | ratelimit: Download speed limit, in bytes/sec. | |
413 | nooverwrites: Prevent overwriting files. | |
414 | retries: Number of times to retry for HTTP error 5xx | |
415 | continuedl: Try to continue downloads if possible. | |
416 | noprogress: Do not print the progress bar. | |
417 | playliststart: Playlist item to start at. | |
8cc44341 | 418 | playlistend: Playlist item to end at. |
331ce0a0 | 419 | logtostderr: Log messages to stderr instead of stdout. |
ccbd296b | 420 | consoletitle: Display progress in console window's titlebar. |
3fb2c487 | 421 | nopart: Do not use temporary .part files. |
e3018902 | 422 | updatetime: Use the Last-modified header to set output file timestamps. |
8b95c387 | 423 | writedescription: Write the video description to a .description file |
6eb08fbf | 424 | writeinfojson: Write the video description to a .info.json file |
4fa74b52 RG |
425 | """ |
426 | ||
d0a9affb | 427 | params = None |
4fa74b52 | 428 | _ies = [] |
65cd34c5 | 429 | _pps = [] |
9bf386d7 | 430 | _download_retcode = None |
7d8d0612 | 431 | _num_downloads = None |
331ce0a0 | 432 | _screen_file = None |
4fa74b52 RG |
433 | |
434 | def __init__(self, params): | |
1c5e2302 | 435 | """Create a FileDownloader object with the given options.""" |
4fa74b52 | 436 | self._ies = [] |
65cd34c5 | 437 | self._pps = [] |
9bf386d7 | 438 | self._download_retcode = 0 |
7d8d0612 | 439 | self._num_downloads = 0 |
331ce0a0 | 440 | self._screen_file = [sys.stdout, sys.stderr][params.get('logtostderr', False)] |
d0a9affb | 441 | self.params = params |
d3975459 | 442 | |
4fa74b52 RG |
443 | @staticmethod |
444 | def pmkdir(filename): | |
445 | """Create directory components in filename. Similar to Unix "mkdir -p".""" | |
446 | components = filename.split(os.sep) | |
447 | aggregate = [os.sep.join(components[0:x]) for x in xrange(1, len(components))] | |
3af1e172 | 448 | aggregate = ['%s%s' % (x, os.sep) for x in aggregate] # Finish names with separator |
4fa74b52 RG |
449 | for dir in aggregate: |
450 | if not os.path.exists(dir): | |
451 | os.mkdir(dir) | |
3fb2c487 | 452 | |
4fa74b52 RG |
453 | @staticmethod |
454 | def format_bytes(bytes): | |
455 | if bytes is None: | |
456 | return 'N/A' | |
8497c36d RG |
457 | if type(bytes) is str: |
458 | bytes = float(bytes) | |
459 | if bytes == 0.0: | |
4fa74b52 RG |
460 | exponent = 0 |
461 | else: | |
8497c36d | 462 | exponent = long(math.log(bytes, 1024.0)) |
4fa74b52 | 463 | suffix = 'bkMGTPEZY'[exponent] |
4fa74b52 RG |
464 | converted = float(bytes) / float(1024**exponent) |
465 | return '%.2f%s' % (converted, suffix) | |
466 | ||
467 | @staticmethod | |
468 | def calc_percent(byte_counter, data_len): | |
469 | if data_len is None: | |
470 | return '---.-%' | |
471 | return '%6s' % ('%3.1f%%' % (float(byte_counter) / float(data_len) * 100.0)) | |
472 | ||
473 | @staticmethod | |
474 | def calc_eta(start, now, total, current): | |
475 | if total is None: | |
476 | return '--:--' | |
477 | dif = now - start | |
478 | if current == 0 or dif < 0.001: # One millisecond | |
479 | return '--:--' | |
480 | rate = float(current) / dif | |
481 | eta = long((float(total) - float(current)) / rate) | |
482 | (eta_mins, eta_secs) = divmod(eta, 60) | |
483 | if eta_mins > 99: | |
484 | return '--:--' | |
485 | return '%02d:%02d' % (eta_mins, eta_secs) | |
486 | ||
5121ef20 | 487 | @staticmethod |
4fa74b52 RG |
488 | def calc_speed(start, now, bytes): |
489 | dif = now - start | |
490 | if bytes == 0 or dif < 0.001: # One millisecond | |
9fcd8355 | 491 | return '%10s' % '---b/s' |
4fa74b52 RG |
492 | return '%10s' % ('%s/s' % FileDownloader.format_bytes(float(bytes) / dif)) |
493 | ||
494 | @staticmethod | |
495 | def best_block_size(elapsed_time, bytes): | |
496 | new_min = max(bytes / 2.0, 1.0) | |
497 | new_max = min(max(bytes * 2.0, 1.0), 4194304) # Do not surpass 4 MB | |
498 | if elapsed_time < 0.001: | |
e1f18b8a | 499 | return long(new_max) |
4fa74b52 RG |
500 | rate = bytes / elapsed_time |
501 | if rate > new_max: | |
e1f18b8a | 502 | return long(new_max) |
4fa74b52 | 503 | if rate < new_min: |
e1f18b8a RG |
504 | return long(new_min) |
505 | return long(rate) | |
4fa74b52 | 506 | |
acd3d842 RG |
507 | @staticmethod |
508 | def parse_bytes(bytestr): | |
509 | """Parse a string indicating a byte quantity into a long integer.""" | |
510 | matchobj = re.match(r'(?i)^(\d+(?:\.\d+)?)([kMGTPEZY]?)$', bytestr) | |
511 | if matchobj is None: | |
512 | return None | |
513 | number = float(matchobj.group(1)) | |
514 | multiplier = 1024.0 ** 'bkmgtpezy'.index(matchobj.group(2).lower()) | |
515 | return long(round(number * multiplier)) | |
516 | ||
4fa74b52 RG |
517 | def add_info_extractor(self, ie): |
518 | """Add an InfoExtractor object to the end of the list.""" | |
519 | self._ies.append(ie) | |
520 | ie.set_downloader(self) | |
d3975459 | 521 | |
65cd34c5 RG |
522 | def add_post_processor(self, pp): |
523 | """Add a PostProcessor object to the end of the chain.""" | |
524 | self._pps.append(pp) | |
525 | pp.set_downloader(self) | |
d3975459 | 526 | |
331ce0a0 | 527 | def to_screen(self, message, skip_eol=False, ignore_encoding_errors=False): |
9fcd8355 | 528 | """Print message to stdout if not in quiet mode.""" |
43ab0ca4 RG |
529 | try: |
530 | if not self.params.get('quiet', False): | |
331ce0a0 RG |
531 | terminator = [u'\n', u''][skip_eol] |
532 | print >>self._screen_file, (u'%s%s' % (message, terminator)).encode(preferredencoding()), | |
533 | self._screen_file.flush() | |
43ab0ca4 RG |
534 | except (UnicodeEncodeError), err: |
535 | if not ignore_encoding_errors: | |
536 | raise | |
d3975459 | 537 | |
7e5cab67 RG |
538 | def to_stderr(self, message): |
539 | """Print message to stderr.""" | |
eae2666c | 540 | print >>sys.stderr, message.encode(preferredencoding()) |
d3975459 | 541 | |
ccbd296b MM |
542 | def to_cons_title(self, message): |
543 | """Set console/terminal window title to message.""" | |
544 | if not self.params.get('consoletitle', False): | |
545 | return | |
546 | if os.name == 'nt' and ctypes.windll.kernel32.GetConsoleWindow(): | |
547 | # c_wchar_p() might not be necessary if `message` is | |
548 | # already of type unicode() | |
549 | ctypes.windll.kernel32.SetConsoleTitleW(ctypes.c_wchar_p(message)) | |
550 | elif 'TERM' in os.environ: | |
551 | sys.stderr.write('\033]0;%s\007' % message.encode(preferredencoding())) | |
552 | ||
22899cea RG |
553 | def fixed_template(self): |
554 | """Checks if the output template is fixed.""" | |
d0a9affb | 555 | return (re.search(ur'(?u)%\(.+?\)s', self.params['outtmpl']) is None) |
9fcd8355 | 556 | |
0086d1ec RG |
557 | def trouble(self, message=None): |
558 | """Determine action to take when a download problem appears. | |
559 | ||
560 | Depending on if the downloader has been configured to ignore | |
e5bf0f55 | 561 | download errors or not, this method may throw an exception or |
9bf386d7 | 562 | not when errors are found, after printing the message. |
0086d1ec RG |
563 | """ |
564 | if message is not None: | |
565 | self.to_stderr(message) | |
d0a9affb | 566 | if not self.params.get('ignoreerrors', False): |
e5bf0f55 | 567 | raise DownloadError(message) |
9bf386d7 | 568 | self._download_retcode = 1 |
0086d1ec | 569 | |
acd3d842 RG |
570 | def slow_down(self, start_time, byte_counter): |
571 | """Sleep if the download speed is over the rate limit.""" | |
d0a9affb | 572 | rate_limit = self.params.get('ratelimit', None) |
acd3d842 RG |
573 | if rate_limit is None or byte_counter == 0: |
574 | return | |
575 | now = time.time() | |
576 | elapsed = now - start_time | |
577 | if elapsed <= 0.0: | |
578 | return | |
579 | speed = float(byte_counter) / elapsed | |
580 | if speed > rate_limit: | |
581 | time.sleep((byte_counter - rate_limit * (now - start_time)) / rate_limit) | |
3fb2c487 RG |
582 | |
583 | def temp_name(self, filename): | |
584 | """Returns a temporary filename for the given filename.""" | |
585 | if self.params.get('nopart', False) or filename == u'-' or \ | |
586 | (os.path.exists(filename) and not os.path.isfile(filename)): | |
587 | return filename | |
588 | return filename + u'.part' | |
589 | ||
8cc42e7c RG |
590 | def undo_temp_name(self, filename): |
591 | if filename.endswith(u'.part'): | |
592 | return filename[:-len(u'.part')] | |
593 | return filename | |
594 | ||
62cf7aaf RG |
595 | def try_rename(self, old_filename, new_filename): |
596 | try: | |
7d950ca1 RG |
597 | if old_filename == new_filename: |
598 | return | |
62cf7aaf RG |
599 | os.rename(old_filename, new_filename) |
600 | except (IOError, OSError), err: | |
601 | self.trouble(u'ERROR: unable to rename file') | |
e3018902 RG |
602 | |
603 | def try_utime(self, filename, last_modified_hdr): | |
604 | """Try to set the last-modified time of the given file.""" | |
605 | if last_modified_hdr is None: | |
606 | return | |
607 | if not os.path.isfile(filename): | |
608 | return | |
609 | timestr = last_modified_hdr | |
610 | if timestr is None: | |
611 | return | |
612 | filetime = timeconvert(timestr) | |
613 | if filetime is None: | |
614 | return | |
615 | try: | |
616 | os.utime(filename,(time.time(), filetime)) | |
617 | except: | |
618 | pass | |
acd3d842 | 619 | |
8b95c387 | 620 | def report_writedescription(self, descfn): |
6eb08fbf PH |
621 | """ Report that the description file is being written """ |
622 | self.to_screen(u'[info] Writing video description to: %s' % descfn, ignore_encoding_errors=True) | |
623 | ||
624 | def report_writeinfojson(self, infofn): | |
625 | """ Report that the metadata file has been written """ | |
626 | self.to_screen(u'[info] Video description metadata as JSON to: %s' % infofn, ignore_encoding_errors=True) | |
8b95c387 | 627 | |
bafa5cd9 RG |
628 | def report_destination(self, filename): |
629 | """Report destination filename.""" | |
331ce0a0 | 630 | self.to_screen(u'[download] Destination: %s' % filename, ignore_encoding_errors=True) |
d3975459 | 631 | |
bafa5cd9 RG |
632 | def report_progress(self, percent_str, data_len_str, speed_str, eta_str): |
633 | """Report download progress.""" | |
d9835247 RG |
634 | if self.params.get('noprogress', False): |
635 | return | |
331ce0a0 | 636 | self.to_screen(u'\r[download] %s of %s at %s ETA %s' % |
bafa5cd9 | 637 | (percent_str, data_len_str, speed_str, eta_str), skip_eol=True) |
ccbd296b MM |
638 | self.to_cons_title(u'youtube-dl - %s of %s at %s ETA %s' % |
639 | (percent_str.strip(), data_len_str.strip(), speed_str.strip(), eta_str.strip())) | |
7db85b2c RG |
640 | |
641 | def report_resuming_byte(self, resume_len): | |
8a9f53be | 642 | """Report attempt to resume at given byte.""" |
331ce0a0 | 643 | self.to_screen(u'[download] Resuming download at byte %s' % resume_len) |
d3975459 | 644 | |
7031008c | 645 | def report_retry(self, count, retries): |
e86e9474 | 646 | """Report retry in case of HTTP error 5xx""" |
331ce0a0 | 647 | self.to_screen(u'[download] Got server HTTP error. Retrying (attempt %d of %d)...' % (count, retries)) |
d3975459 | 648 | |
7db85b2c RG |
649 | def report_file_already_downloaded(self, file_name): |
650 | """Report file has already been fully downloaded.""" | |
43ab0ca4 | 651 | try: |
331ce0a0 | 652 | self.to_screen(u'[download] %s has already been downloaded' % file_name) |
43ab0ca4 | 653 | except (UnicodeEncodeError), err: |
331ce0a0 | 654 | self.to_screen(u'[download] The file has already been downloaded') |
d3975459 | 655 | |
7db85b2c RG |
656 | def report_unable_to_resume(self): |
657 | """Report it was impossible to resume download.""" | |
331ce0a0 | 658 | self.to_screen(u'[download] Unable to resume') |
d3975459 | 659 | |
bafa5cd9 RG |
660 | def report_finish(self): |
661 | """Report download finished.""" | |
d9835247 | 662 | if self.params.get('noprogress', False): |
331ce0a0 | 663 | self.to_screen(u'[download] Download completed') |
d9835247 | 664 | else: |
331ce0a0 | 665 | self.to_screen(u'') |
d3975459 | 666 | |
df372a65 RG |
667 | def increment_downloads(self): |
668 | """Increment the ordinal that assigns a number to each file.""" | |
669 | self._num_downloads += 1 | |
bafa5cd9 | 670 | |
9f796346 GI |
671 | def prepare_filename(self, info_dict): |
672 | """Generate the output filename.""" | |
673 | try: | |
674 | template_dict = dict(info_dict) | |
675 | template_dict['epoch'] = unicode(long(time.time())) | |
676 | template_dict['autonumber'] = unicode('%05d' % self._num_downloads) | |
677 | filename = self.params['outtmpl'] % template_dict | |
678 | return filename | |
679 | except (ValueError, KeyError), err: | |
680 | self.trouble(u'ERROR: invalid system charset or erroneous output template') | |
681 | return None | |
682 | ||
c8619e01 RG |
683 | def process_info(self, info_dict): |
684 | """Process a single dictionary returned by an InfoExtractor.""" | |
9f796346 | 685 | filename = self.prepare_filename(info_dict) |
c8619e01 RG |
686 | # Do nothing else if in simulate mode |
687 | if self.params.get('simulate', False): | |
cbfff4db RG |
688 | # Forced printings |
689 | if self.params.get('forcetitle', False): | |
490fd7ae | 690 | print info_dict['title'].encode(preferredencoding(), 'xmlcharrefreplace') |
cbfff4db | 691 | if self.params.get('forceurl', False): |
490fd7ae | 692 | print info_dict['url'].encode(preferredencoding(), 'xmlcharrefreplace') |
7e58d568 RG |
693 | if self.params.get('forcethumbnail', False) and 'thumbnail' in info_dict: |
694 | print info_dict['thumbnail'].encode(preferredencoding(), 'xmlcharrefreplace') | |
695 | if self.params.get('forcedescription', False) and 'description' in info_dict: | |
696 | print info_dict['description'].encode(preferredencoding(), 'xmlcharrefreplace') | |
9f796346 GI |
697 | if self.params.get('forcefilename', False) and filename is not None: |
698 | print filename.encode(preferredencoding(), 'xmlcharrefreplace') | |
cbfff4db | 699 | |
9bf386d7 | 700 | return |
d3975459 | 701 | |
9f796346 | 702 | if filename is None: |
38ed1344 | 703 | return |
850ab765 | 704 | if self.params.get('nooverwrites', False) and os.path.exists(filename): |
5c44af18 | 705 | self.to_stderr(u'WARNING: file exists and will be skipped') |
9bf386d7 | 706 | return |
7b7759f5 | 707 | |
c8619e01 RG |
708 | try: |
709 | self.pmkdir(filename) | |
710 | except (OSError, IOError), err: | |
db7e31b8 | 711 | self.trouble(u'ERROR: unable to create directories: %s' % str(err)) |
9bf386d7 | 712 | return |
7b7759f5 | 713 | |
8b95c387 PH |
714 | if self.params.get('writedescription', False): |
715 | try: | |
716 | descfn = filename + '.description' | |
6eb08fbf | 717 | self.report_writedescription(descfn) |
1293ce58 PH |
718 | descfile = open(descfn, 'wb') |
719 | try: | |
8b95c387 | 720 | descfile.write(info_dict['description'].encode('utf-8')) |
1293ce58 PH |
721 | finally: |
722 | descfile.close() | |
8b95c387 PH |
723 | except (OSError, IOError): |
724 | self.trouble(u'ERROR: Cannot write description file: %s' % str(descfn)) | |
725 | return | |
726 | ||
6eb08fbf PH |
727 | if self.params.get('writeinfojson', False): |
728 | infofn = filename + '.info.json' | |
729 | self.report_writeinfojson(infofn) | |
730 | try: | |
731 | json.dump | |
732 | except (NameError,AttributeError): | |
733 | self.trouble(u'ERROR: No JSON encoder found. Update to Python 2.6+, setup a json module, or leave out --write-info-json.') | |
734 | return | |
735 | try: | |
1293ce58 PH |
736 | infof = open(infofn, 'wb') |
737 | try: | |
6eb08fbf | 738 | json.dump(info_dict, infof) |
1293ce58 PH |
739 | finally: |
740 | infof.close() | |
6eb08fbf PH |
741 | except (OSError, IOError): |
742 | self.trouble(u'ERROR: Cannot write metadata to JSON file: %s' % str(infofn)) | |
743 | return | |
744 | ||
c8619e01 | 745 | try: |
e616ec0c | 746 | success = self._do_download(filename, info_dict['url'].encode('utf-8'), info_dict.get('player_url', None)) |
c8619e01 | 747 | except (OSError, IOError), err: |
73f4e7af | 748 | raise UnavailableVideoError |
c8619e01 | 749 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: |
db7e31b8 | 750 | self.trouble(u'ERROR: unable to download video data: %s' % str(err)) |
9bf386d7 | 751 | return |
d69a1c91 | 752 | except (ContentTooShortError, ), err: |
db7e31b8 | 753 | self.trouble(u'ERROR: content too short (expected %s bytes and served %s)' % (err.expected, err.downloaded)) |
d69a1c91 | 754 | return |
7b7759f5 | 755 | |
55e7c75e RG |
756 | if success: |
757 | try: | |
758 | self.post_process(filename, info_dict) | |
759 | except (PostProcessingError), err: | |
db7e31b8 | 760 | self.trouble(u'ERROR: postprocessing: %s' % str(err)) |
55e7c75e | 761 | return |
c8619e01 | 762 | |
4fa74b52 RG |
763 | def download(self, url_list): |
764 | """Download a given list of URLs.""" | |
22899cea | 765 | if len(url_list) > 1 and self.fixed_template(): |
d0a9affb | 766 | raise SameFileError(self.params['outtmpl']) |
