2 # -*- coding: utf-8 -*-
4 from __future__ import absolute_import
15 import xml.etree.ElementTree
22 class InfoExtractor(object):
23 """Information Extractor class.
25 Information extractors are the classes that, given a URL, extract
26 information about the video (or videos) the URL refers to. This
27 information includes the real video URL, the video title, author and
28 others. The information is stored in a dictionary which is then
29 passed to the FileDownloader. The FileDownloader processes this
30 information possibly downloading the video to the file system, among
31 other possible outcomes.
33 The dictionaries must include the following fields:
37 title: Video title, unescaped.
38 ext: Video filename extension.
40 The following fields are optional:
42 format: The video format, defaults to ext (used for --get-format)
43 thumbnail: Full URL to a video thumbnail image.
44 description: One-line video description.
45 uploader: Full name of the video uploader.
46 upload_date: Video upload date (YYYYMMDD).
47 uploader_id: Nickname or id of the video uploader.
48 location: Physical location of the video.
49 player_url: SWF Player URL (used for rtmpdump).
50 subtitles: The .srt file contents.
51 urlhandle: [internal] The urlHandle to be used to download the file,
52 like returned by urllib.request.urlopen
54 The fields should all be Unicode strings.
56 Subclasses of this one should re-define the _real_initialize() and
57 _real_extract() methods and define a _VALID_URL regexp.
58 Probably, they should also be added to the list of extractors.
60 _real_extract() must return a *list* of information dictionaries as
63 Finally, the _WORKING attribute should be set to False for broken IEs
64 in order to warn the users and skip the tests.
71 def __init__(self, downloader=None):
72 """Constructor. Receives an optional downloader."""
74 self.set_downloader(downloader)
76 def suitable(self, url):
77 """Receives a URL and returns True if suitable for this IE."""
78 return re.match(self._VALID_URL, url) is not None
81 """Getter method for _WORKING."""
85 """Initializes an instance (authentication, etc)."""
87 self._real_initialize()
90 def extract(self, url):
91 """Extracts URL information and returns it in list of dicts."""
93 return self._real_extract(url)
95 def set_downloader(self, downloader):
96 """Sets the downloader for this IE."""
97 self._downloader = downloader
99 def _real_initialize(self):
100 """Real initialization process. Redefine in subclasses."""
103 def _real_extract(self, url):
104 """Real extraction process. Redefine in subclasses."""
109 return type(self).__name__[:-2]
111 def _request_webpage(self, url_or_request, video_id, note=None, errnote=None):
112 """ Returns the response handle """
114 note = u'Downloading video webpage'
115 self._downloader.to_screen(u'[%s] %s: %s' % (self.IE_NAME, video_id, note))
117 return compat_urllib_request.urlopen(url_or_request)
118 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
120 errnote = u'Unable to download webpage'
121 raise ExtractorError(u'%s: %s' % (errnote, compat_str(err)), sys.exc_info()[2])
123 def _download_webpage(self, url_or_request, video_id, note=None, errnote=None):
124 """ Returns the data of the page as a string """
125 urlh = self._request_webpage(url_or_request, video_id, note, errnote)
126 webpage_bytes = urlh.read()
127 return webpage_bytes.decode('utf-8', 'replace')
130 class YoutubeIE(InfoExtractor):
131 """Information extractor for youtube.com."""
135 (?:https?://)? # http(s):// (optional)
136 (?:youtu\.be/|(?:\w+\.)?youtube(?:-nocookie)?\.com/|
137 tube\.majestyc\.net/) # the various hostnames, with wildcard subdomains
138 (?:.*?\#/)? # handle anchor (#/) redirect urls
139 (?!view_play_list|my_playlists|artist|playlist) # ignore playlist URLs
140 (?: # the various things that can precede the ID:
141 (?:(?:v|embed|e)/) # v/ or embed/ or e/
142 |(?: # or the v= param in all its forms
143 (?:watch(?:_popup)?(?:\.php)?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
144 (?:\?|\#!?) # the params delimiter ? or # or #!
145 (?:.*?&)? # any other preceding param (like /?s=tuff&v=xxxx)
148 )? # optional -> youtube.com/xxxx is OK
149 )? # all until now is optional -> you can pass the naked ID
150 ([0-9A-Za-z_-]+) # here is it! the YouTube video ID
151 (?(1).+)? # if we found the ID, everything can follow
153 _LANG_URL = r'http://www.youtube.com/?hl=en&persist_hl=1&gl=US&persist_gl=1&opt_out_ackd=1'
154 _LOGIN_URL = 'https://accounts.google.com/ServiceLogin'
155 _AGE_URL = 'http://www.youtube.com/verify_age?next_url=/&gl=US&hl=en'
156 _NEXT_URL_RE = r'[\?&]next_url=([^&]+)'
157 _NETRC_MACHINE = 'youtube'
158 # Listed in order of quality
159 _available_formats = ['38', '37', '46', '22', '45', '35', '44', '34', '18', '43', '6', '5', '17', '13']
160 _available_formats_prefer_free = ['38', '46', '37', '45', '22', '44', '35', '43', '34', '18', '6', '5', '17', '13']
161 _video_extensions = {
167 '38': 'video', # You actually don't know if this will be MOV, AVI or whatever
173 _video_dimensions = {
191 def suitable(self, url):
192 """Receives a URL and returns True if suitable for this IE."""
193 return re.match(self._VALID_URL, url, re.VERBOSE) is not None
195 def report_lang(self):
196 """Report attempt to set language."""
197 self._downloader.to_screen(u'[youtube] Setting language')
199 def report_login(self):
200 """Report attempt to log in."""
201 self._downloader.to_screen(u'[youtube] Logging in')
203 def report_age_confirmation(self):
204 """Report attempt to confirm age."""
205 self._downloader.to_screen(u'[youtube] Confirming age')
207 def report_video_webpage_download(self, video_id):
208 """Report attempt to download video webpage."""
209 self._downloader.to_screen(u'[youtube] %s: Downloading video webpage' % video_id)
211 def report_video_info_webpage_download(self, video_id):
212 """Report attempt to download video info webpage."""
213 self._downloader.to_screen(u'[youtube] %s: Downloading video info webpage' % video_id)
215 def report_video_subtitles_download(self, video_id):
216 """Report attempt to download video info webpage."""
217 self._downloader.to_screen(u'[youtube] %s: Downloading video subtitles' % video_id)
219 def report_information_extraction(self, video_id):
220 """Report attempt to extract video information."""
221 self._downloader.to_screen(u'[youtube] %s: Extracting video information' % video_id)
223 def report_unavailable_format(self, video_id, format):
224 """Report extracted video URL."""
225 self._downloader.to_screen(u'[youtube] %s: Format %s not available' % (video_id, format))
227 def report_rtmp_download(self):
228 """Indicate the download will use the RTMP protocol."""
229 self._downloader.to_screen(u'[youtube] RTMP download detected')
231 def _closed_captions_xml_to_srt(self, xml_string):
233 texts = re.findall(r'<text start="([\d\.]+)"( dur="([\d\.]+)")?>([^<]+)</text>', xml_string, re.MULTILINE)
234 # TODO parse xml instead of regex
235 for n, (start, dur_tag, dur, caption) in enumerate(texts):
236 if not dur: dur = '4'
238 end = start + float(dur)
239 start = "%02i:%02i:%02i,%03i" %(start/(60*60), start/60%60, start%60, start%1*1000)
240 end = "%02i:%02i:%02i,%03i" %(end/(60*60), end/60%60, end%60, end%1*1000)
241 caption = unescapeHTML(caption)
242 caption = unescapeHTML(caption) # double cycle, intentional
243 srt += str(n+1) + '\n'
244 srt += start + ' --> ' + end + '\n'
245 srt += caption + '\n\n'
248 def _extract_subtitles(self, video_id):
249 self.report_video_subtitles_download(video_id)
250 request = compat_urllib_request.Request('http://video.google.com/timedtext?hl=en&type=list&v=%s' % video_id)
252 srt_list = compat_urllib_request.urlopen(request).read().decode('utf-8')
253 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
254 return (u'WARNING: unable to download video subtitles: %s' % compat_str(err), None)
255 srt_lang_list = re.findall(r'name="([^"]*)"[^>]+lang_code="([\w\-]+)"', srt_list)
256 srt_lang_list = dict((l[1], l[0]) for l in srt_lang_list)
257 if not srt_lang_list:
258 return (u'WARNING: video has no closed captions', None)
259 if self._downloader.params.get('subtitleslang', False):
260 srt_lang = self._downloader.params.get('subtitleslang')
261 elif 'en' in srt_lang_list:
264 srt_lang = list(srt_lang_list.keys())[0]
265 if not srt_lang in srt_lang_list:
266 return (u'WARNING: no closed captions found in the specified language', None)
267 params = compat_urllib_parse.urlencode({
269 'name': srt_lang_list[srt_lang].encode('utf-8'),
272 url = 'http://www.youtube.com/api/timedtext?' + params
274 srt_xml = compat_urllib_request.urlopen(url).read().decode('utf-8')
275 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
276 return (u'WARNING: unable to download video subtitles: %s' % compat_str(err), None)
278 return (u'WARNING: Did not fetch video subtitles', None)
279 return (None, self._closed_captions_xml_to_srt(srt_xml))
281 def _print_formats(self, formats):
282 print('Available formats:')
284 print('%s\t:\t%s\t[%s]' %(x, self._video_extensions.get(x, 'flv'), self._video_dimensions.get(x, '???')))
286 def _real_initialize(self):
287 if self._downloader is None:
292 downloader_params = self._downloader.params
294 # Attempt to use provided username and password or .netrc data
295 if downloader_params.get('username', None) is not None:
296 username = downloader_params['username']
297 password = downloader_params['password']
298 elif downloader_params.get('usenetrc', False):
300 info = netrc.netrc().authenticators(self._NETRC_MACHINE)
305 raise netrc.NetrcParseError('No authenticators for %s' % self._NETRC_MACHINE)
306 except (IOError, netrc.NetrcParseError) as err:
307 self._downloader.to_stderr(u'WARNING: parsing .netrc: %s' % compat_str(err))
311 request = compat_urllib_request.Request(self._LANG_URL)
314 compat_urllib_request.urlopen(request).read()
315 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
316 self._downloader.to_stderr(u'WARNING: unable to set language: %s' % compat_str(err))
319 # No authentication to be performed
323 request = compat_urllib_request.Request(self._LOGIN_URL)
325 login_page = compat_urllib_request.urlopen(request).read().decode('utf-8')
326 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
327 self._downloader.to_stderr(u'WARNING: unable to fetch login page: %s' % compat_str(err))
332 match = re.search(re.compile(r'<input.+?name="GALX".+?value="(.+?)"', re.DOTALL), login_page)
334 galx = match.group(1)
336 match = re.search(re.compile(r'<input.+?name="dsh".+?value="(.+?)"', re.DOTALL), login_page)
342 u'continue': u'http://www.youtube.com/signin?action_handle_signin=true&feature=sign_in_button&hl=en_US&nomobiletemp=1',
346 u'PersistentCookie': u'yes',
348 u'bgresponse': u'js_disabled',
349 u'checkConnection': u'',
350 u'checkedDomains': u'youtube',
356 u'signIn': u'Sign in',
358 u'service': u'youtube',
362 # Convert to UTF-8 *before* urlencode because Python 2.x's urlencode
364 login_form = dict((k.encode('utf-8'), v.encode('utf-8')) for k,v in login_form_strs.items())
365 login_data = compat_urllib_parse.urlencode(login_form).encode('ascii')
366 request = compat_urllib_request.Request(self._LOGIN_URL, login_data)
369 login_results = compat_urllib_request.urlopen(request).read().decode('utf-8')
370 if re.search(r'(?i)<form[^>]* id="gaia_loginform"', login_results) is not None:
371 self._downloader.to_stderr(u'WARNING: unable to log in: bad username or password')
373 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
374 self._downloader.to_stderr(u'WARNING: unable to log in: %s' % compat_str(err))
380 'action_confirm': 'Confirm',
382 request = compat_urllib_request.Request(self._AGE_URL, compat_urllib_parse.urlencode(age_form))
384 self.report_age_confirmation()
385 age_results = compat_urllib_request.urlopen(request).read().decode('utf-8')
386 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
387 self._downloader.trouble(u'ERROR: unable to confirm age: %s' % compat_str(err))
390 def _extract_id(self, url):
391 mobj = re.match(self._VALID_URL, url, re.VERBOSE)
393 self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
395 video_id = mobj.group(2)
398 def _real_extract(self, url):
399 # Extract original video URL from URL with redirection, like age verification, using next_url parameter
400 mobj = re.search(self._NEXT_URL_RE, url)
402 url = 'http://www.youtube.com/' + compat_urllib_parse.unquote(mobj.group(1)).lstrip('/')
403 video_id = self._extract_id(url)
406 self.report_video_webpage_download(video_id)
407 url = 'http://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1' % video_id
408 request = compat_urllib_request.Request(url)
410 video_webpage_bytes = compat_urllib_request.urlopen(request).read()
411 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
412 self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % compat_str(err))
415 video_webpage = video_webpage_bytes.decode('utf-8', 'ignore')
417 # Attempt to extract SWF player URL
418 mobj = re.search(r'swfConfig.*?"(http:\\/\\/.*?watch.*?-.*?\.swf)"', video_webpage)
420 player_url = re.sub(r'\\(.)', r'\1', mobj.group(1))
425 self.report_video_info_webpage_download(video_id)
426 for el_type in ['&el=embedded', '&el=detailpage', '&el=vevo', '']:
427 video_info_url = ('http://www.youtube.com/get_video_info?&video_id=%s%s&ps=default&eurl=&gl=US&hl=en'
428 % (video_id, el_type))
429 request = compat_urllib_request.Request(video_info_url)
431 video_info_webpage_bytes = compat_urllib_request.urlopen(request).read()
432 video_info_webpage = video_info_webpage_bytes.decode('utf-8', 'ignore')
433 video_info = compat_parse_qs(video_info_webpage)
434 if 'token' in video_info:
436 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
437 self._downloader.trouble(u'ERROR: unable to download video info webpage: %s' % compat_str(err))
439 if 'token' not in video_info:
440 if 'reason' in video_info:
441 self._downloader.trouble(u'ERROR: YouTube said: %s' % video_info['reason'][0])
443 self._downloader.trouble(u'ERROR: "token" parameter not in video info for unknown reason')
446 # Check for "rental" videos
447 if 'ypc_video_rental_bar_text' in video_info and 'author' not in video_info:
448 self._downloader.trouble(u'ERROR: "rental" videos not supported')
451 # Start extracting information
452 self.report_information_extraction(video_id)
455 if 'author' not in video_info:
456 self._downloader.trouble(u'ERROR: unable to extract uploader name')
458 video_uploader = compat_urllib_parse.unquote_plus(video_info['author'][0])
461 video_uploader_id = None
462 mobj = re.search(r'<link itemprop="url" href="http://www.youtube.com/(?:user|channel)/([^"]+)">', video_webpage)
464 video_uploader_id = mobj.group(1)
466 self._downloader.trouble(u'WARNING: unable to extract uploader nickname')
469 if 'title' not in video_info:
470 self._downloader.trouble(u'ERROR: unable to extract video title')
472 video_title = compat_urllib_parse.unquote_plus(video_info['title'][0])
475 if 'thumbnail_url' not in video_info:
476 self._downloader.trouble(u'WARNING: unable to extract video thumbnail')
478 else: # don't panic if we can't find it
479 video_thumbnail = compat_urllib_parse.unquote_plus(video_info['thumbnail_url'][0])
483 mobj = re.search(r'id="eow-date.*?>(.*?)</span>', video_webpage, re.DOTALL)
485 upload_date = ' '.join(re.sub(r'[/,-]', r' ', mobj.group(1)).split())
486 format_expressions = ['%d %B %Y', '%B %d %Y', '%b %d %Y']
487 for expression in format_expressions:
489 upload_date = datetime.datetime.strptime(upload_date, expression).strftime('%Y%m%d')
494 video_description = get_element_by_id("eow-description", video_webpage)
495 if video_description:
496 video_description = clean_html(video_description)
498 video_description = ''
501 video_subtitles = None
502 if self._downloader.params.get('writesubtitles', False):
503 (srt_error, video_subtitles) = self._extract_subtitles(video_id)
505 self._downloader.trouble(srt_error)
507 if 'length_seconds' not in video_info:
508 self._downloader.trouble(u'WARNING: unable to extract video duration')
511 video_duration = compat_urllib_parse.unquote_plus(video_info['length_seconds'][0])
514 video_token = compat_urllib_parse.unquote_plus(video_info['token'][0])
516 # Decide which formats to download
517 req_format = self._downloader.params.get('format', None)
519 if 'conn' in video_info and video_info['conn'][0].startswith('rtmp'):
520 self.report_rtmp_download()
521 video_url_list = [(None, video_info['conn'][0])]
522 elif 'url_encoded_fmt_stream_map' in video_info and len(video_info['url_encoded_fmt_stream_map']) >= 1:
523 url_data_strs = video_info['url_encoded_fmt_stream_map'][0].split(',')
524 url_data = [compat_parse_qs(uds) for uds in url_data_strs]
525 url_data = [ud for ud in url_data if 'itag' in ud and 'url' in ud]
526 url_map = dict((ud['itag'][0], ud['url'][0] + '&signature=' + ud['sig'][0]) for ud in url_data)
528 format_limit = self._downloader.params.get('format_limit', None)
529 available_formats = self._available_formats_prefer_free if self._downloader.params.get('prefer_free_formats', False) else self._available_formats
530 if format_limit is not None and format_limit in available_formats:
531 format_list = available_formats[available_formats.index(format_limit):]
533 format_list = available_formats
534 existing_formats = [x for x in format_list if x in url_map]
535 if len(existing_formats) == 0:
536 self._downloader.trouble(u'ERROR: no known formats available for video')
538 if self._downloader.params.get('listformats', None):
539 self._print_formats(existing_formats)
541 if req_format is None or req_format == 'best':
542 video_url_list = [(existing_formats[0], url_map[existing_formats[0]])] # Best quality
543 elif req_format == 'worst':
544 video_url_list = [(existing_formats[len(existing_formats)-1], url_map[existing_formats[len(existing_formats)-1]])] # worst quality
545 elif req_format in ('-1', 'all'):
546 video_url_list = [(f, url_map[f]) for f in existing_formats] # All formats
548 # Specific formats. We pick the first in a slash-delimeted sequence.
