2 # -*- coding: utf-8 -*-
4 from __future__ import absolute_import
15 import xml.etree.ElementTree
26 class InfoExtractor(object):
27 """Information Extractor class.
29 Information extractors are the classes that, given a URL, extract
30 information about the video (or videos) the URL refers to. This
31 information includes the real video URL, the video title, author and
32 others. The information is stored in a dictionary which is then
33 passed to the FileDownloader. The FileDownloader processes this
34 information possibly downloading the video to the file system, among
35 other possible outcomes.
37 The dictionaries must include the following fields:
41 title: Video title, unescaped.
42 ext: Video filename extension.
44 The following fields are optional:
46 format: The video format, defaults to ext (used for --get-format)
47 thumbnail: Full URL to a video thumbnail image.
48 description: One-line video description.
49 uploader: Full name of the video uploader.
50 upload_date: Video upload date (YYYYMMDD).
51 uploader_id: Nickname or id of the video uploader.
52 location: Physical location of the video.
53 player_url: SWF Player URL (used for rtmpdump).
54 subtitles: The subtitle file contents.
55 urlhandle: [internal] The urlHandle to be used to download the file,
56 like returned by urllib.request.urlopen
58 The fields should all be Unicode strings.
60 Subclasses of this one should re-define the _real_initialize() and
61 _real_extract() methods and define a _VALID_URL regexp.
62 Probably, they should also be added to the list of extractors.
64 _real_extract() must return a *list* of information dictionaries as
67 Finally, the _WORKING attribute should be set to False for broken IEs
68 in order to warn the users and skip the tests.
75 def __init__(self, downloader=None):
76 """Constructor. Receives an optional downloader."""
78 self.set_downloader(downloader)
81 def suitable(cls, url):
82 """Receives a URL and returns True if suitable for this IE."""
83 return re.match(cls._VALID_URL, url) is not None
87 """Getter method for _WORKING."""
91 """Initializes an instance (authentication, etc)."""
93 self._real_initialize()
96 def extract(self, url):
97 """Extracts URL information and returns it in list of dicts."""
99 return self._real_extract(url)
101 def set_downloader(self, downloader):
102 """Sets the downloader for this IE."""
103 self._downloader = downloader
105 def _real_initialize(self):
106 """Real initialization process. Redefine in subclasses."""
109 def _real_extract(self, url):
110 """Real extraction process. Redefine in subclasses."""
115 return type(self).__name__[:-2]
117 def _request_webpage(self, url_or_request, video_id, note=None, errnote=None):
118 """ Returns the response handle """
120 self.report_download_webpage(video_id)
121 elif note is not False:
122 self.to_screen(u'%s: %s' % (video_id, note))
124 return compat_urllib_request.urlopen(url_or_request)
125 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
127 errnote = u'Unable to download webpage'
128 raise ExtractorError(u'%s: %s' % (errnote, compat_str(err)), sys.exc_info()[2])
130 def _download_webpage_handle(self, url_or_request, video_id, note=None, errnote=None):
131 """ Returns a tuple (page content as string, URL handle) """
132 urlh = self._request_webpage(url_or_request, video_id, note, errnote)
133 content_type = urlh.headers.get('Content-Type', '')
134 m = re.match(r'[a-zA-Z0-9_.-]+/[a-zA-Z0-9_.-]+\s*;\s*charset=(.+)', content_type)
136 encoding = m.group(1)
139 webpage_bytes = urlh.read()
140 if self._downloader.params.get('dump_intermediate_pages', False):
142 url = url_or_request.get_full_url()
143 except AttributeError:
145 self.to_screen(u'Dumping request to ' + url)
146 dump = base64.b64encode(webpage_bytes).decode('ascii')
147 self._downloader.to_screen(dump)
148 content = webpage_bytes.decode(encoding, 'replace')
149 return (content, urlh)
151 def _download_webpage(self, url_or_request, video_id, note=None, errnote=None):
152 """ Returns the data of the page as a string """
153 return self._download_webpage_handle(url_or_request, video_id, note, errnote)[0]
155 def to_screen(self, msg):
156 """Print msg to screen, prefixing it with '[ie_name]'"""
157 self._downloader.to_screen(u'[%s] %s' % (self.IE_NAME, msg))
159 def report_extraction(self, id_or_name):
160 """Report information extraction."""
161 self.to_screen(u'%s: Extracting information' % id_or_name)
163 def report_download_webpage(self, video_id):
164 """Report webpage download."""
165 self.to_screen(u'%s: Downloading webpage' % video_id)
167 def report_age_confirmation(self):
168 """Report attempt to confirm age."""
169 self.to_screen(u'Confirming age')
171 #Methods for following #608
172 #They set the correct value of the '_type' key
173 def video_result(self, video_info):
174 """Returns a video"""
175 video_info['_type'] = 'video'
177 def url_result(self, url, ie=None):
178 """Returns a url that points to a page that should be processed"""
179 #TODO: ie should be the class used for getting the info
180 video_info = {'_type': 'url',
184 def playlist_result(self, entries, playlist_id=None, playlist_title=None):
185 """Returns a playlist"""
186 video_info = {'_type': 'playlist',
189 video_info['id'] = playlist_id
191 video_info['title'] = playlist_title
194 class SearchInfoExtractor(InfoExtractor):
196 Base class for paged search queries extractors.
197 They accept urls in the format _SEARCH_KEY(|all|[0-9]):{query}
198 Instances should define _SEARCH_KEY and _MAX_RESULTS.
202 def _make_valid_url(cls):
203 return r'%s(?P<prefix>|[1-9][0-9]*|all):(?P<query>[\s\S]+)' % cls._SEARCH_KEY
206 def suitable(cls, url):
207 return re.match(cls._make_valid_url(), url) is not None
209 def _real_extract(self, query):
210 mobj = re.match(self._make_valid_url(), query)
212 raise ExtractorError(u'Invalid search query "%s"' % query)
214 prefix = mobj.group('prefix')
215 query = mobj.group('query')
217 return self._get_n_results(query, 1)
218 elif prefix == 'all':
219 return self._get_n_results(query, self._MAX_RESULTS)
223 raise ExtractorError(u'invalid download number %s for query "%s"' % (n, query))
224 elif n > self._MAX_RESULTS:
225 self._downloader.report_warning(u'%s returns max %i results (you requested %i)' % (self._SEARCH_KEY, self._MAX_RESULTS, n))
226 n = self._MAX_RESULTS
227 return self._get_n_results(query, n)
229 def _get_n_results(self, query, n):
230 """Get a specified number of results for a query"""
231 raise NotImplementedError("This method must be implemented by sublclasses")
234 class YoutubeIE(InfoExtractor):
235 """Information extractor for youtube.com."""
239 (?:https?://)? # http(s):// (optional)
240 (?:youtu\.be/|(?:\w+\.)?youtube(?:-nocookie)?\.com/|
241 tube\.majestyc\.net/) # the various hostnames, with wildcard subdomains
242 (?:.*?\#/)? # handle anchor (#/) redirect urls
243 (?: # the various things that can precede the ID:
244 (?:(?:v|embed|e)/) # v/ or embed/ or e/
245 |(?: # or the v= param in all its forms
246 (?:watch(?:_popup)?(?:\.php)?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
247 (?:\?|\#!?) # the params delimiter ? or # or #!
248 (?:.*?&)? # any other preceding param (like /?s=tuff&v=xxxx)
251 )? # optional -> youtube.com/xxxx is OK
252 )? # all until now is optional -> you can pass the naked ID
253 ([0-9A-Za-z_-]+) # here is it! the YouTube video ID
254 (?(1).+)? # if we found the ID, everything can follow
256 _LANG_URL = r'https://www.youtube.com/?hl=en&persist_hl=1&gl=US&persist_gl=1&opt_out_ackd=1'
257 _LOGIN_URL = 'https://accounts.google.com/ServiceLogin'
258 _AGE_URL = 'http://www.youtube.com/verify_age?next_url=/&gl=US&hl=en'
259 _NEXT_URL_RE = r'[\?&]next_url=([^&]+)'
260 _NETRC_MACHINE = 'youtube'
261 # Listed in order of quality
262 _available_formats = ['38', '37', '46', '22', '45', '35', '44', '34', '18', '43', '6', '5', '17', '13']
263 _available_formats_prefer_free = ['38', '46', '37', '45', '22', '44', '35', '43', '34', '18', '6', '5', '17', '13']
264 _video_extensions = {
270 '38': 'video', # You actually don't know if this will be MOV, AVI or whatever
276 _video_dimensions = {
295 def suitable(cls, url):
296 """Receives a URL and returns True if suitable for this IE."""
297 if YoutubePlaylistIE.suitable(url): return False
298 return re.match(cls._VALID_URL, url, re.VERBOSE) is not None
300 def report_lang(self):
301 """Report attempt to set language."""