22899cea | 767 | |
4fa74b52 RG |
768 | for url in url_list: |
769 | suitable_found = False | |
770 | for ie in self._ies: | |
c8619e01 | 771 | # Go to next InfoExtractor if not suitable |
4fa74b52 RG |
772 | if not ie.suitable(url): |
773 | continue | |
c8619e01 | 774 | |
4fa74b52 RG |
775 | # Suitable InfoExtractor found |
776 | suitable_found = True | |
c8619e01 | 777 | |
6f21f686 RG |
778 | # Extract information from URL and process it |
779 | ie.extract(url) | |
65cd34c5 | 780 | |
c8619e01 | 781 | # Suitable InfoExtractor had been found; go to next URL |
4fa74b52 | 782 | break |
c8619e01 | 783 | |
4fa74b52 | 784 | if not suitable_found: |
db7e31b8 | 785 | self.trouble(u'ERROR: no suitable InfoExtractor: %s' % url) |
bb681b88 | 786 | |
9bf386d7 | 787 | return self._download_retcode |
65cd34c5 RG |
788 | |
789 | def post_process(self, filename, ie_info): | |
790 | """Run the postprocessing chain on the given file.""" | |
791 | info = dict(ie_info) | |
792 | info['filepath'] = filename | |
793 | for pp in self._pps: | |
794 | info = pp.run(info) | |
795 | if info is None: | |
796 | break | |
d3975459 | 797 | |
e616ec0c | 798 | def _download_with_rtmpdump(self, filename, url, player_url): |
0487b407 | 799 | self.report_destination(filename) |
62cf7aaf | 800 | tmpfilename = self.temp_name(filename) |
0487b407 RG |
801 | |
802 | # Check for rtmpdump first | |
803 | try: | |
804 | subprocess.call(['rtmpdump', '-h'], stdout=(file(os.path.devnull, 'w')), stderr=subprocess.STDOUT) | |
805 | except (OSError, IOError): | |
806 | self.trouble(u'ERROR: RTMP download detected but "rtmpdump" could not be run') | |
807 | return False | |
808 | ||
809 | # Download using rtmpdump. rtmpdump returns exit code 2 when | |
810 | # the connection was interrumpted and resuming appears to be | |
811 | # possible. This is part of rtmpdump's normal usage, AFAIK. | |
62cf7aaf | 812 | basic_args = ['rtmpdump', '-q'] + [[], ['-W', player_url]][player_url is not None] + ['-r', url, '-o', tmpfilename] |
1c1821f8 RG |
813 | retval = subprocess.call(basic_args + [[], ['-e', '-k', '1']][self.params.get('continuedl', False)]) |
814 | while retval == 2 or retval == 1: | |
62cf7aaf | 815 | prevsize = os.path.getsize(tmpfilename) |
331ce0a0 | 816 | self.to_screen(u'\r[rtmpdump] %s bytes' % prevsize, skip_eol=True) |
e616ec0c | 817 | time.sleep(5.0) # This seems to be needed |
1c1821f8 | 818 | retval = subprocess.call(basic_args + ['-e'] + [[], ['-k', '1']][retval == 1]) |
62cf7aaf | 819 | cursize = os.path.getsize(tmpfilename) |
e616ec0c RG |
820 | if prevsize == cursize and retval == 1: |
821 | break | |
0487b407 | 822 | if retval == 0: |
62cf7aaf RG |
823 | self.to_screen(u'\r[rtmpdump] %s bytes' % os.path.getsize(tmpfilename)) |
824 | self.try_rename(tmpfilename, filename) | |
0487b407 RG |
825 | return True |
826 | else: | |
db7e31b8 | 827 | self.trouble(u'\nERROR: rtmpdump exited with code %d' % retval) |
0487b407 RG |
828 | return False |
829 | ||
e616ec0c | 830 | def _do_download(self, filename, url, player_url): |
62cf7aaf | 831 | # Check file already present |
3fb2c487 | 832 | if self.params.get('continuedl', False) and os.path.isfile(filename) and not self.params.get('nopart', False): |
62cf7aaf RG |
833 | self.report_file_already_downloaded(filename) |
834 | return True | |
835 | ||
0487b407 RG |
836 | # Attempt to download using rtmpdump |
837 | if url.startswith('rtmp'): | |
e616ec0c | 838 | return self._download_with_rtmpdump(filename, url, player_url) |
0487b407 | 839 | |
62cf7aaf | 840 | tmpfilename = self.temp_name(filename) |
55e7c75e | 841 | stream = None |
9c457d2a | 842 | open_mode = 'wb' |
1987c232 RG |
843 | |
844 | # Do not include the Accept-Encoding header | |
845 | headers = {'Youtubedl-no-compression': 'True'} | |
846 | basic_request = urllib2.Request(url, None, headers) | |
847 | request = urllib2.Request(url, None, headers) | |
7db85b2c | 848 | |
9c457d2a | 849 | # Establish possible resume length |
62cf7aaf RG |
850 | if os.path.isfile(tmpfilename): |
851 | resume_len = os.path.getsize(tmpfilename) | |
55e7c75e RG |
852 | else: |
853 | resume_len = 0 | |
9c457d2a RG |
854 | |
855 | # Request parameters in case of being able to resume | |
850ab765 | 856 | if self.params.get('continuedl', False) and resume_len != 0: |
7db85b2c RG |
857 | self.report_resuming_byte(resume_len) |
858 | request.add_header('Range','bytes=%d-' % resume_len) | |
9c457d2a | 859 | open_mode = 'ab' |
55e7c75e | 860 | |
7031008c RG |
861 | count = 0 |
862 | retries = self.params.get('retries', 0) | |
101e0d1e | 863 | while count <= retries: |
7031008c RG |
864 | # Establish connection |
865 | try: | |
866 | data = urllib2.urlopen(request) | |
867 | break | |
868 | except (urllib2.HTTPError, ), err: | |
ac249f42 | 869 | if (err.code < 500 or err.code >= 600) and err.code != 416: |
101e0d1e | 870 | # Unexpected HTTP error |
7031008c | 871 | raise |
101e0d1e RG |
872 | elif err.code == 416: |
873 | # Unable to resume (requested range not satisfiable) | |
874 | try: | |
875 | # Open the connection again without the range header | |
876 | data = urllib2.urlopen(basic_request) | |
877 | content_length = data.info()['Content-Length'] | |
878 | except (urllib2.HTTPError, ), err: | |
ac249f42 | 879 | if err.code < 500 or err.code >= 600: |
101e0d1e RG |
880 | raise |
881 | else: | |
882 | # Examine the reported length | |
268fb2bd | 883 | if (content_length is not None and |
7a9054ec | 884 | (resume_len - 100 < long(content_length) < resume_len + 100)): |
268fb2bd RG |
885 | # The file had already been fully downloaded. |
886 | # Explanation to the above condition: in issue #175 it was revealed that | |
887 | # YouTube sometimes adds or removes a few bytes from the end of the file, | |
888 | # changing the file size slightly and causing problems for some users. So | |
889 | # I decided to implement a suggested change and consider the file | |
890 | # completely downloaded if the file size differs less than 100 bytes from | |
891 | # the one in the hard drive. | |
101e0d1e | 892 | self.report_file_already_downloaded(filename) |
62cf7aaf | 893 | self.try_rename(tmpfilename, filename) |
101e0d1e RG |
894 | return True |
895 | else: | |
896 | # The length does not match, we start the download over | |
897 | self.report_unable_to_resume() | |
898 | open_mode = 'wb' | |
899 | break | |
900 | # Retry | |
901 | count += 1 | |
902 | if count <= retries: | |
903 | self.report_retry(count, retries) | |
904 | ||
905 | if count > retries: | |
906 | self.trouble(u'ERROR: giving up after %s retries' % retries) | |
907 | return False | |
7db85b2c | 908 | |
4fa74b52 | 909 | data_len = data.info().get('Content-length', None) |
106d091e RG |
910 | if data_len is not None: |
911 | data_len = long(data_len) + resume_len | |
4fa74b52 | 912 | data_len_str = self.format_bytes(data_len) |
106d091e | 913 | byte_counter = 0 + resume_len |
4fa74b52 RG |
914 | block_size = 1024 |
915 | start = time.time() | |
916 | while True: | |
bafa5cd9 | 917 | # Download and write |
4fa74b52 RG |
918 | before = time.time() |
919 | data_block = data.read(block_size) | |
920 | after = time.time() | |
975a91d0 | 921 | if len(data_block) == 0: |
4fa74b52 | 922 | break |
975a91d0 | 923 | byte_counter += len(data_block) |
55e7c75e RG |
924 | |
925 | # Open file just in time | |
926 | if stream is None: | |
927 | try: | |
62cf7aaf | 928 | (stream, tmpfilename) = sanitize_open(tmpfilename, open_mode) |
8cc42e7c | 929 | filename = self.undo_temp_name(tmpfilename) |
55e7c75e RG |
930 | self.report_destination(filename) |
931 | except (OSError, IOError), err: | |
db7e31b8 | 932 | self.trouble(u'ERROR: unable to open for writing: %s' % str(err)) |
55e7c75e | 933 | return False |
131efd1a RG |
934 | try: |
935 | stream.write(data_block) | |
936 | except (IOError, OSError), err: | |
d67e0974 RG |
937 | self.trouble(u'\nERROR: unable to write data: %s' % str(err)) |
938 | return False | |
975a91d0 | 939 | block_size = self.best_block_size(after - before, len(data_block)) |
4fa74b52 | 940 | |
55e7c75e RG |
941 | # Progress message |
942 | percent_str = self.calc_percent(byte_counter, data_len) | |
975a91d0 RG |
943 | eta_str = self.calc_eta(start, time.time(), data_len - resume_len, byte_counter - resume_len) |
944 | speed_str = self.calc_speed(start, time.time(), byte_counter - resume_len) | |
55e7c75e RG |
945 | self.report_progress(percent_str, data_len_str, speed_str, eta_str) |
946 | ||
acd3d842 | 947 | # Apply rate limit |
975a91d0 | 948 | self.slow_down(start, byte_counter - resume_len) |
acd3d842 | 949 | |
6f0ff3ba | 950 | stream.close() |
bafa5cd9 | 951 | self.report_finish() |
b905e5f5 | 952 | if data_len is not None and byte_counter != data_len: |
d69a1c91 | 953 | raise ContentTooShortError(byte_counter, long(data_len)) |
62cf7aaf | 954 | self.try_rename(tmpfilename, filename) |
e3018902 | 955 | |
09bd408c | 956 | # Update file modification time |
e3018902 RG |
957 | if self.params.get('updatetime', True): |
958 | self.try_utime(filename, data.info().get('last-modified', None)) | |
959 | ||
55e7c75e | 960 | return True |
4fa74b52 RG |
961 | |
962 | class InfoExtractor(object): | |
963 | """Information Extractor class. | |
964 | ||
965 | Information extractors are the classes that, given a URL, extract | |
966 | information from the video (or videos) the URL refers to. This | |
967 | information includes the real video URL, the video title and simplified | |
2851b2ca RG |
968 | title, author and others. The information is stored in a dictionary |
969 | which is then passed to the FileDownloader. The FileDownloader | |
970 | processes this information possibly downloading the video to the file | |
971 | system, among other possible outcomes. The dictionaries must include | |
4fa74b52 RG |
972 | the following fields: |
973 | ||
974 | id: Video identifier. | |
975 | url: Final video URL. | |
976 | uploader: Nickname of the video uploader. | |
977 | title: Literal title. | |
978 | stitle: Simplified title. | |
979 | ext: Video filename extension. | |
6ba562b0 | 980 | format: Video format. |
e616ec0c | 981 | player_url: SWF Player URL (may be None). |
4fa74b52 | 982 | |
7e58d568 RG |
983 | The following fields are optional. Their primary purpose is to allow |
984 | youtube-dl to serve as the backend for a video search function, such | |
985 | as the one in youtube2mp3. They are only used when their respective | |
986 | forced printing functions are called: | |
987 | ||
988 | thumbnail: Full URL to a video thumbnail image. | |
989 | description: One-line video description. | |
990 | ||
4fa74b52 RG |
991 | Subclasses of this one should re-define the _real_initialize() and |
992 | _real_extract() methods, as well as the suitable() static method. | |
993 | Probably, they should also be instantiated and added to the main | |
994 | downloader. | |
995 | """ | |
996 | ||
997 | _ready = False | |
998 | _downloader = None | |
999 | ||
1000 | def __init__(self, downloader=None): | |
1001 | """Constructor. Receives an optional downloader.""" | |
1002 | self._ready = False | |
1003 | self.set_downloader(downloader) | |
1004 | ||
1005 | @staticmethod | |
1006 | def suitable(url): | |
1007 | """Receives a URL and returns True if suitable for this IE.""" | |
020f7150 | 1008 | return False |
4fa74b52 RG |
1009 | |
1010 | def initialize(self): | |
1c5e2302 | 1011 | """Initializes an instance (authentication, etc).""" |
4fa74b52 RG |
1012 | if not self._ready: |
1013 | self._real_initialize() | |
1014 | self._ready = True | |
1015 | ||
1016 | def extract(self, url): | |
1017 | """Extracts URL information and returns it in list of dicts.""" | |
1018 | self.initialize() | |
1019 | return self._real_extract(url) | |
1020 | ||
1021 | def set_downloader(self, downloader): | |
1022 | """Sets the downloader for this IE.""" | |
1023 | self._downloader = downloader | |
d3975459 | 1024 | |
4fa74b52 RG |
1025 | def _real_initialize(self): |
1026 | """Real initialization process. Redefine in subclasses.""" | |
1027 | pass | |
1028 | ||
1029 | def _real_extract(self, url): | |
1030 | """Real extraction process. Redefine in subclasses.""" | |
1031 | pass | |
1032 | ||
1033 | class YoutubeIE(InfoExtractor): | |
1034 | """Information extractor for youtube.com.""" | |
1035 | ||
86e709d3 | 1036 | _VALID_URL = r'^((?:https?://)?(?:youtu\.be/|(?:\w+\.)?youtube(?:-nocookie)?\.com/)(?:(?:(?:v|embed|e)/)|(?:(?:watch(?:_popup)?(?:\.php)?)?(?:\?|#!?)(?:.+&)?v=))?)?([0-9A-Za-z_-]+)(?(1).+)?$' |
9715661c | 1037 | _LANG_URL = r'http://www.youtube.com/?hl=en&persist_hl=1&gl=US&persist_gl=1&opt_out_ackd=1' |
7df4635f | 1038 | _LOGIN_URL = 'https://www.youtube.com/signup?next=/&gl=US&hl=en' |
72ac78b8 | 1039 | _AGE_URL = 'http://www.youtube.com/verify_age?next_url=/&gl=US&hl=en' |
4fa74b52 | 1040 | _NETRC_MACHINE = 'youtube' |
497cd3e6 RG |
1041 | # Listed in order of quality |
1042 | _available_formats = ['38', '37', '22', '45', '35', '34', '43', '18', '6', '5', '17', '13'] | |
7b7759f5 | 1043 | _video_extensions = { |
1044 | '13': '3gp', | |
1045 | '17': 'mp4', | |
1046 | '18': 'mp4', | |
1047 | '22': 'mp4', | |
d9bc015b | 1048 | '37': 'mp4', |
9e9647d9 | 1049 | '38': 'video', # You actually don't know if this will be MOV, AVI or whatever |
0b59bf4a RG |
1050 | '43': 'webm', |
1051 | '45': 'webm', | |
7b7759f5 | 1052 | } |
4fa74b52 | 1053 | |
020f7150 RG |
1054 | @staticmethod |
1055 | def suitable(url): | |
1056 | return (re.match(YoutubeIE._VALID_URL, url) is not None) | |
1057 | ||
72ac78b8 RG |
1058 | def report_lang(self): |
1059 | """Report attempt to set language.""" | |
331ce0a0 | 1060 | self._downloader.to_screen(u'[youtube] Setting language') |
72ac78b8 | 1061 | |
bafa5cd9 RG |
1062 | def report_login(self): |
1063 | """Report attempt to log in.""" | |
331ce0a0 | 1064 | self._downloader.to_screen(u'[youtube] Logging in') |
d3975459 | 1065 | |
bafa5cd9 RG |
1066 | def report_age_confirmation(self): |
1067 | """Report attempt to confirm age.""" | |
331ce0a0 | 1068 | self._downloader.to_screen(u'[youtube] Confirming age') |
d3975459 | 1069 | |
e616ec0c RG |
1070 | def report_video_webpage_download(self, video_id): |
1071 | """Report attempt to download video webpage.""" | |
331ce0a0 | 1072 | self._downloader.to_screen(u'[youtube] %s: Downloading video webpage' % video_id) |
d3975459 | 1073 | |
71b7300e RG |
1074 | def report_video_info_webpage_download(self, video_id): |
1075 | """Report attempt to download video info webpage.""" | |
331ce0a0 | 1076 | self._downloader.to_screen(u'[youtube] %s: Downloading video info webpage' % video_id) |
d3975459 | 1077 | |
bafa5cd9 RG |
1078 | def report_information_extraction(self, video_id): |
1079 | """Report attempt to extract video information.""" | |
331ce0a0 | 1080 | self._downloader.to_screen(u'[youtube] %s: Extracting video information' % video_id) |
d3975459 | 1081 | |
7b7759f5 | 1082 | def report_unavailable_format(self, video_id, format): |
1083 | """Report extracted video URL.""" | |
331ce0a0 | 1084 | self._downloader.to_screen(u'[youtube] %s: Format %s not available' % (video_id, format)) |
d3975459 | 1085 | |
0487b407 RG |
1086 | def report_rtmp_download(self): |
1087 | """Indicate the download will use the RTMP protocol.""" | |
331ce0a0 | 1088 | self._downloader.to_screen(u'[youtube] RTMP download detected') |
d3975459 | 1089 | |
4fa74b52 RG |
1090 | def _real_initialize(self): |
1091 | if self._downloader is None: | |
1092 | return | |
1093 | ||
1094 | username = None | |
1095 | password = None | |
d0a9affb | 1096 | downloader_params = self._downloader.params |
4fa74b52 RG |
1097 | |
1098 | # Attempt to use provided username and password or .netrc data | |
1099 | if downloader_params.get('username', None) is not None: | |
1100 | username = downloader_params['username'] | |
1101 | password = downloader_params['password'] | |
1102 | elif downloader_params.get('usenetrc', False): | |
1103 | try: | |
1104 | info = netrc.netrc().authenticators(self._NETRC_MACHINE) | |
1105 | if info is not None: | |
1106 | username = info[0] | |
1107 | password = info[2] | |
1108 | else: | |
1109 | raise netrc.NetrcParseError('No authenticators for %s' % self._NETRC_MACHINE) | |
1110 | except (IOError, netrc.NetrcParseError), err: | |
6f21f686 | 1111 | self._downloader.to_stderr(u'WARNING: parsing .netrc: %s' % str(err)) |
4fa74b52 RG |
1112 | return |
1113 | ||
72ac78b8 | 1114 | # Set language |
1987c232 | 1115 | request = urllib2.Request(self._LANG_URL) |
72ac78b8 RG |
1116 | try: |
1117 | self.report_lang() | |
1118 | urllib2.urlopen(request).read() | |
1119 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
6f21f686 | 1120 | self._downloader.to_stderr(u'WARNING: unable to set language: %s' % str(err)) |
72ac78b8 RG |
1121 | return |
1122 | ||
cc109403 RG |