549 # For example, if '1/2/3/4' is requested and '2' and '4' are available, we pick '2'.
550 req_formats = req_format.split('/')
551 video_url_list = None
552 for rf in req_formats:
554 video_url_list = [(rf, url_map[rf])]
556 if video_url_list is None:
557 self._downloader.trouble(u'ERROR: requested format not available')
560 self._downloader.trouble(u'ERROR: no conn or url_encoded_fmt_stream_map information found in video info')
564 for format_param, video_real_url in video_url_list:
566 video_extension = self._video_extensions.get(format_param, 'flv')
568 video_format = '{0} - {1}'.format(format_param if format_param else video_extension,
569 self._video_dimensions.get(format_param, '???'))
573 'url': video_real_url,
574 'uploader': video_uploader,
575 'uploader_id': video_uploader_id,
576 'upload_date': upload_date,
577 'title': video_title,
578 'ext': video_extension,
579 'format': video_format,
580 'thumbnail': video_thumbnail,
581 'description': video_description,
582 'player_url': player_url,
583 'subtitles': video_subtitles,
584 'duration': video_duration
589 class MetacafeIE(InfoExtractor):
590 """Information Extractor for metacafe.com."""
592 _VALID_URL = r'(?:http://)?(?:www\.)?metacafe\.com/watch/([^/]+)/([^/]+)/.*'
593 _DISCLAIMER = 'http://www.metacafe.com/family_filter/'
594 _FILTER_POST = 'http://www.metacafe.com/f/index.php?inputType=filter&controllerGroup=user'
595 IE_NAME = u'metacafe'
597 def __init__(self, downloader=None):
598 InfoExtractor.__init__(self, downloader)
600 def report_disclaimer(self):
601 """Report disclaimer retrieval."""
602 self._downloader.to_screen(u'[metacafe] Retrieving disclaimer')
604 def report_age_confirmation(self):
605 """Report attempt to confirm age."""
606 self._downloader.to_screen(u'[metacafe] Confirming age')
608 def report_download_webpage(self, video_id):
609 """Report webpage download."""
610 self._downloader.to_screen(u'[metacafe] %s: Downloading webpage' % video_id)
612 def report_extraction(self, video_id):
613 """Report information extraction."""
614 self._downloader.to_screen(u'[metacafe] %s: Extracting information' % video_id)
616 def _real_initialize(self):
617 # Retrieve disclaimer
618 request = compat_urllib_request.Request(self._DISCLAIMER)
620 self.report_disclaimer()
621 disclaimer = compat_urllib_request.urlopen(request).read()
622 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
623 self._downloader.trouble(u'ERROR: unable to retrieve disclaimer: %s' % compat_str(err))
629 'submit': "Continue - I'm over 18",
631 request = compat_urllib_request.Request(self._FILTER_POST, compat_urllib_parse.urlencode(disclaimer_form))
633 self.report_age_confirmation()
634 disclaimer = compat_urllib_request.urlopen(request).read()
635 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
636 self._downloader.trouble(u'ERROR: unable to confirm age: %s' % compat_str(err))
639 def _real_extract(self, url):
640 # Extract id and simplified title from URL
641 mobj = re.match(self._VALID_URL, url)
643 self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
646 video_id = mobj.group(1)
648 # Check if video comes from YouTube
649 mobj2 = re.match(r'^yt-(.*)$', video_id)
650 if mobj2 is not None:
651 self._downloader.download(['http://www.youtube.com/watch?v=%s' % mobj2.group(1)])
654 # Retrieve video webpage to extract further information
655 request = compat_urllib_request.Request('http://www.metacafe.com/watch/%s/' % video_id)
657 self.report_download_webpage(video_id)
658 webpage = compat_urllib_request.urlopen(request).read()
659 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
660 self._downloader.trouble(u'ERROR: unable retrieve video webpage: %s' % compat_str(err))
663 # Extract URL, uploader and title from webpage
664 self.report_extraction(video_id)
665 mobj = re.search(r'(?m)&mediaURL=([^&]+)', webpage)
667 mediaURL = compat_urllib_parse.unquote(mobj.group(1))
668 video_extension = mediaURL[-3:]
670 # Extract gdaKey if available
671 mobj = re.search(r'(?m)&gdaKey=(.*?)&', webpage)
675 gdaKey = mobj.group(1)
676 video_url = '%s?__gda__=%s' % (mediaURL, gdaKey)
678 mobj = re.search(r' name="flashvars" value="(.*?)"', webpage)
680 self._downloader.trouble(u'ERROR: unable to extract media URL')
682 vardict = compat_parse_qs(mobj.group(1))
683 if 'mediaData' not in vardict:
684 self._downloader.trouble(u'ERROR: unable to extract media URL')
686 mobj = re.search(r'"mediaURL":"(http.*?)","key":"(.*?)"', vardict['mediaData'][0])
688 self._downloader.trouble(u'ERROR: unable to extract media URL')
690 mediaURL = mobj.group(1).replace('\\/', '/')
691 video_extension = mediaURL[-3:]
692 video_url = '%s?__gda__=%s' % (mediaURL, mobj.group(2))
694 mobj = re.search(r'(?im)<title>(.*) - Video</title>', webpage)
696 self._downloader.trouble(u'ERROR: unable to extract title')
698 video_title = mobj.group(1).decode('utf-8')
700 mobj = re.search(r'submitter=(.*?);', webpage)
702 self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
704 video_uploader = mobj.group(1)
707 'id': video_id.decode('utf-8'),
708 'url': video_url.decode('utf-8'),
709 'uploader': video_uploader.decode('utf-8'),
711 'title': video_title,
712 'ext': video_extension.decode('utf-8'),
716 class DailymotionIE(InfoExtractor):
717 """Information Extractor for Dailymotion"""
719 _VALID_URL = r'(?i)(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/video/([^/]+)'
720 IE_NAME = u'dailymotion'
723 def __init__(self, downloader=None):
724 InfoExtractor.__init__(self, downloader)
726 def report_extraction(self, video_id):
727 """Report information extraction."""
728 self._downloader.to_screen(u'[dailymotion] %s: Extracting information' % video_id)
730 def _real_extract(self, url):
731 # Extract id and simplified title from URL
732 mobj = re.match(self._VALID_URL, url)
734 self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
737 video_id = mobj.group(1).split('_')[0].split('?')[0]
739 video_extension = 'mp4'
741 # Retrieve video webpage to extract further information
742 request = compat_urllib_request.Request(url)
743 request.add_header('Cookie', 'family_filter=off')
744 webpage = self._download_webpage(request, video_id)
746 # Extract URL, uploader and title from webpage
747 self.report_extraction(video_id)
748 mobj = re.search(r'\s*var flashvars = (.*)', webpage)
750 self._downloader.trouble(u'ERROR: unable to extract media URL')
752 flashvars = compat_urllib_parse.unquote(mobj.group(1))
754 for key in ['hd1080URL', 'hd720URL', 'hqURL', 'sdURL', 'ldURL', 'video_url']:
757 self._downloader.to_screen(u'[dailymotion] Using %s' % key)
760 self._downloader.trouble(u'ERROR: unable to extract video URL')
763 mobj = re.search(r'"' + max_quality + r'":"(.+?)"', flashvars)
765 self._downloader.trouble(u'ERROR: unable to extract video URL')
768 video_url = compat_urllib_parse.unquote(mobj.group(1)).replace('\\/', '/')
770 # TODO: support choosing qualities
772 mobj = re.search(r'<meta property="og:title" content="(?P<title>[^"]*)" />', webpage)
774 self._downloader.trouble(u'ERROR: unable to extract title')
776 video_title = unescapeHTML(mobj.group('title'))
778 video_uploader = None
779 mobj = re.search(r'(?im)<span class="owner[^\"]+?">[^<]+?<a [^>]+?>([^<]+?)</a>', webpage)
781 # lookin for official user
782 mobj_official = re.search(r'<span rel="author"[^>]+?>([^<]+?)</span>', webpage)
783 if mobj_official is None:
784 self._downloader.trouble(u'WARNING: unable to extract uploader nickname')
786 video_uploader = mobj_official.group(1)
788 video_uploader = mobj.group(1)
790 video_upload_date = None
791 mobj = re.search(r'<div class="[^"]*uploaded_cont[^"]*" title="[^"]*">([0-9]{2})-([0-9]{2})-([0-9]{4})</div>', webpage)
793 video_upload_date = mobj.group(3) + mobj.group(2) + mobj.group(1)
798 'uploader': video_uploader,
799 'upload_date': video_upload_date,
800 'title': video_title,
801 'ext': video_extension,
805 class PhotobucketIE(InfoExtractor):
806 """Information extractor for photobucket.com."""
808 _VALID_URL = r'(?:http://)?(?:[a-z0-9]+\.)?photobucket\.com/.*[\?\&]current=(.*\.flv)'
809 IE_NAME = u'photobucket'
811 def __init__(self, downloader=None):
812 InfoExtractor.__init__(self, downloader)
814 def report_download_webpage(self, video_id):
815 """Report webpage download."""
816 self._downloader.to_screen(u'[photobucket] %s: Downloading webpage' % video_id)
818 def report_extraction(self, video_id):
819 """Report information extraction."""
820 self._downloader.to_screen(u'[photobucket] %s: Extracting information' % video_id)
822 def _real_extract(self, url):
823 # Extract id from URL
824 mobj = re.match(self._VALID_URL, url)
826 self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
829 video_id = mobj.group(1)
831 video_extension = 'flv'
833 # Retrieve video webpage to extract further information
834 request = compat_urllib_request.Request(url)
836 self.report_download_webpage(video_id)
837 webpage = compat_urllib_request.urlopen(request).read()
838 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
839 self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err))
842 # Extract URL, uploader, and title from webpage
843 self.report_extraction(video_id)
844 mobj = re.search(r'<link rel="video_src" href=".*\?file=([^"]+)" />', webpage)
846 self._downloader.trouble(u'ERROR: unable to extract media URL')
848 mediaURL = compat_urllib_parse.unquote(mobj.group(1))
852 mobj = re.search(r'<title>(.*) video by (.*) - Photobucket</title>', webpage)
854 self._downloader.trouble(u'ERROR: unable to extract title')
856 video_title = mobj.group(1).decode('utf-8')
858 video_uploader = mobj.group(2).decode('utf-8')
861 'id': video_id.decode('utf-8'),
862 'url': video_url.decode('utf-8'),
863 'uploader': video_uploader,
865 'title': video_title,
866 'ext': video_extension.decode('utf-8'),
870 class YahooIE(InfoExtractor):
871 """Information extractor for video.yahoo.com."""
874 # _VALID_URL matches all Yahoo! Video URLs
875 # _VPAGE_URL matches only the extractable '/watch/' URLs
876 _VALID_URL = r'(?:http://)?(?:[a-z]+\.)?video\.yahoo\.com/(?:watch|network)/([0-9]+)(?:/|\?v=)([0-9]+)(?:[#\?].*)?'
877 _VPAGE_URL = r'(?:http://)?video\.yahoo\.com/watch/([0-9]+)/([0-9]+)(?:[#\?].*)?'
878 IE_NAME = u'video.yahoo'
880 def __init__(self, downloader=None):
881 InfoExtractor.__init__(self, downloader)
883 def report_download_webpage(self, video_id):
884 """Report webpage download."""
885 self._downloader.to_screen(u'[video.yahoo] %s: Downloading webpage' % video_id)
887 def report_extraction(self, video_id):
888 """Report information extraction."""
889 self._downloader.to_screen(u'[video.yahoo] %s: Extracting information' % video_id)
891 def _real_extract(self, url, new_video=True):
892 # Extract ID from URL
893 mobj = re.match(self._VALID_URL, url)
895 self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
898 video_id = mobj.group(2)
899 video_extension = 'flv'
901 # Rewrite valid but non-extractable URLs as
902 # extractable English language /watch/ URLs
903 if re.match(self._VPAGE_URL, url) is None:
904 request = compat_urllib_request.Request(url)
906 webpage = compat_urllib_request.urlopen(request).read()
907 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
908 self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err))
911 mobj = re.search(r'\("id", "([0-9]+)"\);', webpage)
913 self._downloader.trouble(u'ERROR: Unable to extract id field')
915 yahoo_id = mobj.group(1)
917 mobj = re.search(r'\("vid", "([0-9]+)"\);', webpage)
919 self._downloader.trouble(u'ERROR: Unable to extract vid field')
921 yahoo_vid = mobj.group(1)
923 url = 'http://video.yahoo.com/watch/%s/%s' % (yahoo_vid, yahoo_id)
924 return self._real_extract(url, new_video=False)
926 # Retrieve video webpage to extract further information
927 request = compat_urllib_request.Request(url)
929 self.report_download_webpage(video_id)
930 webpage = compat_urllib_request.urlopen(request).read()
931 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
932 self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err))
935 # Extract uploader and title from webpage
936 self.report_extraction(video_id)
937 mobj = re.search(r'<meta name="title" content="(.*)" />', webpage)
939 self._downloader.trouble(u'ERROR: unable to extract video title')
941 video_title = mobj.group(1).decode('utf-8')
943 mobj = re.search(r'<h2 class="ti-5"><a href="http://video\.yahoo\.com/(people|profile)/[0-9]+" beacon=".*">(.*)</a></h2>', webpage)
945 self._downloader.trouble(u'ERROR: unable to extract video uploader')
947 video_uploader = mobj.group(1).decode('utf-8')
949 # Extract video thumbnail
950 mobj = re.search(r'<link rel="image_src" href="(.*)" />', webpage)
952 self._downloader.trouble(u'ERROR: unable to extract video thumbnail')
954 video_thumbnail = mobj.group(1).decode('utf-8')
956 # Extract video description
957 mobj = re.search(r'<meta name="description" content="(.*)" />', webpage)
959 self._downloader.trouble(u'ERROR: unable to extract video description')
961 video_description = mobj.group(1).decode('utf-8')
962 if not video_description:
963 video_description = 'No description available.'
965 # Extract video height and width
966 mobj = re.search(r'<meta name="video_height" content="([0-9]+)" />', webpage)
968 self._downloader.trouble(u'ERROR: unable to extract video height')
970 yv_video_height = mobj.group(1)
972 mobj = re.search(r'<meta name="video_width" content="([0-9]+)" />', webpage)
974 self._downloader.trouble(u'ERROR: unable to extract video width')
976 yv_video_width = mobj.group(1)
978 # Retrieve video playlist to extract media URL
979 # I'm not completely sure what all these options are, but we
980 # seem to need most of them, otherwise the server sends a 401.
981 yv_lg = 'R0xx6idZnW2zlrKP8xxAIR' # not sure what this represents
982 yv_bitrate = '700' # according to Wikipedia this is hard-coded
983 request = compat_urllib_request.Request('http://cosmos.bcst.yahoo.com/up/yep/process/getPlaylistFOP.php?node_id=' + video_id +
984 '&tech=flash&mode=playlist&lg=' + yv_lg + '&bitrate=' + yv_bitrate + '&vidH=' + yv_video_height +
985 '&vidW=' + yv_video_width + '&swf=as3&rd=video.yahoo.com&tk=null&adsupported=v1,v2,&eventid=1301797')
987 self.report_download_webpage(video_id)
988 webpage = compat_urllib_request.urlopen(request).read()
989 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
990 self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err))
993 # Extract media URL from playlist XML
994 mobj = re.search(r'<STREAM APP="(http://.*)" FULLPATH="/?(/.*\.flv\?[^"]*)"', webpage)
996 self._downloader.trouble(u'ERROR: Unable to extract media URL')
998 video_url = compat_urllib_parse.unquote(mobj.group(1) + mobj.group(2)).decode('utf-8')
999 video_url = unescapeHTML(video_url)
1002 'id': video_id.decode('utf-8'),
1004 'uploader': video_uploader,
1005 'upload_date': None,
1006 'title': video_title,
1007 'ext': video_extension.decode('utf-8'),
1008 'thumbnail': video_thumbnail.decode('utf-8'),
1009 'description': video_description,
1013 class VimeoIE(InfoExtractor):
1014 """Information extractor for vimeo.com."""