302 self.to_screen(u'Setting language')
304 def report_login(self):
305 """Report attempt to log in."""
306 self.to_screen(u'Logging in')
308 def report_video_webpage_download(self, video_id):
309 """Report attempt to download video webpage."""
310 self.to_screen(u'%s: Downloading video webpage' % video_id)
312 def report_video_info_webpage_download(self, video_id):
313 """Report attempt to download video info webpage."""
314 self.to_screen(u'%s: Downloading video info webpage' % video_id)
316 def report_video_subtitles_download(self, video_id):
317 """Report attempt to download video info webpage."""
318 self.to_screen(u'%s: Checking available subtitles' % video_id)
320 def report_video_subtitles_request(self, video_id, sub_lang, format):
321 """Report attempt to download video info webpage."""
322 self.to_screen(u'%s: Downloading video subtitles for %s.%s' % (video_id, sub_lang, format))
324 def report_video_subtitles_available(self, video_id, sub_lang_list):
325 """Report available subtitles."""
326 sub_lang = ",".join(list(sub_lang_list.keys()))
327 self.to_screen(u'%s: Available subtitles for video: %s' % (video_id, sub_lang))
329 def report_information_extraction(self, video_id):
330 """Report attempt to extract video information."""
331 self.to_screen(u'%s: Extracting video information' % video_id)
333 def report_unavailable_format(self, video_id, format):
334 """Report extracted video URL."""
335 self.to_screen(u'%s: Format %s not available' % (video_id, format))
337 def report_rtmp_download(self):
338 """Indicate the download will use the RTMP protocol."""
339 self.to_screen(u'RTMP download detected')
341 def _get_available_subtitles(self, video_id):
342 self.report_video_subtitles_download(video_id)
343 request = compat_urllib_request.Request('http://video.google.com/timedtext?hl=en&type=list&v=%s' % video_id)
345 sub_list = compat_urllib_request.urlopen(request).read().decode('utf-8')
346 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
347 return (u'unable to download video subtitles: %s' % compat_str(err), None)
348 sub_lang_list = re.findall(r'name="([^"]*)"[^>]+lang_code="([\w\-]+)"', sub_list)
349 sub_lang_list = dict((l[1], l[0]) for l in sub_lang_list)
350 if not sub_lang_list:
351 return (u'video doesn\'t have subtitles', None)
354 def _list_available_subtitles(self, video_id):
355 sub_lang_list = self._get_available_subtitles(video_id)
356 self.report_video_subtitles_available(video_id, sub_lang_list)
358 def _request_subtitle(self, sub_lang, sub_name, video_id, format):
361 (error_message, sub_lang, sub)
363 self.report_video_subtitles_request(video_id, sub_lang, format)
364 params = compat_urllib_parse.urlencode({
370 url = 'http://www.youtube.com/api/timedtext?' + params
372 sub = compat_urllib_request.urlopen(url).read().decode('utf-8')
373 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
374 return (u'unable to download video subtitles: %s' % compat_str(err), None, None)
376 return (u'Did not fetch video subtitles', None, None)
377 return (None, sub_lang, sub)
379 def _request_automatic_caption(self, video_id, webpage):
380 """We need the webpage for getting the captions url, pass it as an
381 argument to speed up the process."""
382 sub_lang = self._downloader.params.get('subtitleslang')
383 sub_format = self._downloader.params.get('subtitlesformat')
384 self.to_screen(u'%s: Looking for automatic captions' % video_id)
385 mobj = re.search(r';ytplayer.config = ({.*?});', webpage)
386 err_msg = u'Couldn\'t find automatic captions for "%s"' % sub_lang
388 return [(err_msg, None, None)]
389 player_config = json.loads(mobj.group(1))
391 args = player_config[u'args']
392 caption_url = args[u'ttsurl']
393 timestamp = args[u'timestamp']
394 params = compat_urllib_parse.urlencode({
401 subtitles_url = caption_url + '&' + params
402 sub = self._download_webpage(subtitles_url, video_id, u'Downloading automatic captions')
403 return [(None, sub_lang, sub)]
405 return [(err_msg, None, None)]
407 def _extract_subtitle(self, video_id):
409 Return a list with a tuple:
410 [(error_message, sub_lang, sub)]
412 sub_lang_list = self._get_available_subtitles(video_id)
413 sub_format = self._downloader.params.get('subtitlesformat')
414 if isinstance(sub_lang_list,tuple): #There was some error, it didn't get the available subtitles
415 return [(sub_lang_list[0], None, None)]
416 if self._downloader.params.get('subtitleslang', False):
417 sub_lang = self._downloader.params.get('subtitleslang')
418 elif 'en' in sub_lang_list:
421 sub_lang = list(sub_lang_list.keys())[0]
422 if not sub_lang in sub_lang_list:
423 return [(u'no closed captions found in the specified language "%s"' % sub_lang, None, None)]
425 subtitle = self._request_subtitle(sub_lang, sub_lang_list[sub_lang].encode('utf-8'), video_id, sub_format)
428 def _extract_all_subtitles(self, video_id):
429 sub_lang_list = self._get_available_subtitles(video_id)
430 sub_format = self._downloader.params.get('subtitlesformat')
431 if isinstance(sub_lang_list,tuple): #There was some error, it didn't get the available subtitles
432 return [(sub_lang_list[0], None, None)]
434 for sub_lang in sub_lang_list:
435 subtitle = self._request_subtitle(sub_lang, sub_lang_list[sub_lang].encode('utf-8'), video_id, sub_format)
436 subtitles.append(subtitle)
439 def _print_formats(self, formats):
440 print('Available formats:')
442 print('%s\t:\t%s\t[%s]' %(x, self._video_extensions.get(x, 'flv'), self._video_dimensions.get(x, '???')))
444 def _real_initialize(self):
445 if self._downloader is None:
450 downloader_params = self._downloader.params
452 # Attempt to use provided username and password or .netrc data
453 if downloader_params.get('username', None) is not None:
454 username = downloader_params['username']
455 password = downloader_params['password']
456 elif downloader_params.get('usenetrc', False):
458 info = netrc.netrc().authenticators(self._NETRC_MACHINE)
463 raise netrc.NetrcParseError('No authenticators for %s' % self._NETRC_MACHINE)
464 except (IOError, netrc.NetrcParseError) as err:
465 self._downloader.report_warning(u'parsing .netrc: %s' % compat_str(err))
469 request = compat_urllib_request.Request(self._LANG_URL)
472 compat_urllib_request.urlopen(request).read()
473 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
474 self._downloader.report_warning(u'unable to set language: %s' % compat_str(err))
477 # No authentication to be performed
481 request = compat_urllib_request.Request(self._LOGIN_URL)
483 login_page = compat_urllib_request.urlopen(request).read().decode('utf-8')
484 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
485 self._downloader.report_warning(u'unable to fetch login page: %s' % compat_str(err))
490 match = re.search(re.compile(r'<input.+?name="GALX".+?value="(.+?)"', re.DOTALL), login_page)
492 galx = match.group(1)
494 match = re.search(re.compile(r'<input.+?name="dsh".+?value="(.+?)"', re.DOTALL), login_page)
500 u'continue': u'https://www.youtube.com/signin?action_handle_signin=true&feature=sign_in_button&hl=en_US&nomobiletemp=1',
504 u'PersistentCookie': u'yes',
506 u'bgresponse': u'js_disabled',
507 u'checkConnection': u'',
508 u'checkedDomains': u'youtube',
514 u'signIn': u'Sign in',
516 u'service': u'youtube',
520 # Convert to UTF-8 *before* urlencode because Python 2.x's urlencode
522 login_form = dict((k.encode('utf-8'), v.encode('utf-8')) for k,v in login_form_strs.items())
523 login_data = compat_urllib_parse.urlencode(login_form).encode('ascii')
524 request = compat_urllib_request.Request(self._LOGIN_URL, login_data)
527 login_results = compat_urllib_request.urlopen(request).read().decode('utf-8')
528 if re.search(r'(?i)<form[^>]* id="gaia_loginform"', login_results) is not None:
529 self._downloader.report_warning(u'unable to log in: bad username or password')
531 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
532 self._downloader.report_warning(u'unable to log in: %s' % compat_str(err))
538 'action_confirm': 'Confirm',
540 request = compat_urllib_request.Request(self._AGE_URL, compat_urllib_parse.urlencode(age_form))
542 self.report_age_confirmation()