1123 | # No authentication to be performed |
1124 | if username is None: | |
1125 | return | |
1126 | ||
4fa74b52 | 1127 | # Log in |
9fcd8355 RG |
1128 | login_form = { |
1129 | 'current_form': 'loginForm', | |
4fa74b52 RG |
1130 | 'next': '/', |
1131 | 'action_login': 'Log In', | |
1132 | 'username': username, | |
9fcd8355 RG |
1133 | 'password': password, |
1134 | } | |
1987c232 | 1135 | request = urllib2.Request(self._LOGIN_URL, urllib.urlencode(login_form)) |
4fa74b52 | 1136 | try: |
bafa5cd9 | 1137 | self.report_login() |
4fa74b52 RG |
1138 | login_results = urllib2.urlopen(request).read() |
1139 | if re.search(r'(?i)<form[^>]* name="loginForm"', login_results) is not None: | |
6f21f686 | 1140 | self._downloader.to_stderr(u'WARNING: unable to log in: bad username or password') |
4fa74b52 RG |
1141 | return |
1142 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
6f21f686 | 1143 | self._downloader.to_stderr(u'WARNING: unable to log in: %s' % str(err)) |
4fa74b52 | 1144 | return |
d3975459 | 1145 | |
4fa74b52 | 1146 | # Confirm age |
9fcd8355 RG |
1147 | age_form = { |
1148 | 'next_url': '/', | |
1149 | 'action_confirm': 'Confirm', | |
1150 | } | |
1987c232 | 1151 | request = urllib2.Request(self._AGE_URL, urllib.urlencode(age_form)) |
4fa74b52 | 1152 | try: |
bafa5cd9 | 1153 | self.report_age_confirmation() |
4fa74b52 RG |
1154 | age_results = urllib2.urlopen(request).read() |
1155 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
147753eb | 1156 | self._downloader.trouble(u'ERROR: unable to confirm age: %s' % str(err)) |
e5bf0f55 | 1157 | return |
4fa74b52 RG |
1158 | |
1159 | def _real_extract(self, url): | |
1160 | # Extract video id from URL | |
020f7150 | 1161 | mobj = re.match(self._VALID_URL, url) |
4fa74b52 | 1162 | if mobj is None: |
147753eb | 1163 | self._downloader.trouble(u'ERROR: invalid URL: %s' % url) |
6f21f686 | 1164 | return |
4fa74b52 RG |
1165 | video_id = mobj.group(2) |
1166 | ||
497cd3e6 RG |
1167 | # Get video webpage |
1168 | self.report_video_webpage_download(video_id) | |
1987c232 | 1169 | request = urllib2.Request('http://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1' % video_id) |
497cd3e6 RG |
1170 | try: |
1171 | video_webpage = urllib2.urlopen(request).read() | |
1172 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
1173 | self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % str(err)) | |
1174 | return | |
968aa884 | 1175 | |
497cd3e6 | 1176 | # Attempt to extract SWF player URL |
b620a5f8 | 1177 | mobj = re.search(r'swfConfig.*?"(http:\\/\\/.*?watch.*?-.*?\.swf)"', video_webpage) |
497cd3e6 | 1178 | if mobj is not None: |
b620a5f8 | 1179 | player_url = re.sub(r'\\(.)', r'\1', mobj.group(1)) |
497cd3e6 RG |
1180 | else: |
1181 | player_url = None | |
1182 | ||
1183 | # Get video info | |
1184 | self.report_video_info_webpage_download(video_id) | |
1185 | for el_type in ['&el=embedded', '&el=detailpage', '&el=vevo', '']: | |
1186 | video_info_url = ('http://www.youtube.com/get_video_info?&video_id=%s%s&ps=default&eurl=&gl=US&hl=en' | |
1187 | % (video_id, el_type)) | |
1987c232 | 1188 | request = urllib2.Request(video_info_url) |
e616ec0c | 1189 | try: |
497cd3e6 RG |
1190 | video_info_webpage = urllib2.urlopen(request).read() |
1191 | video_info = parse_qs(video_info_webpage) | |
1192 | if 'token' in video_info: | |
1193 | break | |
e616ec0c | 1194 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: |
497cd3e6 | 1195 | self._downloader.trouble(u'ERROR: unable to download video info webpage: %s' % str(err)) |
e616ec0c | 1196 | return |
f95f29fd RG |
1197 | if 'token' not in video_info: |
1198 | if 'reason' in video_info: | |
8e686771 | 1199 | self._downloader.trouble(u'ERROR: YouTube said: %s' % video_info['reason'][0].decode('utf-8')) |
f95f29fd RG |
1200 | else: |
1201 | self._downloader.trouble(u'ERROR: "token" parameter not in video info for unknown reason') | |
1202 | return | |
1203 | ||
1204 | # Start extracting information | |
497cd3e6 RG |
1205 | self.report_information_extraction(video_id) |
1206 | ||
1207 | # uploader | |
1208 | if 'author' not in video_info: | |
1209 | self._downloader.trouble(u'ERROR: unable to extract uploader nickname') | |
1210 | return | |
1211 | video_uploader = urllib.unquote_plus(video_info['author'][0]) | |
e616ec0c | 1212 | |
497cd3e6 RG |
1213 | # title |
1214 | if 'title' not in video_info: | |
1215 | self._downloader.trouble(u'ERROR: unable to extract video title') | |
1216 | return | |
1217 | video_title = urllib.unquote_plus(video_info['title'][0]) | |
1218 | video_title = video_title.decode('utf-8') | |
1219 | video_title = sanitize_title(video_title) | |
1220 | ||
1221 | # simplified title | |
1222 | simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title) | |
1223 | simple_title = simple_title.strip(ur'_') | |
1224 | ||
1225 | # thumbnail image | |
1226 | if 'thumbnail_url' not in video_info: | |
1227 | self._downloader.trouble(u'WARNING: unable to extract video thumbnail') | |
1228 | video_thumbnail = '' | |
1229 | else: # don't panic if we can't find it | |
1230 | video_thumbnail = urllib.unquote_plus(video_info['thumbnail_url'][0]) | |
1231 | ||
b3a27b52 NA |
1232 | # upload date |
1233 | upload_date = u'NA' | |
3efa45c3 | 1234 | mobj = re.search(r'id="eow-date.*?>(.*?)</span>', video_webpage, re.DOTALL) |
b3a27b52 | 1235 | if mobj is not None: |
a1f03c7b | 1236 | upload_date = ' '.join(re.sub(r'[/,-]', r' ', mobj.group(1)).split()) |
87cbd213 | 1237 | format_expressions = ['%d %B %Y', '%B %d %Y', '%b %d %Y'] |
a1f03c7b NA |
1238 | for expression in format_expressions: |
1239 | try: | |
1240 | upload_date = datetime.datetime.strptime(upload_date, expression).strftime('%Y%m%d') | |
1241 | except: | |
1242 | pass | |
b3a27b52 | 1243 | |
497cd3e6 | 1244 | # description |
c6b55a8d PH |
1245 | try: |
1246 | lxml.etree | |
1247 | except NameError: | |
1248 | video_description = u'No description available.' | |
8b95c387 | 1249 | if self._downloader.params.get('forcedescription', False) or self._downloader.params.get('writedescription', False): |
c6b55a8d PH |
1250 | mobj = re.search(r'<meta name="description" content="(.*)"(?:\s*/)?>', video_webpage) |
1251 | if mobj is not None: | |
1252 | video_description = mobj.group(1).decode('utf-8') | |
1253 | else: | |
1254 | html_parser = lxml.etree.HTMLParser(encoding='utf-8') | |
1255 | vwebpage_doc = lxml.etree.parse(StringIO.StringIO(video_webpage), html_parser) | |
1256 | video_description = u''.join(vwebpage_doc.xpath('id("eow-description")//text()')) | |
91e6a385 | 1257 | # TODO use another parser |
497cd3e6 | 1258 | |
5ce7d172 RG |
1259 | # token |
1260 | video_token = urllib.unquote_plus(video_info['token'][0]) | |
1261 | ||
497cd3e6 | 1262 | # Decide which formats to download |
f83ae781 | 1263 | req_format = self._downloader.params.get('format', None) |
2e3a32e4 | 1264 | |
f137bef9 PH |
1265 | if 'conn' in video_info and video_info['conn'][0].startswith('rtmp'): |
1266 | self.report_rtmp_download() | |
1267 | video_url_list = [(None, video_info['conn'][0])] | |
f137bef9 | 1268 | elif 'url_encoded_fmt_stream_map' in video_info and len(video_info['url_encoded_fmt_stream_map']) >= 1: |
0ac22e4f | 1269 | url_data_strs = video_info['url_encoded_fmt_stream_map'][0].split(',') |
8519c32d | 1270 | url_data = [parse_qs(uds) for uds in url_data_strs] |
f137bef9 | 1271 | url_data = filter(lambda ud: 'itag' in ud and 'url' in ud, url_data) |
8519c32d | 1272 | url_map = dict((ud['itag'][0], ud['url'][0]) for ud in url_data) |
2b70537d | 1273 | |
497cd3e6 RG |
1274 | format_limit = self._downloader.params.get('format_limit', None) |
1275 | if format_limit is not None and format_limit in self._available_formats: | |
1276 | format_list = self._available_formats[self._available_formats.index(format_limit):] | |
e616ec0c | 1277 | else: |
497cd3e6 RG |
1278 | format_list = self._available_formats |
1279 | existing_formats = [x for x in format_list if x in url_map] | |
1280 | if len(existing_formats) == 0: | |
1281 | self._downloader.trouble(u'ERROR: no known formats available for video') | |
968aa884 | 1282 | return |
f83ae781 | 1283 | if req_format is None: |
d157d259 | 1284 | video_url_list = [(existing_formats[0], url_map[existing_formats[0]])] # Best quality |
f83ae781 | 1285 | elif req_format == '-1': |
d157d259 | 1286 | video_url_list = [(f, url_map[f]) for f in existing_formats] # All formats |
497cd3e6 | 1287 | else: |
5c132793 RG |
1288 | # Specific format |
1289 | if req_format not in url_map: | |
1290 | self._downloader.trouble(u'ERROR: requested format not available') | |
1291 | return | |
1292 | video_url_list = [(req_format, url_map[req_format])] # Specific format | |
497cd3e6 | 1293 | else: |
f3dc18d8 | 1294 | self._downloader.trouble(u'ERROR: no conn or url_encoded_fmt_stream_map information found in video info') |
497cd3e6 | 1295 | return |
7b7759f5 | 1296 | |
497cd3e6 RG |
1297 | for format_param, video_real_url in video_url_list: |
1298 | # At this point we have a new video | |
1299 | self._downloader.increment_downloads() | |
1300 | ||
1301 | # Extension | |
1302 | video_extension = self._video_extensions.get(format_param, 'flv') | |
7e58d568 | 1303 | |
968aa884 | 1304 | try: |
7b7759f5 | 1305 | # Process video information |
1306 | self._downloader.process_info({ | |
1307 | 'id': video_id.decode('utf-8'), | |
1308 | 'url': video_real_url.decode('utf-8'), | |
1309 | 'uploader': video_uploader.decode('utf-8'), | |
138b11f3 | 1310 | 'upload_date': upload_date, |
7b7759f5 | 1311 | 'title': video_title, |
1312 | 'stitle': simple_title, | |
1313 | 'ext': video_extension.decode('utf-8'), | |
6ba562b0 | 1314 | 'format': (format_param is None and u'NA' or format_param.decode('utf-8')), |
7e58d568 | 1315 | 'thumbnail': video_thumbnail.decode('utf-8'), |
c6b55a8d | 1316 | 'description': video_description, |
e616ec0c | 1317 | 'player_url': player_url, |
7b7759f5 | 1318 | }) |
497cd3e6 | 1319 | except UnavailableVideoError, err: |
09cc744c | 1320 | self._downloader.trouble(u'\nERROR: unable to download video') |
42bcd27d | 1321 | |
4fa74b52 | 1322 | |
020f7150 RG |
1323 | class MetacafeIE(InfoExtractor): |
1324 | """Information Extractor for metacafe.com.""" | |
1325 | ||
1326 | _VALID_URL = r'(?:http://)?(?:www\.)?metacafe\.com/watch/([^/]+)/([^/]+)/.*' | |
2546e767 | 1327 | _DISCLAIMER = 'http://www.metacafe.com/family_filter/' |
dbccb6cd | 1328 | _FILTER_POST = 'http://www.metacafe.com/f/index.php?inputType=filter&controllerGroup=user' |
020f7150 RG |
1329 | _youtube_ie = None |
1330 | ||
1331 | def __init__(self, youtube_ie, downloader=None): | |
1332 | InfoExtractor.__init__(self, downloader) | |
1333 | self._youtube_ie = youtube_ie | |
1334 | ||
1335 | @staticmethod | |
1336 | def suitable(url): | |
1337 | return (re.match(MetacafeIE._VALID_URL, url) is not None) | |
1338 | ||
1339 | def report_disclaimer(self): | |
1340 | """Report disclaimer retrieval.""" | |
331ce0a0 | 1341 | self._downloader.to_screen(u'[metacafe] Retrieving disclaimer') |
020f7150 RG |
1342 | |
1343 | def report_age_confirmation(self): | |
1344 | """Report attempt to confirm age.""" | |
331ce0a0 | 1345 | self._downloader.to_screen(u'[metacafe] Confirming age') |
d3975459 | 1346 | |
020f7150 RG |
1347 | def report_download_webpage(self, video_id): |
1348 | """Report webpage download.""" | |
331ce0a0 | 1349 | self._downloader.to_screen(u'[metacafe] %s: Downloading webpage' % video_id) |
d3975459 | 1350 | |
020f7150 RG |
1351 | def report_extraction(self, video_id): |
1352 | """Report information extraction.""" | |
331ce0a0 | 1353 | self._downloader.to_screen(u'[metacafe] %s: Extracting information' % video_id) |
020f7150 RG |
1354 | |
1355 | def _real_initialize(self): | |
1356 | # Retrieve disclaimer | |
1987c232 | 1357 | request = urllib2.Request(self._DISCLAIMER) |
020f7150 RG |
1358 | try: |
1359 | self.report_disclaimer() | |
1360 | disclaimer = urllib2.urlopen(request).read() | |
1361 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
147753eb | 1362 | self._downloader.trouble(u'ERROR: unable to retrieve disclaimer: %s' % str(err)) |
020f7150 RG |
1363 | return |
1364 | ||
1365 | # Confirm age | |
1366 | disclaimer_form = { | |
2546e767 | 1367 | 'filters': '0', |
020f7150 RG |
1368 | 'submit': "Continue - I'm over 18", |
1369 | } | |
1987c232 | 1370 | request = urllib2.Request(self._FILTER_POST, urllib.urlencode(disclaimer_form)) |
020f7150 RG |
1371 | try: |
1372 | self.report_age_confirmation() | |
1373 | disclaimer = urllib2.urlopen(request).read() | |
1374 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
147753eb | 1375 | self._downloader.trouble(u'ERROR: unable to confirm age: %s' % str(err)) |
020f7150 | 1376 | return |
d3975459 | 1377 | |
020f7150 RG |
1378 | def _real_extract(self, url): |
1379 | # Extract id and simplified title from URL | |
1380 | mobj = re.match(self._VALID_URL, url) | |
1381 | if mobj is None: | |
147753eb | 1382 | self._downloader.trouble(u'ERROR: invalid URL: %s' % url) |
6f21f686 | 1383 | return |
020f7150 RG |
1384 | |
1385 | video_id = mobj.group(1) | |
1386 | ||
1387 | # Check if video comes from YouTube | |
1388 | mobj2 = re.match(r'^yt-(.*)$', video_id) | |
1389 | if mobj2 is not None: | |
6f21f686 RG |
1390 | self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % mobj2.group(1)) |
1391 | return | |
020f7150 | 1392 | |
df372a65 | 1393 | # At this point we have a new video |
9bf7fa52 | 1394 | self._downloader.increment_downloads() |
df372a65 | 1395 | |
020f7150 | 1396 | simple_title = mobj.group(2).decode('utf-8') |
020f7150 RG |
1397 | |
1398 | # Retrieve video webpage to extract further information | |
1399 | request = urllib2.Request('http://www.metacafe.com/watch/%s/' % video_id) | |
1400 | try: | |
1401 | self.report_download_webpage(video_id) | |
1402 | webpage = urllib2.urlopen(request).read() | |
1403 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
147753eb | 1404 | self._downloader.trouble(u'ERROR: unable retrieve video webpage: %s' % str(err)) |
6f21f686 | 1405 | return |
020f7150 RG |
1406 | |
1407 | # Extract URL, uploader and title from webpage | |
1408 | self.report_extraction(video_id) | |
18963a36 | 1409 | mobj = re.search(r'(?m)&mediaURL=([^&]+)', webpage) |
c6c555cf RG |
1410 | if mobj is not None: |
1411 | mediaURL = urllib.unquote(mobj.group(1)) | |
6b57e8c5 | 1412 | video_extension = mediaURL[-3:] |
d3975459 | 1413 | |
c6c555cf RG |
1414 | # Extract gdaKey if available |
1415 | mobj = re.search(r'(?m)&gdaKey=(.*?)&', webpage) | |
1416 | if mobj is None: | |
1417 | video_url = mediaURL | |
1418 | else: | |
1419 | gdaKey = mobj.group(1) | |
1420 | video_url = '%s?__gda__=%s' % (mediaURL, gdaKey) | |
109626fc | 1421 | else: |
c6c555cf RG |
1422 | mobj = re.search(r' name="flashvars" value="(.*?)"', webpage) |
1423 | if mobj is None: | |
1424 | self._downloader.trouble(u'ERROR: unable to extract media URL') | |
1425 | return | |
1426 | vardict = parse_qs(mobj.group(1)) | |
1427 | if 'mediaData' not in vardict: | |
1428 | self._downloader.trouble(u'ERROR: unable to extract media URL') | |
1429 | return | |
1430 | mobj = re.search(r'"mediaURL":"(http.*?)","key":"(.*?)"', vardict['mediaData'][0]) | |
1431 | if mobj is None: | |
1432 | self._downloader.trouble(u'ERROR: unable to extract media URL') | |
1433 | return | |
6b57e8c5 RG |
1434 | mediaURL = mobj.group(1).replace('\\/', '/') |
1435 | video_extension = mediaURL[-3:] | |
1436 | video_url = '%s?__gda__=%s' % (mediaURL, mobj.group(2)) | |
020f7150 | 1437 | |
2546e767 | 1438 | mobj = re.search(r'(?im)<title>(.*) - Video</title>', webpage) |
020f7150 | 1439 | if mobj is None: |
147753eb | 1440 | self._downloader.trouble(u'ERROR: unable to extract title') |
6f21f686 | 1441 | return |
020f7150 | 1442 | video_title = mobj.group(1).decode('utf-8') |
490fd7ae | 1443 | video_title = sanitize_title(video_title) |
020f7150 | 1444 | |
29f07568 | 1445 | mobj = re.search(r'(?ms)By:\s*<a .*?>(.+?)<', webpage) |
020f7150 | 1446 | if mobj is None: |
147753eb | 1447 | self._downloader.trouble(u'ERROR: unable to extract uploader nickname') |
6f21f686 | 1448 | return |
dbccb6cd | 1449 | video_uploader = mobj.group(1) |
020f7150 | 1450 | |
42bcd27d | 1451 | try: |
1452 | # Process video information | |
1453 | self._downloader.process_info({ | |
1454 | 'id': video_id.decode('utf-8'), | |
1455 | 'url': video_url.decode('utf-8'), | |
1456 | 'uploader': video_uploader.decode('utf-8'), | |
138b11f3 | 1457 | 'upload_date': u'NA', |
42bcd27d | 1458 | 'title': video_title, |
1459 | 'stitle': simple_title, | |
1460 | 'ext': video_extension.decode('utf-8'), | |
6ba562b0 | 1461 | 'format': u'NA', |
e616ec0c | 1462 | 'player_url': None, |
42bcd27d | 1463 | }) |
73f4e7af | 1464 | except UnavailableVideoError: |