1016 # _VALID_URL matches Vimeo URLs
1017 _VALID_URL = r'(?P<proto>https?://)?(?:(?:www|player)\.)?vimeo\.com/(?:(?:groups|album)/[^/]+/)?(?P<direct_link>play_redirect_hls\?clip_id=)?(?:videos?/)?(?P<id>[0-9]+)'
1020 def __init__(self, downloader=None):
1021 InfoExtractor.__init__(self, downloader)
1023 def report_download_webpage(self, video_id):
1024 """Report webpage download."""
1025 self._downloader.to_screen(u'[vimeo] %s: Downloading webpage' % video_id)
1027 def report_extraction(self, video_id):
1028 """Report information extraction."""
1029 self._downloader.to_screen(u'[vimeo] %s: Extracting information' % video_id)
1031 def _real_extract(self, url, new_video=True):
1032 # Extract ID from URL
1033 mobj = re.match(self._VALID_URL, url)
1035 self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
1038 video_id = mobj.group('id')
1039 if not mobj.group('proto'):
1040 url = 'https://' + url
1041 if mobj.group('direct_link'):
1042 url = 'https://vimeo.com/' + video_id
1044 # Retrieve video webpage to extract further information
1045 request = compat_urllib_request.Request(url, None, std_headers)
1047 self.report_download_webpage(video_id)
1048 webpage_bytes = compat_urllib_request.urlopen(request).read()
1049 webpage = webpage_bytes.decode('utf-8')
1050 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
1051 self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err))
1054 # Now we begin extracting as much information as we can from what we
1055 # retrieved. First we extract the information common to all extractors,
1056 # and latter we extract those that are Vimeo specific.
1057 self.report_extraction(video_id)
1059 # Extract the config JSON
1061 config = webpage.split(' = {config:')[1].split(',assets:')[0]
1062 config = json.loads(config)
1064 self._downloader.trouble(u'ERROR: unable to extract info section')
1068 video_title = config["video"]["title"]
1070 # Extract uploader and uploader_id
1071 video_uploader = config["video"]["owner"]["name"]
1072 video_uploader_id = config["video"]["owner"]["url"].split('/')[-1]
1074 # Extract video thumbnail
1075 video_thumbnail = config["video"]["thumbnail"]
1077 # Extract video description
1078 video_description = get_element_by_attribute("itemprop", "description", webpage)
1079 if video_description: video_description = clean_html(video_description)
1080 else: video_description = ''
1082 # Extract upload date
1083 video_upload_date = None
1084 mobj = re.search(r'<meta itemprop="dateCreated" content="(\d{4})-(\d{2})-(\d{2})T', webpage)
1085 if mobj is not None:
1086 video_upload_date = mobj.group(1) + mobj.group(2) + mobj.group(3)
1088 # Vimeo specific: extract request signature and timestamp
1089 sig = config['request']['signature']
1090 timestamp = config['request']['timestamp']
1092 # Vimeo specific: extract video codec and quality information
1093 # First consider quality, then codecs, then take everything
1094 # TODO bind to format param
1095 codecs = [('h264', 'mp4'), ('vp8', 'flv'), ('vp6', 'flv')]
1096 files = { 'hd': [], 'sd': [], 'other': []}
1097 for codec_name, codec_extension in codecs:
1098 if codec_name in config["video"]["files"]:
1099 if 'hd' in config["video"]["files"][codec_name]:
1100 files['hd'].append((codec_name, codec_extension, 'hd'))
1101 elif 'sd' in config["video"]["files"][codec_name]:
1102 files['sd'].append((codec_name, codec_extension, 'sd'))
1104 files['other'].append((codec_name, codec_extension, config["video"]["files"][codec_name][0]))
1106 for quality in ('hd', 'sd', 'other'):
1107 if len(files[quality]) > 0:
1108 video_quality = files[quality][0][2]
1109 video_codec = files[quality][0][0]
1110 video_extension = files[quality][0][1]
1111 self._downloader.to_screen(u'[vimeo] %s: Downloading %s file at %s quality' % (video_id, video_codec.upper(), video_quality))
1114 self._downloader.trouble(u'ERROR: no known codec found')
1117 video_url = "http://player.vimeo.com/play_redirect?clip_id=%s&sig=%s&time=%s&quality=%s&codecs=%s&type=moogaloop_local&embed_location=" \
1118 %(video_id, sig, timestamp, video_quality, video_codec.upper())
1123 'uploader': video_uploader,
1124 'uploader_id': video_uploader_id,
1125 'upload_date': video_upload_date,
1126 'title': video_title,
1127 'ext': video_extension,
1128 'thumbnail': video_thumbnail,
1129 'description': video_description,
1133 class ArteTvIE(InfoExtractor):
1134 """arte.tv information extractor."""
1136 _VALID_URL = r'(?:http://)?videos\.arte\.tv/(?:fr|de)/videos/.*'
1137 _LIVE_URL = r'index-[0-9]+\.html$'
1139 IE_NAME = u'arte.tv'
1141 def __init__(self, downloader=None):
1142 InfoExtractor.__init__(self, downloader)
1144 def report_download_webpage(self, video_id):
1145 """Report webpage download."""
1146 self._downloader.to_screen(u'[arte.tv] %s: Downloading webpage' % video_id)
1148 def report_extraction(self, video_id):
1149 """Report information extraction."""
1150 self._downloader.to_screen(u'[arte.tv] %s: Extracting information' % video_id)
1152 def fetch_webpage(self, url):
1153 request = compat_urllib_request.Request(url)
1155 self.report_download_webpage(url)
1156 webpage = compat_urllib_request.urlopen(request).read()
1157 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
1158 self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err))
1160 except ValueError as err:
1161 self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
1165 def grep_webpage(self, url, regex, regexFlags, matchTuples):
1166 page = self.fetch_webpage(url)
1167 mobj = re.search(regex, page, regexFlags)
1171 self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
1174 for (i, key, err) in matchTuples:
1175 if mobj.group(i) is None:
1176 self._downloader.trouble(err)
1179 info[key] = mobj.group(i)
1183 def extractLiveStream(self, url):
1184 video_lang = url.split('/')[-4]
1185 info = self.grep_webpage(
1187 r'src="(.*?/videothek_js.*?\.js)',
1190 (1, 'url', u'ERROR: Invalid URL: %s' % url)
1193 http_host = url.split('/')[2]
1194 next_url = 'http://%s%s' % (http_host, compat_urllib_parse.unquote(info.get('url')))
1195 info = self.grep_webpage(
1197 r'(s_artestras_scst_geoFRDE_' + video_lang + '.*?)\'.*?' +
1198 '(http://.*?\.swf).*?' +
1202 (1, 'path', u'ERROR: could not extract video path: %s' % url),
1203 (2, 'player', u'ERROR: could not extract video player: %s' % url),
1204 (3, 'url', u'ERROR: could not extract video url: %s' % url)
1207 video_url = u'%s/%s' % (info.get('url'), info.get('path'))
1209 def extractPlus7Stream(self, url):
1210 video_lang = url.split('/')[-3]
1211 info = self.grep_webpage(
1213 r'param name="movie".*?videorefFileUrl=(http[^\'"&]*)',
1216 (1, 'url', u'ERROR: Invalid URL: %s' % url)
1219 next_url = compat_urllib_parse.unquote(info.get('url'))
1220 info = self.grep_webpage(
1222 r'<video lang="%s" ref="(http[^\'"&]*)' % video_lang,
1225 (1, 'url', u'ERROR: Could not find <video> tag: %s' % url)
1228 next_url = compat_urllib_parse.unquote(info.get('url'))
1230 info = self.grep_webpage(
1232 r'<video id="(.*?)".*?>.*?' +
1233 '<name>(.*?)</name>.*?' +
1234 '<dateVideo>(.*?)</dateVideo>.*?' +
1235 '<url quality="hd">(.*?)</url>',
1238 (1, 'id', u'ERROR: could not extract video id: %s' % url),
1239 (2, 'title', u'ERROR: could not extract video title: %s' % url),
1240 (3, 'date', u'ERROR: could not extract video date: %s' % url),
1241 (4, 'url', u'ERROR: could not extract video url: %s' % url)
1246 'id': info.get('id'),
1247 'url': compat_urllib_parse.unquote(info.get('url')),
1248 'uploader': u'arte.tv',
1249 'upload_date': info.get('date'),
1250 'title': info.get('title').decode('utf-8'),
1256 def _real_extract(self, url):
1257 video_id = url.split('/')[-1]
1258 self.report_extraction(video_id)
1260 if re.search(self._LIVE_URL, video_id) is not None:
1261 self.extractLiveStream(url)
1264 info = self.extractPlus7Stream(url)
1269 class GenericIE(InfoExtractor):
1270 """Generic last-resort information extractor."""
1273 IE_NAME = u'generic'
1275 def __init__(self, downloader=None):
1276 InfoExtractor.__init__(self, downloader)
1278 def report_download_webpage(self, video_id):
1279 """Report webpage download."""
1280 self._downloader.to_screen(u'WARNING: Falling back on generic information extractor.')
1281 self._downloader.to_screen(u'[generic] %s: Downloading webpage' % video_id)
1283 def report_extraction(self, video_id):
1284 """Report information extraction."""
1285 self._downloader.to_screen(u'[generic] %s: Extracting information' % video_id)
1287 def report_following_redirect(self, new_url):
1288 """Report information extraction."""
1289 self._downloader.to_screen(u'[redirect] Following redirect to %s' % new_url)
1291 def _test_redirect(self, url):
1292 """Check if it is a redirect, like url shorteners, in case restart chain."""
1293 class HeadRequest(compat_urllib_request.Request):
1294 def get_method(self):
1297 class HEADRedirectHandler(compat_urllib_request.HTTPRedirectHandler):
1299 Subclass the HTTPRedirectHandler to make it use our
1300 HeadRequest also on the redirected URL
1302 def redirect_request(self, req, fp, code, msg, headers, newurl):
1303 if code in (301, 302, 303, 307):
1304 newurl = newurl.replace(' ', '%20')
1305 newheaders = dict((k,v) for k,v in req.headers.items()
1306 if k.lower() not in ("content-length", "content-type"))
1307 return HeadRequest(newurl,
1309 origin_req_host=req.get_origin_req_host(),
1312 raise compat_urllib_error.HTTPError(req.get_full_url(), code, msg, headers, fp)
1314 class HTTPMethodFallback(compat_urllib_request.BaseHandler):
1316 Fallback to GET if HEAD is not allowed (405 HTTP error)
1318 def http_error_405(self, req, fp, code, msg, headers):
1322 newheaders = dict((k,v) for k,v in req.headers.items()
1323 if k.lower() not in ("content-length", "content-type"))
1324 return self.parent.open(compat_urllib_request.Request(req.get_full_url(),
1326 origin_req_host=req.get_origin_req_host(),
1330 opener = compat_urllib_request.OpenerDirector()
1331 for handler in [compat_urllib_request.HTTPHandler, compat_urllib_request.HTTPDefaultErrorHandler,
1332 HTTPMethodFallback, HEADRedirectHandler,
1333 compat_urllib_error.HTTPErrorProcessor, compat_urllib_request.HTTPSHandler]:
1334 opener.add_handler(handler())
1336 response = opener.open(HeadRequest(url))
1337 new_url = response.geturl()
1342 self.report_following_redirect(new_url)
1343 self._downloader.download([new_url])
1346 def _real_extract(self, url):
1347 if self._test_redirect(url): return
1349 video_id = url.split('/')[-1]
1350 request = compat_urllib_request.Request(url)
1352 self.report_download_webpage(video_id)
1353 webpage = compat_urllib_request.urlopen(request).read()
1354 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
1355 self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err))
1357 except ValueError as err:
1358 # since this is the last-resort InfoExtractor, if
1359 # this error is thrown, it'll be thrown here
1360 self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
1363 self.report_extraction(video_id)
1364 # Start with something easy: JW Player in SWFObject
1365 mobj = re.search(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage)
1367 # Broaden the search a little bit
1368 mobj = re.search(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage)
1370 self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
1373 # It's possible that one of the regexes
1374 # matched, but returned an empty group:
1375 if mobj.group(1) is None:
1376 self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
1379 video_url = compat_urllib_parse.unquote(mobj.group(1))
1380 video_id = os.path.basename(video_url)
1382 # here's a fun little line of code for you:
1383 video_extension = os.path.splitext(video_id)[1][1:]
1384 video_id = os.path.splitext(video_id)[0]
1386 # it's tempting to parse this further, but you would
1387 # have to take into account all the variations like
1388 # Video Title - Site Name
1389 # Site Name | Video Title
1390 # Video Title - Tagline | Site Name
1391 # and so on and so forth; it's just not practical
1392 mobj = re.search(r'<title>(.*)</title>', webpage)
1394 self._downloader.trouble(u'ERROR: unable to extract title')
1396 video_title = mobj.group(1)
1398 # video uploader is domain name
1399 mobj = re.match(r'(?:https?://)?([^/]*)/.*', url)
1401 self._downloader.trouble(u'ERROR: unable to extract title')
1403 video_uploader = mobj.group(1)
1408 'uploader': video_uploader,
1409 'upload_date': None,
1410 'title': video_title,
1411 'ext': video_extension,
1415 class YoutubeSearchIE(InfoExtractor):
1416 """Information Extractor for YouTube search queries."""
1417 _VALID_URL = r'ytsearch(\d+|all)?:[\s\S]+'
1418 _API_URL = 'https://gdata.youtube.com/feeds/api/videos?q=%s&start-index=%i&max-results=50&v=2&alt=jsonc'
1419 _max_youtube_results = 1000
1420 IE_NAME = u'youtube:search'
1422 def __init__(self, downloader=None):
1423 InfoExtractor.__init__(self, downloader)
1425 def report_download_page(self, query, pagenum):
1426 """Report attempt to download search page with given number."""
1427 query = query.decode(preferredencoding())
1428 self._downloader.to_screen(u'[youtube] query "%s": Downloading page %s' % (query, pagenum))
1430 def _real_extract(self, query):
1431 mobj = re.match(self._VALID_URL, query)
1433 self._downloader.trouble(u'ERROR: invalid search query "%s"' % query)
1436 prefix, query = query.split(':')
1438 query = query.encode('utf-8')
1440 self._download_n_results(query, 1)
1442 elif prefix == 'all':
1443 self._download_n_results(query, self._max_youtube_results)
1449 self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query))
1451 elif n > self._max_youtube_results:
1452 self._downloader.to_stderr(u'WARNING: ytsearch returns max %i results (you requested %i)' % (self._max_youtube_results, n))
1453 n = self._max_youtube_results
1454 self._download_n_results(query, n)
1456 except ValueError: # parsing prefix as integer fails
1457 self._download_n_results(query, 1)
1460 def _download_n_results(self, query, n):
1461 """Downloads a specified number of results for a query"""
1467 while (50 * pagenum) < limit:
1468 self.report_download_page(query, pagenum+1)
1469 result_url = self._API_URL % (compat_urllib_parse.quote_plus(query), (50*pagenum)+1)
1470 request = compat_urllib_request.Request(result_url)
1472 data = compat_urllib_request.urlopen(request).read()
1473 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
1474 self._downloader.trouble(u'ERROR: unable to download API page: %s' % compat_str(err))
1476 api_response = json.loads(data)['data']
1478 new_ids = list(video['id'] for video in api_response['items'])
1479 video_ids += new_ids
1481 limit = min(n, api_response['totalItems'])
1484 if len(video_ids) > n:
1485 video_ids = video_ids[:n]
1486 for id in video_ids:
1487 self._downloader.download(['http://www.youtube.com/watch?v=%s' % id])
1491 class GoogleSearchIE(InfoExtractor):
1492 """Information Extractor for Google Video search queries."""
1493 _VALID_URL = r'gvsearch(\d+|all)?:[\s\S]+'
1494 _TEMPLATE_URL = 'http://video.google.com/videosearch?q=%s+site:video.google.com&start=%s&hl=en'
1495 _VIDEO_INDICATOR = r'<a href="http://video\.google\.com/videoplay\?docid=([^"\&]+)'
1496 _MORE_PAGES_INDICATOR = r'class="pn" id="pnnext"'
1497 _max_google_results = 1000
1498 IE_NAME = u'video.google:search'
1500 def __init__(self, downloader=None):
1501 InfoExtractor.__init__(self, downloader)
1503 def report_download_page(self, query, pagenum):
1504 """Report attempt to download playlist page with given number."""