543 age_results = compat_urllib_request.urlopen(request).read().decode('utf-8')
544 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
545 raise ExtractorError(u'Unable to confirm age: %s' % compat_str(err))
547 def _extract_id(self, url):
548 mobj = re.match(self._VALID_URL, url, re.VERBOSE)
550 raise ExtractorError(u'Invalid URL: %s' % url)
551 video_id = mobj.group(2)
554 def _real_extract(self, url):
555 # Extract original video URL from URL with redirection, like age verification, using next_url parameter
556 mobj = re.search(self._NEXT_URL_RE, url)
558 url = 'https://www.youtube.com/' + compat_urllib_parse.unquote(mobj.group(1)).lstrip('/')
559 video_id = self._extract_id(url)
562 self.report_video_webpage_download(video_id)
563 url = 'https://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1' % video_id
564 request = compat_urllib_request.Request(url)
566 video_webpage_bytes = compat_urllib_request.urlopen(request).read()
567 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
568 raise ExtractorError(u'Unable to download video webpage: %s' % compat_str(err))
570 video_webpage = video_webpage_bytes.decode('utf-8', 'ignore')
572 # Attempt to extract SWF player URL
573 mobj = re.search(r'swfConfig.*?"(http:\\/\\/.*?watch.*?-.*?\.swf)"', video_webpage)
575 player_url = re.sub(r'\\(.)', r'\1', mobj.group(1))
580 self.report_video_info_webpage_download(video_id)
581 for el_type in ['&el=embedded', '&el=detailpage', '&el=vevo', '']:
582 video_info_url = ('https://www.youtube.com/get_video_info?&video_id=%s%s&ps=default&eurl=&gl=US&hl=en'
583 % (video_id, el_type))
584 video_info_webpage = self._download_webpage(video_info_url, video_id,
586 errnote='unable to download video info webpage')
587 video_info = compat_parse_qs(video_info_webpage)
588 if 'token' in video_info:
590 if 'token' not in video_info:
591 if 'reason' in video_info:
592 raise ExtractorError(u'YouTube said: %s' % video_info['reason'][0])
594 raise ExtractorError(u'"token" parameter not in video info for unknown reason')
596 # Check for "rental" videos
597 if 'ypc_video_rental_bar_text' in video_info and 'author' not in video_info:
598 raise ExtractorError(u'"rental" videos not supported')
600 # Start extracting information
601 self.report_information_extraction(video_id)
604 if 'author' not in video_info:
605 raise ExtractorError(u'Unable to extract uploader name')
606 video_uploader = compat_urllib_parse.unquote_plus(video_info['author'][0])
609 video_uploader_id = None
610 mobj = re.search(r'<link itemprop="url" href="http://www.youtube.com/(?:user|channel)/([^"]+)">', video_webpage)
612 video_uploader_id = mobj.group(1)
614 self._downloader.report_warning(u'unable to extract uploader nickname')
617 if 'title' not in video_info:
618 raise ExtractorError(u'Unable to extract video title')
619 video_title = compat_urllib_parse.unquote_plus(video_info['title'][0])
622 if 'thumbnail_url' not in video_info:
623 self._downloader.report_warning(u'unable to extract video thumbnail')
625 else: # don't panic if we can't find it
626 video_thumbnail = compat_urllib_parse.unquote_plus(video_info['thumbnail_url'][0])
630 mobj = re.search(r'id="eow-date.*?>(.*?)</span>', video_webpage, re.DOTALL)
632 upload_date = ' '.join(re.sub(r'[/,-]', r' ', mobj.group(1)).split())
633 upload_date = unified_strdate(upload_date)
636 video_description = get_element_by_id("eow-description", video_webpage)
637 if video_description:
638 video_description = clean_html(video_description)
640 fd_mobj = re.search(r'<meta name="description" content="([^"]+)"', video_webpage)
642 video_description = unescapeHTML(fd_mobj.group(1))
644 video_description = u''
647 video_subtitles = None
649 if self._downloader.params.get('writesubtitles', False):
650 video_subtitles = self._extract_subtitle(video_id)
652 (sub_error, sub_lang, sub) = video_subtitles[0]
654 # We try with the automatic captions
655 video_subtitles = self._request_automatic_caption(video_id, video_webpage)
656 (sub_error_auto, sub_lang, sub) = video_subtitles[0]
660 # We report the original error
661 self._downloader.report_error(sub_error)
663 if self._downloader.params.get('allsubtitles', False):
664 video_subtitles = self._extract_all_subtitles(video_id)
665 for video_subtitle in video_subtitles:
666 (sub_error, sub_lang, sub) = video_subtitle
668 self._downloader.report_error(sub_error)
670 if self._downloader.params.get('listsubtitles', False):
671 sub_lang_list = self._list_available_subtitles(video_id)
674 if 'length_seconds' not in video_info:
675 self._downloader.report_warning(u'unable to extract video duration')
678 video_duration = compat_urllib_parse.unquote_plus(video_info['length_seconds'][0])
681 video_token = compat_urllib_parse.unquote_plus(video_info['token'][0])
683 # Decide which formats to download
684 req_format = self._downloader.params.get('format', None)
686 if 'conn' in video_info and video_info['conn'][0].startswith('rtmp'):
687 self.report_rtmp_download()
688 video_url_list = [(None, video_info['conn'][0])]
689 elif 'url_encoded_fmt_stream_map' in video_info and len(video_info['url_encoded_fmt_stream_map']) >= 1:
691 for url_data_str in video_info['url_encoded_fmt_stream_map'][0].split(','):
692 url_data = compat_parse_qs(url_data_str)
693 if 'itag' in url_data and 'url' in url_data:
694 url = url_data['url'][0] + '&signature=' + url_data['sig'][0]
695 if not 'ratebypass' in url: url += '&ratebypass=yes'
696 url_map[url_data['itag'][0]] = url
698 format_limit = self._downloader.params.get('format_limit', None)
699 available_formats = self._available_formats_prefer_free if self._downloader.params.get('prefer_free_formats', False) else self._available_formats
700 if format_limit is not None and format_limit in available_formats:
701 format_list = available_formats[available_formats.index(format_limit):]
703 format_list = available_formats
704 existing_formats = [x for x in format_list if x in url_map]
705 if len(existing_formats) == 0:
706 raise ExtractorError(u'no known formats available for video')
707 if self._downloader.params.get('listformats', None):
708 self._print_formats(existing_formats)
710 if req_format is None or req_format == 'best':
711 video_url_list = [(existing_formats[0], url_map[existing_formats[0]])] # Best quality
712 elif req_format == 'worst':
713 video_url_list = [(existing_formats[len(existing_formats)-1], url_map[existing_formats[len(existing_formats)-1]])] # worst quality
714 elif req_format in ('-1', 'all'):
715 video_url_list = [(f, url_map[f]) for f in existing_formats] # All formats
717 # Specific formats. We pick the first in a slash-delimeted sequence.
718 # For example, if '1/2/3/4' is requested and '2' and '4' are available, we pick '2'.
719 req_formats = req_format.split('/')
720 video_url_list = None
721 for rf in req_formats:
723 video_url_list = [(rf, url_map[rf])]
725 if video_url_list is None:
726 raise ExtractorError(u'requested format not available')
728 raise ExtractorError(u'no conn or url_encoded_fmt_stream_map information found in video info')
731 for format_param, video_real_url in video_url_list:
733 video_extension = self._video_extensions.get(format_param, 'flv')
735 video_format = '{0} - {1}'.format(format_param if format_param else video_extension,
736 self._video_dimensions.get(format_param, '???'))
740 'url': video_real_url,
741 'uploader': video_uploader,
742 'uploader_id': video_uploader_id,
743 'upload_date': upload_date,
744 'title': video_title,
745 'ext': video_extension,
746 'format': video_format,
747 'thumbnail': video_thumbnail,
748 'description': video_description,
749 'player_url': player_url,
750 'subtitles': video_subtitles,
751 'duration': video_duration
756 class MetacafeIE(InfoExtractor):
757 """Information Extractor for metacafe.com."""
759 _VALID_URL = r'(?:http://)?(?:www\.)?metacafe\.com/watch/([^/]+)/([^/]+)/.*'
760 _DISCLAIMER = 'http://www.metacafe.com/family_filter/'
761 _FILTER_POST = 'http://www.metacafe.com/f/index.php?inputType=filter&controllerGroup=user'
762 IE_NAME = u'metacafe'
764 def report_disclaimer(self):
765 """Report disclaimer retrieval."""