09cc744c | 1465 | self._downloader.trouble(u'\nERROR: unable to download video') |
020f7150 | 1466 | |
25af2bce | 1467 | |
4135fa45 WB |
1468 | class DailymotionIE(InfoExtractor): |
1469 | """Information Extractor for Dailymotion""" | |
1470 | ||
1471 | _VALID_URL = r'(?i)(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/video/([^_/]+)_([^/]+)' | |
4135fa45 WB |
1472 | |
1473 | def __init__(self, downloader=None): | |
1474 | InfoExtractor.__init__(self, downloader) | |
1475 | ||
1476 | @staticmethod | |
1477 | def suitable(url): | |
1478 | return (re.match(DailymotionIE._VALID_URL, url) is not None) | |
1479 | ||
4135fa45 WB |
1480 | def report_download_webpage(self, video_id): |
1481 | """Report webpage download.""" | |
331ce0a0 | 1482 | self._downloader.to_screen(u'[dailymotion] %s: Downloading webpage' % video_id) |
d3975459 | 1483 | |
4135fa45 WB |
1484 | def report_extraction(self, video_id): |
1485 | """Report information extraction.""" | |
331ce0a0 | 1486 | self._downloader.to_screen(u'[dailymotion] %s: Extracting information' % video_id) |
4135fa45 WB |
1487 | |
1488 | def _real_initialize(self): | |
1489 | return | |
1490 | ||
4135fa45 WB |
1491 | def _real_extract(self, url): |
1492 | # Extract id and simplified title from URL | |
1493 | mobj = re.match(self._VALID_URL, url) | |
1494 | if mobj is None: | |
1495 | self._downloader.trouble(u'ERROR: invalid URL: %s' % url) | |
1496 | return | |
1497 | ||
df372a65 | 1498 | # At this point we have a new video |
9bf7fa52 | 1499 | self._downloader.increment_downloads() |
4135fa45 WB |
1500 | video_id = mobj.group(1) |
1501 | ||
1502 | simple_title = mobj.group(2).decode('utf-8') | |
1503 | video_extension = 'flv' | |
1504 | ||
1505 | # Retrieve video webpage to extract further information | |
1506 | request = urllib2.Request(url) | |
1507 | try: | |
1508 | self.report_download_webpage(video_id) | |
1509 | webpage = urllib2.urlopen(request).read() | |
1510 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
1511 | self._downloader.trouble(u'ERROR: unable retrieve video webpage: %s' % str(err)) | |
1512 | return | |
1513 | ||
1514 | # Extract URL, uploader and title from webpage | |
1515 | self.report_extraction(video_id) | |
1516 | mobj = re.search(r'(?i)addVariable\(\"video\"\s*,\s*\"([^\"]*)\"\)', webpage) | |
1517 | if mobj is None: | |
1518 | self._downloader.trouble(u'ERROR: unable to extract media URL') | |
1519 | return | |
1520 | mediaURL = urllib.unquote(mobj.group(1)) | |
1521 | ||
1522 | # if needed add http://www.dailymotion.com/ if relative URL | |
1523 | ||
1524 | video_url = mediaURL | |
1525 | ||
1526 | # '<meta\s+name="title"\s+content="Dailymotion\s*[:\-]\s*(.*?)"\s*\/\s*>' | |
1527 | mobj = re.search(r'(?im)<title>Dailymotion\s*[\-:]\s*(.+?)</title>', webpage) | |
1528 | if mobj is None: | |
1529 | self._downloader.trouble(u'ERROR: unable to extract title') | |
1530 | return | |
1531 | video_title = mobj.group(1).decode('utf-8') | |
1532 | video_title = sanitize_title(video_title) | |
1533 | ||
c02d8e40 | 1534 | mobj = re.search(r'(?im)<Attribute name="owner">(.+?)</Attribute>', webpage) |
4135fa45 WB |
1535 | if mobj is None: |
1536 | self._downloader.trouble(u'ERROR: unable to extract uploader nickname') | |
1537 | return | |
1538 | video_uploader = mobj.group(1) | |
1539 | ||
1540 | try: | |
1541 | # Process video information | |
1542 | self._downloader.process_info({ | |
1543 | 'id': video_id.decode('utf-8'), | |
1544 | 'url': video_url.decode('utf-8'), | |
1545 | 'uploader': video_uploader.decode('utf-8'), | |
138b11f3 | 1546 | 'upload_date': u'NA', |
4135fa45 WB |
1547 | 'title': video_title, |
1548 | 'stitle': simple_title, | |
1549 | 'ext': video_extension.decode('utf-8'), | |
1550 | 'format': u'NA', | |
1551 | 'player_url': None, | |
1552 | }) | |
73f4e7af | 1553 | except UnavailableVideoError: |
09cc744c | 1554 | self._downloader.trouble(u'\nERROR: unable to download video') |
4135fa45 | 1555 | |
49c0028a | 1556 | class GoogleIE(InfoExtractor): |
1557 | """Information extractor for video.google.com.""" | |
1558 | ||
490fd7ae | 1559 | _VALID_URL = r'(?:http://)?video\.google\.(?:com(?:\.au)?|co\.(?:uk|jp|kr|cr)|ca|de|es|fr|it|nl|pl)/videoplay\?docid=([^\&]+).*' |
49c0028a | 1560 | |
1561 | def __init__(self, downloader=None): | |
1562 | InfoExtractor.__init__(self, downloader) | |
1563 | ||
1564 | @staticmethod | |
1565 | def suitable(url): | |
1566 | return (re.match(GoogleIE._VALID_URL, url) is not None) | |
1567 | ||
1568 | def report_download_webpage(self, video_id): | |
1569 | """Report webpage download.""" | |
331ce0a0 | 1570 | self._downloader.to_screen(u'[video.google] %s: Downloading webpage' % video_id) |
49c0028a | 1571 | |
1572 | def report_extraction(self, video_id): | |
1573 | """Report information extraction.""" | |
331ce0a0 | 1574 | self._downloader.to_screen(u'[video.google] %s: Extracting information' % video_id) |
49c0028a | 1575 | |
1576 | def _real_initialize(self): | |
1577 | return | |
1578 | ||
1579 | def _real_extract(self, url): | |
1580 | # Extract id from URL | |
1581 | mobj = re.match(self._VALID_URL, url) | |
1582 | if mobj is None: | |
1583 | self._downloader.trouble(u'ERROR: Invalid URL: %s' % url) | |
1584 | return | |
1585 | ||
df372a65 | 1586 | # At this point we have a new video |
9bf7fa52 | 1587 | self._downloader.increment_downloads() |
49c0028a | 1588 | video_id = mobj.group(1) |
1589 | ||
1590 | video_extension = 'mp4' | |
1591 | ||
1592 | # Retrieve video webpage to extract further information | |
490fd7ae | 1593 | request = urllib2.Request('http://video.google.com/videoplay?docid=%s&hl=en&oe=utf-8' % video_id) |
49c0028a | 1594 | try: |
1595 | self.report_download_webpage(video_id) | |
1596 | webpage = urllib2.urlopen(request).read() | |
1597 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
1598 | self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err)) | |
1599 | return | |
1600 | ||
1601 | # Extract URL, uploader, and title from webpage | |
1602 | self.report_extraction(video_id) | |
490fd7ae RG |
1603 | mobj = re.search(r"download_url:'([^']+)'", webpage) |
1604 | if mobj is None: | |
1605 | video_extension = 'flv' | |
1606 | mobj = re.search(r"(?i)videoUrl\\x3d(.+?)\\x26", webpage) | |
49c0028a | 1607 | if mobj is None: |
1608 | self._downloader.trouble(u'ERROR: unable to extract media URL') | |
1609 | return | |
1610 | mediaURL = urllib.unquote(mobj.group(1)) | |
1611 | mediaURL = mediaURL.replace('\\x3d', '\x3d') | |
1612 | mediaURL = mediaURL.replace('\\x26', '\x26') | |
1613 | ||
1614 | video_url = mediaURL | |
1615 | ||
1616 | mobj = re.search(r'<title>(.*)</title>', webpage) | |
1617 | if mobj is None: | |
1618 | self._downloader.trouble(u'ERROR: unable to extract title') | |
1619 | return | |
1620 | video_title = mobj.group(1).decode('utf-8') | |
490fd7ae | 1621 | video_title = sanitize_title(video_title) |
31cbdaaf | 1622 | simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title) |
49c0028a | 1623 | |
7e58d568 RG |
1624 | # Extract video description |
1625 | mobj = re.search(r'<span id=short-desc-content>([^<]*)</span>', webpage) | |
1626 | if mobj is None: | |
1627 | self._downloader.trouble(u'ERROR: unable to extract video description') | |
1628 | return | |
1629 | video_description = mobj.group(1).decode('utf-8') | |
1630 | if not video_description: | |
1631 | video_description = 'No description available.' | |
1632 | ||
1633 | # Extract video thumbnail | |
1634 | if self._downloader.params.get('forcethumbnail', False): | |
1635 | request = urllib2.Request('http://video.google.com/videosearch?q=%s+site:video.google.com&hl=en' % abs(int(video_id))) | |
1636 | try: | |
1637 | webpage = urllib2.urlopen(request).read() | |
1638 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
1639 | self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err)) | |
1640 | return | |
1641 | mobj = re.search(r'<img class=thumbnail-img (?:.* )?src=(http.*)>', webpage) | |
1642 | if mobj is None: | |
1643 | self._downloader.trouble(u'ERROR: unable to extract video thumbnail') | |
1644 | return | |
1645 | video_thumbnail = mobj.group(1) | |
1646 | else: # we need something to pass to process_info | |
1647 | video_thumbnail = '' | |
1648 | ||
1649 | ||
49c0028a | 1650 | try: |
1651 | # Process video information | |
1652 | self._downloader.process_info({ | |
1653 | 'id': video_id.decode('utf-8'), | |
1654 | 'url': video_url.decode('utf-8'), | |
6ba562b0 | 1655 | 'uploader': u'NA', |
138b11f3 | 1656 | 'upload_date': u'NA', |
490fd7ae | 1657 | 'title': video_title, |
31cbdaaf | 1658 | 'stitle': simple_title, |
49c0028a | 1659 | 'ext': video_extension.decode('utf-8'), |
6ba562b0 | 1660 | 'format': u'NA', |
e616ec0c | 1661 | 'player_url': None, |
49c0028a | 1662 | }) |
73f4e7af | 1663 | except UnavailableVideoError: |
09cc744c | 1664 | self._downloader.trouble(u'\nERROR: unable to download video') |
49c0028a | 1665 | |
1666 | ||
1667 | class PhotobucketIE(InfoExtractor): | |
1668 | """Information extractor for photobucket.com.""" | |
1669 | ||
1670 | _VALID_URL = r'(?:http://)?(?:[a-z0-9]+\.)?photobucket\.com/.*[\?\&]current=(.*\.flv)' | |
1671 | ||
1672 | def __init__(self, downloader=None): | |
1673 | InfoExtractor.__init__(self, downloader) | |
1674 | ||
1675 | @staticmethod | |
1676 | def suitable(url): | |
1677 | return (re.match(PhotobucketIE._VALID_URL, url) is not None) | |
1678 | ||
1679 | def report_download_webpage(self, video_id): | |
1680 | """Report webpage download.""" | |
331ce0a0 | 1681 | self._downloader.to_screen(u'[photobucket] %s: Downloading webpage' % video_id) |
49c0028a | 1682 | |
1683 | def report_extraction(self, video_id): | |
1684 | """Report information extraction.""" | |
331ce0a0 | 1685 | self._downloader.to_screen(u'[photobucket] %s: Extracting information' % video_id) |
49c0028a | 1686 | |
1687 | def _real_initialize(self): | |
1688 | return | |
1689 | ||
1690 | def _real_extract(self, url): | |
1691 | # Extract id from URL | |
1692 | mobj = re.match(self._VALID_URL, url) | |
1693 | if mobj is None: | |
1694 | self._downloader.trouble(u'ERROR: Invalid URL: %s' % url) | |
1695 | return | |
1696 | ||
df372a65 | 1697 | # At this point we have a new video |
9bf7fa52 | 1698 | self._downloader.increment_downloads() |
49c0028a | 1699 | video_id = mobj.group(1) |
1700 | ||
1701 | video_extension = 'flv' | |
1702 | ||
1703 | # Retrieve video webpage to extract further information | |
1704 | request = urllib2.Request(url) | |
1705 | try: | |
1706 | self.report_download_webpage(video_id) | |
1707 | webpage = urllib2.urlopen(request).read() | |
1708 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
1709 | self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err)) | |
1710 | return | |
1711 | ||
1712 | # Extract URL, uploader, and title from webpage | |
1713 | self.report_extraction(video_id) | |
1714 | mobj = re.search(r'<link rel="video_src" href=".*\?file=([^"]+)" />', webpage) | |
1715 | if mobj is None: | |
1716 | self._downloader.trouble(u'ERROR: unable to extract media URL') | |
1717 | return | |
1718 | mediaURL = urllib.unquote(mobj.group(1)) | |
1719 | ||
1720 | video_url = mediaURL | |
1721 | ||
1722 | mobj = re.search(r'<title>(.*) video by (.*) - Photobucket</title>', webpage) | |
1723 | if mobj is None: | |
1724 | self._downloader.trouble(u'ERROR: unable to extract title') | |
1725 | return | |
1726 | video_title = mobj.group(1).decode('utf-8') | |
490fd7ae | 1727 | video_title = sanitize_title(video_title) |
31cbdaaf | 1728 | simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title) |
49c0028a | 1729 | |
1730 | video_uploader = mobj.group(2).decode('utf-8') | |
1731 | ||
1732 | try: | |
1733 | # Process video information | |
1734 | self._downloader.process_info({ | |
1735 | 'id': video_id.decode('utf-8'), | |
1736 | 'url': video_url.decode('utf-8'), | |
490fd7ae | 1737 | 'uploader': video_uploader, |
138b11f3 | 1738 | 'upload_date': u'NA', |
490fd7ae | 1739 | 'title': video_title, |
31cbdaaf | 1740 | 'stitle': simple_title, |
490fd7ae | 1741 | 'ext': video_extension.decode('utf-8'), |
6ba562b0 | 1742 | 'format': u'NA', |
e616ec0c | 1743 | 'player_url': None, |
490fd7ae | 1744 | }) |
73f4e7af | 1745 | except UnavailableVideoError: |
09cc744c | 1746 | self._downloader.trouble(u'\nERROR: unable to download video') |
490fd7ae RG |
1747 | |
1748 | ||
61945318 RG |
1749 | class YahooIE(InfoExtractor): |
1750 | """Information extractor for video.yahoo.com.""" | |
1751 | ||
1752 | # _VALID_URL matches all Yahoo! Video URLs | |
1753 | # _VPAGE_URL matches only the extractable '/watch/' URLs | |
1754 | _VALID_URL = r'(?:http://)?(?:[a-z]+\.)?video\.yahoo\.com/(?:watch|network)/([0-9]+)(?:/|\?v=)([0-9]+)(?:[#\?].*)?' | |
1755 | _VPAGE_URL = r'(?:http://)?video\.yahoo\.com/watch/([0-9]+)/([0-9]+)(?:[#\?].*)?' | |
1756 | ||
1757 | def __init__(self, downloader=None): | |
1758 | InfoExtractor.__init__(self, downloader) | |
1759 | ||
1760 | @staticmethod | |
1761 | def suitable(url): | |
1762 | return (re.match(YahooIE._VALID_URL, url) is not None) | |
1763 | ||
1764 | def report_download_webpage(self, video_id): | |
1765 | """Report webpage download.""" | |
331ce0a0 | 1766 | self._downloader.to_screen(u'[video.yahoo] %s: Downloading webpage' % video_id) |
61945318 RG |
1767 | |
1768 | def report_extraction(self, video_id): | |
1769 | """Report information extraction.""" | |
331ce0a0 | 1770 | self._downloader.to_screen(u'[video.yahoo] %s: Extracting information' % video_id) |
61945318 RG |
1771 | |
1772 | def _real_initialize(self): | |
1773 | return | |
1774 | ||
df372a65 | 1775 | def _real_extract(self, url, new_video=True): |
61945318 RG |
1776 | # Extract ID from URL |
1777 | mobj = re.match(self._VALID_URL, url) | |
1778 | if mobj is None: | |
1779 | self._downloader.trouble(u'ERROR: Invalid URL: %s' % url) | |
1780 | return | |
1781 | ||
df372a65 | 1782 | # At this point we have a new video |
9bf7fa52 | 1783 | self._downloader.increment_downloads() |
61945318 RG |
1784 | video_id = mobj.group(2) |
1785 | video_extension = 'flv' | |
1786 | ||
1787 | # Rewrite valid but non-extractable URLs as | |
1788 | # extractable English language /watch/ URLs | |
1789 | if re.match(self._VPAGE_URL, url) is None: | |
1790 | request = urllib2.Request(url) | |
1791 | try: | |
1792 | webpage = urllib2.urlopen(request).read() | |
1793 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
1794 | self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err)) | |
1795 | return | |
1796 | ||
1797 | mobj = re.search(r'\("id", "([0-9]+)"\);', webpage) | |
1798 | if mobj is None: | |
1799 | self._downloader.trouble(u'ERROR: Unable to extract id field') | |
1800 | return | |
1801 | yahoo_id = mobj.group(1) | |
1802 | ||
1803 | mobj = re.search(r'\("vid", "([0-9]+)"\);', webpage) | |
1804 | if mobj is None: | |
1805 | self._downloader.trouble(u'ERROR: Unable to extract vid field') | |
1806 | return | |
1807 | yahoo_vid = mobj.group(1) | |
1808 | ||
1809 | url = 'http://video.yahoo.com/watch/%s/%s' % (yahoo_vid, yahoo_id) | |
df372a65 | 1810 | return self._real_extract(url, new_video=False) |
61945318 RG |
1811 | |
1812 | # Retrieve video webpage to extract further information | |
1813 | request = urllib2.Request(url) | |
1814 | try: | |
1815 | self.report_download_webpage(video_id) | |
1816 | webpage = urllib2.urlopen(request).read() | |
1817 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
1818 | self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err)) | |
1819 | return | |
1820 | ||
1821 | # Extract uploader and title from webpage | |
1822 | self.report_extraction(video_id) | |
1823 | mobj = re.search(r'<meta name="title" content="(.*)" />', webpage) | |
1824 | if mobj is None: | |
1825 | self._downloader.trouble(u'ERROR: unable to extract video title') | |
1826 | return | |
1827 | video_title = mobj.group(1).decode('utf-8') | |
1828 | simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title) | |
1829 | ||
1830 | mobj = re.search(r'<h2 class="ti-5"><a href="http://video\.yahoo\.com/(people|profile)/[0-9]+" beacon=".*">(.*)</a></h2>', webpage) | |
1831 | if mobj is None: | |
1832 | self._downloader.trouble(u'ERROR: unable to extract video uploader') | |
1833 | return | |
1834 | video_uploader = mobj.group(1).decode('utf-8') | |
1835 | ||
7e58d568 RG |
1836 | # Extract video thumbnail |
1837 | mobj = re.search(r'<link rel="image_src" href="(.*)" />', webpage) | |
1838 | if mobj is None: | |
1839 | self._downloader.trouble(u'ERROR: unable to extract video thumbnail') | |
1840 | return | |
1841 | video_thumbnail = mobj.group(1).decode('utf-8') | |
1842 | ||
1843 | # Extract video description | |
1844 | mobj = re.search(r'<meta name="description" content="(.*)" />', webpage) | |
1845 | if mobj is None: | |
1846 | self._downloader.trouble(u'ERROR: unable to extract video description') | |