1505 query = query.decode(preferredencoding())
1506 self._downloader.to_screen(u'[video.google] query "%s": Downloading page %s' % (query, pagenum))
1508 def _real_extract(self, query):
1509 mobj = re.match(self._VALID_URL, query)
1511 self._downloader.trouble(u'ERROR: invalid search query "%s"' % query)
1514 prefix, query = query.split(':')
1516 query = query.encode('utf-8')
1518 self._download_n_results(query, 1)
1520 elif prefix == 'all':
1521 self._download_n_results(query, self._max_google_results)
1527 self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query))
1529 elif n > self._max_google_results:
1530 self._downloader.to_stderr(u'WARNING: gvsearch returns max %i results (you requested %i)' % (self._max_google_results, n))
1531 n = self._max_google_results
1532 self._download_n_results(query, n)
1534 except ValueError: # parsing prefix as integer fails
1535 self._download_n_results(query, 1)
1538 def _download_n_results(self, query, n):
1539 """Downloads a specified number of results for a query"""
1545 self.report_download_page(query, pagenum)
1546 result_url = self._TEMPLATE_URL % (compat_urllib_parse.quote_plus(query), pagenum*10)
1547 request = compat_urllib_request.Request(result_url)
1549 page = compat_urllib_request.urlopen(request).read()
1550 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
1551 self._downloader.trouble(u'ERROR: unable to download webpage: %s' % compat_str(err))
1554 # Extract video identifiers
1555 for mobj in re.finditer(self._VIDEO_INDICATOR, page):
1556 video_id = mobj.group(1)
1557 if video_id not in video_ids:
1558 video_ids.append(video_id)
1559 if len(video_ids) == n:
1560 # Specified n videos reached
1561 for id in video_ids:
1562 self._downloader.download(['http://video.google.com/videoplay?docid=%s' % id])
1565 if re.search(self._MORE_PAGES_INDICATOR, page) is None:
1566 for id in video_ids:
1567 self._downloader.download(['http://video.google.com/videoplay?docid=%s' % id])
1570 pagenum = pagenum + 1
1573 class YahooSearchIE(InfoExtractor):
1574 """Information Extractor for Yahoo! Video search queries."""
1577 _VALID_URL = r'yvsearch(\d+|all)?:[\s\S]+'
1578 _TEMPLATE_URL = 'http://video.yahoo.com/search/?p=%s&o=%s'
1579 _VIDEO_INDICATOR = r'href="http://video\.yahoo\.com/watch/([0-9]+/[0-9]+)"'
1580 _MORE_PAGES_INDICATOR = r'\s*Next'
1581 _max_yahoo_results = 1000
1582 IE_NAME = u'video.yahoo:search'
1584 def __init__(self, downloader=None):
1585 InfoExtractor.__init__(self, downloader)
1587 def report_download_page(self, query, pagenum):
1588 """Report attempt to download playlist page with given number."""
1589 query = query.decode(preferredencoding())
1590 self._downloader.to_screen(u'[video.yahoo] query "%s": Downloading page %s' % (query, pagenum))
1592 def _real_extract(self, query):
1593 mobj = re.match(self._VALID_URL, query)
1595 self._downloader.trouble(u'ERROR: invalid search query "%s"' % query)
1598 prefix, query = query.split(':')
1600 query = query.encode('utf-8')
1602 self._download_n_results(query, 1)
1604 elif prefix == 'all':
1605 self._download_n_results(query, self._max_yahoo_results)
1611 self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query))
1613 elif n > self._max_yahoo_results:
1614 self._downloader.to_stderr(u'WARNING: yvsearch returns max %i results (you requested %i)' % (self._max_yahoo_results, n))
1615 n = self._max_yahoo_results
1616 self._download_n_results(query, n)
1618 except ValueError: # parsing prefix as integer fails
1619 self._download_n_results(query, 1)
1622 def _download_n_results(self, query, n):
1623 """Downloads a specified number of results for a query"""
1626 already_seen = set()
1630 self.report_download_page(query, pagenum)
1631 result_url = self._TEMPLATE_URL % (compat_urllib_parse.quote_plus(query), pagenum)
1632 request = compat_urllib_request.Request(result_url)
1634 page = compat_urllib_request.urlopen(request).read()
1635 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
1636 self._downloader.trouble(u'ERROR: unable to download webpage: %s' % compat_str(err))
1639 # Extract video identifiers
1640 for mobj in re.finditer(self._VIDEO_INDICATOR, page):
1641 video_id = mobj.group(1)
1642 if video_id not in already_seen:
1643 video_ids.append(video_id)
1644 already_seen.add(video_id)
1645 if len(video_ids) == n:
1646 # Specified n videos reached
1647 for id in video_ids:
1648 self._downloader.download(['http://video.yahoo.com/watch/%s' % id])
1651 if re.search(self._MORE_PAGES_INDICATOR, page) is None:
1652 for id in video_ids:
1653 self._downloader.download(['http://video.yahoo.com/watch/%s' % id])
1656 pagenum = pagenum + 1
1659 class YoutubePlaylistIE(InfoExtractor):
1660 """Information Extractor for YouTube playlists."""
1662 _VALID_URL = r'(?:(?:https?://)?(?:\w+\.)?youtube\.com/(?:(?:course|view_play_list|my_playlists|artist|playlist)\?.*?(p|a|list)=|user/.*?/user/|p/|user/.*?#[pg]/c/)(?:PL|EC)?|PL|EC)([0-9A-Za-z-_]{10,})(?:/.*?/([0-9A-Za-z_-]+))?.*'
1663 _TEMPLATE_URL = 'http://www.youtube.com/%s?%s=%s&page=%s&gl=US&hl=en'
1664 _VIDEO_INDICATOR_TEMPLATE = r'/watch\?v=(.+?)&([^&"]+&)*list=.*?%s'
1665 _MORE_PAGES_INDICATOR = u"Next \N{RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK}"
1666 IE_NAME = u'youtube:playlist'
1668 def __init__(self, downloader=None):
1669 InfoExtractor.__init__(self, downloader)
1671 def report_download_page(self, playlist_id, pagenum):
1672 """Report attempt to download playlist page with given number."""
1673 self._downloader.to_screen(u'[youtube] PL %s: Downloading page #%s' % (playlist_id, pagenum))
1675 def _real_extract(self, url):
1676 # Extract playlist id
1677 mobj = re.match(self._VALID_URL, url)
1679 self._downloader.trouble(u'ERROR: invalid url: %s' % url)
1683 if mobj.group(3) is not None:
1684 self._downloader.download([mobj.group(3)])
1687 # Download playlist pages
1688 # prefix is 'p' as default for playlists but there are other types that need extra care
1689 playlist_prefix = mobj.group(1)
1690 if playlist_prefix == 'a':
1691 playlist_access = 'artist'
1693 playlist_prefix = 'p'
1694 playlist_access = 'view_play_list'
1695 playlist_id = mobj.group(2)
1700 self.report_download_page(playlist_id, pagenum)
1701 url = self._TEMPLATE_URL % (playlist_access, playlist_prefix, playlist_id, pagenum)
1702 request = compat_urllib_request.Request(url)
1704 page = compat_urllib_request.urlopen(request).read().decode('utf-8')
1705 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
1706 self._downloader.trouble(u'ERROR: unable to download webpage: %s' % compat_str(err))
1709 # Extract video identifiers
1711 for mobj in re.finditer(self._VIDEO_INDICATOR_TEMPLATE % playlist_id, page):
1712 if mobj.group(1) not in ids_in_page:
1713 ids_in_page.append(mobj.group(1))
1714 video_ids.extend(ids_in_page)
1716 if self._MORE_PAGES_INDICATOR not in page:
1718 pagenum = pagenum + 1
1720 total = len(video_ids)
1722 playliststart = self._downloader.params.get('playliststart', 1) - 1
1723 playlistend = self._downloader.params.get('playlistend', -1)
1724 if playlistend == -1:
1725 video_ids = video_ids[playliststart:]
1727 video_ids = video_ids[playliststart:playlistend]
1729 if len(video_ids) == total:
1730 self._downloader.to_screen(u'[youtube] PL %s: Found %i videos' % (playlist_id, total))
1732 self._downloader.to_screen(u'[youtube] PL %s: Found %i videos, downloading %i' % (playlist_id, total, len(video_ids)))
1734 for id in video_ids:
1735 self._downloader.download(['http://www.youtube.com/watch?v=%s' % id])
1739 class YoutubeChannelIE(InfoExtractor):
1740 """Information Extractor for YouTube channels."""
1742 _VALID_URL = r"^(?:https?://)?(?:youtu\.be|(?:\w+\.)?youtube(?:-nocookie)?\.com)/channel/([0-9A-Za-z_-]+)(?:/.*)?$"
1743 _TEMPLATE_URL = 'http://www.youtube.com/channel/%s/videos?sort=da&flow=list&view=0&page=%s&gl=US&hl=en'
1744 _MORE_PAGES_INDICATOR = u"Next \N{RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK}"
1745 IE_NAME = u'youtube:channel'
1747 def report_download_page(self, channel_id, pagenum):
1748 """Report attempt to download channel page with given number."""
1749 self._downloader.to_screen(u'[youtube] Channel %s: Downloading page #%s' % (channel_id, pagenum))
1751 def _real_extract(self, url):
1752 # Extract channel id
1753 mobj = re.match(self._VALID_URL, url)
1755 self._downloader.trouble(u'ERROR: invalid url: %s' % url)
1758 # Download channel pages
1759 channel_id = mobj.group(1)
1764 self.report_download_page(channel_id, pagenum)
1765 url = self._TEMPLATE_URL % (channel_id, pagenum)
1766 request = compat_urllib_request.Request(url)
1768 page = compat_urllib_request.urlopen(request).read().decode('utf8')
1769 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
1770 self._downloader.trouble(u'ERROR: unable to download webpage: %s' % compat_str(err))
1773 # Extract video identifiers
1775 for mobj in re.finditer(r'href="/watch\?v=([0-9A-Za-z_-]+)&', page):
1776 if mobj.group(1) not in ids_in_page:
1777 ids_in_page.append(mobj.group(1))
1778 video_ids.extend(ids_in_page)
1780 if self._MORE_PAGES_INDICATOR not in page:
1782 pagenum = pagenum + 1
1784 self._downloader.to_screen(u'[youtube] Channel %s: Found %i videos' % (channel_id, len(video_ids)))
1786 for id in video_ids:
1787 self._downloader.download(['http://www.youtube.com/watch?v=%s' % id])
1791 class YoutubeUserIE(InfoExtractor):
1792 """Information Extractor for YouTube users."""
1794 _VALID_URL = r'(?:(?:(?:https?://)?(?:\w+\.)?youtube\.com/user/)|ytuser:)([A-Za-z0-9_-]+)'
1795 _TEMPLATE_URL = 'http://gdata.youtube.com/feeds/api/users/%s'
1796 _GDATA_PAGE_SIZE = 50
1797 _GDATA_URL = 'http://gdata.youtube.com/feeds/api/users/%s/uploads?max-results=%d&start-index=%d'
1798 _VIDEO_INDICATOR = r'/watch\?v=(.+?)[\<&]'
1799 IE_NAME = u'youtube:user'
1801 def __init__(self, downloader=None):
1802 InfoExtractor.__init__(self, downloader)
1804 def report_download_page(self, username, start_index):
1805 """Report attempt to download user page."""
1806 self._downloader.to_screen(u'[youtube] user %s: Downloading video ids from %d to %d' %
1807 (username, start_index, start_index + self._GDATA_PAGE_SIZE))
1809 def _real_extract(self, url):
1811 mobj = re.match(self._VALID_URL, url)
1813 self._downloader.trouble(u'ERROR: invalid url: %s' % url)
1816 username = mobj.group(1)
1818 # Download video ids using YouTube Data API. Result size per
1819 # query is limited (currently to 50 videos) so we need to query
1820 # page by page until there are no video ids - it means we got
1827 start_index = pagenum * self._GDATA_PAGE_SIZE + 1
1828 self.report_download_page(username, start_index)
1830 request = compat_urllib_request.Request(self._GDATA_URL % (username, self._GDATA_PAGE_SIZE, start_index))
1833 page = compat_urllib_request.urlopen(request).read().decode('utf-8')
1834 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
1835 self._downloader.trouble(u'ERROR: unable to download webpage: %s' % compat_str(err))
1838 # Extract video identifiers
1841 for mobj in re.finditer(self._VIDEO_INDICATOR, page):
1842 if mobj.group(1) not in ids_in_page:
1843 ids_in_page.append(mobj.group(1))
1845 video_ids.extend(ids_in_page)
1847 # A little optimization - if current page is not
1848 # "full", ie. does not contain PAGE_SIZE video ids then
1849 # we can assume that this page is the last one - there
1850 # are no more ids on further pages - no need to query
1853 if len(ids_in_page) < self._GDATA_PAGE_SIZE:
1858 all_ids_count = len(video_ids)
1859 playliststart = self._downloader.params.get('playliststart', 1) - 1
1860 playlistend = self._downloader.params.get('playlistend', -1)
1862 if playlistend == -1:
1863 video_ids = video_ids[playliststart:]
1865 video_ids = video_ids[playliststart:playlistend]
1867 self._downloader.to_screen(u"[youtube] user %s: Collected %d video ids (downloading %d of them)" %
1868 (username, all_ids_count, len(video_ids)))
1870 for video_id in video_ids:
1871 self._downloader.download(['http://www.youtube.com/watch?v=%s' % video_id])
1874 class BlipTVUserIE(InfoExtractor):
1875 """Information Extractor for blip.tv users."""
1877 _VALID_URL = r'(?:(?:(?:https?://)?(?:\w+\.)?blip\.tv/)|bliptvuser:)([^/]+)/*$'
1879 IE_NAME = u'blip.tv:user'
1881 def __init__(self, downloader=None):
1882 InfoExtractor.__init__(self, downloader)
1884 def report_download_page(self, username, pagenum):
1885 """Report attempt to download user page."""
1886 self._downloader.to_screen(u'[%s] user %s: Downloading video ids from page %d' %
1887 (self.IE_NAME, username, pagenum))
1889 def _real_extract(self, url):
1891 mobj = re.match(self._VALID_URL, url)
1893 self._downloader.trouble(u'ERROR: invalid url: %s' % url)
1896 username = mobj.group(1)
1898 page_base = 'http://m.blip.tv/pr/show_get_full_episode_list?users_id=%s&lite=0&esi=1'
1900 request = compat_urllib_request.Request(url)
1903 page = compat_urllib_request.urlopen(request).read().decode('utf-8')
1904 mobj = re.search(r'data-users-id="([^"]+)"', page)
1905 page_base = page_base % mobj.group(1)
1906 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
1907 self._downloader.trouble(u'ERROR: unable to download webpage: %s' % compat_str(err))
1911 # Download video ids using BlipTV Ajax calls. Result size per
1912 # query is limited (currently to 12 videos) so we need to query
1913 # page by page until there are no video ids - it means we got
1920 self.report_download_page(username, pagenum)
1922 request = compat_urllib_request.Request( page_base + "&page=" + str(pagenum) )
1925 page = compat_urllib_request.urlopen(request).read().decode('utf-8')
1926 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
1927 self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err))
1930 # Extract video identifiers
1933 for mobj in re.finditer(r'href="/([^"]+)"', page):
1934 if mobj.group(1) not in ids_in_page:
1935 ids_in_page.append(unescapeHTML(mobj.group(1)))
1937 video_ids.extend(ids_in_page)
1939 # A little optimization - if current page is not
1940 # "full", ie. does not contain PAGE_SIZE video ids then
1941 # we can assume that this page is the last one - there
1942 # are no more ids on further pages - no need to query
1945 if len(ids_in_page) < self._PAGE_SIZE:
1950 all_ids_count = len(video_ids)
1951 playliststart = self._downloader.params.get('playliststart', 1) - 1
1952 playlistend = self._downloader.params.get('playlistend', -1)
1954 if playlistend == -1:
1955 video_ids = video_ids[playliststart:]
1957 video_ids = video_ids[playliststart:playlistend]
1959 self._downloader.to_screen(u"[%s] user %s: Collected %d video ids (downloading %d of them)" %
1960 (self.IE_NAME, username, all_ids_count, len(video_ids)))
1962 for video_id in video_ids:
1963 self._downloader.download([u'http://blip.tv/'+video_id])
1966 class DepositFilesIE(InfoExtractor):
1967 """Information extractor for depositfiles.com"""
1969 _VALID_URL = r'(?:http://)?(?:\w+\.)?depositfiles\.com/(?:../(?#locale))?files/(.+)'
1971 def report_download_webpage(self, file_id):
1972 """Report webpage download."""
1973 self._downloader.to_screen(u'[DepositFiles] %s: Downloading webpage' % file_id)
1975 def report_extraction(self, file_id):
1976 """Report information extraction."""
1977 self._downloader.to_screen(u'[DepositFiles] %s: Extracting information' % file_id)
1979 def _real_extract(self, url):
1980 file_id = url.split('/')[-1]
1981 # Rebuild url in english locale
1982 url = 'http://depositfiles.com/en/files/' + file_id
1984 # Retrieve file webpage with 'Free download' button pressed
1985 free_download_indication = { 'gateway_result' : '1' }
1986 request = compat_urllib_request.Request(url, compat_urllib_parse.urlencode(free_download_indication))
1988 self.report_download_webpage(file_id)
1989 webpage = compat_urllib_request.urlopen(request).read()
1990 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
1991 self._downloader.trouble(u'ERROR: Unable to retrieve file webpage: %s' % compat_str(err))
1994 # Search for the real file URL
1995 mobj = re.search(r'<form action="(http://fileshare.+?)"', webpage)
1996 if (mobj is None) or (mobj.group(1) is None):
1997 # Try to figure out reason of the error.