766 self.to_screen(u'Retrieving disclaimer')
768 def _real_initialize(self):
769 # Retrieve disclaimer
770 request = compat_urllib_request.Request(self._DISCLAIMER)
772 self.report_disclaimer()
773 disclaimer = compat_urllib_request.urlopen(request).read()
774 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
775 raise ExtractorError(u'Unable to retrieve disclaimer: %s' % compat_str(err))
780 'submit': "Continue - I'm over 18",
782 request = compat_urllib_request.Request(self._FILTER_POST, compat_urllib_parse.urlencode(disclaimer_form))
784 self.report_age_confirmation()
785 disclaimer = compat_urllib_request.urlopen(request).read()
786 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
787 raise ExtractorError(u'Unable to confirm age: %s' % compat_str(err))
789 def _real_extract(self, url):
790 # Extract id and simplified title from URL
791 mobj = re.match(self._VALID_URL, url)
793 raise ExtractorError(u'Invalid URL: %s' % url)
795 video_id = mobj.group(1)
797 # Check if video comes from YouTube
798 mobj2 = re.match(r'^yt-(.*)$', video_id)
799 if mobj2 is not None:
800 return [self.url_result('http://www.youtube.com/watch?v=%s' % mobj2.group(1), 'Youtube')]
802 # Retrieve video webpage to extract further information
803 webpage = self._download_webpage('http://www.metacafe.com/watch/%s/' % video_id, video_id)
805 # Extract URL, uploader and title from webpage
806 self.report_extraction(video_id)
807 mobj = re.search(r'(?m)&mediaURL=([^&]+)', webpage)
809 mediaURL = compat_urllib_parse.unquote(mobj.group(1))
810 video_extension = mediaURL[-3:]
812 # Extract gdaKey if available
813 mobj = re.search(r'(?m)&gdaKey=(.*?)&', webpage)
817 gdaKey = mobj.group(1)
818 video_url = '%s?__gda__=%s' % (mediaURL, gdaKey)
820 mobj = re.search(r' name="flashvars" value="(.*?)"', webpage)
822 raise ExtractorError(u'Unable to extract media URL')
823 vardict = compat_parse_qs(mobj.group(1))
824 if 'mediaData' not in vardict:
825 raise ExtractorError(u'Unable to extract media URL')
826 mobj = re.search(r'"mediaURL":"(?P<mediaURL>http.*?)",(.*?)"key":"(?P<key>.*?)"', vardict['mediaData'][0])
828 raise ExtractorError(u'Unable to extract media URL')
829 mediaURL = mobj.group('mediaURL').replace('\\/', '/')
830 video_extension = mediaURL[-3:]
831 video_url = '%s?__gda__=%s' % (mediaURL, mobj.group('key'))
833 mobj = re.search(r'(?im)<title>(.*) - Video</title>', webpage)
835 raise ExtractorError(u'Unable to extract title')
836 video_title = mobj.group(1).decode('utf-8')
838 mobj = re.search(r'submitter=(.*?);', webpage)
840 raise ExtractorError(u'Unable to extract uploader nickname')
841 video_uploader = mobj.group(1)
844 'id': video_id.decode('utf-8'),
845 'url': video_url.decode('utf-8'),
846 'uploader': video_uploader.decode('utf-8'),
848 'title': video_title,
849 'ext': video_extension.decode('utf-8'),
852 class DailymotionIE(InfoExtractor):
853 """Information Extractor for Dailymotion"""
855 _VALID_URL = r'(?i)(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/video/([^/]+)'
856 IE_NAME = u'dailymotion'
858 def _real_extract(self, url):
859 # Extract id and simplified title from URL
860 mobj = re.match(self._VALID_URL, url)
862 raise ExtractorError(u'Invalid URL: %s' % url)
864 video_id = mobj.group(1).split('_')[0].split('?')[0]
866 video_extension = 'mp4'
868 # Retrieve video webpage to extract further information
869 request = compat_urllib_request.Request(url)
870 request.add_header('Cookie', 'family_filter=off')
871 webpage = self._download_webpage(request, video_id)
873 # Extract URL, uploader and title from webpage
874 self.report_extraction(video_id)
875 mobj = re.search(r'\s*var flashvars = (.*)', webpage)
877 raise ExtractorError(u'Unable to extract media URL')
878 flashvars = compat_urllib_parse.unquote(mobj.group(1))
880 for key in ['hd1080URL', 'hd720URL', 'hqURL', 'sdURL', 'ldURL', 'video_url']:
883 self.to_screen(u'Using %s' % key)
886 raise ExtractorError(u'Unable to extract video URL')
888 mobj = re.search(r'"' + max_quality + r'":"(.+?)"', flashvars)
890 raise ExtractorError(u'Unable to extract video URL')
892 video_url = compat_urllib_parse.unquote(mobj.group(1)).replace('\\/', '/')
894 # TODO: support choosing qualities
896 mobj = re.search(r'<meta property="og:title" content="(?P<title>[^"]*)" />', webpage)
898 raise ExtractorError(u'Unable to extract title')
899 video_title = unescapeHTML(mobj.group('title'))
901 video_uploader = None
902 mobj = re.search(r'(?im)<span class="owner[^\"]+?">[^<]+?<a [^>]+?>([^<]+?)</a>', webpage)
904 # lookin for official user
905 mobj_official = re.search(r'<span rel="author"[^>]+?>([^<]+?)</span>', webpage)
906 if mobj_official is None:
907 self._downloader.report_warning(u'unable to extract uploader nickname')
909 video_uploader = mobj_official.group(1)
911 video_uploader = mobj.group(1)
913 video_upload_date = None
914 mobj = re.search(r'<div class="[^"]*uploaded_cont[^"]*" title="[^"]*">([0-9]{2})-([0-9]{2})-([0-9]{4})</div>', webpage)
916 video_upload_date = mobj.group(3) + mobj.group(2) + mobj.group(1)
921 'uploader': video_uploader,
922 'upload_date': video_upload_date,
923 'title': video_title,
924 'ext': video_extension,
928 class PhotobucketIE(InfoExtractor):
929 """Information extractor for photobucket.com."""
931 # TODO: the original _VALID_URL was:
932 # r'(?:http://)?(?:[a-z0-9]+\.)?photobucket\.com/.*[\?\&]current=(.*\.flv)'
933 # Check if it's necessary to keep the old extracion process
934 _VALID_URL = r'(?:http://)?(?:[a-z0-9]+\.)?photobucket\.com/.*(([\?\&]current=)|_)(?P<id>.*)\.(?P<ext>(flv)|(mp4))'
935 IE_NAME = u'photobucket'
937 def _real_extract(self, url):
938 # Extract id from URL
939 mobj = re.match(self._VALID_URL, url)
941 raise ExtractorError(u'Invalid URL: %s' % url)
943 video_id = mobj.group('id')
945 video_extension = mobj.group('ext')
947 # Retrieve video webpage to extract further information
948 webpage = self._download_webpage(url, video_id)
950 # Extract URL, uploader, and title from webpage
951 self.report_extraction(video_id)
952 # We try first by looking the javascript code:
953 mobj = re.search(r'Pb\.Data\.Shared\.put\(Pb\.Data\.Shared\.MEDIA, (?P<json>.*?)\);', webpage)
955 info = json.loads(mobj.group('json'))
958 'url': info[u'downloadUrl'],
959 'uploader': info[u'username'],
960 'upload_date': datetime.date.fromtimestamp(info[u'creationDate']).strftime('%Y%m%d'),
961 'title': info[u'title'],
962 'ext': video_extension,
963 'thumbnail': info[u'thumbUrl'],
966 # We try looking in other parts of the webpage
967 mobj = re.search(r'<link rel="video_src" href=".*\?file=([^"]+)" />', webpage)
969 raise ExtractorError(u'Unable to extract media URL')
970 mediaURL = compat_urllib_parse.unquote(mobj.group(1))
974 mobj = re.search(r'<title>(.*) video by (.*) - Photobucket</title>', webpage)
976 raise ExtractorError(u'Unable to extract title')
977 video_title = mobj.group(1).decode('utf-8')
979 video_uploader = mobj.group(2).decode('utf-8')
982 'id': video_id.decode('utf-8'),
983 'url': video_url.decode('utf-8'),
984 'uploader': video_uploader,
986 'title': video_title,
987 'ext': video_extension.decode('utf-8'),
991 class YahooIE(InfoExtractor):
992 """Information extractor for screen.yahoo.com."""