1847 | return | |
1848 | video_description = mobj.group(1).decode('utf-8') | |
1849 | if not video_description: video_description = 'No description available.' | |
1850 | ||
61945318 RG |
1851 | # Extract video height and width |
1852 | mobj = re.search(r'<meta name="video_height" content="([0-9]+)" />', webpage) | |
1853 | if mobj is None: | |
1854 | self._downloader.trouble(u'ERROR: unable to extract video height') | |
1855 | return | |
1856 | yv_video_height = mobj.group(1) | |
1857 | ||
1858 | mobj = re.search(r'<meta name="video_width" content="([0-9]+)" />', webpage) | |
1859 | if mobj is None: | |
1860 | self._downloader.trouble(u'ERROR: unable to extract video width') | |
1861 | return | |
1862 | yv_video_width = mobj.group(1) | |
1863 | ||
1864 | # Retrieve video playlist to extract media URL | |
1865 | # I'm not completely sure what all these options are, but we | |
1866 | # seem to need most of them, otherwise the server sends a 401. | |
1867 | yv_lg = 'R0xx6idZnW2zlrKP8xxAIR' # not sure what this represents | |
1868 | yv_bitrate = '700' # according to Wikipedia this is hard-coded | |
1869 | request = urllib2.Request('http://cosmos.bcst.yahoo.com/up/yep/process/getPlaylistFOP.php?node_id=' + video_id + | |
7a9054ec GV |
1870 | '&tech=flash&mode=playlist&lg=' + yv_lg + '&bitrate=' + yv_bitrate + '&vidH=' + yv_video_height + |
1871 | '&vidW=' + yv_video_width + '&swf=as3&rd=video.yahoo.com&tk=null&adsupported=v1,v2,&eventid=1301797') | |
61945318 RG |
1872 | try: |
1873 | self.report_download_webpage(video_id) | |
1874 | webpage = urllib2.urlopen(request).read() | |
1875 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
1876 | self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err)) | |
1877 | return | |
1878 | ||
1879 | # Extract media URL from playlist XML | |
1880 | mobj = re.search(r'<STREAM APP="(http://.*)" FULLPATH="/?(/.*\.flv\?[^"]*)"', webpage) | |
1881 | if mobj is None: | |
1882 | self._downloader.trouble(u'ERROR: Unable to extract media URL') | |
1883 | return | |
1884 | video_url = urllib.unquote(mobj.group(1) + mobj.group(2)).decode('utf-8') | |
1885 | video_url = re.sub(r'(?u)&(.+?);', htmlentity_transform, video_url) | |
1886 | ||
1887 | try: | |
1888 | # Process video information | |
1889 | self._downloader.process_info({ | |
1890 | 'id': video_id.decode('utf-8'), | |
1891 | 'url': video_url, | |
1892 | 'uploader': video_uploader, | |
138b11f3 | 1893 | 'upload_date': u'NA', |
61945318 RG |
1894 | 'title': video_title, |
1895 | 'stitle': simple_title, | |
1896 | 'ext': video_extension.decode('utf-8'), | |
7e58d568 RG |
1897 | 'thumbnail': video_thumbnail.decode('utf-8'), |
1898 | 'description': video_description, | |
1899 | 'thumbnail': video_thumbnail, | |
1900 | 'description': video_description, | |
e616ec0c | 1901 | 'player_url': None, |
61945318 | 1902 | }) |
73f4e7af | 1903 | except UnavailableVideoError: |
09cc744c | 1904 | self._downloader.trouble(u'\nERROR: unable to download video') |
61945318 RG |
1905 | |
1906 | ||
490fd7ae RG |
1907 | class GenericIE(InfoExtractor): |
1908 | """Generic last-resort information extractor.""" | |
1909 | ||
1910 | def __init__(self, downloader=None): | |
1911 | InfoExtractor.__init__(self, downloader) | |
1912 | ||
1913 | @staticmethod | |
1914 | def suitable(url): | |
1915 | return True | |
1916 | ||
1917 | def report_download_webpage(self, video_id): | |
1918 | """Report webpage download.""" | |
331ce0a0 RG |
1919 | self._downloader.to_screen(u'WARNING: Falling back on generic information extractor.') |
1920 | self._downloader.to_screen(u'[generic] %s: Downloading webpage' % video_id) | |
490fd7ae RG |
1921 | |
1922 | def report_extraction(self, video_id): | |
1923 | """Report information extraction.""" | |
331ce0a0 | 1924 | self._downloader.to_screen(u'[generic] %s: Extracting information' % video_id) |
490fd7ae RG |
1925 | |
1926 | def _real_initialize(self): | |
1927 | return | |
1928 | ||
1929 | def _real_extract(self, url): | |
df372a65 | 1930 | # At this point we have a new video |
9bf7fa52 | 1931 | self._downloader.increment_downloads() |
df372a65 | 1932 | |
490fd7ae RG |
1933 | video_id = url.split('/')[-1] |
1934 | request = urllib2.Request(url) | |
1935 | try: | |
1936 | self.report_download_webpage(video_id) | |
1937 | webpage = urllib2.urlopen(request).read() | |
1938 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
1939 | self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err)) | |
1940 | return | |
1941 | except ValueError, err: | |
1942 | # since this is the last-resort InfoExtractor, if | |
1943 | # this error is thrown, it'll be thrown here | |
1944 | self._downloader.trouble(u'ERROR: Invalid URL: %s' % url) | |
1945 | return | |
1946 | ||
a9806fd8 | 1947 | self.report_extraction(video_id) |
490fd7ae RG |
1948 | # Start with something easy: JW Player in SWFObject |
1949 | mobj = re.search(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage) | |
1950 | if mobj is None: | |
1951 | # Broaden the search a little bit | |
1952 | mobj = re.search(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage) | |
1953 | if mobj is None: | |
1954 | self._downloader.trouble(u'ERROR: Invalid URL: %s' % url) | |
1955 | return | |
1956 | ||
1957 | # It's possible that one of the regexes | |
1958 | # matched, but returned an empty group: | |
1959 | if mobj.group(1) is None: | |
1960 | self._downloader.trouble(u'ERROR: Invalid URL: %s' % url) | |
1961 | return | |
1962 | ||
1963 | video_url = urllib.unquote(mobj.group(1)) | |
1964 | video_id = os.path.basename(video_url) | |
1965 | ||
1966 | # here's a fun little line of code for you: | |
1967 | video_extension = os.path.splitext(video_id)[1][1:] | |
1968 | video_id = os.path.splitext(video_id)[0] | |
1969 | ||
1970 | # it's tempting to parse this further, but you would | |
1971 | # have to take into account all the variations like | |
1972 | # Video Title - Site Name | |
1973 | # Site Name | Video Title | |
1974 | # Video Title - Tagline | Site Name | |
1975 | # and so on and so forth; it's just not practical | |
1976 | mobj = re.search(r'<title>(.*)</title>', webpage) | |
1977 | if mobj is None: | |
1978 | self._downloader.trouble(u'ERROR: unable to extract title') | |
1979 | return | |
1980 | video_title = mobj.group(1).decode('utf-8') | |
1981 | video_title = sanitize_title(video_title) | |
31cbdaaf | 1982 | simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title) |
490fd7ae RG |
1983 | |
1984 | # video uploader is domain name | |
1985 | mobj = re.match(r'(?:https?://)?([^/]*)/.*', url) | |
1986 | if mobj is None: | |
1987 | self._downloader.trouble(u'ERROR: unable to extract title') | |
1988 | return | |
1989 | video_uploader = mobj.group(1).decode('utf-8') | |
1990 | ||
1991 | try: | |
1992 | # Process video information | |
1993 | self._downloader.process_info({ | |
1994 | 'id': video_id.decode('utf-8'), | |
1995 | 'url': video_url.decode('utf-8'), | |
1996 | 'uploader': video_uploader, | |
138b11f3 | 1997 | 'upload_date': u'NA', |
490fd7ae | 1998 | 'title': video_title, |
31cbdaaf | 1999 | 'stitle': simple_title, |
49c0028a | 2000 | 'ext': video_extension.decode('utf-8'), |
6ba562b0 | 2001 | 'format': u'NA', |
e616ec0c | 2002 | 'player_url': None, |
49c0028a | 2003 | }) |
73f4e7af | 2004 | except UnavailableVideoError, err: |
09cc744c | 2005 | self._downloader.trouble(u'\nERROR: unable to download video') |
49c0028a | 2006 | |
2007 | ||
25af2bce RG |
2008 | class YoutubeSearchIE(InfoExtractor): |
2009 | """Information Extractor for YouTube search queries.""" | |
2010 | _VALID_QUERY = r'ytsearch(\d+|all)?:[\s\S]+' | |
2011 | _TEMPLATE_URL = 'http://www.youtube.com/results?search_query=%s&page=%s&gl=US&hl=en' | |
2012 | _VIDEO_INDICATOR = r'href="/watch\?v=.+?"' | |
304a4d85 | 2013 | _MORE_PAGES_INDICATOR = r'(?m)>\s*Next\s*</a>' |
25af2bce | 2014 | _youtube_ie = None |
fd9288c3 | 2015 | _max_youtube_results = 1000 |
25af2bce | 2016 | |
f995f712 | 2017 | def __init__(self, youtube_ie, downloader=None): |
25af2bce RG |
2018 | InfoExtractor.__init__(self, downloader) |
2019 | self._youtube_ie = youtube_ie | |
d3975459 | 2020 | |
25af2bce RG |
2021 | @staticmethod |
2022 | def suitable(url): | |
2023 | return (re.match(YoutubeSearchIE._VALID_QUERY, url) is not None) | |
2024 | ||
2025 | def report_download_page(self, query, pagenum): | |
2026 | """Report attempt to download playlist page with given number.""" | |
490fd7ae | 2027 | query = query.decode(preferredencoding()) |
331ce0a0 | 2028 | self._downloader.to_screen(u'[youtube] query "%s": Downloading page %s' % (query, pagenum)) |
25af2bce RG |
2029 | |
2030 | def _real_initialize(self): | |
2031 | self._youtube_ie.initialize() | |
d3975459 | 2032 | |
25af2bce RG |
2033 | def _real_extract(self, query): |
2034 | mobj = re.match(self._VALID_QUERY, query) | |
2035 | if mobj is None: | |
147753eb | 2036 | self._downloader.trouble(u'ERROR: invalid search query "%s"' % query) |
6f21f686 | 2037 | return |
25af2bce RG |
2038 | |
2039 | prefix, query = query.split(':') | |
2040 | prefix = prefix[8:] | |
490fd7ae | 2041 | query = query.encode('utf-8') |
f995f712 | 2042 | if prefix == '': |
6f21f686 RG |
2043 | self._download_n_results(query, 1) |
2044 | return | |
f995f712 | 2045 | elif prefix == 'all': |
6f21f686 RG |
2046 | self._download_n_results(query, self._max_youtube_results) |
2047 | return | |
f995f712 | 2048 | else: |
25af2bce | 2049 | try: |
e1f18b8a | 2050 | n = long(prefix) |
25af2bce | 2051 | if n <= 0: |
147753eb | 2052 | self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query)) |
6f21f686 | 2053 | return |
257453b9 | 2054 | elif n > self._max_youtube_results: |
6f21f686 | 2055 | self._downloader.to_stderr(u'WARNING: ytsearch returns max %i results (you requested %i)' % (self._max_youtube_results, n)) |
257453b9 | 2056 | n = self._max_youtube_results |
6f21f686 RG |
2057 | self._download_n_results(query, n) |
2058 | return | |
e1f18b8a | 2059 | except ValueError: # parsing prefix as integer fails |
6f21f686 RG |
2060 | self._download_n_results(query, 1) |
2061 | return | |
25af2bce RG |
2062 | |
2063 | def _download_n_results(self, query, n): | |
2064 | """Downloads a specified number of results for a query""" | |
2065 | ||
2066 | video_ids = [] | |
2067 | already_seen = set() | |
2068 | pagenum = 1 | |
2069 | ||
2070 | while True: | |
2071 | self.report_download_page(query, pagenum) | |
a9633f14 | 2072 | result_url = self._TEMPLATE_URL % (urllib.quote_plus(query), pagenum) |
1987c232 | 2073 | request = urllib2.Request(result_url) |
25af2bce RG |
2074 | try: |
2075 | page = urllib2.urlopen(request).read() | |
2076 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
147753eb | 2077 | self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err)) |
6f21f686 | 2078 | return |
25af2bce RG |
2079 | |
2080 | # Extract video identifiers | |
2081 | for mobj in re.finditer(self._VIDEO_INDICATOR, page): | |
2082 | video_id = page[mobj.span()[0]:mobj.span()[1]].split('=')[2][:-1] | |
2083 | if video_id not in already_seen: | |
2084 | video_ids.append(video_id) | |
2085 | already_seen.add(video_id) | |
2086 | if len(video_ids) == n: | |
2087 | # Specified n videos reached | |
25af2bce | 2088 | for id in video_ids: |
6f21f686 RG |
2089 | self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id) |
2090 | return | |
25af2bce | 2091 | |
304a4d85 | 2092 | if re.search(self._MORE_PAGES_INDICATOR, page) is None: |
25af2bce | 2093 | for id in video_ids: |
6f21f686 RG |
2094 | self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id) |
2095 | return | |
25af2bce RG |
2096 | |
2097 | pagenum = pagenum + 1 | |
2098 | ||
7e58d568 RG |
2099 | class GoogleSearchIE(InfoExtractor): |
2100 | """Information Extractor for Google Video search queries.""" | |
2101 | _VALID_QUERY = r'gvsearch(\d+|all)?:[\s\S]+' | |
2102 | _TEMPLATE_URL = 'http://video.google.com/videosearch?q=%s+site:video.google.com&start=%s&hl=en' | |
2103 | _VIDEO_INDICATOR = r'videoplay\?docid=([^\&>]+)\&' | |
2104 | _MORE_PAGES_INDICATOR = r'<span>Next</span>' | |
2105 | _google_ie = None | |
2106 | _max_google_results = 1000 | |
2107 | ||
2108 | def __init__(self, google_ie, downloader=None): | |
2109 | InfoExtractor.__init__(self, downloader) | |
2110 | self._google_ie = google_ie | |
d3975459 | 2111 | |
7e58d568 RG |
2112 | @staticmethod |
2113 | def suitable(url): | |
2114 | return (re.match(GoogleSearchIE._VALID_QUERY, url) is not None) | |
2115 | ||
2116 | def report_download_page(self, query, pagenum): | |
2117 | """Report attempt to download playlist page with given number.""" | |
2118 | query = query.decode(preferredencoding()) | |
331ce0a0 | 2119 | self._downloader.to_screen(u'[video.google] query "%s": Downloading page %s' % (query, pagenum)) |
7e58d568 RG |
2120 | |
2121 | def _real_initialize(self): | |
2122 | self._google_ie.initialize() | |
d3975459 | 2123 | |
7e58d568 RG |
2124 | def _real_extract(self, query): |
2125 | mobj = re.match(self._VALID_QUERY, query) | |
2126 | if mobj is None: | |
2127 | self._downloader.trouble(u'ERROR: invalid search query "%s"' % query) | |
2128 | return | |
2129 | ||
2130 | prefix, query = query.split(':') | |
2131 | prefix = prefix[8:] | |
2132 | query = query.encode('utf-8') | |
2133 | if prefix == '': | |
2134 | self._download_n_results(query, 1) | |
2135 | return | |
2136 | elif prefix == 'all': | |
2137 | self._download_n_results(query, self._max_google_results) | |
2138 | return | |
2139 | else: | |
2140 | try: | |
2141 | n = long(prefix) | |
2142 | if n <= 0: | |
2143 | self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query)) | |
2144 | return | |
2145 | elif n > self._max_google_results: | |
2146 | self._downloader.to_stderr(u'WARNING: gvsearch returns max %i results (you requested %i)' % (self._max_google_results, n)) | |
2147 | n = self._max_google_results | |
2148 | self._download_n_results(query, n) | |
2149 | return | |
2150 | except ValueError: # parsing prefix as integer fails | |
2151 | self._download_n_results(query, 1) | |
2152 | return | |
2153 | ||
2154 | def _download_n_results(self, query, n): | |
2155 | """Downloads a specified number of results for a query""" | |
2156 | ||
2157 | video_ids = [] | |
2158 | already_seen = set() | |
2159 | pagenum = 1 | |
2160 | ||
2161 | while True: | |
2162 | self.report_download_page(query, pagenum) | |
2163 | result_url = self._TEMPLATE_URL % (urllib.quote_plus(query), pagenum) | |
1987c232 | 2164 | request = urllib2.Request(result_url) |
7e58d568 RG |
2165 | try: |
2166 | page = urllib2.urlopen(request).read() | |
2167 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
2168 | self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err)) | |
2169 | return | |
2170 | ||
2171 | # Extract video identifiers | |
2172 | for mobj in re.finditer(self._VIDEO_INDICATOR, page): | |
2173 | video_id = mobj.group(1) | |
2174 | if video_id not in already_seen: | |
2175 | video_ids.append(video_id) | |
2176 | already_seen.add(video_id) | |
2177 | if len(video_ids) == n: | |
2178 | # Specified n videos reached | |
2179 | for id in video_ids: | |
2180 | self._google_ie.extract('http://video.google.com/videoplay?docid=%s' % id) | |
2181 | return | |
2182 | ||
2183 | if re.search(self._MORE_PAGES_INDICATOR, page) is None: | |
2184 | for id in video_ids: | |
2185 | self._google_ie.extract('http://video.google.com/videoplay?docid=%s' % id) | |
2186 | return | |
2187 | ||
2188 | pagenum = pagenum + 1 | |
2189 | ||
2190 | class YahooSearchIE(InfoExtractor): | |
2191 | """Information Extractor for Yahoo! Video search queries.""" | |
2192 | _VALID_QUERY = r'yvsearch(\d+|all)?:[\s\S]+' | |
2193 | _TEMPLATE_URL = 'http://video.yahoo.com/search/?p=%s&o=%s' | |
2194 | _VIDEO_INDICATOR = r'href="http://video\.yahoo\.com/watch/([0-9]+/[0-9]+)"' | |
2195 | _MORE_PAGES_INDICATOR = r'\s*Next' | |
2196 | _yahoo_ie = None | |
2197 | _max_yahoo_results = 1000 | |
2198 | ||
2199 | def __init__(self, yahoo_ie, downloader=None): | |
2200 | InfoExtractor.__init__(self, downloader) | |
2201 | self._yahoo_ie = yahoo_ie | |
d3975459 | 2202 | |
7e58d568 RG |
2203 | @staticmethod |
2204 | def suitable(url): | |
2205 | return (re.match(YahooSearchIE._VALID_QUERY, url) is not None) | |
2206 | ||
2207 | def report_download_page(self, query, pagenum): | |
2208 | """Report attempt to download playlist page with given number.""" | |
2209 | query = query.decode(preferredencoding()) | |
331ce0a0 | 2210 | self._downloader.to_screen(u'[video.yahoo] query "%s": Downloading page %s' % (query, pagenum)) |
7e58d568 RG |
2211 | |
2212 | def _real_initialize(self): | |
2213 | self._yahoo_ie.initialize() | |
d3975459 | 2214 | |
7e58d568 RG |
2215 | def _real_extract(self, query): |
2216 | mobj = re.match(self._VALID_QUERY, query) | |