1998 mobj = re.search(r'<strong>(Attention.*?)</strong>', webpage, re.DOTALL)
1999 if (mobj is not None) and (mobj.group(1) is not None):
2000 restriction_message = re.sub('\s+', ' ', mobj.group(1)).strip()
2001 self._downloader.trouble(u'ERROR: %s' % restriction_message)
2003 self._downloader.trouble(u'ERROR: unable to extract download URL from: %s' % url)
2006 file_url = mobj.group(1)
2007 file_extension = os.path.splitext(file_url)[1][1:]
2009 # Search for file title
2010 mobj = re.search(r'<b title="(.*?)">', webpage)
2012 self._downloader.trouble(u'ERROR: unable to extract title')
2014 file_title = mobj.group(1).decode('utf-8')
2017 'id': file_id.decode('utf-8'),
2018 'url': file_url.decode('utf-8'),
2020 'upload_date': None,
2021 'title': file_title,
2022 'ext': file_extension.decode('utf-8'),
2026 class FacebookIE(InfoExtractor):
2027 """Information Extractor for Facebook"""
2029 _VALID_URL = r'^(?:https?://)?(?:\w+\.)?facebook\.com/(?:video/video|photo)\.php\?(?:.*?)v=(?P<ID>\d+)(?:.*)'
2030 _LOGIN_URL = 'https://login.facebook.com/login.php?m&next=http%3A%2F%2Fm.facebook.com%2Fhome.php&'
2031 _NETRC_MACHINE = 'facebook'
2032 IE_NAME = u'facebook'
2034 def report_login(self):
2035 """Report attempt to log in."""
2036 self._downloader.to_screen(u'[%s] Logging in' % self.IE_NAME)
2038 def _real_initialize(self):
2039 if self._downloader is None:
2044 downloader_params = self._downloader.params
2046 # Attempt to use provided username and password or .netrc data
2047 if downloader_params.get('username', None) is not None:
2048 useremail = downloader_params['username']
2049 password = downloader_params['password']
2050 elif downloader_params.get('usenetrc', False):
2052 info = netrc.netrc().authenticators(self._NETRC_MACHINE)
2053 if info is not None:
2057 raise netrc.NetrcParseError('No authenticators for %s' % self._NETRC_MACHINE)
2058 except (IOError, netrc.NetrcParseError) as err:
2059 self._downloader.to_stderr(u'WARNING: parsing .netrc: %s' % compat_str(err))
2062 if useremail is None:
2071 request = compat_urllib_request.Request(self._LOGIN_URL, compat_urllib_parse.urlencode(login_form))
2074 login_results = compat_urllib_request.urlopen(request).read()
2075 if re.search(r'<form(.*)name="login"(.*)</form>', login_results) is not None:
2076 self._downloader.to_stderr(u'WARNING: unable to log in: bad username/password, or exceded login rate limit (~3/min). Check credentials or wait.')
2078 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
2079 self._downloader.to_stderr(u'WARNING: unable to log in: %s' % compat_str(err))
2082 def _real_extract(self, url):
2083 mobj = re.match(self._VALID_URL, url)
2085 self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
2087 video_id = mobj.group('ID')
2089 url = 'https://www.facebook.com/video/video.php?v=%s' % video_id
2090 webpage = self._download_webpage(url, video_id)
2092 BEFORE = '[["allowFullScreen","true"],["allowScriptAccess","always"],["salign","tl"],["scale","noscale"],["wmode","opaque"]].forEach(function(param) {swf.addParam(param[0], param[1]);});\n'
2093 AFTER = '.forEach(function(variable) {swf.addVariable(variable[0], variable[1]);});'
2094 m = re.search(re.escape(BEFORE) + '(.*?)' + re.escape(AFTER), webpage)
2096 raise ExtractorError(u'Cannot parse data')
2097 data = dict(json.loads(m.group(1)))
2098 params_raw = compat_urllib_parse.unquote(data['params'])
2099 params = json.loads(params_raw)
2100 video_url = params['hd_src']
2101 video_duration = int(params['video_duration'])
2103 m = re.search('<h2 class="uiHeaderTitle">([^<]+)</h2>', webpage)
2105 raise ExtractorError(u'Cannot find title in webpage')
2106 video_title = unescapeHTML(m.group(1))
2110 'title': video_title,
2113 'duration': video_duration,
2114 'thumbnail': params['thumbnail_src'],
2119 class BlipTVIE(InfoExtractor):
2120 """Information extractor for blip.tv"""
2122 _VALID_URL = r'^(?:https?://)?(?:\w+\.)?blip\.tv(/.+)$'
2123 _URL_EXT = r'^.*\.([a-z0-9]+)$'
2124 IE_NAME = u'blip.tv'
2126 def report_extraction(self, file_id):
2127 """Report information extraction."""
2128 self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, file_id))
2130 def report_direct_download(self, title):
2131 """Report information extraction."""
2132 self._downloader.to_screen(u'[%s] %s: Direct download detected' % (self.IE_NAME, title))
2134 def _real_extract(self, url):
2135 mobj = re.match(self._VALID_URL, url)
2137 self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
2144 json_url = url + cchar + 'skin=json&version=2&no_wrap=1'
2145 request = compat_urllib_request.Request(json_url)
2146 request.add_header('User-Agent', 'iTunes/10.6.1')
2147 self.report_extraction(mobj.group(1))
2150 urlh = compat_urllib_request.urlopen(request)
2151 if urlh.headers.get('Content-Type', '').startswith('video/'): # Direct download
2152 basename = url.split('/')[-1]
2153 title,ext = os.path.splitext(basename)
2154 title = title.decode('UTF-8')
2155 ext = ext.replace('.', '')
2156 self.report_direct_download(title)
2161 'upload_date': None,
2166 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
2167 raise ExtractorError(u'ERROR: unable to download video info webpage: %s' % compat_str(err))
2168 if info is None: # Regular URL
2170 json_code_bytes = urlh.read()
2171 json_code = json_code_bytes.decode('utf-8')
2172 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
2173 self._downloader.trouble(u'ERROR: unable to read video info webpage: %s' % compat_str(err))
2177 json_data = json.loads(json_code)
2178 if 'Post' in json_data:
2179 data = json_data['Post']
2183 upload_date = datetime.datetime.strptime(data['datestamp'], '%m-%d-%y %H:%M%p').strftime('%Y%m%d')
2184 video_url = data['media']['url']
2185 umobj = re.match(self._URL_EXT, video_url)
2187 raise ValueError('Can not determine filename extension')
2188 ext = umobj.group(1)
2191 'id': data['item_id'],
2193 'uploader': data['display_name'],
2194 'upload_date': upload_date,
2195 'title': data['title'],
2197 'format': data['media']['mimeType'],
2198 'thumbnail': data['thumbnailUrl'],
2199 'description': data['description'],
2200 'player_url': data['embedUrl'],
2201 'user_agent': 'iTunes/10.6.1',
2203 except (ValueError,KeyError) as err:
2204 self._downloader.trouble(u'ERROR: unable to parse video information: %s' % repr(err))
2210 class MyVideoIE(InfoExtractor):
2211 """Information Extractor for myvideo.de."""
2213 _VALID_URL = r'(?:http://)?(?:www\.)?myvideo\.de/watch/([0-9]+)/([^?/]+).*'
2214 IE_NAME = u'myvideo'
2216 def __init__(self, downloader=None):
2217 InfoExtractor.__init__(self, downloader)
2219 def report_extraction(self, video_id):
2220 """Report information extraction."""
2221 self._downloader.to_screen(u'[myvideo] %s: Extracting information' % video_id)
2223 def _real_extract(self,url):
2224 mobj = re.match(self._VALID_URL, url)
2226 self._download.trouble(u'ERROR: invalid URL: %s' % url)
2229 video_id = mobj.group(1)
2232 webpage_url = 'http://www.myvideo.de/watch/%s' % video_id
2233 webpage = self._download_webpage(webpage_url, video_id)
2235 self.report_extraction(video_id)
2236 mobj = re.search(r'<link rel=\'image_src\' href=\'(http://is[0-9].myvideo\.de/de/movie[0-9]+/[a-f0-9]+)/thumbs/.*?\.jpg\' />',
2239 self._downloader.trouble(u'ERROR: unable to extract media URL')
2241 video_url = mobj.group(1) + ('/%s.flv' % video_id)
2243 mobj = re.search('<title>([^<]+)</title>', webpage)
2245 self._downloader.trouble(u'ERROR: unable to extract title')
2248 video_title = mobj.group(1)
2254 'upload_date': None,
2255 'title': video_title,
2259 class ComedyCentralIE(InfoExtractor):
2260 """Information extractor for The Daily Show and Colbert Report """
2262 # urls can be abbreviations like :thedailyshow or :colbert
2263 # urls for episodes like:
2264 # or urls for clips like: http://www.thedailyshow.com/watch/mon-december-10-2012/any-given-gun-day
2265 # or: http://www.colbertnation.com/the-colbert-report-videos/421667/november-29-2012/moon-shattering-news
2266 # or: http://www.colbertnation.com/the-colbert-report-collections/422008/festival-of-lights/79524
2267 _VALID_URL = r"""^(:(?P<shortname>tds|thedailyshow|cr|colbert|colbertnation|colbertreport)
2268 |(https?://)?(www\.)?
2269 (?P<showname>thedailyshow|colbertnation)\.com/
2270 (full-episodes/(?P<episode>.*)|
2272 (the-colbert-report-(videos|collections)/(?P<clipID>[0-9]+)/[^/]*/(?P<cntitle>.*?))
2273 |(watch/(?P<date>[^/]*)/(?P<tdstitle>.*)))))
2276 _available_formats = ['3500', '2200', '1700', '1200', '750', '400']
2278 _video_extensions = {
2286 _video_dimensions = {
2295 def suitable(self, url):
2296 """Receives a URL and returns True if suitable for this IE."""
2297 return re.match(self._VALID_URL, url, re.VERBOSE) is not None
2299 def report_extraction(self, episode_id):
2300 self._downloader.to_screen(u'[comedycentral] %s: Extracting information' % episode_id)
2302 def report_config_download(self, episode_id, media_id):
2303 self._downloader.to_screen(u'[comedycentral] %s: Downloading configuration for %s' % (episode_id, media_id))
2305 def report_index_download(self, episode_id):
2306 self._downloader.to_screen(u'[comedycentral] %s: Downloading show index' % episode_id)
2308 def _print_formats(self, formats):
2309 print('Available formats:')
2311 print('%s\t:\t%s\t[%s]' %(x, self._video_extensions.get(x, 'mp4'), self._video_dimensions.get(x, '???')))
2314 def _real_extract(self, url):
2315 mobj = re.match(self._VALID_URL, url, re.VERBOSE)
2317 self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
2320 if mobj.group('shortname'):
2321 if mobj.group('shortname') in ('tds', 'thedailyshow'):
2322 url = u'http://www.thedailyshow.com/full-episodes/'
2324 url = u'http://www.colbertnation.com/full-episodes/'
2325 mobj = re.match(self._VALID_URL, url, re.VERBOSE)
2326 assert mobj is not None
2328 if mobj.group('clip'):
2329 if mobj.group('showname') == 'thedailyshow':
2330 epTitle = mobj.group('tdstitle')
2332 epTitle = mobj.group('cntitle')
2335 dlNewest = not mobj.group('episode')
2337 epTitle = mobj.group('showname')
2339 epTitle = mobj.group('episode')
2341 req = compat_urllib_request.Request(url)
2342 self.report_extraction(epTitle)
2344 htmlHandle = compat_urllib_request.urlopen(req)
2345 html = htmlHandle.read()
2346 webpage = html.decode('utf-8')
2347 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
2348 self._downloader.trouble(u'ERROR: unable to download webpage: %s' % compat_str(err))
2351 url = htmlHandle.geturl()
2352 mobj = re.match(self._VALID_URL, url, re.VERBOSE)
2354 self._downloader.trouble(u'ERROR: Invalid redirected URL: ' + url)
2356 if mobj.group('episode') == '':
2357 self._downloader.trouble(u'ERROR: Redirected URL is still not specific: ' + url)
2359 epTitle = mobj.group('episode')
2361 mMovieParams = re.findall('(?:<param name="movie" value="|var url = ")(http://media.mtvnservices.com/([^"]*(?:episode|video).*?:.*?))"', webpage)
2363 if len(mMovieParams) == 0:
2364 # The Colbert Report embeds the information in a without
2365 # a URL prefix; so extract the alternate reference
2366 # and then add the URL prefix manually.
2368 altMovieParams = re.findall('data-mgid="([^"]*(?:episode|video).*?:.*?)"', webpage)
2369 if len(altMovieParams) == 0:
2370 self._downloader.trouble(u'ERROR: unable to find Flash URL in webpage ' + url)
2373 mMovieParams = [("http://media.mtvnservices.com/" + altMovieParams[0], altMovieParams[0])]
2375 uri = mMovieParams[0][1]
2376 indexUrl = 'http://shadow.comedycentral.com/feeds/video_player/mrss/?' + compat_urllib_parse.urlencode({'uri': uri})
2377 self.report_index_download(epTitle)
2379 indexXml = compat_urllib_request.urlopen(indexUrl).read()
2380 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
2381 self._downloader.trouble(u'ERROR: unable to download episode index: ' + compat_str(err))
2386 idoc = xml.etree.ElementTree.fromstring(indexXml)
2387 itemEls = idoc.findall('.//item')
2388 for partNum,itemEl in enumerate(itemEls):
2389 mediaId = itemEl.findall('./guid')[0].text
2390 shortMediaId = mediaId.split(':')[-1]
2391 showId = mediaId.split(':')[-2].replace('.com', '')
2392 officialTitle = itemEl.findall('./title')[0].text
2393 officialDate = itemEl.findall('./pubDate')[0].text
2395 configUrl = ('http://www.comedycentral.com/global/feeds/entertainment/media/mediaGenEntertainment.jhtml?' +
2396 compat_urllib_parse.urlencode({'uri': mediaId}))
2397 configReq = compat_urllib_request.Request(configUrl)
2398 self.report_config_download(epTitle, shortMediaId)
2400 configXml = compat_urllib_request.urlopen(configReq).read()
2401 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
2402 self._downloader.trouble(u'ERROR: unable to download webpage: %s' % compat_str(err))
2405 cdoc = xml.etree.ElementTree.fromstring(configXml)
2407 for rendition in cdoc.findall('.//rendition'):
2408 finfo = (rendition.attrib['bitrate'], rendition.findall('./src')[0].text)
2412 self._downloader.trouble(u'\nERROR: unable to download ' + mediaId + ': No videos found')
2415 if self._downloader.params.get('listformats', None):
2416 self._print_formats([i[0] for i in turls])
2419 # For now, just pick the highest bitrate
2420 format,rtmp_video_url = turls[-1]
2422 # Get the format arg from the arg stream
2423 req_format = self._downloader.params.get('format', None)
2425 # Select format if we can find one
2428 format, rtmp_video_url = f, v
2431 m = re.match(r'^rtmpe?://.*?/(?P<finalid>gsp.comedystor/.*)$', rtmp_video_url)
2433 raise ExtractorError(u'Cannot transform RTMP url')
2434 base = 'http://mtvnmobile.vo.llnwd.net/kip0/_pxn=1+_pxI0=Ripod-h264+_pxL0=undefined+_pxM0=+_pxK=18639+_pxE=mp4/44620/mtvnorigin/'
2435 video_url = base + m.group('finalid')
2437 effTitle = showId + u'-' + epTitle + u' part ' + compat_str(partNum+1)
2442 'upload_date': officialDate,
2447 'description': officialTitle,
2449 results.append(info)
2454 class EscapistIE(InfoExtractor):
2455 """Information extractor for The Escapist """
2457 _VALID_URL = r'^(https?://)?(www\.)?escapistmagazine\.com/videos/view/(?P<showname>[^/]+)/(?P<episode>[^/?]+)[/?]?.*$'
2458 IE_NAME = u'escapist'
2460 def report_extraction(self, showName):
2461 self._downloader.to_screen(u'[escapist] %s: Extracting information' % showName)
2463 def report_config_download(self, showName):
2464 self._downloader.to_screen(u'[escapist] %s: Downloading configuration' % showName)
2466 def _real_extract(self, url):
2467 mobj = re.match(self._VALID_URL, url)
2469 self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
2471 showName = mobj.group('showname')
2472 videoId = mobj.group('episode')
2474 self.report_extraction(showName)
2476 webPage = compat_urllib_request.urlopen(url)
2477 webPageBytes = webPage.read()
2478 m = re.match(r'text/html; charset="?([^"]+)"?', webPage.headers['Content-Type'])
2479 webPage = webPageBytes.decode(m.group(1) if m else 'utf-8')
2480 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
2481 self._downloader.trouble(u'ERROR: unable to download webpage: ' + compat_str(err))
2484 descMatch = re.search('<meta name="description" content="([^"]*)"', webPage)
2485 description = unescapeHTML(descMatch.group(1))
2486 imgMatch = re.search('<meta property="og:image" content="([^"]*)"', webPage)
2487 imgUrl = unescapeHTML(imgMatch.group(1))
2488 playerUrlMatch = re.search('<meta property="og:video" content="([^"]*)"', webPage)
2489 playerUrl = unescapeHTML(playerUrlMatch.group(1))
2490 configUrlMatch = re.search('config=(.*)$', playerUrl)
2491 configUrl = compat_urllib_parse.unquote(configUrlMatch.group(1))
2493 self.report_config_download(showName)
2495 configJSON = compat_urllib_request.urlopen(configUrl)
2496 m = re.match(r'text/html; charset="?([^"]+)"?', configJSON.headers['Content-Type'])
2497 configJSON = configJSON.read().decode(m.group(1) if m else 'utf-8')
2498 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
2499 self._downloader.trouble(u'ERROR: unable to download configuration: ' + compat_str(err))
2502 # Technically, it's JavaScript, not JSON
2503 configJSON = configJSON.replace("'", '"')
2506 config = json.loads(configJSON)
2507 except (ValueError,) as err:
2508 self._downloader.trouble(u'ERROR: Invalid JSON in configuration file: ' + compat_str(err))
2511 playlist = config['playlist']
2512 videoUrl = playlist[1]['url']
2517 'uploader': showName,
2518 'upload_date': None,
2521 'thumbnail': imgUrl,
2522 'description': description,
2523 'player_url': playerUrl,
2528 class CollegeHumorIE(InfoExtractor):
2529 """Information extractor for collegehumor.com"""
2532 _VALID_URL = r'^(?:https?://)?(?:www\.)?collegehumor\.com/video/(?P<videoid>[0-9]+)/(?P<shorttitle>.*)$'
2533 IE_NAME = u'collegehumor'
2535 def report_manifest(self, video_id):
2536 """Report information extraction."""