993 _VALID_URL = r'http://screen\.yahoo\.com/.*?-(?P<id>\d*?)\.html'
995 def _real_extract(self, url):
996 mobj = re.match(self._VALID_URL, url)
998 raise ExtractorError(u'Invalid URL: %s' % url)
999 video_id = mobj.group('id')
1000 webpage = self._download_webpage(url, video_id)
1001 m_id = re.search(r'YUI\.namespace\("Media"\)\.CONTENT_ID = "(?P<new_id>.+?)";', webpage)
1004 # TODO: Check which url parameters are required
1005 info_url = 'http://cosmos.bcst.yahoo.com/rest/v2/pops;lmsoverride=1;outputformat=mrss;cb=974419660;id=%s;rd=news.yahoo.com;datacontext=mdb;lg=KCa2IihxG3qE60vQ7HtyUy' % video_id
1006 webpage = self._download_webpage(info_url, video_id, u'Downloading info webpage')
1007 info_re = r'''<title><!\[CDATA\[(?P<title>.*?)\]\]></title>.*
1008 <description><!\[CDATA\[(?P<description>.*?)\]\]></description>.*
1009 <media:pubStart><!\[CDATA\[(?P<date>.*?)\ .*\]\]></media:pubStart>.*
1010 <media:content\ medium="image"\ url="(?P<thumb>.*?)"\ name="LARGETHUMB"
1012 self.report_extraction(video_id)
1013 m_info = re.search(info_re, webpage, re.VERBOSE|re.DOTALL)
1015 raise ExtractorError(u'Unable to extract video info')
1016 video_title = m_info.group('title')
1017 video_description = m_info.group('description')
1018 video_thumb = m_info.group('thumb')
1019 video_date = m_info.group('date')
1020 video_date = datetime.datetime.strptime(video_date, '%m/%d/%Y').strftime('%Y%m%d')
1022 # TODO: Find a way to get mp4 videos
1023 rest_url = 'http://cosmos.bcst.yahoo.com/rest/v2/pops;element=stream;outputformat=mrss;id=%s;lmsoverride=1;bw=375;dynamicstream=1;cb=83521105;tech=flv,mp4;rd=news.yahoo.com;datacontext=mdb;lg=KCa2IihxG3qE60vQ7HtyUy' % video_id
1024 webpage = self._download_webpage(rest_url, video_id, u'Downloading video url webpage')
1025 m_rest = re.search(r'<media:content url="(?P<url>.*?)" path="(?P<path>.*?)"', webpage)
1026 video_url = m_rest.group('url')
1027 video_path = m_rest.group('path')
1029 raise ExtractorError(u'Unable to extract video url')
1031 else: # We have to use a different method if another id is defined
1032 long_id = m_id.group('new_id')
1033 info_url = 'http://video.query.yahoo.com/v1/public/yql?q=SELECT%20*%20FROM%20yahoo.media.video.streams%20WHERE%20id%3D%22' + long_id + '%22%20AND%20format%3D%22mp4%2Cflv%22%20AND%20protocol%3D%22rtmp%2Chttp%22%20AND%20plrs%3D%2286Gj0vCaSzV_Iuf6hNylf2%22%20AND%20acctid%3D%22389%22%20AND%20plidl%3D%22%22%20AND%20pspid%3D%22792700001%22%20AND%20offnetwork%3D%22false%22%20AND%20site%3D%22ivy%22%20AND%20lang%3D%22en-US%22%20AND%20region%3D%22US%22%20AND%20override%3D%22none%22%3B&env=prod&format=json&callback=YUI.Env.JSONP.yui_3_8_1_1_1368368376830_335'
1034 webpage = self._download_webpage(info_url, video_id, u'Downloading info json')
1035 json_str = re.search(r'YUI.Env.JSONP.yui.*?\((.*?)\);', webpage).group(1)
1036 info = json.loads(json_str)
1037 res = info[u'query'][u'results'][u'mediaObj'][0]
1038 stream = res[u'streams'][0]
1039 video_path = stream[u'path']
1040 video_url = stream[u'host']
1042 video_title = meta[u'title']
1043 video_description = meta[u'description']
1044 video_thumb = meta[u'thumbnail']
1045 video_date = None # I can't find it
1050 'play_path': video_path,
1051 'title':video_title,
1052 'description': video_description,
1053 'thumbnail': video_thumb,
1054 'upload_date': video_date,
1059 class VimeoIE(InfoExtractor):
1060 """Information extractor for vimeo.com."""
1062 # _VALID_URL matches Vimeo URLs
1063 _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]+)'
1066 def _real_extract(self, url, new_video=True):
1067 # Extract ID from URL
1068 mobj = re.match(self._VALID_URL, url)
1070 raise ExtractorError(u'Invalid URL: %s' % url)
1072 video_id = mobj.group('id')
1073 if not mobj.group('proto'):
1074 url = 'https://' + url
1075 if mobj.group('direct_link'):
1076 url = 'https://vimeo.com/' + video_id
1078 # Retrieve video webpage to extract further information
1079 request = compat_urllib_request.Request(url, None, std_headers)
1080 webpage = self._download_webpage(request, video_id)
1082 # Now we begin extracting as much information as we can from what we
1083 # retrieved. First we extract the information common to all extractors,
1084 # and latter we extract those that are Vimeo specific.
1085 self.report_extraction(video_id)
1087 # Extract the config JSON
1089 config = webpage.split(' = {config:')[1].split(',assets:')[0]
1090 config = json.loads(config)
1092 if re.search('The creator of this video has not given you permission to embed it on this domain.', webpage):
1093 raise ExtractorError(u'The author has restricted the access to this video, try with the "--referer" option')
1095 raise ExtractorError(u'Unable to extract info section')
1098 video_title = config["video"]["title"]
1100 # Extract uploader and uploader_id
1101 video_uploader = config["video"]["owner"]["name"]
1102 video_uploader_id = config["video"]["owner"]["url"].split('/')[-1]
1104 # Extract video thumbnail
1105 video_thumbnail = config["video"]["thumbnail"]
1107 # Extract video description
1108 video_description = get_element_by_attribute("itemprop", "description", webpage)
1109 if video_description: video_description = clean_html(video_description)
1110 else: video_description = u''
1112 # Extract upload date
1113 video_upload_date = None
1114 mobj = re.search(r'<meta itemprop="dateCreated" content="(\d{4})-(\d{2})-(\d{2})T', webpage)
1115 if mobj is not None:
1116 video_upload_date = mobj.group(1) + mobj.group(2) + mobj.group(3)
1118 # Vimeo specific: extract request signature and timestamp
1119 sig = config['request']['signature']
1120 timestamp = config['request']['timestamp']
1122 # Vimeo specific: extract video codec and quality information
1123 # First consider quality, then codecs, then take everything
1124 # TODO bind to format param
1125 codecs = [('h264', 'mp4'), ('vp8', 'flv'), ('vp6', 'flv')]
1126 files = { 'hd': [], 'sd': [], 'other': []}
1127 for codec_name, codec_extension in codecs:
1128 if codec_name in config["video"]["files"]:
1129 if 'hd' in config["video"]["files"][codec_name]:
1130 files['hd'].append((codec_name, codec_extension, 'hd'))
1131 elif 'sd' in config["video"]["files"][codec_name]:
1132 files['sd'].append((codec_name, codec_extension, 'sd'))
1134 files['other'].append((codec_name, codec_extension, config["video"]["files"][codec_name][0]))
1136 for quality in ('hd', 'sd', 'other'):
1137 if len(files[quality]) > 0:
1138 video_quality = files[quality][0][2]
1139 video_codec = files[quality][0][0]
1140 video_extension = files[quality][0][1]
1141 self.to_screen(u'%s: Downloading %s file at %s quality' % (video_id, video_codec.upper(), video_quality))
1144 raise ExtractorError(u'No known codec found')
1146 video_url = "http://player.vimeo.com/play_redirect?clip_id=%s&sig=%s&time=%s&quality=%s&codecs=%s&type=moogaloop_local&embed_location=" \
1147 %(video_id, sig, timestamp, video_quality, video_codec.upper())
1152 'uploader': video_uploader,
1153 'uploader_id': video_uploader_id,
1154 'upload_date': video_upload_date,
1155 'title': video_title,
1156 'ext': video_extension,
1157 'thumbnail': video_thumbnail,
1158 'description': video_description,
1162 class ArteTvIE(InfoExtractor):
1163 """arte.tv information extractor."""