2217 | if mobj is None: | |
2218 | self._downloader.trouble(u'ERROR: invalid search query "%s"' % query) | |
2219 | return | |
2220 | ||
2221 | prefix, query = query.split(':') | |
2222 | prefix = prefix[8:] | |
2223 | query = query.encode('utf-8') | |
2224 | if prefix == '': | |
2225 | self._download_n_results(query, 1) | |
2226 | return | |
2227 | elif prefix == 'all': | |
2228 | self._download_n_results(query, self._max_yahoo_results) | |
2229 | return | |
2230 | else: | |
2231 | try: | |
2232 | n = long(prefix) | |
2233 | if n <= 0: | |
2234 | self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query)) | |
2235 | return | |
2236 | elif n > self._max_yahoo_results: | |
2237 | self._downloader.to_stderr(u'WARNING: yvsearch returns max %i results (you requested %i)' % (self._max_yahoo_results, n)) | |
2238 | n = self._max_yahoo_results | |
2239 | self._download_n_results(query, n) | |
2240 | return | |
2241 | except ValueError: # parsing prefix as integer fails | |
2242 | self._download_n_results(query, 1) | |
2243 | return | |
2244 | ||
2245 | def _download_n_results(self, query, n): | |
2246 | """Downloads a specified number of results for a query""" | |
2247 | ||
2248 | video_ids = [] | |
2249 | already_seen = set() | |
2250 | pagenum = 1 | |
2251 | ||
2252 | while True: | |
2253 | self.report_download_page(query, pagenum) | |
2254 | result_url = self._TEMPLATE_URL % (urllib.quote_plus(query), pagenum) | |
1987c232 | 2255 | request = urllib2.Request(result_url) |
7e58d568 RG |
2256 | try: |
2257 | page = urllib2.urlopen(request).read() | |
2258 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
2259 | self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err)) | |
2260 | return | |
2261 | ||
2262 | # Extract video identifiers | |
2263 | for mobj in re.finditer(self._VIDEO_INDICATOR, page): | |
2264 | video_id = mobj.group(1) | |
2265 | if video_id not in already_seen: | |
2266 | video_ids.append(video_id) | |
2267 | already_seen.add(video_id) | |
2268 | if len(video_ids) == n: | |
2269 | # Specified n videos reached | |
2270 | for id in video_ids: | |
2271 | self._yahoo_ie.extract('http://video.yahoo.com/watch/%s' % id) | |
2272 | return | |
2273 | ||
2274 | if re.search(self._MORE_PAGES_INDICATOR, page) is None: | |
2275 | for id in video_ids: | |
2276 | self._yahoo_ie.extract('http://video.yahoo.com/watch/%s' % id) | |
2277 | return | |
2278 | ||
2279 | pagenum = pagenum + 1 | |
2280 | ||
0c2dc87d RG |
2281 | class YoutubePlaylistIE(InfoExtractor): |
2282 | """Information Extractor for YouTube playlists.""" | |
2283 | ||
d119b54d | 2284 | _VALID_URL = r'(?:http://)?(?:\w+\.)?youtube.com/(?:(?:view_play_list|my_playlists|artist)\?.*?(p|a)=|user/.*?/user/|p/|user/.*?#[pg]/c/)([0-9A-Za-z]+)(?:/.*?/([0-9A-Za-z_-]+))?.*' |
f74e22ae | 2285 | _TEMPLATE_URL = 'http://www.youtube.com/%s?%s=%s&page=%s&gl=US&hl=en' |
0c2dc87d | 2286 | _VIDEO_INDICATOR = r'/watch\?v=(.+?)&' |
ce5cafea | 2287 | _MORE_PAGES_INDICATOR = r'(?m)>\s*Next\s*</a>' |
0c2dc87d RG |
2288 | _youtube_ie = None |
2289 | ||
2290 | def __init__(self, youtube_ie, downloader=None): | |
2291 | InfoExtractor.__init__(self, downloader) | |
2292 | self._youtube_ie = youtube_ie | |
d3975459 | 2293 | |
0c2dc87d RG |
2294 | @staticmethod |
2295 | def suitable(url): | |
2296 | return (re.match(YoutubePlaylistIE._VALID_URL, url) is not None) | |
2297 | ||
2298 | def report_download_page(self, playlist_id, pagenum): | |
2299 | """Report attempt to download playlist page with given number.""" | |
331ce0a0 | 2300 | self._downloader.to_screen(u'[youtube] PL %s: Downloading page #%s' % (playlist_id, pagenum)) |
0c2dc87d RG |
2301 | |
2302 | def _real_initialize(self): | |
2303 | self._youtube_ie.initialize() | |
d3975459 | 2304 | |
0c2dc87d RG |
2305 | def _real_extract(self, url): |
2306 | # Extract playlist id | |
2307 | mobj = re.match(self._VALID_URL, url) | |
2308 | if mobj is None: | |
147753eb | 2309 | self._downloader.trouble(u'ERROR: invalid url: %s' % url) |
6f21f686 | 2310 | return |
0c2dc87d | 2311 | |
d119b54d RG |
2312 | # Single video case |
2313 | if mobj.group(3) is not None: | |
2314 | self._youtube_ie.extract(mobj.group(3)) | |
2315 | return | |
2316 | ||
0c2dc87d | 2317 | # Download playlist pages |
f74e22ae GI |
2318 | # prefix is 'p' as default for playlists but there are other types that need extra care |
2319 | playlist_prefix = mobj.group(1) | |
2320 | if playlist_prefix == 'a': | |
2321 | playlist_access = 'artist' | |
2322 | else: | |
7cc3c6fd | 2323 | playlist_prefix = 'p' |
f74e22ae GI |
2324 | playlist_access = 'view_play_list' |
2325 | playlist_id = mobj.group(2) | |
0c2dc87d RG |
2326 | video_ids = [] |
2327 | pagenum = 1 | |
2328 | ||
2329 | while True: | |
2330 | self.report_download_page(playlist_id, pagenum) | |
f74e22ae | 2331 | request = urllib2.Request(self._TEMPLATE_URL % (playlist_access, playlist_prefix, playlist_id, pagenum)) |
0c2dc87d RG |
2332 | try: |
2333 | page = urllib2.urlopen(request).read() | |
2334 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
147753eb | 2335 | self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err)) |
6f21f686 | 2336 | return |
0c2dc87d RG |
2337 | |
2338 | # Extract video identifiers | |
27d98b6e | 2339 | ids_in_page = [] |
0c2dc87d | 2340 | for mobj in re.finditer(self._VIDEO_INDICATOR, page): |
27d98b6e RG |
2341 | if mobj.group(1) not in ids_in_page: |
2342 | ids_in_page.append(mobj.group(1)) | |
2343 | video_ids.extend(ids_in_page) | |
0c2dc87d | 2344 | |
ce5cafea | 2345 | if re.search(self._MORE_PAGES_INDICATOR, page) is None: |
0c2dc87d RG |
2346 | break |
2347 | pagenum = pagenum + 1 | |
2348 | ||
8cc44341 RG |
2349 | playliststart = self._downloader.params.get('playliststart', 1) - 1 |
2350 | playlistend = self._downloader.params.get('playlistend', -1) | |
2351 | video_ids = video_ids[playliststart:playlistend] | |
2352 | ||
0c2dc87d | 2353 | for id in video_ids: |
6f21f686 RG |
2354 | self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id) |
2355 | return | |
0c2dc87d | 2356 | |
c39c05cd A |
2357 | class YoutubeUserIE(InfoExtractor): |
2358 | """Information Extractor for YouTube users.""" | |
2359 | ||
5aba6ea4 | 2360 | _VALID_URL = r'(?:(?:(?:http://)?(?:\w+\.)?youtube.com/user/)|ytuser:)([A-Za-z0-9_-]+)' |
c39c05cd | 2361 | _TEMPLATE_URL = 'http://gdata.youtube.com/feeds/api/users/%s' |
5aba6ea4 RG |
2362 | _GDATA_PAGE_SIZE = 50 |
2363 | _GDATA_URL = 'http://gdata.youtube.com/feeds/api/users/%s/uploads?max-results=%d&start-index=%d' | |
2364 | _VIDEO_INDICATOR = r'/watch\?v=(.+?)&' | |
c39c05cd A |
2365 | _youtube_ie = None |
2366 | ||
2367 | def __init__(self, youtube_ie, downloader=None): | |
2368 | InfoExtractor.__init__(self, downloader) | |
2369 | self._youtube_ie = youtube_ie | |
d3975459 | 2370 | |
c39c05cd A |
2371 | @staticmethod |
2372 | def suitable(url): | |
2373 | return (re.match(YoutubeUserIE._VALID_URL, url) is not None) | |
2374 | ||
5aba6ea4 | 2375 | def report_download_page(self, username, start_index): |
c39c05cd | 2376 | """Report attempt to download user page.""" |
5aba6ea4 RG |
2377 | self._downloader.to_screen(u'[youtube] user %s: Downloading video ids from %d to %d' % |
2378 | (username, start_index, start_index + self._GDATA_PAGE_SIZE)) | |
c39c05cd A |
2379 | |
2380 | def _real_initialize(self): | |
2381 | self._youtube_ie.initialize() | |
d3975459 | 2382 | |
c39c05cd A |
2383 | def _real_extract(self, url): |
2384 | # Extract username | |
2385 | mobj = re.match(self._VALID_URL, url) | |
2386 | if mobj is None: | |
2387 | self._downloader.trouble(u'ERROR: invalid url: %s' % url) | |
2388 | return | |
2389 | ||
c39c05cd | 2390 | username = mobj.group(1) |
5aba6ea4 RG |
2391 | |
2392 | # Download video ids using YouTube Data API. Result size per | |
2393 | # query is limited (currently to 50 videos) so we need to query | |
2394 | # page by page until there are no video ids - it means we got | |
2395 | # all of them. | |
2396 | ||
c39c05cd | 2397 | video_ids = [] |
5aba6ea4 | 2398 | pagenum = 0 |
c39c05cd | 2399 | |
5aba6ea4 RG |
2400 | while True: |
2401 | start_index = pagenum * self._GDATA_PAGE_SIZE + 1 | |
2402 | self.report_download_page(username, start_index) | |
c39c05cd | 2403 | |
5aba6ea4 | 2404 | request = urllib2.Request(self._GDATA_URL % (username, self._GDATA_PAGE_SIZE, start_index)) |
c39c05cd | 2405 | |
5aba6ea4 RG |
2406 | try: |
2407 | page = urllib2.urlopen(request).read() | |
2408 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
2409 | self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err)) | |
2410 | return | |
c39c05cd | 2411 | |
5aba6ea4 RG |
2412 | # Extract video identifiers |
2413 | ids_in_page = [] | |
2414 | ||
2415 | for mobj in re.finditer(self._VIDEO_INDICATOR, page): | |
2416 | if mobj.group(1) not in ids_in_page: | |
2417 | ids_in_page.append(mobj.group(1)) | |
2418 | ||
2419 | video_ids.extend(ids_in_page) | |
2420 | ||
2421 | # A little optimization - if current page is not | |
2422 | # "full", ie. does not contain PAGE_SIZE video ids then | |
2423 | # we can assume that this page is the last one - there | |
2424 | # are no more ids on further pages - no need to query | |
2425 | # again. | |
2426 | ||
2427 | if len(ids_in_page) < self._GDATA_PAGE_SIZE: | |
2428 | break | |
2429 | ||
2430 | pagenum += 1 | |
2431 | ||
2432 | all_ids_count = len(video_ids) | |
8cc44341 RG |
2433 | playliststart = self._downloader.params.get('playliststart', 1) - 1 |
2434 | playlistend = self._downloader.params.get('playlistend', -1) | |
204c9398 | 2435 | |
5aba6ea4 RG |
2436 | if playlistend == -1: |
2437 | video_ids = video_ids[playliststart:] | |
2438 | else: | |
2439 | video_ids = video_ids[playliststart:playlistend] | |
7a9054ec | 2440 | |
5aba6ea4 | 2441 | self._downloader.to_screen("[youtube] user %s: Collected %d video ids (downloading %d of them)" % |
7a9054ec | 2442 | (username, all_ids_count, len(video_ids))) |
5aba6ea4 RG |
2443 | |
2444 | for video_id in video_ids: | |
2445 | self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % video_id) | |
2446 | ||
c39c05cd | 2447 | |
27179cfd VV |
2448 | class DepositFilesIE(InfoExtractor): |
2449 | """Information extractor for depositfiles.com""" | |
2450 | ||
2451 | _VALID_URL = r'(?:http://)?(?:\w+\.)?depositfiles.com/(?:../(?#locale))?files/(.+)' | |
2452 | ||
2453 | def __init__(self, downloader=None): | |
2454 | InfoExtractor.__init__(self, downloader) | |
2455 | ||
2456 | @staticmethod | |
2457 | def suitable(url): | |
2458 | return (re.match(DepositFilesIE._VALID_URL, url) is not None) | |
2459 | ||
2460 | def report_download_webpage(self, file_id): | |
2461 | """Report webpage download.""" | |
2462 | self._downloader.to_screen(u'[DepositFiles] %s: Downloading webpage' % file_id) | |
2463 | ||
2464 | def report_extraction(self, file_id): | |
2465 | """Report information extraction.""" | |
2466 | self._downloader.to_screen(u'[DepositFiles] %s: Extracting information' % file_id) | |
2467 | ||
2468 | def _real_initialize(self): | |
2469 | return | |
2470 | ||
2471 | def _real_extract(self, url): | |
2472 | # At this point we have a new file | |
2473 | self._downloader.increment_downloads() | |
2474 | ||
2475 | file_id = url.split('/')[-1] | |
2476 | # Rebuild url in english locale | |
2477 | url = 'http://depositfiles.com/en/files/' + file_id | |
2478 | ||
2479 | # Retrieve file webpage with 'Free download' button pressed | |
2480 | free_download_indication = { 'gateway_result' : '1' } | |
1987c232 | 2481 | request = urllib2.Request(url, urllib.urlencode(free_download_indication)) |
27179cfd VV |
2482 | try: |
2483 | self.report_download_webpage(file_id) | |
2484 | webpage = urllib2.urlopen(request).read() | |
2485 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
2486 | self._downloader.trouble(u'ERROR: Unable to retrieve file webpage: %s' % str(err)) | |
2487 | return | |
2488 | ||
2489 | # Search for the real file URL | |
2490 | mobj = re.search(r'<form action="(http://fileshare.+?)"', webpage) | |
2491 | if (mobj is None) or (mobj.group(1) is None): | |
2492 | # Try to figure out reason of the error. | |
2493 | mobj = re.search(r'<strong>(Attention.*?)</strong>', webpage, re.DOTALL) | |
2494 | if (mobj is not None) and (mobj.group(1) is not None): | |
2495 | restriction_message = re.sub('\s+', ' ', mobj.group(1)).strip() | |
2496 | self._downloader.trouble(u'ERROR: %s' % restriction_message) | |
2497 | else: | |
2498 | self._downloader.trouble(u'ERROR: unable to extract download URL from: %s' % url) | |
2499 | return | |
2500 | ||
2501 | file_url = mobj.group(1) | |
2502 | file_extension = os.path.splitext(file_url)[1][1:] | |
2503 | ||
2504 | # Search for file title | |
2505 | mobj = re.search(r'<b title="(.*?)">', webpage) | |
2506 | if mobj is None: | |
2507 | self._downloader.trouble(u'ERROR: unable to extract title') | |
2508 | return | |
2509 | file_title = mobj.group(1).decode('utf-8') | |
2510 | ||
2511 | try: | |
2512 | # Process file information | |
2513 | self._downloader.process_info({ | |
2514 | 'id': file_id.decode('utf-8'), | |
2515 | 'url': file_url.decode('utf-8'), | |
2516 | 'uploader': u'NA', | |
2517 | 'upload_date': u'NA', | |
2518 | 'title': file_title, | |
2519 | 'stitle': file_title, | |
2520 | 'ext': file_extension.decode('utf-8'), | |
2521 | 'format': u'NA', | |
2522 | 'player_url': None, | |
2523 | }) | |
2524 | except UnavailableVideoError, err: | |
2525 | self._downloader.trouble(u'ERROR: unable to download file') | |
2526 | ||
9f5f9602 GI |
2527 | class FacebookIE(InfoExtractor): |
2528 | """Information Extractor for Facebook""" | |
2529 | ||
2530 | _VALID_URL = r'^(?:https?://)?(?:\w+\.)?facebook.com/video/video.php\?(?:.*?)v=(?P<ID>\d+)(?:.*)' | |
2531 | _LOGIN_URL = 'https://login.facebook.com/login.php?m&next=http%3A%2F%2Fm.facebook.com%2Fhome.php&' | |
2532 | _NETRC_MACHINE = 'facebook' | |
2533 | _available_formats = ['highqual', 'lowqual'] | |
2534 | _video_extensions = { | |
2535 | 'highqual': 'mp4', | |
2536 | 'lowqual': 'mp4', | |
2537 | } | |
2538 | ||
2539 | def __init__(self, downloader=None): | |
2540 | InfoExtractor.__init__(self, downloader) | |
2541 | ||
2542 | @staticmethod | |
2543 | def suitable(url): | |
2544 | return (re.match(FacebookIE._VALID_URL, url) is not None) | |
2545 | ||
2546 | def _reporter(self, message): | |
2547 | """Add header and report message.""" | |
2548 | self._downloader.to_screen(u'[facebook] %s' % message) | |
2549 | ||
2550 | def report_login(self): | |
2551 | """Report attempt to log in.""" | |
2552 | self._reporter(u'Logging in') | |
2553 | ||
2554 | def report_video_webpage_download(self, video_id): | |
2555 | """Report attempt to download video webpage.""" | |
2556 | self._reporter(u'%s: Downloading video webpage' % video_id) | |
2557 | ||
2558 | def report_information_extraction(self, video_id): | |
2559 | """Report attempt to extract video information.""" | |
2560 | self._reporter(u'%s: Extracting video information' % video_id) | |
2561 | ||
2562 | def _parse_page(self, video_webpage): | |
2563 | """Extract video information from page""" | |
2564 | # General data | |
2565 | data = {'title': r'class="video_title datawrap">(.*?)</', | |
2566 | 'description': r'<div class="datawrap">(.*?)</div>', | |
2567 | 'owner': r'\("video_owner_name", "(.*?)"\)', | |
2568 | 'upload_date': r'data-date="(.*?)"', | |
2569 | 'thumbnail': r'\("thumb_url", "(?P<THUMB>.*?)"\)', | |
2570 | } | |
2571 | video_info = {} | |
2572 | for piece in data.keys(): | |
2573 | mobj = re.search(data[piece], video_webpage) | |
2574 | if mobj is not None: | |
2575 | video_info[piece] = urllib.unquote_plus(mobj.group(1).decode("unicode_escape")) | |
2576 | ||
2577 | # Video urls | |
2578 | video_urls = {} | |
2579 | for fmt in self._available_formats: | |
2580 | mobj = re.search(r'\("%s_src\", "(.+?)"\)' % fmt, video_webpage) | |
2581 | if mobj is not None: | |
2582 | # URL is in a Javascript segment inside an escaped Unicode format within | |
2583 | # the generally utf-8 page | |
2584 | video_urls[fmt] = urllib.unquote_plus(mobj.group(1).decode("unicode_escape")) | |
2585 | video_info['video_urls'] = video_urls | |
2586 | ||
2587 | return video_info | |
2588 | ||
2589 | def _real_initialize(self): | |
2590 | if self._downloader is None: | |
2591 | return | |
2592 | ||
2593 | useremail = None | |
2594 | password = None | |
2595 | downloader_params = self._downloader.params | |
2596 | ||
2597 | # Attempt to use provided username and password or .netrc data | |
2598 | if downloader_params.get('username', None) is not None: | |
2599 | useremail = downloader_params['username'] | |
2600 | password = downloader_params['password'] | |
2601 | elif downloader_params.get('usenetrc', False): | |
2602 | try: | |
2603 | info = netrc.netrc().authenticators(self._NETRC_MACHINE) | |