2537 self._downloader.to_screen(u'[%s] %s: Downloading XML manifest' % (self.IE_NAME, video_id))
2539 def report_extraction(self, video_id):
2540 """Report information extraction."""
2541 self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id))
2543 def _real_extract(self, url):
2544 mobj = re.match(self._VALID_URL, url)
2546 self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
2548 video_id = mobj.group('videoid')
2553 'upload_date': None,
2556 self.report_extraction(video_id)
2557 xmlUrl = 'http://www.collegehumor.com/moogaloop/video/' + video_id
2559 metaXml = compat_urllib_request.urlopen(xmlUrl).read()
2560 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
2561 self._downloader.trouble(u'ERROR: unable to download video info XML: %s' % compat_str(err))
2564 mdoc = xml.etree.ElementTree.fromstring(metaXml)
2566 videoNode = mdoc.findall('./video')[0]
2567 info['description'] = videoNode.findall('./description')[0].text
2568 info['title'] = videoNode.findall('./caption')[0].text
2569 info['thumbnail'] = videoNode.findall('./thumbnail')[0].text
2570 manifest_url = videoNode.findall('./file')[0].text
2572 self._downloader.trouble(u'\nERROR: Invalid metadata XML file')
2575 manifest_url += '?hdcore=2.10.3'
2576 self.report_manifest(video_id)
2578 manifestXml = compat_urllib_request.urlopen(manifest_url).read()
2579 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
2580 self._downloader.trouble(u'ERROR: unable to download video info XML: %s' % compat_str(err))
2583 adoc = xml.etree.ElementTree.fromstring(manifestXml)
2585 media_node = adoc.findall('./{http://ns.adobe.com/f4m/1.0}media')[0]
2586 node_id = media_node.attrib['url']
2587 video_id = adoc.findall('./{http://ns.adobe.com/f4m/1.0}id')[0].text
2588 except IndexError as err:
2589 self._downloader.trouble(u'\nERROR: Invalid manifest file')
2592 url_pr = compat_urllib_parse_urlparse(manifest_url)
2593 url = url_pr.scheme + '://' + url_pr.netloc + '/z' + video_id[:-2] + '/' + node_id + 'Seg1-Frag1'
2600 class XVideosIE(InfoExtractor):
2601 """Information extractor for xvideos.com"""
2603 _VALID_URL = r'^(?:https?://)?(?:www\.)?xvideos\.com/video([0-9]+)(?:.*)'
2604 IE_NAME = u'xvideos'
2606 def report_extraction(self, video_id):
2607 """Report information extraction."""
2608 self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id))
2610 def _real_extract(self, url):
2611 mobj = re.match(self._VALID_URL, url)
2613 self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
2615 video_id = mobj.group(1)
2617 webpage = self._download_webpage(url, video_id)
2619 self.report_extraction(video_id)
2623 mobj = re.search(r'flv_url=(.+?)&', webpage)
2625 self._downloader.trouble(u'ERROR: unable to extract video url')
2627 video_url = compat_urllib_parse.unquote(mobj.group(1))
2631 mobj = re.search(r'<title>(.*?)\s+-\s+XVID', webpage)
2633 self._downloader.trouble(u'ERROR: unable to extract video title')
2635 video_title = mobj.group(1)
2638 # Extract video thumbnail
2639 mobj = re.search(r'http://(?:img.*?\.)xvideos.com/videos/thumbs/[a-fA-F0-9]+/[a-fA-F0-9]+/[a-fA-F0-9]+/[a-fA-F0-9]+/([a-fA-F0-9.]+jpg)', webpage)
2641 self._downloader.trouble(u'ERROR: unable to extract video thumbnail')
2643 video_thumbnail = mobj.group(0)
2649 'upload_date': None,
2650 'title': video_title,
2652 'thumbnail': video_thumbnail,
2653 'description': None,
2659 class SoundcloudIE(InfoExtractor):
2660 """Information extractor for soundcloud.com
2661 To access the media, the uid of the song and a stream token
2662 must be extracted from the page source and the script must make
2663 a request to media.soundcloud.com/crossdomain.xml. Then
2664 the media can be grabbed by requesting from an url composed
2665 of the stream token and uid
2668 _VALID_URL = r'^(?:https?://)?(?:www\.)?soundcloud\.com/([\w\d-]+)/([\w\d-]+)'
2669 IE_NAME = u'soundcloud'
2671 def __init__(self, downloader=None):
2672 InfoExtractor.__init__(self, downloader)
2674 def report_resolve(self, video_id):
2675 """Report information extraction."""
2676 self._downloader.to_screen(u'[%s] %s: Resolving id' % (self.IE_NAME, video_id))
2678 def report_extraction(self, video_id):
2679 """Report information extraction."""
2680 self._downloader.to_screen(u'[%s] %s: Retrieving stream' % (self.IE_NAME, video_id))
2682 def _real_extract(self, url):
2683 mobj = re.match(self._VALID_URL, url)
2685 self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
2688 # extract uploader (which is in the url)
2689 uploader = mobj.group(1)
2690 # extract simple title (uploader + slug of song title)
2691 slug_title = mobj.group(2)
2692 simple_title = uploader + u'-' + slug_title
2694 self.report_resolve('%s/%s' % (uploader, slug_title))
2696 url = 'http://soundcloud.com/%s/%s' % (uploader, slug_title)
2697 resolv_url = 'http://api.soundcloud.com/resolve.json?url=' + url + '&client_id=b45b1aa10f1ac2941910a7f0d10f8e28'
2698 request = compat_urllib_request.Request(resolv_url)
2700 info_json_bytes = compat_urllib_request.urlopen(request).read()
2701 info_json = info_json_bytes.decode('utf-8')
2702 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
2703 self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % compat_str(err))
2706 info = json.loads(info_json)
2707 video_id = info['id']
2708 self.report_extraction('%s/%s' % (uploader, slug_title))
2710 streams_url = 'https://api.sndcdn.com/i1/tracks/' + str(video_id) + '/streams?client_id=b45b1aa10f1ac2941910a7f0d10f8e28'
2711 request = compat_urllib_request.Request(streams_url)
2713 stream_json_bytes = compat_urllib_request.urlopen(request).read()
2714 stream_json = stream_json_bytes.decode('utf-8')
2715 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
2716 self._downloader.trouble(u'ERROR: unable to download stream definitions: %s' % compat_str(err))
2719 streams = json.loads(stream_json)
2720 mediaURL = streams['http_mp3_128_url']
2725 'uploader': info['user']['username'],
2726 'upload_date': info['created_at'],
2727 'title': info['title'],
2729 'description': info['description'],
2733 class InfoQIE(InfoExtractor):
2734 """Information extractor for infoq.com"""
2735 _VALID_URL = r'^(?:https?://)?(?:www\.)?infoq\.com/[^/]+/[^/]+$'
2737 def report_extraction(self, video_id):
2738 """Report information extraction."""
2739 self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id))
2741 def _real_extract(self, url):
2742 mobj = re.match(self._VALID_URL, url)
2744 self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
2747 webpage = self._download_webpage(url, video_id=url)
2748 self.report_extraction(url)
2751 mobj = re.search(r"jsclassref='([^']*)'", webpage)
2753 self._downloader.trouble(u'ERROR: unable to extract video url')
2755 real_id = compat_urllib_parse.unquote(base64.b64decode(mobj.group(1).encode('ascii')).decode('utf-8'))
2756 video_url = 'rtmpe://video.infoq.com/cfx/st/' + real_id
2759 mobj = re.search(r'contentTitle = "(.*?)";', webpage)
2761 self._downloader.trouble(u'ERROR: unable to extract video title')
2763 video_title = mobj.group(1)
2765 # Extract description
2766 video_description = u'No description available.'
2767 mobj = re.search(r'<meta name="description" content="(.*)"(?:\s*/)?>', webpage)
2768 if mobj is not None:
2769 video_description = mobj.group(1)
2771 video_filename = video_url.split('/')[-1]
2772 video_id, extension = video_filename.split('.')
2778 'upload_date': None,
2779 'title': video_title,
2780 'ext': extension, # Extension is always(?) mp4, but seems to be flv
2782 'description': video_description,
2787 class MixcloudIE(InfoExtractor):
2788 """Information extractor for www.mixcloud.com"""
2790 _WORKING = False # New API, but it seems good http://www.mixcloud.com/developers/documentation/
2791 _VALID_URL = r'^(?:https?://)?(?:www\.)?mixcloud\.com/([\w\d-]+)/([\w\d-]+)'
2792 IE_NAME = u'mixcloud'
2794 def __init__(self, downloader=None):
2795 InfoExtractor.__init__(self, downloader)
2797 def report_download_json(self, file_id):
2798 """Report JSON download."""
2799 self._downloader.to_screen(u'[%s] Downloading json' % self.IE_NAME)
2801 def report_extraction(self, file_id):
2802 """Report information extraction."""
2803 self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, file_id))
2805 def get_urls(self, jsonData, fmt, bitrate='best'):
2806 """Get urls from 'audio_formats' section in json"""
2809 bitrate_list = jsonData[fmt]
2810 if bitrate is None or bitrate == 'best' or bitrate not in bitrate_list:
2811 bitrate = max(bitrate_list) # select highest
2813 url_list = jsonData[fmt][bitrate]
2814 except TypeError: # we have no bitrate info.
2815 url_list = jsonData[fmt]
2818 def check_urls(self, url_list):
2819 """Returns 1st active url from list"""
2820 for url in url_list:
2822 compat_urllib_request.urlopen(url)
2824 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
2829 def _print_formats(self, formats):
2830 print('Available formats:')
2831 for fmt in formats.keys():
2832 for b in formats[fmt]:
2834 ext = formats[fmt][b][0]
2835 print('%s\t%s\t[%s]' % (fmt, b, ext.split('.')[-1]))
2836 except TypeError: # we have no bitrate info
2837 ext = formats[fmt][0]
2838 print('%s\t%s\t[%s]' % (fmt, '??', ext.split('.')[-1]))
2841 def _real_extract(self, url):
2842 mobj = re.match(self._VALID_URL, url)
2844 self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
2846 # extract uploader & filename from url
2847 uploader = mobj.group(1).decode('utf-8')
2848 file_id = uploader + "-" + mobj.group(2).decode('utf-8')
2850 # construct API request
2851 file_url = 'http://www.mixcloud.com/api/1/cloudcast/' + '/'.join(url.split('/')[-3:-1]) + '.json'
2852 # retrieve .json file with links to files
2853 request = compat_urllib_request.Request(file_url)
2855 self.report_download_json(file_url)
2856 jsonData = compat_urllib_request.urlopen(request).read()
2857 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
2858 self._downloader.trouble(u'ERROR: Unable to retrieve file: %s' % compat_str(err))
2862 json_data = json.loads(jsonData)
2863 player_url = json_data['player_swf_url']
2864 formats = dict(json_data['audio_formats'])
2866 req_format = self._downloader.params.get('format', None)
2869 if self._downloader.params.get('listformats', None):
2870 self._print_formats(formats)
2873 if req_format is None or req_format == 'best':
2874 for format_param in formats.keys():
2875 url_list = self.get_urls(formats, format_param)
2877 file_url = self.check_urls(url_list)
2878 if file_url is not None:
2881 if req_format not in formats:
2882 self._downloader.trouble(u'ERROR: format is not available')
2885 url_list = self.get_urls(formats, req_format)
2886 file_url = self.check_urls(url_list)
2887 format_param = req_format
2890 'id': file_id.decode('utf-8'),
2891 'url': file_url.decode('utf-8'),
2892 'uploader': uploader.decode('utf-8'),
2893 'upload_date': None,
2894 'title': json_data['name'],
2895 'ext': file_url.split('.')[-1].decode('utf-8'),
2896 'format': (format_param is None and u'NA' or format_param.decode('utf-8')),
2897 'thumbnail': json_data['thumbnail_url'],
2898 'description': json_data['description'],
2899 'player_url': player_url.decode('utf-8'),
2902 class StanfordOpenClassroomIE(InfoExtractor):
2903 """Information extractor for Stanford's Open ClassRoom"""
2905 _VALID_URL = r'^(?:https?://)?openclassroom.stanford.edu(?P<path>/?|(/MainFolder/(?:HomePage|CoursePage|VideoPage)\.php([?]course=(?P<course>[^&]+)(&video=(?P<video>[^&]+))?(&.*)?)?))$'
2906 IE_NAME = u'stanfordoc'
2908 def report_download_webpage(self, objid):
2909 """Report information extraction."""
2910 self._downloader.to_screen(u'[%s] %s: Downloading webpage' % (self.IE_NAME, objid))
2912 def report_extraction(self, video_id):
2913 """Report information extraction."""
2914 self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id))
2916 def _real_extract(self, url):
2917 mobj = re.match(self._VALID_URL, url)
2919 raise ExtractorError(u'Invalid URL: %s' % url)
2921 if mobj.group('course') and mobj.group('video'): # A specific video
2922 course = mobj.group('course')
2923 video = mobj.group('video')
2925 'id': course + '_' + video,
2927 'upload_date': None,
2930 self.report_extraction(info['id'])
2931 baseUrl = 'http://openclassroom.stanford.edu/MainFolder/courses/' + course + '/videos/'
2932 xmlUrl = baseUrl + video + '.xml'
2934 metaXml = compat_urllib_request.urlopen(xmlUrl).read()
2935 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
2936 self._downloader.trouble(u'ERROR: unable to download video info XML: %s' % compat_str(err))
2938 mdoc = xml.etree.ElementTree.fromstring(metaXml)
2940 info['title'] = mdoc.findall('./title')[0].text
2941 info['url'] = baseUrl + mdoc.findall('./videoFile')[0].text
2943 self._downloader.trouble(u'\nERROR: Invalid metadata XML file')
2945 info['ext'] = info['url'].rpartition('.')[2]
2947 elif mobj.group('course'): # A course page
2948 course = mobj.group('course')
2953 'upload_date': None,
2956 coursepage = self._download_webpage(url, info['id'],
2957 note='Downloading course info page',
2958 errnote='Unable to download course info page')
2960 m = re.search('<h1>([^<]+)</h1>', coursepage)
2962 info['title'] = unescapeHTML(m.group(1))
2964 info['title'] = info['id']
2966 m = re.search('<description>([^<]+)</description>', coursepage)
2968 info['description'] = unescapeHTML(m.group(1))
2970 links = orderedSet(re.findall('<a href="(VideoPage.php\?[^"]+)">', coursepage))
2973 'type': 'reference',
2974 'url': 'http://openclassroom.stanford.edu/MainFolder/' + unescapeHTML(vpage),
2978 for entry in info['list']:
2979 assert entry['type'] == 'reference'
2980 results += self.extract(entry['url'])
2984 'id': 'Stanford OpenClassroom',
2987 'upload_date': None,
2990 self.report_download_webpage(info['id'])
2991 rootURL = 'http://openclassroom.stanford.edu/MainFolder/HomePage.php'
2993 rootpage = compat_urllib_request.urlopen(rootURL).read()
2994 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
2995 self._downloader.trouble(u'ERROR: unable to download course info page: ' + compat_str(err))
2998 info['title'] = info['id']
3000 links = orderedSet(re.findall('<a href="(CoursePage.php\?[^"]+)">', rootpage))
3003 'type': 'reference',
3004 'url': 'http://openclassroom.stanford.edu/MainFolder/' + unescapeHTML(cpage),
3009 for entry in info['list']:
3010 assert entry['type'] == 'reference'
3011 results += self.extract(entry['url'])
3014 class MTVIE(InfoExtractor):
3015 """Information extractor for MTV.com"""
3017 _VALID_URL = r'^(?P<proto>https?://)?(?:www\.)?mtv\.com/videos/[^/]+/(?P<videoid>[0-9]+)/[^/]+$'
3020 def report_extraction(self, video_id):
3021 """Report information extraction."""