1165 _VALID_URL = r'(?:http://)?videos\.arte\.tv/(?:fr|de)/videos/.*'
1166 _LIVE_URL = r'index-[0-9]+\.html$'
1168 IE_NAME = u'arte.tv'
1170 def fetch_webpage(self, url):
1171 request = compat_urllib_request.Request(url)
1173 self.report_download_webpage(url)
1174 webpage = compat_urllib_request.urlopen(request).read()
1175 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
1176 raise ExtractorError(u'Unable to retrieve video webpage: %s' % compat_str(err))
1177 except ValueError as err:
1178 raise ExtractorError(u'Invalid URL: %s' % url)
1181 def grep_webpage(self, url, regex, regexFlags, matchTuples):
1182 page = self.fetch_webpage(url)
1183 mobj = re.search(regex, page, regexFlags)
1187 raise ExtractorError(u'Invalid URL: %s' % url)
1189 for (i, key, err) in matchTuples:
1190 if mobj.group(i) is None:
1191 raise ExtractorError(err)
1193 info[key] = mobj.group(i)
1197 def extractLiveStream(self, url):
1198 video_lang = url.split('/')[-4]
1199 info = self.grep_webpage(
1201 r'src="(.*?/videothek_js.*?\.js)',
1204 (1, 'url', u'Invalid URL: %s' % url)
1207 http_host = url.split('/')[2]
1208 next_url = 'http://%s%s' % (http_host, compat_urllib_parse.unquote(info.get('url')))
1209 info = self.grep_webpage(
1211 r'(s_artestras_scst_geoFRDE_' + video_lang + '.*?)\'.*?' +
1212 '(http://.*?\.swf).*?' +
1216 (1, 'path', u'could not extract video path: %s' % url),
1217 (2, 'player', u'could not extract video player: %s' % url),
1218 (3, 'url', u'could not extract video url: %s' % url)
1221 video_url = u'%s/%s' % (info.get('url'), info.get('path'))
1223 def extractPlus7Stream(self, url):
1224 video_lang = url.split('/')[-3]
1225 info = self.grep_webpage(
1227 r'param name="movie".*?videorefFileUrl=(http[^\'"&]*)',
1230 (1, 'url', u'Invalid URL: %s' % url)
1233 next_url = compat_urllib_parse.unquote(info.get('url'))
1234 info = self.grep_webpage(
1236 r'<video lang="%s" ref="(http[^\'"&]*)' % video_lang,
1239 (1, 'url', u'Could not find <video> tag: %s' % url)
1242 next_url = compat_urllib_parse.unquote(info.get('url'))
1244 info = self.grep_webpage(
1246 r'<video id="(.*?)".*?>.*?' +
1247 '<name>(.*?)</name>.*?' +
1248 '<dateVideo>(.*?)</dateVideo>.*?' +
1249 '<url quality="hd">(.*?)</url>',
1252 (1, 'id', u'could not extract video id: %s' % url),
1253 (2, 'title', u'could not extract video title: %s' % url),
1254 (3, 'date', u'could not extract video date: %s' % url),
1255 (4, 'url', u'could not extract video url: %s' % url)
1260 'id': info.get('id'),
1261 'url': compat_urllib_parse.unquote(info.get('url')),
1262 'uploader': u'arte.tv',
1263 'upload_date': unified_strdate(info.get('date')),
1264 'title': info.get('title').decode('utf-8'),
1270 def _real_extract(self, url):
1271 video_id = url.split('/')[-1]
1272 self.report_extraction(video_id)
1274 if re.search(self._LIVE_URL, video_id) is not None:
1275 self.extractLiveStream(url)
1278 info = self.extractPlus7Stream(url)
1283 class GenericIE(InfoExtractor):
1284 """Generic last-resort information extractor."""
1287 IE_NAME = u'generic'
1289 def report_download_webpage(self, video_id):
1290 """Report webpage download."""
1291 if not self._downloader.params.get('test', False):
1292 self._downloader.report_warning(u'Falling back on generic information extractor.')
1293 super(GenericIE, self).report_download_webpage(video_id)
1295 def report_following_redirect(self, new_url):
1296 """Report information extraction."""
1297 self._downloader.to_screen(u'[redirect] Following redirect to %s' % new_url)
1299 def _test_redirect(self, url):
1300 """Check if it is a redirect, like url shorteners, in case return the new url."""
1301 class HeadRequest(compat_urllib_request.Request):
1302 def get_method(self):
1305 class HEADRedirectHandler(compat_urllib_request.HTTPRedirectHandler):
1307 Subclass the HTTPRedirectHandler to make it use our
1308 HeadRequest also on the redirected URL
1310 def redirect_request(self, req, fp, code, msg, headers, newurl):
1311 if code in (301, 302, 303, 307):
1312 newurl = newurl.replace(' ', '%20')
1313 newheaders = dict((k,v) for k,v in req.headers.items()
1314 if k.lower() not in ("content-length", "content-type"))
1315 return HeadRequest(newurl,
1317 origin_req_host=req.get_origin_req_host(),
1320 raise compat_urllib_error.HTTPError(req.get_full_url(), code, msg, headers, fp)
1322 class HTTPMethodFallback(compat_urllib_request.BaseHandler):
1324 Fallback to GET if HEAD is not allowed (405 HTTP error)
1326 def http_error_405(self, req, fp, code, msg, headers):
1330 newheaders = dict((k,v) for k,v in req.headers.items()
1331 if k.lower() not in ("content-length", "content-type"))
1332 return self.parent.open(compat_urllib_request.Request(req.get_full_url(),
1334 origin_req_host=req.get_origin_req_host(),
1338 opener = compat_urllib_request.OpenerDirector()
1339 for handler in [compat_urllib_request.HTTPHandler, compat_urllib_request.HTTPDefaultErrorHandler,
1340 HTTPMethodFallback, HEADRedirectHandler,
1341 compat_urllib_request.HTTPErrorProcessor, compat_urllib_request.HTTPSHandler]:
1342 opener.add_handler(handler())
1344 response = opener.open(HeadRequest(url))
1345 if response is None:
1346 raise ExtractorError(u'Invalid URL protocol')
1347 new_url = response.geturl()
1352 self.report_following_redirect(new_url)
1355 def _real_extract(self, url):
1356 new_url = self._test_redirect(url)
1357 if new_url: return [self.url_result(new_url)]
1359 video_id = url.split('/')[-1]
1361 webpage = self._download_webpage(url, video_id)
1362 except ValueError as err:
1363 # since this is the last-resort InfoExtractor, if
1364 # this error is thrown, it'll be thrown here
1365 raise ExtractorError(u'Invalid URL: %s' % url)
1367 self.report_extraction(video_id)
1368 # Start with something easy: JW Player in SWFObject
1369 mobj = re.search(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage)
1371 # Broaden the search a little bit
1372 mobj = re.search(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage)
1374 # Broaden the search a little bit: JWPlayer JS loader
1375 mobj = re.search(r'[^A-Za-z0-9]?file:\s*["\'](http[^\'"&]*)', webpage)
1377 raise ExtractorError(u'Invalid URL: %s' % url)
1379 # It's possible that one of the regexes
1380 # matched, but returned an empty group:
1381 if mobj.group(1) is None:
1382 raise ExtractorError(u'Invalid URL: %s' % url)
1384 video_url = compat_urllib_parse.unquote(mobj.group(1))
1385 video_id = os.path.basename(video_url)
1387 # here's a fun little line of code for you:
1388 video_extension = os.path.splitext(video_id)[1][1:]
1389 video_id = os.path.splitext(video_id)[0]
1391 # it's tempting to parse this further, but you would
1392 # have to take into account all the variations like
1393 # Video Title - Site Name
1394 # Site Name | Video Title
1395 # Video Title - Tagline | Site Name
1396 # and so on and so forth; it's just not practical
1397 mobj = re.search(r'<title>(.*)</title>', webpage)
1399 raise ExtractorError(u'Unable to extract title')
1400 video_title = mobj.group(1)
1402 # video uploader is domain name
1403 mobj = re.match(r'(?:https?://)?([^/]*)/.*', url)
1405 raise ExtractorError(u'Unable to extract title')
1406 video_uploader = mobj.group(1)
1411 'uploader': video_uploader,
1412 'upload_date': None,
1413 'title': video_title,
1414 'ext': video_extension,
1418 class YoutubeSearchIE(SearchInfoExtractor):
1419 """Information Extractor for YouTube search queries."""
1420 _API_URL = 'https://gdata.youtube.com/feeds/api/videos?q=%s&start-index=%i&max-results=50&v=2&alt=jsonc'
1422 IE_NAME = u'youtube:search'
1423 _SEARCH_KEY = 'ytsearch'
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 _get_n_results(self, query, n):
1431 """Get a specified number of results for a query"""
1437 while (50 * pagenum) < limit:
1438 self.report_download_page(query, pagenum+1)
1439 result_url = self._API_URL % (compat_urllib_parse.quote_plus(query), (50*pagenum)+1)
1440 request = compat_urllib_request.Request(result_url)
1442 data = compat_urllib_request.urlopen(request).read().decode('utf-8')
1443 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
1444 raise ExtractorError(u'Unable to download API page: %s' % compat_str(err))
1445 api_response = json.loads(data)['data']
1447 if not 'items' in api_response:
1448 raise ExtractorError(u'[youtube] No video results')
1450 new_ids = list(video['id'] for video in api_response['items'])
1451 video_ids += new_ids
1453 limit = min(n, api_response['totalItems'])
1456 if len(video_ids) > n:
1457 video_ids = video_ids[:n]
1458 videos = [self.url_result('http://www.youtube.com/watch?v=%s' % id, 'Youtube') for id in video_ids]
1459 return self.playlist_result(videos, query)
1462 class GoogleSearchIE(SearchInfoExtractor):
1463 """Information Extractor for Google Video search queries."""