2604 | if info is not None: | |
2605 | useremail = info[0] | |
2606 | password = info[2] | |
2607 | else: | |
2608 | raise netrc.NetrcParseError('No authenticators for %s' % self._NETRC_MACHINE) | |
2609 | except (IOError, netrc.NetrcParseError), err: | |
2610 | self._downloader.to_stderr(u'WARNING: parsing .netrc: %s' % str(err)) | |
2611 | return | |
2612 | ||
2613 | if useremail is None: | |
2614 | return | |
2615 | ||
2616 | # Log in | |
2617 | login_form = { | |
2618 | 'email': useremail, | |
2619 | 'pass': password, | |
2620 | 'login': 'Log+In' | |
2621 | } | |
2622 | request = urllib2.Request(self._LOGIN_URL, urllib.urlencode(login_form)) | |
2623 | try: | |
2624 | self.report_login() | |
2625 | login_results = urllib2.urlopen(request).read() | |
2626 | if re.search(r'<form(.*)name="login"(.*)</form>', login_results) is not None: | |
2627 | self._downloader.to_stderr(u'WARNING: unable to log in: bad username/password, or exceded login rate limit (~3/min). Check credentials or wait.') | |
2628 | return | |
2629 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
2630 | self._downloader.to_stderr(u'WARNING: unable to log in: %s' % str(err)) | |
2631 | return | |
2632 | ||
2633 | def _real_extract(self, url): | |
2634 | mobj = re.match(self._VALID_URL, url) | |
2635 | if mobj is None: | |
2636 | self._downloader.trouble(u'ERROR: invalid URL: %s' % url) | |
2637 | return | |
2638 | video_id = mobj.group('ID') | |
2639 | ||
2640 | # Get video webpage | |
2641 | self.report_video_webpage_download(video_id) | |
2642 | request = urllib2.Request('https://www.facebook.com/video/video.php?v=%s' % video_id) | |
2643 | try: | |
2644 | page = urllib2.urlopen(request) | |
2645 | video_webpage = page.read() | |
2646 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
2647 | self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % str(err)) | |
2648 | return | |
2649 | ||
2650 | # Start extracting information | |
2651 | self.report_information_extraction(video_id) | |
2652 | ||
2653 | # Extract information | |
2654 | video_info = self._parse_page(video_webpage) | |
2655 | ||
2656 | # uploader | |
2657 | if 'owner' not in video_info: | |
2658 | self._downloader.trouble(u'ERROR: unable to extract uploader nickname') | |
2659 | return | |
2660 | video_uploader = video_info['owner'] | |
2661 | ||
2662 | # title | |
2663 | if 'title' not in video_info: | |
2664 | self._downloader.trouble(u'ERROR: unable to extract video title') | |
2665 | return | |
2666 | video_title = video_info['title'] | |
2667 | video_title = video_title.decode('utf-8') | |
2668 | video_title = sanitize_title(video_title) | |
2669 | ||
2670 | # simplified title | |
2671 | simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title) | |
2672 | simple_title = simple_title.strip(ur'_') | |
2673 | ||
2674 | # thumbnail image | |
2675 | if 'thumbnail' not in video_info: | |
2676 | self._downloader.trouble(u'WARNING: unable to extract video thumbnail') | |
2677 | video_thumbnail = '' | |
2678 | else: | |
2679 | video_thumbnail = video_info['thumbnail'] | |
2680 | ||
2681 | # upload date | |
2682 | upload_date = u'NA' | |
2683 | if 'upload_date' in video_info: | |
2684 | upload_time = video_info['upload_date'] | |
2685 | timetuple = email.utils.parsedate_tz(upload_time) | |
2686 | if timetuple is not None: | |
2687 | try: | |
2688 | upload_date = time.strftime('%Y%m%d', timetuple[0:9]) | |
2689 | except: | |
2690 | pass | |
2691 | ||
2692 | # description | |
8b95c387 | 2693 | video_description = video_info.get('description', 'No description available.') |
9f5f9602 GI |
2694 | |
2695 | url_map = video_info['video_urls'] | |
2696 | if len(url_map.keys()) > 0: | |
2697 | # Decide which formats to download | |
2698 | req_format = self._downloader.params.get('format', None) | |
2699 | format_limit = self._downloader.params.get('format_limit', None) | |
2700 | ||
2701 | if format_limit is not None and format_limit in self._available_formats: | |
2702 | format_list = self._available_formats[self._available_formats.index(format_limit):] | |
2703 | else: | |
2704 | format_list = self._available_formats | |
2705 | existing_formats = [x for x in format_list if x in url_map] | |
2706 | if len(existing_formats) == 0: | |
2707 | self._downloader.trouble(u'ERROR: no known formats available for video') | |
2708 | return | |
2709 | if req_format is None: | |
2710 | video_url_list = [(existing_formats[0], url_map[existing_formats[0]])] # Best quality | |
2711 | elif req_format == '-1': | |
2712 | video_url_list = [(f, url_map[f]) for f in existing_formats] # All formats | |
2713 | else: | |
2714 | # Specific format | |
2715 | if req_format not in url_map: | |
2716 | self._downloader.trouble(u'ERROR: requested format not available') | |
2717 | return | |
2718 | video_url_list = [(req_format, url_map[req_format])] # Specific format | |
2719 | ||
2720 | for format_param, video_real_url in video_url_list: | |
2721 | ||
2722 | # At this point we have a new video | |
2723 | self._downloader.increment_downloads() | |
2724 | ||
2725 | # Extension | |
2726 | video_extension = self._video_extensions.get(format_param, 'mp4') | |
2727 | ||
9f5f9602 GI |
2728 | try: |
2729 | # Process video information | |
2730 | self._downloader.process_info({ | |
2731 | 'id': video_id.decode('utf-8'), | |
2732 | 'url': video_real_url.decode('utf-8'), | |
2733 | 'uploader': video_uploader.decode('utf-8'), | |
2734 | 'upload_date': upload_date, | |
2735 | 'title': video_title, | |
2736 | 'stitle': simple_title, | |
2737 | 'ext': video_extension.decode('utf-8'), | |
2738 | 'format': (format_param is None and u'NA' or format_param.decode('utf-8')), | |
2739 | 'thumbnail': video_thumbnail.decode('utf-8'), | |
2740 | 'description': video_description.decode('utf-8'), | |
2741 | 'player_url': None, | |
2742 | }) | |
2743 | except UnavailableVideoError, err: | |
2744 | self._downloader.trouble(u'\nERROR: unable to download video') | |
2745 | ||
7745f5d8 PH |
2746 | class BlipTVIE(InfoExtractor): |
2747 | """Information extractor for blip.tv""" | |
2748 | ||
1cab2c6d | 2749 | _VALID_URL = r'^(?:https?://)?(?:\w+\.)?blip\.tv(/.+)$' |
7745f5d8 PH |
2750 | _URL_EXT = r'^.*\.([a-z0-9]+)$' |
2751 | ||
2752 | @staticmethod | |
2753 | def suitable(url): | |
2754 | return (re.match(BlipTVIE._VALID_URL, url) is not None) | |
2755 | ||
7745f5d8 PH |
2756 | def report_extraction(self, file_id): |
2757 | """Report information extraction.""" | |
aded78d9 | 2758 | self._downloader.to_screen(u'[blip.tv] %s: Extracting information' % file_id) |
7745f5d8 PH |
2759 | |
2760 | def _simplify_title(self, title): | |
2761 | res = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', title) | |
2762 | res = res.strip(ur'_') | |
2763 | return res | |
2764 | ||
2765 | def _real_extract(self, url): | |
2766 | mobj = re.match(self._VALID_URL, url) | |
2767 | if mobj is None: | |
2768 | self._downloader.trouble(u'ERROR: invalid URL: %s' % url) | |
2769 | return | |
2770 | ||
1293ce58 PH |
2771 | if '?' in url: |
2772 | cchar = '&' | |
2773 | else: | |
2774 | cchar = '?' | |
2775 | json_url = url + cchar + 'skin=json&version=2&no_wrap=1' | |
7745f5d8 | 2776 | request = urllib2.Request(json_url) |
aded78d9 | 2777 | self.report_extraction(mobj.group(1)) |
7745f5d8 PH |
2778 | try: |
2779 | json_code = urllib2.urlopen(request).read() | |
2780 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
2781 | self._downloader.trouble(u'ERROR: unable to download video info webpage: %s' % str(err)) | |
2782 | return | |
2783 | try: | |
2784 | json_data = json.loads(json_code) | |
1293ce58 PH |
2785 | if 'Post' in json_data: |
2786 | data = json_data['Post'] | |
2787 | else: | |
2788 | data = json_data | |
7745f5d8 PH |
2789 | |
2790 | upload_date = datetime.datetime.strptime(data['datestamp'], '%m-%d-%y %H:%M%p').strftime('%Y%m%d') | |
2791 | video_url = data['media']['url'] | |
2792 | umobj = re.match(self._URL_EXT, video_url) | |
2793 | if umobj is None: | |
2794 | raise ValueError('Can not determine filename extension') | |
2795 | ext = umobj.group(1) | |
2796 | ||
a1cab7ce PH |
2797 | self._downloader.increment_downloads() |
2798 | ||
7745f5d8 PH |
2799 | info = { |
2800 | 'id': data['item_id'], | |
2801 | 'url': video_url, | |
2802 | 'uploader': data['display_name'], | |
2803 | 'upload_date': upload_date, | |
2804 | 'title': data['title'], | |
2805 | 'stitle': self._simplify_title(data['title']), | |
2806 | 'ext': ext, | |
2807 | 'format': data['media']['mimeType'], | |
2808 | 'thumbnail': data['thumbnailUrl'], | |
2809 | 'description': data['description'], | |
2810 | 'player_url': data['embedUrl'] | |
2811 | } | |
2812 | except (ValueError,KeyError), err: | |
aded78d9 | 2813 | self._downloader.trouble(u'ERROR: unable to parse video information: %s' % repr(err)) |
7745f5d8 PH |
2814 | return |
2815 | ||
2816 | try: | |
2817 | self._downloader.process_info(info) | |
2818 | except UnavailableVideoError, err: | |
2819 | self._downloader.trouble(u'\nERROR: unable to download video') | |
2820 | ||
2821 | ||
65cd34c5 RG |
2822 | class PostProcessor(object): |
2823 | """Post Processor class. | |
2824 | ||
2825 | PostProcessor objects can be added to downloaders with their | |
2826 | add_post_processor() method. When the downloader has finished a | |
2827 | successful download, it will take its internal chain of PostProcessors | |
2828 | and start calling the run() method on each one of them, first with | |
2829 | an initial argument and then with the returned value of the previous | |
2830 | PostProcessor. | |
2831 | ||
2832 | The chain will be stopped if one of them ever returns None or the end | |
2833 | of the chain is reached. | |
2834 | ||
2835 | PostProcessor objects follow a "mutual registration" process similar | |
2836 | to InfoExtractor objects. | |
2837 | """ | |
2838 | ||
2839 | _downloader = None | |
2840 | ||
2841 | def __init__(self, downloader=None): | |
2842 | self._downloader = downloader | |
2843 | ||
65cd34c5 RG |
2844 | def set_downloader(self, downloader): |
2845 | """Sets the downloader for this PP.""" | |
2846 | self._downloader = downloader | |
d3975459 | 2847 | |
65cd34c5 RG |
2848 | def run(self, information): |
2849 | """Run the PostProcessor. | |
2850 | ||
2851 | The "information" argument is a dictionary like the ones | |
2f11508a | 2852 | composed by InfoExtractors. The only difference is that this |
65cd34c5 RG |
2853 | one has an extra field called "filepath" that points to the |
2854 | downloaded file. | |
2855 | ||
2856 | When this method returns None, the postprocessing chain is | |
2857 | stopped. However, this method may return an information | |
2858 | dictionary that will be passed to the next postprocessing | |
2859 | object in the chain. It can be the one it received after | |
2860 | changing some fields. | |
2861 | ||
2862 | In addition, this method may raise a PostProcessingError | |
2863 | exception that will be taken into account by the downloader | |
2864 | it was called from. | |
2865 | """ | |
2866 | return information # by default, do nothing | |
d3975459 | 2867 | |
3072fab1 RG |
2868 | class FFmpegExtractAudioPP(PostProcessor): |
2869 | ||
2870 | def __init__(self, downloader=None, preferredcodec=None): | |
2871 | PostProcessor.__init__(self, downloader) | |
2872 | if preferredcodec is None: | |
2873 | preferredcodec = 'best' | |
2874 | self._preferredcodec = preferredcodec | |
2875 | ||
2876 | @staticmethod | |
2877 | def get_audio_codec(path): | |
da273188 | 2878 | try: |
2727dbf7 RG |
2879 | cmd = ['ffprobe', '-show_streams', '--', path] |
2880 | handle = subprocess.Popen(cmd, stderr=file(os.path.devnull, 'w'), stdout=subprocess.PIPE) | |
da273188 RG |
2881 | output = handle.communicate()[0] |
2882 | if handle.wait() != 0: | |
2883 | return None | |
2884 | except (IOError, OSError): | |
3072fab1 RG |
2885 | return None |
2886 | audio_codec = None | |
2887 | for line in output.split('\n'): | |
2888 | if line.startswith('codec_name='): | |
2889 | audio_codec = line.split('=')[1].strip() | |
2890 | elif line.strip() == 'codec_type=audio' and audio_codec is not None: | |
2891 | return audio_codec | |
2892 | return None | |
2893 | ||
2894 | @staticmethod | |
2895 | def run_ffmpeg(path, out_path, codec, more_opts): | |
2896 | try: | |
2727dbf7 RG |
2897 | cmd = ['ffmpeg', '-y', '-i', path, '-vn', '-acodec', codec] + more_opts + ['--', out_path] |
2898 | ret = subprocess.call(cmd, stdout=file(os.path.devnull, 'w'), stderr=subprocess.STDOUT) | |
3072fab1 RG |
2899 | return (ret == 0) |
2900 | except (IOError, OSError): | |
2901 | return False | |
2902 | ||
2903 | def run(self, information): | |
2904 | path = information['filepath'] | |
2905 | ||
2906 | filecodec = self.get_audio_codec(path) | |
2907 | if filecodec is None: | |
da273188 | 2908 | self._downloader.to_stderr(u'WARNING: unable to obtain file audio codec with ffprobe') |
3072fab1 RG |
2909 | return None |
2910 | ||
2911 | more_opts = [] | |
2912 | if self._preferredcodec == 'best' or self._preferredcodec == filecodec: | |
2913 | if filecodec == 'aac' or filecodec == 'mp3': | |
2914 | # Lossless if possible | |
2915 | acodec = 'copy' | |
2916 | extension = filecodec | |
2917 | if filecodec == 'aac': | |
2918 | more_opts = ['-f', 'adts'] | |
2919 | else: | |
2920 | # MP3 otherwise. | |
2921 | acodec = 'libmp3lame' | |
2922 | extension = 'mp3' | |
2923 | more_opts = ['-ab', '128k'] | |
2924 | else: | |
2925 | # We convert the audio (lossy) | |
2926 | acodec = {'mp3': 'libmp3lame', 'aac': 'aac'}[self._preferredcodec] | |
2927 | extension = self._preferredcodec | |
2928 | more_opts = ['-ab', '128k'] | |
2929 | if self._preferredcodec == 'aac': | |
2930 | more_opts += ['-f', 'adts'] | |
2931 | ||
2932 | (prefix, ext) = os.path.splitext(path) | |
2933 | new_path = prefix + '.' + extension | |
2934 | self._downloader.to_screen(u'[ffmpeg] Destination: %s' % new_path) | |
2935 | status = self.run_ffmpeg(path, new_path, acodec, more_opts) | |
2936 | ||
2937 | if not status: | |
1bd92582 | 2938 | self._downloader.to_stderr(u'WARNING: error running ffmpeg') |
3072fab1 RG |
2939 | return None |
2940 | ||
2941 | try: | |
2942 | os.remove(path) | |
2943 | except (IOError, OSError): | |
2944 | self._downloader.to_stderr(u'WARNING: Unable to remove downloaded video file') | |
2945 | return None | |
2946 | ||
2947 | information['filepath'] = new_path | |
2948 | return information | |
2949 | ||
5fb3df4a GV |
2950 | |
2951 | def updateSelf(downloader, filename): | |
2952 | ''' Update the program file with the latest version from the repository ''' | |
2953 | # Note: downloader only used for options | |
2954 | if not os.access(filename, os.W_OK): | |
2955 | sys.exit('ERROR: no write permissions on %s' % filename) | |
2956 | ||
2957 | downloader.to_screen('Updating to latest stable version...') | |
2958 | ||
4fa74b52 | 2959 | try: |
5fb3df4a GV |
2960 | latest_url = 'http://github.com/rg3/youtube-dl/raw/master/LATEST_VERSION' |
2961 | latest_version = urllib.urlopen(latest_url).read().strip() | |
2962 | prog_url = 'http://github.com/rg3/youtube-dl/raw/%s/youtube-dl' % latest_version | |
2963 | newcontent = urllib.urlopen(prog_url).read() | |
2964 | except (IOError, OSError), err: | |
2965 | sys.exit('ERROR: unable to download latest version') | |
f9f1e798 | 2966 | |
5fb3df4a GV |
2967 | try: |
2968 | stream = open(filename, 'w') | |
2969 | stream.write(newcontent) | |
2970 | stream.close() | |
2971 | except (IOError, OSError), err: | |
2972 | sys.exit('ERROR: unable to overwrite current version') | |
4bec29ef | 2973 | |
5fb3df4a | 2974 | downloader.to_screen('Updated to version %s' % latest_version) |
80066952 | 2975 | |
4f9f96f6 GV |
2976 | def parseOpts(): |
2977 | # Deferred imports | |
2978 | import getpass | |
2979 | import optparse | |
e7cf18cb | 2980 | |
4f9f96f6 GV |
2981 | def _format_option_string(option): |
2982 | ''' ('-o', '--option') -> -o, --format METAVAR''' | |
80066952 | 2983 | |
4f9f96f6 GV |
2984 | opts = [] |
2985 | ||
2986 | if option._short_opts: opts.append(option._short_opts[0]) | |
2987 | if option._long_opts: opts.append(option._long_opts[0]) | |
2988 | if len(opts) > 1: opts.insert(1, ', ') | |
2989 | ||
2990 | if option.takes_value(): opts.append(' %s' % option.metavar) | |
2991 | ||
2992 | return "".join(opts) | |
2993 | ||
6a4f0a11 GV |
2994 | def _find_term_columns(): |
2995 | columns = os.environ.get('COLUMNS', None) | |
2c8d32de PH |
2996 | if columns: |
2997 | return int(columns) | |
2998 | ||
4f2a5e06 PH |
2999 | try: |
3000 | sp = subprocess.Popen(['stty', 'size'], stdout=subprocess.PIPE, stderr=subprocess.PIPE) | |
3001 | out,err = sp.communicate() | |
eb0387a8 | 3002 | return int(out.split()[1]) |
4f2a5e06 PH |
3003 | except: |
3004 | pass | |
2c8d32de | 3005 | return None |