3022 self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id))
3024 def _real_extract(self, url):
3025 mobj = re.match(self._VALID_URL, url)
3027 self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
3029 if not mobj.group('proto'):
3030 url = 'http://' + url
3031 video_id = mobj.group('videoid')
3033 webpage = self._download_webpage(url, video_id)
3035 mobj = re.search(r'<meta name="mtv_vt" content="([^"]+)"/>', webpage)
3037 self._downloader.trouble(u'ERROR: unable to extract song name')
3039 song_name = unescapeHTML(mobj.group(1).decode('iso-8859-1'))
3040 mobj = re.search(r'<meta name="mtv_an" content="([^"]+)"/>', webpage)
3042 self._downloader.trouble(u'ERROR: unable to extract performer')
3044 performer = unescapeHTML(mobj.group(1).decode('iso-8859-1'))
3045 video_title = performer + ' - ' + song_name
3047 mobj = re.search(r'<meta name="mtvn_uri" content="([^"]+)"/>', webpage)
3049 self._downloader.trouble(u'ERROR: unable to mtvn_uri')
3051 mtvn_uri = mobj.group(1)
3053 mobj = re.search(r'MTVN.Player.defaultPlaylistId = ([0-9]+);', webpage)
3055 self._downloader.trouble(u'ERROR: unable to extract content id')
3057 content_id = mobj.group(1)
3059 videogen_url = 'http://www.mtv.com/player/includes/mediaGen.jhtml?uri=' + mtvn_uri + '&id=' + content_id + '&vid=' + video_id + '&ref=www.mtvn.com&viewUri=' + mtvn_uri
3060 self.report_extraction(video_id)
3061 request = compat_urllib_request.Request(videogen_url)
3063 metadataXml = compat_urllib_request.urlopen(request).read()
3064 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
3065 self._downloader.trouble(u'ERROR: unable to download video metadata: %s' % compat_str(err))
3068 mdoc = xml.etree.ElementTree.fromstring(metadataXml)
3069 renditions = mdoc.findall('.//rendition')
3071 # For now, always pick the highest quality.
3072 rendition = renditions[-1]
3075 _,_,ext = rendition.attrib['type'].partition('/')
3076 format = ext + '-' + rendition.attrib['width'] + 'x' + rendition.attrib['height'] + '_' + rendition.attrib['bitrate']
3077 video_url = rendition.find('./src').text
3079 self._downloader.trouble('Invalid rendition field.')
3085 'uploader': performer,
3086 'upload_date': None,
3087 'title': video_title,
3095 class YoukuIE(InfoExtractor):
3096 _VALID_URL = r'(?:http://)?v\.youku\.com/v_show/id_(?P<ID>[A-Za-z0-9]+)\.html'
3098 def report_download_webpage(self, file_id):
3099 """Report webpage download."""
3100 self._downloader.to_screen(u'[%s] %s: Downloading webpage' % (self.IE_NAME, file_id))
3102 def report_extraction(self, file_id):
3103 """Report information extraction."""
3104 self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, file_id))
3107 nowTime = int(time.time() * 1000)
3108 random1 = random.randint(1000,1998)
3109 random2 = random.randint(1000,9999)
3111 return "%d%d%d" %(nowTime,random1,random2)
3113 def _get_file_ID_mix_string(self, seed):
3115 source = list("abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ/\:._-1234567890")
3117 for i in range(len(source)):
3118 seed = (seed * 211 + 30031 ) % 65536
3119 index = math.floor(seed / 65536 * len(source) )
3120 mixed.append(source[int(index)])
3121 source.remove(source[int(index)])
3122 #return ''.join(mixed)
3125 def _get_file_id(self, fileId, seed):
3126 mixed = self._get_file_ID_mix_string(seed)
3127 ids = fileId.split('*')
3131 realId.append(mixed[int(ch)])
3132 return ''.join(realId)
3134 def _real_extract(self, url):
3135 mobj = re.match(self._VALID_URL, url)
3137 self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
3139 video_id = mobj.group('ID')
3141 info_url = 'http://v.youku.com/player/getPlayList/VideoIDS/' + video_id
3143 request = compat_urllib_request.Request(info_url, None, std_headers)
3145 self.report_download_webpage(video_id)
3146 jsondata = compat_urllib_request.urlopen(request).read()
3147 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
3148 self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err))
3151 self.report_extraction(video_id)
3153 jsonstr = jsondata.decode('utf-8')
3154 config = json.loads(jsonstr)
3156 video_title = config['data'][0]['title']
3157 seed = config['data'][0]['seed']
3159 format = self._downloader.params.get('format', None)
3160 supported_format = list(config['data'][0]['streamfileids'].keys())
3162 if format is None or format == 'best':
3163 if 'hd2' in supported_format:
3168 elif format == 'worst':
3176 fileid = config['data'][0]['streamfileids'][format]
3177 keys = [s['k'] for s in config['data'][0]['segs'][format]]
3178 except (UnicodeDecodeError, ValueError, KeyError):
3179 self._downloader.trouble(u'ERROR: unable to extract info section')
3183 sid = self._gen_sid()
3184 fileid = self._get_file_id(fileid, seed)
3186 #column 8,9 of fileid represent the segment number
3187 #fileid[7:9] should be changed
3188 for index, key in enumerate(keys):
3190 temp_fileid = '%s%02X%s' % (fileid[0:8], index, fileid[10:])
3191 download_url = 'http://f.youku.com/player/getFlvPath/sid/%s_%02X/st/flv/fileid/%s?k=%s' % (sid, index, temp_fileid, key)
3194 'id': '%s_part%02d' % (video_id, index),
3195 'url': download_url,
3197 'upload_date': None,
3198 'title': video_title,
3201 files_info.append(info)
3206 class XNXXIE(InfoExtractor):
3207 """Information extractor for xnxx.com"""
3209 _VALID_URL = r'^(?:https?://)?video\.xnxx\.com/video([0-9]+)/(.*)'
3211 VIDEO_URL_RE = r'flv_url=(.*?)&'
3212 VIDEO_TITLE_RE = r'<title>(.*?)\s+-\s+XNXX.COM'
3213 VIDEO_THUMB_RE = r'url_bigthumb=(.*?)&'
3215 def report_webpage(self, video_id):
3216 """Report information extraction"""
3217 self._downloader.to_screen(u'[%s] %s: Downloading webpage' % (self.IE_NAME, video_id))
3219 def report_extraction(self, video_id):
3220 """Report information extraction"""
3221 self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id))
3223 def _real_extract(self, url):
3224 mobj = re.match(self._VALID_URL, url)
3226 self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
3228 video_id = mobj.group(1)
3230 self.report_webpage(video_id)
3232 # Get webpage content
3234 webpage_bytes = compat_urllib_request.urlopen(url).read()
3235 webpage = webpage_bytes.decode('utf-8')
3236 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
3237 self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % err)
3240 result = re.search(self.VIDEO_URL_RE, webpage)
3242 self._downloader.trouble(u'ERROR: unable to extract video url')
3244 video_url = compat_urllib_parse.unquote(result.group(1))
3246 result = re.search(self.VIDEO_TITLE_RE, webpage)
3248 self._downloader.trouble(u'ERROR: unable to extract video title')
3250 video_title = result.group(1)
3252 result = re.search(self.VIDEO_THUMB_RE, webpage)
3254 self._downloader.trouble(u'ERROR: unable to extract video thumbnail')
3256 video_thumbnail = result.group(1)
3262 'upload_date': None,
3263 'title': video_title,
3265 'thumbnail': video_thumbnail,
3266 'description': None,
3270 class GooglePlusIE(InfoExtractor):
3271 """Information extractor for plus.google.com."""
3273 _VALID_URL = r'(?:https://)?plus\.google\.com/(?:[^/]+/)*?posts/(\w+)'
3274 IE_NAME = u'plus.google'
3276 def __init__(self, downloader=None):
3277 InfoExtractor.__init__(self, downloader)
3279 def report_extract_entry(self, url):
3280 """Report downloading extry"""
3281 self._downloader.to_screen(u'[plus.google] Downloading entry: %s' % url)
3283 def report_date(self, upload_date):
3284 """Report downloading extry"""
3285 self._downloader.to_screen(u'[plus.google] Entry date: %s' % upload_date)
3287 def report_uploader(self, uploader):
3288 """Report downloading extry"""
3289 self._downloader.to_screen(u'[plus.google] Uploader: %s' % uploader)
3291 def report_title(self, video_title):
3292 """Report downloading extry"""
3293 self._downloader.to_screen(u'[plus.google] Title: %s' % video_title)
3295 def report_extract_vid_page(self, video_page):
3296 """Report information extraction."""
3297 self._downloader.to_screen(u'[plus.google] Extracting video page: %s' % video_page)
3299 def _real_extract(self, url):
3300 # Extract id from URL
3301 mobj = re.match(self._VALID_URL, url)
3303 self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
3306 post_url = mobj.group(0)
3307 video_id = mobj.group(1)
3309 video_extension = 'flv'
3311 # Step 1, Retrieve post webpage to extract further information
3312 self.report_extract_entry(post_url)
3313 request = compat_urllib_request.Request(post_url)
3315 webpage = compat_urllib_request.urlopen(request).read().decode('utf-8')
3316 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
3317 self._downloader.trouble(u'ERROR: Unable to retrieve entry webpage: %s' % compat_str(err))
3320 # Extract update date
3322 pattern = 'title="Timestamp">(.*?)</a>'
3323 mobj = re.search(pattern, webpage)
3325 upload_date = mobj.group(1)
3326 # Convert timestring to a format suitable for filename
3327 upload_date = datetime.datetime.strptime(upload_date, "%Y-%m-%d")
3328 upload_date = upload_date.strftime('%Y%m%d')
3329 self.report_date(upload_date)
3333 pattern = r'rel\="author".*?>(.*?)</a>'
3334 mobj = re.search(pattern, webpage)
3336 uploader = mobj.group(1)
3337 self.report_uploader(uploader)
3340 # Get the first line for title
3342 pattern = r'<meta name\=\"Description\" content\=\"(.*?)[\n<"]'
3343 mobj = re.search(pattern, webpage)
3345 video_title = mobj.group(1)
3346 self.report_title(video_title)
3348 # Step 2, Stimulate clicking the image box to launch video
3349 pattern = '"(https\://plus\.google\.com/photos/.*?)",,"image/jpeg","video"\]'
3350 mobj = re.search(pattern, webpage)
3352 self._downloader.trouble(u'ERROR: unable to extract video page URL')
3354 video_page = mobj.group(1)
3355 request = compat_urllib_request.Request(video_page)
3357 webpage = compat_urllib_request.urlopen(request).read().decode('utf-8')
3358 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
3359 self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err))
3361 self.report_extract_vid_page(video_page)
3364 # Extract video links on video page
3365 """Extract video links of all sizes"""
3366 pattern = '\d+,\d+,(\d+),"(http\://redirector\.googlevideo\.com.*?)"'
3367 mobj = re.findall(pattern, webpage)
3369 self._downloader.trouble(u'ERROR: unable to extract video links')
3371 # Sort in resolution
3372 links = sorted(mobj)
3374 # Choose the lowest of the sort, i.e. highest resolution
3375 video_url = links[-1]
3376 # Only get the url. The resolution part in the tuple has no use anymore
3377 video_url = video_url[-1]
3378 # Treat escaped \u0026 style hex
3380 video_url = video_url.decode("unicode_escape")
3381 except AttributeError: # Python 3
3382 video_url = bytes(video_url, 'ascii').decode('unicode-escape')
3388 'uploader': uploader,
3389 'upload_date': upload_date,
3390 'title': video_title,
3391 'ext': video_extension,
3394 class NBAIE(InfoExtractor):
3395 _VALID_URL = r'^(?:https?://)?(?:watch\.|www\.)?nba\.com/(?:nba/)?video(/[^?]*)(\?.*)?$'
3398 def _real_extract(self, url):
3399 mobj = re.match(self._VALID_URL, url)
3401 self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
3404 video_id = mobj.group(1)
3405 if video_id.endswith('/index.html'):
3406 video_id = video_id[:-len('/index.html')]
3408 webpage = self._download_webpage(url, video_id)
3410 video_url = u'http://ht-mobile.cdn.turner.com/nba/big' + video_id + '_nba_1280x720.mp4'
3411 def _findProp(rexp, default=None):
3412 m = re.search(rexp, webpage)
3414 return unescapeHTML(m.group(1))
3418 shortened_video_id = video_id.rpartition('/')[2]
3419 title = _findProp(r'<meta property="og:title" content="(.*?)"', shortened_video_id).replace('NBA.com: ', '')
3421 'id': shortened_video_id,
3425 'uploader_date': _findProp(r'<b>Date:</b> (.*?)</div>'),
3426 'description': _findProp(r'<div class="description">(.*?)</h1>'),
3430 class JustinTVIE(InfoExtractor):
3431 """Information extractor for justin.tv and twitch.tv"""
3432 # TODO: One broadcast may be split into multiple videos. The key
3433 # 'broadcast_id' is the same for all parts, and 'broadcast_part'
3434 # starts at 1 and increases. Can we treat all parts as one video?
3436 _VALID_URL = r"""(?x)^(?:http://)?(?:www\.)?(?:twitch|justin)\.tv/
3437 ([^/]+)(?:/b/([^/]+))?/?(?:\#.*)?$"""
3438 _JUSTIN_PAGE_LIMIT = 100
3439 IE_NAME = u'justin.tv'
3441 def report_extraction(self, file_id):
3442 """Report information extraction."""
3443 self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, file_id))
3445 def report_download_page(self, channel, offset):
3446 """Report attempt to download a single page of videos."""
3447 self._downloader.to_screen(u'[%s] %s: Downloading video information from %d to %d' %
3448 (self.IE_NAME, channel, offset, offset + self._JUSTIN_PAGE_LIMIT))
3450 # Return count of items, list of *valid* items
3451 def _parse_page(self, url):
3453 urlh = compat_urllib_request.urlopen(url)
3454 webpage_bytes = urlh.read()
3455 webpage = webpage_bytes.decode('utf-8', 'ignore')
3456 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
3457 self._downloader.trouble(u'ERROR: unable to download video info JSON: %s' % compat_str(err))
3460 response = json.loads(webpage)
3461 if type(response) != list:
3462 error_text = response.get('error', 'unknown error')
3463 self._downloader.trouble(u'ERROR: Justin.tv API: %s' % error_text)
3466 for clip in response:
3467 video_url = clip['video_file_url']
3469 video_extension = os.path.splitext(video_url)[1][1:]
3470 video_date = re.sub('-', '', clip['start_time'][:10])
3471 video_uploader_id = clip.get('user_id', clip.get('channel_id'))
3472 video_id = clip['id']
3473 video_title = clip.get('title', video_id)
3477 'title': video_title,
3478 'uploader': clip.get('channel_name', video_uploader_id),
3479 'uploader_id': video_uploader_id,
3480 'upload_date': video_date,
3481 'ext': video_extension,
3483 return (len(response), info)
3485 def _real_extract(self, url):
3486 mobj = re.match(self._VALID_URL, url)
3488 self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
3491 api = 'http://api.justin.tv'
3492 video_id = mobj.group(mobj.lastindex)
3494 if mobj.lastindex == 1:
3496 api += '/channel/archives/%s.json'
3498 api += '/broadcast/by_archive/%s.json'
3499 api = api % (video_id,)
3501 self.report_extraction(video_id)
3505 limit = self._JUSTIN_PAGE_LIMIT
3508 self.report_download_page(video_id, offset)
3509 page_url = api + ('?offset=%d&limit=%d' % (offset, limit))
3510 page_count, page_info = self._parse_page(page_url)
3511 info.extend(page_info)
3512 if not paged or page_count != limit:
3517 class FunnyOrDieIE(InfoExtractor):
3518 _VALID_URL = r'^(?:https?://)?(?:www\.)?funnyordie\.com/videos/(?P<id>[0-9a-f]+)/.*$'
3520 def _real_extract(self, url):
3521 mobj = re.match(self._VALID_URL, url)
3523 self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
3526 video_id = mobj.group('id')
3527 webpage = self._download_webpage(url, video_id)
3529 m = re.search(r'<video[^>]*>\s*<source[^>]*>\s*<source src="(?P<url>[^"]+)"', webpage, re.DOTALL)
3531 self._downloader.trouble(u'ERROR: unable to find video information')
3532 video_url = unescapeHTML(m.group('url'))
3534 m = re.search(r"class='player_page_h1'>\s+<a.*?>(?P<title>.*?)</a>", webpage)
3536 self._downloader.trouble(u'Cannot find video title')
3537 title = unescapeHTML(m.group('title'))
3539 m = re.search(r'<meta property="og:description" content="(?P<desc>.*?)"', webpage)
3541 desc = unescapeHTML(m.group('desc'))
3550 'description': desc,
3554 class TweetReelIE(InfoExtractor):
3555 _VALID_URL = r'^(?:https?://)?(?:www\.)?tweetreel\.com/[?](?P<id>[0-9a-z]+)$'
3557 def _real_extract(self, url):
3558 mobj = re.match(self._VALID_URL, url)
3560 self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
3563 video_id = mobj.group('id')
3564 webpage = self._download_webpage(url, video_id)
3566 m = re.search(r'<div id="left" status_id="([0-9]+)">', webpage)
3568 self._downloader.trouble(u'ERROR: Cannot find status ID')
3569 status_id = m.group(1)
3571 m = re.search(r'<div class="tweet_text">(.*?)</div>', webpage, flags=re.DOTALL)
3573 self._downloader.trouble(u'WARNING: Cannot find description')
3574 desc = unescapeHTML(re.sub('<a.*?</a>', '', m.group(1))).strip()
3576 m = re.search(r'<div class="tweet_info">.*?from <a target="_blank" href="https?://twitter.com/(?P<uploader_id>.+?)">(?P<uploader>.+?)</a>', webpage, flags=re.DOTALL)
3578 self._downloader.trouble(u'ERROR: Cannot find uploader')
3579 uploader = unescapeHTML(m.group('uploader'))
3580 uploader_id = unescapeHTML(m.group('uploader_id'))
3582 m = re.search(r'<span unixtime="([0-9]+)"', webpage)
3584 self._downloader.trouble(u'ERROR: Cannot find upload date')
3585 upload_date = datetime.datetime.fromtimestamp(int(m.group(1))).strftime('%Y%m%d')
3588 video_url = 'http://files.tweetreel.com/video/' + status_id + '.mov'
3595 'description': desc,
3596 'uploader': uploader,
3597 'uploader_id': uploader_id,
3598 'internal_id': status_id,
3599 'upload_date': upload_date
3603 class SteamIE(InfoExtractor):
3604 _VALID_URL = r"""http://store.steampowered.com/
3605 (?P<urltype>video|app)/ #If the page is only for videos or for a game
3607 (?P<videoID>\d*)(?P<extra>\??) #For urltype == video we sometimes get the videoID
3610 def suitable(self, url):
3611 """Receives a URL and returns True if suitable for this IE."""