1464 _MORE_PAGES_INDICATOR = r'id="pnnext" class="pn"'
1466 IE_NAME = u'video.google:search'
1467 _SEARCH_KEY = 'gvsearch'
1469 def _get_n_results(self, query, n):
1470 """Get a specified number of results for a query"""
1473 '_type': 'playlist',
1478 for pagenum in itertools.count(1):
1479 result_url = u'http://www.google.com/search?tbm=vid&q=%s&start=%s&hl=en' % (compat_urllib_parse.quote_plus(query), pagenum*10)
1480 webpage = self._download_webpage(result_url, u'gvsearch:' + query,
1481 note='Downloading result page ' + str(pagenum))
1483 for mobj in re.finditer(r'<h3 class="r"><a href="([^"]+)"', webpage):
1486 'url': mobj.group(1)
1488 res['entries'].append(e)
1490 if (pagenum * 10 > n) or not re.search(self._MORE_PAGES_INDICATOR, webpage):
1493 class YahooSearchIE(SearchInfoExtractor):
1494 """Information Extractor for Yahoo! Video search queries."""
1497 IE_NAME = u'screen.yahoo:search'
1498 _SEARCH_KEY = 'yvsearch'
1500 def _get_n_results(self, query, n):
1501 """Get a specified number of results for a query"""
1504 '_type': 'playlist',
1508 for pagenum in itertools.count(0):
1509 result_url = u'http://video.search.yahoo.com/search/?p=%s&fr=screen&o=js&gs=0&b=%d' % (compat_urllib_parse.quote_plus(query), pagenum * 30)
1510 webpage = self._download_webpage(result_url, query,
1511 note='Downloading results page '+str(pagenum+1))
1512 info = json.loads(webpage)
1514 results = info[u'results']
1516 for (i, r) in enumerate(results):
1517 if (pagenum * 30) +i >= n:
1519 mobj = re.search(r'(?P<url>screen\.yahoo\.com/.*?-\d*?\.html)"', r)
1520 e = self.url_result('http://' + mobj.group('url'), 'Yahoo')
1521 res['entries'].append(e)
1522 if (pagenum * 30 +i >= n) or (m[u'last'] >= (m[u'total'] -1 )):
1528 class YoutubePlaylistIE(InfoExtractor):
1529 """Information Extractor for YouTube playlists."""
1531 _VALID_URL = r"""(?:
1536 (?:course|view_play_list|my_playlists|artist|playlist|watch)
1537 \? (?:.*?&)*? (?:p|a|list)=
1540 ((?:PL|EC|UU)?[0-9A-Za-z-_]{10,})
1543 ((?:PL|EC|UU)[0-9A-Za-z-_]{10,})
1545 _TEMPLATE_URL = 'https://gdata.youtube.com/feeds/api/playlists/%s?max-results=%i&start-index=%i&v=2&alt=json'
1547 IE_NAME = u'youtube:playlist'
1550 def suitable(cls, url):
1551 """Receives a URL and returns True if suitable for this IE."""
1552 return re.match(cls._VALID_URL, url, re.VERBOSE) is not None
1554 def _real_extract(self, url):
1555 # Extract playlist id
1556 mobj = re.match(self._VALID_URL, url, re.VERBOSE)
1558 raise ExtractorError(u'Invalid URL: %s' % url)
1560 # Download playlist videos from API
1561 playlist_id = mobj.group(1) or mobj.group(2)
1566 url = self._TEMPLATE_URL % (playlist_id, self._MAX_RESULTS, self._MAX_RESULTS * (page_num - 1) + 1)
1567 page = self._download_webpage(url, playlist_id, u'Downloading page #%s' % page_num)
1570 response = json.loads(page)
1571 except ValueError as err:
1572 raise ExtractorError(u'Invalid JSON in API response: ' + compat_str(err))
1574 if 'feed' not in response:
1575 raise ExtractorError(u'Got a malformed response from YouTube API')
1576 playlist_title = response['feed']['title']['$t']
1577 if 'entry' not in response['feed']:
1578 # Number of videos is a multiple of self._MAX_RESULTS
1581 videos += [ (entry['yt$position']['$t'], entry['content']['src'])
1582 for entry in response['feed']['entry']
1583 if 'content' in entry ]
1585 if len(response['feed']['entry']) < self._MAX_RESULTS:
1589 videos = [v[1] for v in sorted(videos)]
1591 url_results = [self.url_result(url, 'Youtube') for url in videos]
1592 return [self.playlist_result(url_results, playlist_id, playlist_title)]
1595 class YoutubeChannelIE(InfoExtractor):
1596 """Information Extractor for YouTube channels."""
1598 _VALID_URL = r"^(?:https?://)?(?:youtu\.be|(?:\w+\.)?youtube(?:-nocookie)?\.com)/channel/([0-9A-Za-z_-]+)"
1599 _TEMPLATE_URL = 'http://www.youtube.com/channel/%s/videos?sort=da&flow=list&view=0&page=%s&gl=US&hl=en'
1600 _MORE_PAGES_INDICATOR = 'yt-uix-load-more'
1601 _MORE_PAGES_URL = 'http://www.youtube.com/channel_ajax?action_load_more_videos=1&flow=list&paging=%s&view=0&sort=da&channel_id=%s'
1602 IE_NAME = u'youtube:channel'
1604 def extract_videos_from_page(self, page):
1606 for mobj in re.finditer(r'href="/watch\?v=([0-9A-Za-z_-]+)&?', page):
1607 if mobj.group(1) not in ids_in_page:
1608 ids_in_page.append(mobj.group(1))
1611 def _real_extract(self, url):
1612 # Extract channel id
1613 mobj = re.match(self._VALID_URL, url)
1615 raise ExtractorError(u'Invalid URL: %s' % url)
1617 # Download channel page
1618 channel_id = mobj.group(1)
1622 url = self._TEMPLATE_URL % (channel_id, pagenum)
1623 page = self._download_webpage(url, channel_id,
1624 u'Downloading page #%s' % pagenum)
1626 # Extract video identifiers
1627 ids_in_page = self.extract_videos_from_page(page)
1628 video_ids.extend(ids_in_page)
1630 # Download any subsequent channel pages using the json-based channel_ajax query
1631 if self._MORE_PAGES_INDICATOR in page:
1633 pagenum = pagenum + 1
1635 url = self._MORE_PAGES_URL % (pagenum, channel_id)
1636 page = self._download_webpage(url, channel_id,
1637 u'Downloading page #%s' % pagenum)
1639 page = json.loads(page)
1641 ids_in_page = self.extract_videos_from_page(page['content_html'])
1642 video_ids.extend(ids_in_page)
1644 if self._MORE_PAGES_INDICATOR not in page['load_more_widget_html']:
1647 self._downloader.to_screen(u'[youtube] Channel %s: Found %i videos' % (channel_id, len(video_ids)))
1649 urls = ['http://www.youtube.com/watch?v=%s' % id for id in video_ids]
1650 url_entries = [self.url_result(url, 'Youtube') for url in urls]
1651 return [self.playlist_result(url_entries, channel_id)]
1654 class YoutubeUserIE(InfoExtractor):
1655 """Information Extractor for YouTube users."""
1657 _VALID_URL = r'(?:(?:(?:https?://)?(?:\w+\.)?youtube\.com/user/)|ytuser:)([A-Za-z0-9_-]+)'
1658 _TEMPLATE_URL = 'http://gdata.youtube.com/feeds/api/users/%s'
1659 _GDATA_PAGE_SIZE = 50
1660 _GDATA_URL = 'http://gdata.youtube.com/feeds/api/users/%s/uploads?max-results=%d&start-index=%d'
1661 _VIDEO_INDICATOR = r'/watch\?v=(.+?)[\<&]'
1662 IE_NAME = u'youtube:user'
1664 def _real_extract(self, url):
1666 mobj = re.match(self._VALID_URL, url)
1668 raise ExtractorError(u'Invalid URL: %s' % url)
1670 username = mobj.group(1)
1672 # Download video ids using YouTube Data API. Result size per
1673 # query is limited (currently to 50 videos) so we need to query
1674 # page by page until there are no video ids - it means we got
1681 start_index = pagenum * self._GDATA_PAGE_SIZE + 1
1683 gdata_url = self._GDATA_URL % (username, self._GDATA_PAGE_SIZE, start_index)
1684 page = self._download_webpage(gdata_url, username,
1685 u'Downloading video ids from %d to %d' % (start_index, start_index + self._GDATA_PAGE_SIZE))
1687 # Extract video identifiers
1690 for mobj in re.finditer(self._VIDEO_INDICATOR, page):
1691 if mobj.group(1) not in ids_in_page:
1692 ids_in_page.append(mobj.group(1))
1694 video_ids.extend(ids_in_page)
1696 # A little optimization - if current page is not
1697 # "full", ie. does not contain PAGE_SIZE video ids then
1698 # we can assume that this page is the last one - there
1699 # are no more ids on further pages - no need to query
1702 if len(ids_in_page) < self._GDATA_PAGE_SIZE:
1707 urls = ['http://www.youtube.com/watch?v=%s' % video_id for video_id in video_ids]
1708 url_results = [self.url_result(url, 'Youtube') for url in urls]
1709 return [self.playlist_result(url_results, playlist_title = username)]
1712 class BlipTVUserIE(InfoExtractor):
1713 """Information Extractor for blip.tv users."""