6a4f0a11 | 3006 | |
51c8e53f GV |
3007 | max_width = 80 |
3008 | max_help_position = 80 | |
3009 | ||
3010 | # No need to wrap help messages if we're on a wide console | |
6a4f0a11 | 3011 | columns = _find_term_columns() |
51c8e53f GV |
3012 | if columns: max_width = columns |
3013 | ||
3014 | fmt = optparse.IndentedHelpFormatter(width=max_width, max_help_position=max_help_position) | |
4f9f96f6 GV |
3015 | fmt.format_option_strings = _format_option_string |
3016 | ||
3017 | kw = { | |
3018 | 'version' : __version__, | |
3019 | 'formatter' : fmt, | |
2c8d32de | 3020 | 'usage' : '%prog [options] url...', |
4f9f96f6 GV |
3021 | 'conflict_handler' : 'resolve', |
3022 | } | |
3023 | ||
3024 | parser = optparse.OptionParser(**kw) | |
3025 | ||
3026 | # option groups | |
3027 | general = optparse.OptionGroup(parser, 'General Options') | |
3028 | authentication = optparse.OptionGroup(parser, 'Authentication Options') | |
3029 | video_format = optparse.OptionGroup(parser, 'Video Format Options') | |
3030 | postproc = optparse.OptionGroup(parser, 'Post-processing Options') | |
3031 | filesystem = optparse.OptionGroup(parser, 'Filesystem Options') | |
3032 | verbosity = optparse.OptionGroup(parser, 'Verbosity / Simulation Options') | |
3033 | ||
3034 | general.add_option('-h', '--help', | |
3035 | action='help', help='print this help text and exit') | |
3036 | general.add_option('-v', '--version', | |
3037 | action='version', help='print program version and exit') | |
3038 | general.add_option('-U', '--update', | |
3039 | action='store_true', dest='update_self', help='update this program to latest stable version') | |
3040 | general.add_option('-i', '--ignore-errors', | |
3041 | action='store_true', dest='ignoreerrors', help='continue on download errors', default=False) | |
3042 | general.add_option('-r', '--rate-limit', | |
3043 | dest='ratelimit', metavar='LIMIT', help='download rate limit (e.g. 50k or 44.6m)') | |
3044 | general.add_option('-R', '--retries', | |
3045 | dest='retries', metavar='RETRIES', help='number of retries (default is 10)', default=10) | |
3046 | general.add_option('--playlist-start', | |
3047 | dest='playliststart', metavar='NUMBER', help='playlist video to start at (default is 1)', default=1) | |
3048 | general.add_option('--playlist-end', | |
3049 | dest='playlistend', metavar='NUMBER', help='playlist video to end at (default is last)', default=-1) | |
3050 | general.add_option('--dump-user-agent', | |
3051 | action='store_true', dest='dump_user_agent', | |
3052 | help='display the current browser identification', default=False) | |
3053 | ||
3054 | authentication.add_option('-u', '--username', | |
3055 | dest='username', metavar='USERNAME', help='account username') | |
3056 | authentication.add_option('-p', '--password', | |
3057 | dest='password', metavar='PASSWORD', help='account password') | |
3058 | authentication.add_option('-n', '--netrc', | |
3059 | action='store_true', dest='usenetrc', help='use .netrc authentication data', default=False) | |
3060 | ||
3061 | ||
3062 | video_format.add_option('-f', '--format', | |
3063 | action='store', dest='format', metavar='FORMAT', help='video format code') | |
3064 | video_format.add_option('--all-formats', | |
3065 | action='store_const', dest='format', help='download all available video formats', const='-1') | |
3066 | video_format.add_option('--max-quality', | |
3067 | action='store', dest='format_limit', metavar='FORMAT', help='highest quality format to download') | |
3068 | ||
3069 | ||
3070 | verbosity.add_option('-q', '--quiet', | |
3071 | action='store_true', dest='quiet', help='activates quiet mode', default=False) | |
3072 | verbosity.add_option('-s', '--simulate', | |
3073 | action='store_true', dest='simulate', help='do not download video', default=False) | |
3074 | verbosity.add_option('-g', '--get-url', | |
3075 | action='store_true', dest='geturl', help='simulate, quiet but print URL', default=False) | |
3076 | verbosity.add_option('-e', '--get-title', | |
3077 | action='store_true', dest='gettitle', help='simulate, quiet but print title', default=False) | |
3078 | verbosity.add_option('--get-thumbnail', | |
3079 | action='store_true', dest='getthumbnail', | |
3080 | help='simulate, quiet but print thumbnail URL', default=False) | |
3081 | verbosity.add_option('--get-description', | |
3082 | action='store_true', dest='getdescription', | |
3083 | help='simulate, quiet but print video description', default=False) | |
3084 | verbosity.add_option('--get-filename', | |
3085 | action='store_true', dest='getfilename', | |
3086 | help='simulate, quiet but print output filename', default=False) | |
3087 | verbosity.add_option('--no-progress', | |
3088 | action='store_true', dest='noprogress', help='do not print progress bar', default=False) | |
3089 | verbosity.add_option('--console-title', | |
3090 | action='store_true', dest='consoletitle', | |
3091 | help='display progress in console titlebar', default=False) | |
3092 | ||
3093 | ||
3094 | filesystem.add_option('-t', '--title', | |
3095 | action='store_true', dest='usetitle', help='use title in file name', default=False) | |
3096 | filesystem.add_option('-l', '--literal', | |
3097 | action='store_true', dest='useliteral', help='use literal title in file name', default=False) | |
3098 | filesystem.add_option('-A', '--auto-number', | |
3099 | action='store_true', dest='autonumber', | |
3100 | help='number downloaded files starting from 00000', default=False) | |
3101 | filesystem.add_option('-o', '--output', | |
3102 | dest='outtmpl', metavar='TEMPLATE', help='output filename template') | |
3103 | filesystem.add_option('-a', '--batch-file', | |
3104 | dest='batchfile', metavar='FILE', help='file containing URLs to download (\'-\' for stdin)') | |
3105 | filesystem.add_option('-w', '--no-overwrites', | |
3106 | action='store_true', dest='nooverwrites', help='do not overwrite files', default=False) | |
3107 | filesystem.add_option('-c', '--continue', | |
3108 | action='store_true', dest='continue_dl', help='resume partially downloaded files', default=False) | |
3109 | filesystem.add_option('--cookies', | |
3110 | dest='cookiefile', metavar='FILE', help='file to dump cookie jar to') | |
3111 | filesystem.add_option('--no-part', | |
3112 | action='store_true', dest='nopart', help='do not use .part files', default=False) | |
3113 | filesystem.add_option('--no-mtime', | |
3114 | action='store_false', dest='updatetime', | |
3115 | help='do not use the Last-modified header to set the file modification time', default=True) | |
2c8d32de PH |
3116 | filesystem.add_option('--write-description', |
3117 | action='store_true', dest='writedescription', | |
3118 | help='write video description to a .description file', default=False) | |
3119 | filesystem.add_option('--write-info-json', | |
3120 | action='store_true', dest='writeinfojson', | |
3121 | help='write video metadata to a .info.json file', default=False) | |
4f9f96f6 GV |
3122 | |
3123 | ||
3124 | postproc.add_option('--extract-audio', action='store_true', dest='extractaudio', default=False, | |
3125 | help='convert video files to audio-only files (requires ffmpeg and ffprobe)') | |
3126 | postproc.add_option('--audio-format', metavar='FORMAT', dest='audioformat', default='best', | |
3127 | help='"best", "aac" or "mp3"; best by default') | |
3128 | ||
3129 | ||
3130 | parser.add_option_group(general) | |
3131 | parser.add_option_group(filesystem) | |
3132 | parser.add_option_group(verbosity) | |
3133 | parser.add_option_group(video_format) | |
3134 | parser.add_option_group(authentication) | |
3135 | parser.add_option_group(postproc) | |
3136 | ||
3137 | opts, args = parser.parse_args() | |
3138 | ||
3139 | return parser, opts, args | |
3140 | ||
5adcaa43 GV |
3141 | def main(): |
3142 | parser, opts, args = parseOpts() | |
4f9f96f6 | 3143 | |
5adcaa43 GV |
3144 | # Open appropriate CookieJar |
3145 | if opts.cookiefile is None: | |
3146 | jar = cookielib.CookieJar() | |
3147 | else: | |
8cc44341 | 3148 | try: |
5adcaa43 GV |
3149 | jar = cookielib.MozillaCookieJar(opts.cookiefile) |
3150 | if os.path.isfile(opts.cookiefile) and os.access(opts.cookiefile, os.R_OK): | |
3151 | jar.load() | |
3152 | except (IOError, OSError), err: | |
3153 | sys.exit(u'ERROR: unable to open cookie file') | |
80066952 | 3154 | |
5adcaa43 GV |
3155 | # Dump user agent |
3156 | if opts.dump_user_agent: | |
3157 | print std_headers['User-Agent'] | |
3158 | sys.exit(0) | |
e7cf18cb | 3159 | |
5adcaa43 GV |
3160 | # General configuration |
3161 | cookie_processor = urllib2.HTTPCookieProcessor(jar) | |
3162 | urllib2.install_opener(urllib2.build_opener(urllib2.ProxyHandler(), cookie_processor, YoutubeDLHandler())) | |
3163 | socket.setdefaulttimeout(300) # 5 minutes should be enough (famous last words) | |
80066952 | 3164 | |
5adcaa43 GV |
3165 | # Batch file verification |
3166 | batchurls = [] | |
3167 | if opts.batchfile is not None: | |
8cc44341 | 3168 | try: |
5adcaa43 GV |
3169 | if opts.batchfile == '-': |
3170 | batchfd = sys.stdin | |
4bec29ef | 3171 | else: |
5adcaa43 GV |
3172 | batchfd = open(opts.batchfile, 'r') |
3173 | batchurls = batchfd.readlines() | |
3174 | batchurls = [x.strip() for x in batchurls] | |
3175 | batchurls = [x for x in batchurls if len(x) > 0 and not re.search(r'^[#/;]', x)] | |
3176 | except IOError: | |
3177 | sys.exit(u'ERROR: batch file could not be read') | |
3178 | all_urls = batchurls + args | |
3179 | ||
3180 | # Conflicting, missing and erroneous options | |
3181 | if opts.usenetrc and (opts.username is not None or opts.password is not None): | |
3182 | parser.error(u'using .netrc conflicts with giving username/password') | |
3183 | if opts.password is not None and opts.username is None: | |
3184 | parser.error(u'account username missing') | |
3185 | if opts.outtmpl is not None and (opts.useliteral or opts.usetitle or opts.autonumber): | |
3186 | parser.error(u'using output template conflicts with using title, literal title or auto number') | |
3187 | if opts.usetitle and opts.useliteral: | |
3188 | parser.error(u'using title conflicts with using literal title') | |
3189 | if opts.username is not None and opts.password is None: | |
3190 | opts.password = getpass.getpass(u'Type account password and press return:') | |
3191 | if opts.ratelimit is not None: | |
3192 | numeric_limit = FileDownloader.parse_bytes(opts.ratelimit) | |
3193 | if numeric_limit is None: | |
3194 | parser.error(u'invalid rate limit specified') | |
3195 | opts.ratelimit = numeric_limit | |
3196 | if opts.retries is not None: | |
8cc44341 | 3197 | try: |
5adcaa43 | 3198 | opts.retries = long(opts.retries) |
8cc44341 | 3199 | except (TypeError, ValueError), err: |
5adcaa43 GV |
3200 | parser.error(u'invalid retry count specified') |
3201 | try: | |
2c8d32de | 3202 | opts.playliststart = int(opts.playliststart) |
5adcaa43 | 3203 | if opts.playliststart <= 0: |
2c8d32de | 3204 | raise ValueError(u'Playlist start must be positive') |
5adcaa43 GV |
3205 | except (TypeError, ValueError), err: |
3206 | parser.error(u'invalid playlist start number specified') | |
3207 | try: | |
2c8d32de | 3208 | opts.playlistend = int(opts.playlistend) |
5adcaa43 | 3209 | if opts.playlistend != -1 and (opts.playlistend <= 0 or opts.playlistend < opts.playliststart): |
2c8d32de | 3210 | raise ValueError(u'Playlist end must be greater than playlist start') |
5adcaa43 GV |
3211 | except (TypeError, ValueError), err: |
3212 | parser.error(u'invalid playlist end number specified') | |
3213 | if opts.extractaudio: | |
3214 | if opts.audioformat not in ['best', 'aac', 'mp3']: | |
3215 | parser.error(u'invalid audio format specified') | |
3216 | ||
3217 | # Information extractors | |
3218 | youtube_ie = YoutubeIE() | |
3219 | metacafe_ie = MetacafeIE(youtube_ie) | |
3220 | dailymotion_ie = DailymotionIE() | |
3221 | youtube_pl_ie = YoutubePlaylistIE(youtube_ie) | |
3222 | youtube_user_ie = YoutubeUserIE(youtube_ie) | |
3223 | youtube_search_ie = YoutubeSearchIE(youtube_ie) | |
3224 | google_ie = GoogleIE() | |
3225 | google_search_ie = GoogleSearchIE(google_ie) | |
3226 | photobucket_ie = PhotobucketIE() | |
3227 | yahoo_ie = YahooIE() | |
3228 | yahoo_search_ie = YahooSearchIE(yahoo_ie) | |
3229 | deposit_files_ie = DepositFilesIE() | |
3230 | facebook_ie = FacebookIE() | |
2c8d32de | 3231 | bliptv_ie = BlipTVIE() |
5adcaa43 GV |
3232 | generic_ie = GenericIE() |
3233 | ||
3234 | # File downloader | |
3235 | fd = FileDownloader({ | |
3236 | 'usenetrc': opts.usenetrc, | |
3237 | 'username': opts.username, | |
3238 | 'password': opts.password, | |
3239 | 'quiet': (opts.quiet or opts.geturl or opts.gettitle or opts.getthumbnail or opts.getdescription or opts.getfilename), | |
3240 | 'forceurl': opts.geturl, | |
3241 | 'forcetitle': opts.gettitle, | |
3242 | 'forcethumbnail': opts.getthumbnail, | |
3243 | 'forcedescription': opts.getdescription, | |
3244 | 'forcefilename': opts.getfilename, | |
3245 | 'simulate': (opts.simulate or opts.geturl or opts.gettitle or opts.getthumbnail or opts.getdescription or opts.getfilename), | |
3246 | 'format': opts.format, | |
3247 | 'format_limit': opts.format_limit, | |
3248 | 'outtmpl': ((opts.outtmpl is not None and opts.outtmpl.decode(preferredencoding())) | |
3249 | or (opts.format == '-1' and opts.usetitle and u'%(stitle)s-%(id)s-%(format)s.%(ext)s') | |
3250 | or (opts.format == '-1' and opts.useliteral and u'%(title)s-%(id)s-%(format)s.%(ext)s') | |
3251 | or (opts.format == '-1' and u'%(id)s-%(format)s.%(ext)s') | |
3252 | or (opts.usetitle and opts.autonumber and u'%(autonumber)s-%(stitle)s-%(id)s.%(ext)s') | |
3253 | or (opts.useliteral and opts.autonumber and u'%(autonumber)s-%(title)s-%(id)s.%(ext)s') | |
3254 | or (opts.usetitle and u'%(stitle)s-%(id)s.%(ext)s') | |
3255 | or (opts.useliteral and u'%(title)s-%(id)s.%(ext)s') | |
3256 | or (opts.autonumber and u'%(autonumber)s-%(id)s.%(ext)s') | |
3257 | or u'%(id)s.%(ext)s'), | |
3258 | 'ignoreerrors': opts.ignoreerrors, | |
3259 | 'ratelimit': opts.ratelimit, | |
3260 | 'nooverwrites': opts.nooverwrites, | |
3261 | 'retries': opts.retries, | |
3262 | 'continuedl': opts.continue_dl, | |
3263 | 'noprogress': opts.noprogress, | |
3264 | 'playliststart': opts.playliststart, | |
3265 | 'playlistend': opts.playlistend, | |
3266 | 'logtostderr': opts.outtmpl == '-', | |
3267 | 'consoletitle': opts.consoletitle, | |
3268 | 'nopart': opts.nopart, | |
3269 | 'updatetime': opts.updatetime, | |
2c8d32de PH |
3270 | 'writedescription': opts.writedescription, |
3271 | 'writeinfojson': opts.writeinfojson, | |
5adcaa43 GV |
3272 | }) |
3273 | fd.add_info_extractor(youtube_search_ie) | |
3274 | fd.add_info_extractor(youtube_pl_ie) | |
3275 | fd.add_info_extractor(youtube_user_ie) | |
3276 | fd.add_info_extractor(metacafe_ie) | |
3277 | fd.add_info_extractor(dailymotion_ie) | |
3278 | fd.add_info_extractor(youtube_ie) | |
3279 | fd.add_info_extractor(google_ie) | |
3280 | fd.add_info_extractor(google_search_ie) | |
3281 | fd.add_info_extractor(photobucket_ie) | |
3282 | fd.add_info_extractor(yahoo_ie) | |
3283 | fd.add_info_extractor(yahoo_search_ie) | |
3284 | fd.add_info_extractor(deposit_files_ie) | |
3285 | fd.add_info_extractor(facebook_ie) | |
2c8d32de | 3286 | fd.add_info_extractor(bliptv_ie) |
5adcaa43 GV |
3287 | |
3288 | # This must come last since it's the | |
3289 | # fallback if none of the others work | |
3290 | fd.add_info_extractor(generic_ie) | |
3291 | ||
3292 | # PostProcessors | |
3293 | if opts.extractaudio: | |
3294 | fd.add_post_processor(FFmpegExtractAudioPP(preferredcodec=opts.audioformat)) | |
3295 | ||
3296 | # Update version | |
3297 | if opts.update_self: | |
3298 | updateSelf(fd, sys.argv[0]) | |
3299 | ||
3300 | # Maybe do nothing | |
3301 | if len(all_urls) < 1: | |
3302 | if not opts.update_self: | |
3303 | parser.error(u'you must provide at least one URL') | |
3304 | else: | |
3305 | sys.exit() | |
3306 | retcode = fd.download(all_urls) | |
80066952 | 3307 | |
5adcaa43 GV |
3308 | # Dump cookie jar if requested |
3309 | if opts.cookiefile is not None: | |
3310 | try: | |
3311 | jar.save() | |
3312 | except (IOError, OSError), err: | |
3313 | sys.exit(u'ERROR: unable to save cookie jar') | |
80066952 | 3314 | |
5adcaa43 | 3315 | sys.exit(retcode) |
80066952 | 3316 | |
4fa74b52 | 3317 | |
5adcaa43 GV |
3318 | if __name__ == '__main__': |
3319 | try: | |
3320 | main() | |
e5bf0f55 RG |
3321 | except DownloadError: |
3322 | sys.exit(1) | |
3323 | except SameFileError: | |
76a7f364 | 3324 | sys.exit(u'ERROR: fixed output name but more than one file to download') |
4fa74b52 | 3325 | except KeyboardInterrupt: |
76a7f364 | 3326 | sys.exit(u'\nERROR: Interrupted by user') |
e9cb9c28 GV |
3327 | |
3328 | # vim: set ts=4 sw=4 sts=4 noet ai si filetype=python: |