3612 return re.match(self._VALID_URL, url, re.VERBOSE) is not None
3614 def _real_extract(self, url):
3615 m = re.match(self._VALID_URL, url, re.VERBOSE)
3616 urlRE = r"'movie_(?P<videoID>\d+)': \{\s*FILENAME: \"(?P<videoURL>[\w:/\.\?=]+)\"(,\s*MOVIE_NAME: \"(?P<videoName>[\w:/\.\?=\+-]+)\")?\s*\},"
3617 gameID = m.group('gameID')
3618 videourl = 'http://store.steampowered.com/video/%s/' % gameID
3619 webpage = self._download_webpage(videourl, gameID)
3620 mweb = re.finditer(urlRE, webpage)
3621 namesRE = r'<span class="title">(?P<videoName>.+?)</span>'
3622 titles = re.finditer(namesRE, webpage)
3624 for vid,vtitle in zip(mweb,titles):
3625 video_id = vid.group('videoID')
3626 title = vtitle.group('videoName')
3627 video_url = vid.group('videoURL')
3629 self._downloader.trouble(u'ERROR: Cannot find video url for %s' % video_id)
3634 'title': unescapeHTML(title)
3639 class UstreamIE(InfoExtractor):
3640 _VALID_URL = r'https?://www\.ustream\.tv/recorded/(?P<videoID>\d+)'
3641 IE_NAME = u'ustream'
3643 def _real_extract(self, url):
3644 m = re.match(self._VALID_URL, url)
3645 video_id = m.group('videoID')
3646 video_url = u'http://tcdn.ustream.tv/video/%s' % video_id
3647 webpage = self._download_webpage(url, video_id)
3648 m = re.search(r'data-title="(?P<title>.+)"',webpage)
3649 title = m.group('title')
3650 m = re.search(r'<a class="state" data-content-type="channel" data-content-id="(?P<uploader>\d+)"',webpage)
3651 uploader = m.group('uploader')
3657 'uploader': uploader
3661 class RBMARadioIE(InfoExtractor):
3662 _VALID_URL = r'https?://(?:www\.)?rbmaradio\.com/shows/(?P<videoID>[^/]+)$'
3664 def _real_extract(self, url):
3665 m = re.match(self._VALID_URL, url)
3666 video_id = m.group('videoID')
3668 webpage = self._download_webpage(url, video_id)
3669 m = re.search(r'<script>window.gon = {.*?};gon\.show=(.+?);</script>', webpage)
3671 raise ExtractorError(u'Cannot find metadata')
3672 json_data = m.group(1)
3675 data = json.loads(json_data)
3676 except ValueError as e:
3677 raise ExtractorError(u'Invalid JSON: ' + str(e))
3679 video_url = data['akamai_url'] + '&cbr=256'
3680 url_parts = compat_urllib_parse_urlparse(video_url)
3681 video_ext = url_parts.path.rpartition('.')[2]
3686 'title': data['title'],
3687 'description': data.get('teaser_text'),
3688 'location': data.get('country_of_origin'),
3689 'uploader': data.get('host', {}).get('name'),
3690 'uploader_id': data.get('host', {}).get('slug'),
3691 'thumbnail': data.get('image', {}).get('large_url_2x'),
3692 'duration': data.get('duration'),
3697 class YouPornIE(InfoExtractor):
3698 """Information extractor for youporn.com."""
3699 _VALID_URL = r'^(?:https?://)?(?:\w+\.)?youporn\.com/watch/(?P<videoid>[0-9]+)/(?P<title>[^/]+)'
3701 def _print_formats(self, formats):
3702 """Print all available formats"""
3703 print(u'Available formats:')
3704 print(u'ext\t\tformat')
3705 print(u'---------------------------------')
3706 for format in formats:
3707 print(u'%s\t\t%s' % (format['ext'], format['format']))
3709 def _specific(self, req_format, formats):
3711 if(x["format"]==req_format):
3715 def _real_extract(self, url):
3716 mobj = re.match(self._VALID_URL, url)
3718 self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
3721 video_id = mobj.group('videoid')
3723 req = compat_urllib_request.Request(url)
3724 req.add_header('Cookie', 'age_verified=1')
3725 webpage = self._download_webpage(req, video_id)
3727 # Get the video title
3728 result = re.search(r'videoTitleArea">(?P<title>.*)</h1>', webpage)
3730 raise ExtractorError(u'ERROR: unable to extract video title')
3731 video_title = result.group('title').strip()
3733 # Get the video date
3734 result = re.search(r'Date:</b>(?P<date>.*)</li>', webpage)
3736 self._downloader.to_stderr(u'WARNING: unable to extract video date')
3739 upload_date = result.group('date').strip()
3741 # Get the video uploader
3742 result = re.search(r'Submitted:</b>(?P<uploader>.*)</li>', webpage)
3744 self._downloader.to_stderr(u'ERROR: unable to extract uploader')
3745 video_uploader = None
3747 video_uploader = result.group('uploader').strip()
3748 video_uploader = clean_html( video_uploader )
3750 # Get all of the formats available
3751 DOWNLOAD_LIST_RE = r'(?s)<ul class="downloadList">(?P<download_list>.*?)</ul>'
3752 result = re.search(DOWNLOAD_LIST_RE, webpage)
3754 raise ExtractorError(u'Unable to extract download list')
3755 download_list_html = result.group('download_list').strip()
3757 # Get all of the links from the page
3758 LINK_RE = r'(?s)<a href="(?P<url>[^"]+)">'
3759 links = re.findall(LINK_RE, download_list_html)
3760 if(len(links) == 0):
3761 raise ExtractorError(u'ERROR: no known formats available for video')
3763 self._downloader.to_screen(u'[youporn] Links found: %d' % len(links))
3768 # A link looks like this:
3769 # http://cdn1.download.youporn.phncdn.com/201210/31/8004515/480p_370k_8004515/YouPorn%20-%20Nubile%20Films%20The%20Pillow%20Fight.mp4?nvb=20121113051249&nva=20121114051249&ir=1200&sr=1200&hash=014b882080310e95fb6a0
3770 # A path looks like this:
3771 # /201210/31/8004515/480p_370k_8004515/YouPorn%20-%20Nubile%20Films%20The%20Pillow%20Fight.mp4
3772 video_url = unescapeHTML( link )
3773 path = compat_urllib_parse_urlparse( video_url ).path
3774 extension = os.path.splitext( path )[1][1:]
3775 format = path.split('/')[4].split('_')[:2]
3778 format = "-".join( format )
3779 title = u'%s-%s-%s' % (video_title, size, bitrate)
3784 'uploader': video_uploader,
3785 'upload_date': upload_date,
3790 'description': None,
3794 if self._downloader.params.get('listformats', None):
3795 self._print_formats(formats)
3798 req_format = self._downloader.params.get('format', None)
3799 self._downloader.to_screen(u'[youporn] Format: %s' % req_format)
3801 if req_format is None or req_format == 'best':
3803 elif req_format == 'worst':
3804 return [formats[-1]]
3805 elif req_format in ('-1', 'all'):
3808 format = self._specific( req_format, formats )
3810 self._downloader.trouble(u'ERROR: requested format not available')
3816 class PornotubeIE(InfoExtractor):
3817 """Information extractor for pornotube.com."""
3818 _VALID_URL = r'^(?:https?://)?(?:\w+\.)?pornotube\.com(/c/(?P<channel>[0-9]+))?(/m/(?P<videoid>[0-9]+))(/(?P<title>.+))$'
3820 def _real_extract(self, url):
3821 mobj = re.match(self._VALID_URL, url)
3823 self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
3826 video_id = mobj.group('videoid')
3827 video_title = mobj.group('title')
3829 # Get webpage content
3830 webpage = self._download_webpage(url, video_id)
3833 VIDEO_URL_RE = r'url: "(?P<url>http://video[0-9].pornotube.com/.+\.flv)",'
3834 result = re.search(VIDEO_URL_RE, webpage)
3836 self._downloader.trouble(u'ERROR: unable to extract video url')
3838 video_url = compat_urllib_parse.unquote(result.group('url'))
3840 #Get the uploaded date
3841 VIDEO_UPLOADED_RE = r'<div class="video_added_by">Added (?P<date>[0-9\/]+) by'
3842 result = re.search(VIDEO_UPLOADED_RE, webpage)
3844 self._downloader.trouble(u'ERROR: unable to extract video title')
3846 upload_date = result.group('date')
3848 info = {'id': video_id,
3851 'upload_date': upload_date,
3852 'title': video_title,
3858 class YouJizzIE(InfoExtractor):
3859 """Information extractor for youjizz.com."""
3860 _VALID_URL = r'^(?:https?://)?(?:\w+\.)?youjizz\.com/videos/(?P<videoid>[^.]+).html$'
3862 def _real_extract(self, url):
3863 mobj = re.match(self._VALID_URL, url)
3865 self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
3868 video_id = mobj.group('videoid')
3870 # Get webpage content
3871 webpage = self._download_webpage(url, video_id)
3873 # Get the video title
3874 result = re.search(r'<title>(?P<title>.*)</title>', webpage)
3876 raise ExtractorError(u'ERROR: unable to extract video title')
3877 video_title = result.group('title').strip()
3879 # Get the embed page
3880 result = re.search(r'https?://www.youjizz.com/videos/embed/(?P<videoid>[0-9]+)', webpage)
3882 raise ExtractorError(u'ERROR: unable to extract embed page')
3884 embed_page_url = result.group(0).strip()
3885 video_id = result.group('videoid')
3887 webpage = self._download_webpage(embed_page_url, video_id)
3890 result = re.search(r'so.addVariable\("file",encodeURIComponent\("(?P<source>[^"]+)"\)\);', webpage)
3892 raise ExtractorError(u'ERROR: unable to extract video url')
3893 video_url = result.group('source')
3895 info = {'id': video_id,
3897 'title': video_title,
3900 'player_url': embed_page_url}
3904 class EightTracksIE(InfoExtractor):
3906 _VALID_URL = r'https?://8tracks.com/(?P<user>[^/]+)/(?P<id>[^/#]+)(?:#.*)?$'
3908 def _real_extract(self, url):
3909 mobj = re.match(self._VALID_URL, url)
3911 raise ExtractorError(u'Invalid URL: %s' % url)
3912 playlist_id = mobj.group('id')
3914 webpage = self._download_webpage(url, playlist_id)
3916 m = re.search(r"PAGE.mix = (.*?);\n", webpage, flags=re.DOTALL)
3918 raise ExtractorError(u'Cannot find trax information')
3919 json_like = m.group(1)
3920 data = json.loads(json_like)
3922 session = str(random.randint(0, 1000000000))
3924 track_count = data['tracks_count']
3925 first_url = 'http://8tracks.com/sets/%s/play?player=sm&mix_id=%s&format=jsonh' % (session, mix_id)
3926 next_url = first_url
3928 for i in itertools.count():
3929 api_json = self._download_webpage(next_url, playlist_id,
3930 note=u'Downloading song information %s/%s' % (str(i+1), track_count),
3931 errnote=u'Failed to download song information')
3932 api_data = json.loads(api_json)
3933 track_data = api_data[u'set']['track']
3935 'id': track_data['id'],
3936 'url': track_data['track_file_stream_url'],
3937 'title': track_data['performer'] + u' - ' + track_data['name'],
3938 'raw_title': track_data['name'],
3939 'uploader_id': data['user']['login'],
3943 if api_data['set']['at_last_track']:
3945 next_url = 'http://8tracks.com/sets/%s/next?player=sm&mix_id=%s&format=jsonh&track_id=%s' % (session, mix_id, track_data['id'])
3948 class KeekIE(InfoExtractor):
3949 _VALID_URL = r'http://(?:www\.)?keek\.com/(?:!|\w+/keeks/)(?P<videoID>\w+)'
3952 def _real_extract(self, url):
3953 m = re.match(self._VALID_URL, url)
3954 video_id = m.group('videoID')
3955 video_url = u'http://cdn.keek.com/keek/video/%s' % video_id
3956 thumbnail = u'http://cdn.keek.com/keek/thumbnail/%s/w100/h75' % video_id
3957 webpage = self._download_webpage(url, video_id)
3958 m = re.search(r'<meta property="og:title" content="(?P<title>.+)"', webpage)
3959 title = unescapeHTML(m.group('title'))
3960 m = re.search(r'<div class="bio-names-and-report">[\s\n]+<h4>(?P<uploader>\w+)</h4>', webpage)
3961 uploader = unescapeHTML(m.group('uploader'))
3967 'thumbnail': thumbnail,
3968 'uploader': uploader
3972 class TEDIE(InfoExtractor):
3973 _VALID_URL=r'http://www.ted.com/talks/(?P<videoName>\w+)'
3974 def _real_extract(self, url):
3975 m=re.match(self._VALID_URL, url)
3976 videoName=m.group('videoName')
3977 webpage=self._download_webpage(url, 0, 'Downloading \"%s\" page' % videoName)
3978 #If the url includes the language we get the title translated
3979 title_RE=r'<h1><span id="altHeadline" >(?P<title>[\s\w:/\.\?=\+-\\\']*)</span></h1>'
3980 title=re.search(title_RE, webpage).group('title')
3981 info_RE=r'''<script\ type="text/javascript">var\ talkDetails\ =(.*?)
3982 "id":(?P<videoID>[\d]+).*?
3983 "mediaSlug":"(?P<mediaSlug>[\w\d]+?)"'''
3984 info_match=re.search(info_RE,webpage,re.VERBOSE)
3985 video_id=info_match.group('videoID')
3986 mediaSlug=info_match.group('mediaSlug')
3987 video_url='http://download.ted.com/talks/%s.mp4' % mediaSlug
3996 class MySpassIE(InfoExtractor):
3997 _VALID_URL = r'http://www.myspass.de/.*'
3999 def _real_extract(self, url):
4000 META_DATA_URL_TEMPLATE = 'http://www.myspass.de/myspass/includes/apps/video/getvideometadataxml.php?id=%s'
4002 # video id is the last path element of the URL
4003 # usually there is a trailing slash, so also try the second but last
4004 url_path = compat_urllib_parse_urlparse(url).path
4005 url_parent_path, video_id = os.path.split(url_path)
4007 _, video_id = os.path.split(url_parent_path)
4010 metadata_url = META_DATA_URL_TEMPLATE % video_id
4011 metadata_text = self._download_webpage(metadata_url, video_id)
4012 metadata = xml.etree.ElementTree.fromstring(metadata_text.encode('utf-8'))
4014 # extract values from metadata
4015 url_flv_el = metadata.find('url_flv')
4016 if url_flv_el is None:
4017 self._downloader.trouble(u'ERROR: unable to extract download url')
4019 video_url = url_flv_el.text
4020 extension = os.path.splitext(video_url)[1][1:]
4021 title_el = metadata.find('title')
4022 if title_el is None:
4023 self._downloader.trouble(u'ERROR: unable to extract title')
4025 title = title_el.text
4026 format_id_el = metadata.find('format_id')
4027 if format_id_el is None:
4030 format = format_id_el.text
4031 description_el = metadata.find('description')
4032 if description_el is not None:
4033 description = description_el.text
4036 imagePreview_el = metadata.find('imagePreview')
4037 if imagePreview_el is not None:
4038 thumbnail = imagePreview_el.text
4047 'thumbnail': thumbnail,
4048 'description': description
4052 def gen_extractors():
4053 """ Return a list of an instance of every supported extractor.
4054 The order does matter; the first extractor matched is the one handling the URL.
4057 YoutubePlaylistIE(),
4081 StanfordOpenClassroomIE(),