1715 _VALID_URL = r'(?:(?:(?:https?://)?(?:\w+\.)?blip\.tv/)|bliptvuser:)([^/]+)/*$'
1717 IE_NAME = u'blip.tv:user'
1719 def _real_extract(self, url):
1721 mobj = re.match(self._VALID_URL, url)
1723 raise ExtractorError(u'Invalid URL: %s' % url)
1725 username = mobj.group(1)
1727 page_base = 'http://m.blip.tv/pr/show_get_full_episode_list?users_id=%s&lite=0&esi=1'
1729 page = self._download_webpage(url, username, u'Downloading user page')
1730 mobj = re.search(r'data-users-id="([^"]+)"', page)
1731 page_base = page_base % mobj.group(1)
1734 # Download video ids using BlipTV Ajax calls. Result size per
1735 # query is limited (currently to 12 videos) so we need to query
1736 # page by page until there are no video ids - it means we got
1743 url = page_base + "&page=" + str(pagenum)
1744 page = self._download_webpage(url, username,
1745 u'Downloading video ids from page %d' % pagenum)
1747 # Extract video identifiers
1750 for mobj in re.finditer(r'href="/([^"]+)"', page):
1751 if mobj.group(1) not in ids_in_page:
1752 ids_in_page.append(unescapeHTML(mobj.group(1)))
1754 video_ids.extend(ids_in_page)
1756 # A little optimization - if current page is not
1757 # "full", ie. does not contain PAGE_SIZE video ids then
1758 # we can assume that this page is the last one - there
1759 # are no more ids on further pages - no need to query
1762 if len(ids_in_page) < self._PAGE_SIZE:
1767 urls = [u'http://blip.tv/%s' % video_id for video_id in video_ids]
1768 url_entries = [self.url_result(url, 'BlipTV') for url in urls]
1769 return [self.playlist_result(url_entries, playlist_title = username)]
1772 class DepositFilesIE(InfoExtractor):
1773 """Information extractor for depositfiles.com"""
1775 _VALID_URL = r'(?:http://)?(?:\w+\.)?depositfiles\.com/(?:../(?#locale))?files/(.+)'
1777 def _real_extract(self, url):
1778 file_id = url.split('/')[-1]
1779 # Rebuild url in english locale
1780 url = 'http://depositfiles.com/en/files/' + file_id
1782 # Retrieve file webpage with 'Free download' button pressed
1783 free_download_indication = { 'gateway_result' : '1' }
1784 request = compat_urllib_request.Request(url, compat_urllib_parse.urlencode(free_download_indication))
1786 self.report_download_webpage(file_id)
1787 webpage = compat_urllib_request.urlopen(request).read()
1788 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
1789 raise ExtractorError(u'Unable to retrieve file webpage: %s' % compat_str(err))
1791 # Search for the real file URL
1792 mobj = re.search(r'<form action="(http://fileshare.+?)"', webpage)
1793 if (mobj is None) or (mobj.group(1) is None):
1794 # Try to figure out reason of the error.
1795 mobj = re.search(r'<strong>(Attention.*?)</strong>', webpage, re.DOTALL)
1796 if (mobj is not None) and (mobj.group(1) is not None):
1797 restriction_message = re.sub('\s+', ' ', mobj.group(1)).strip()
1798 raise ExtractorError(u'%s' % restriction_message)
1800 raise ExtractorError(u'Unable to extract download URL from: %s' % url)
1802 file_url = mobj.group(1)
1803 file_extension = os.path.splitext(file_url)[1][1:]
1805 # Search for file title
1806 mobj = re.search(r'<b title="(.*?)">', webpage)
1808 raise ExtractorError(u'Unable to extract title')
1809 file_title = mobj.group(1).decode('utf-8')
1812 'id': file_id.decode('utf-8'),
1813 'url': file_url.decode('utf-8'),
1815 'upload_date': None,
1816 'title': file_title,
1817 'ext': file_extension.decode('utf-8'),
1821 class FacebookIE(InfoExtractor):
1822 """Information Extractor for Facebook"""
1824 _VALID_URL = r'^(?:https?://)?(?:\w+\.)?facebook\.com/(?:video/video|photo)\.php\?(?:.*?)v=(?P<ID>\d+)(?:.*)'
1825 _LOGIN_URL = 'https://login.facebook.com/login.php?m&next=http%3A%2F%2Fm.facebook.com%2Fhome.php&'
1826 _NETRC_MACHINE = 'facebook'
1827 IE_NAME = u'facebook'
1829 def report_login(self):
1830 """Report attempt to log in."""
1831 self.to_screen(u'Logging in')
1833 def _real_initialize(self):
1834 if self._downloader is None:
1839 downloader_params = self._downloader.params
1841 # Attempt to use provided username and password or .netrc data
1842 if downloader_params.get('username', None) is not None:
1843 useremail = downloader_params['username']
1844 password = downloader_params['password']
1845 elif downloader_params.get('usenetrc', False):
1847 info = netrc.netrc().authenticators(self._NETRC_MACHINE)
1848 if info is not None:
1852 raise netrc.NetrcParseError('No authenticators for %s' % self._NETRC_MACHINE)
1853 except (IOError, netrc.NetrcParseError) as err:
1854 self._downloader.report_warning(u'parsing .netrc: %s' % compat_str(err))
1857 if useremail is None:
1866 request = compat_urllib_request.Request(self._LOGIN_URL, compat_urllib_parse.urlencode(login_form))
1869 login_results = compat_urllib_request.urlopen(request).read()
1870 if re.search(r'<form(.*)name="login"(.*)</form>', login_results) is not None:
1871 self._downloader.report_warning(u'unable to log in: bad username/password, or exceded login rate limit (~3/min). Check credentials or wait.')
1873 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
1874 self._downloader.report_warning(u'unable to log in: %s' % compat_str(err))
1877 def _real_extract(self, url):
1878 mobj = re.match(self._VALID_URL, url)
1880 raise ExtractorError(u'Invalid URL: %s' % url)
1881 video_id = mobj.group('ID')
1883 url = 'https://www.facebook.com/video/video.php?v=%s' % video_id
1884 webpage = self._download_webpage(url, video_id)
1886 BEFORE = '{swf.addParam(param[0], param[1]);});\n'
1887 AFTER = '.forEach(function(variable) {swf.addVariable(variable[0], variable[1]);});'
1888 m = re.search(re.escape(BEFORE) + '(.*?)' + re.escape(AFTER), webpage)
1890 raise ExtractorError(u'Cannot parse data')
1891 data = dict(json.loads(m.group(1)))
1892 params_raw = compat_urllib_parse.unquote(data['params'])
1893 params = json.loads(params_raw)
1894 video_data = params['video_data'][0]
1895 video_url = video_data.get('hd_src')
1897 video_url = video_data['sd_src']
1899 raise ExtractorError(u'Cannot find video URL')
1900 video_duration = int(video_data['video_duration'])
1901 thumbnail = video_data['thumbnail_src']
1903 m = re.search('<h2 class="uiHeaderTitle">([^<]+)</h2>', webpage)
1905 raise ExtractorError(u'Cannot find title in webpage')
1906 video_title = unescapeHTML(m.group(1))
1910 'title': video_title,
1913 'duration': video_duration,
1914 'thumbnail': thumbnail,
1919 class BlipTVIE(InfoExtractor):
1920 """Information extractor for blip.tv"""
1922 _VALID_URL = r'^(?:https?://)?(?:\w+\.)?blip\.tv(/.+)$'
1923 _URL_EXT = r'^.*\.([a-z0-9]+)$'
1924 IE_NAME = u'blip.tv'
1926 def report_direct_download(self, title):
1927 """Report information extraction."""
1928 self.to_screen(u'%s: Direct download detected' % title)
1930 def _real_extract(self, url):
1931 mobj = re.match(self._VALID_URL, url)
1933 raise ExtractorError(u'Invalid URL: %s' % url)
1935 urlp = compat_urllib_parse_urlparse(url)
1936 if urlp.path.startswith('/play/'):
1937 request = compat_urllib_request.Request(url)
1938 response = compat_urllib_request.urlopen(request)
1939 redirecturl = response.geturl()
1940 rurlp = compat_urllib_parse_urlparse(redirecturl)
1941 file_id = compat_parse_qs(rurlp.fragment)['file'][0].rpartition('/')[2]
1942 url = 'http://blip.tv/a/a-' + file_id
1943 return self._real_extract(url)
1950 json_url = url + cchar + 'skin=json&version=2&no_wrap=1'
1951 request = compat_urllib_request.Request(json_url)
1952 request.add_header('User-Agent', 'iTunes/10.6.1')
1953 self.report_extraction(mobj.group(1))
1956 urlh = compat_urllib_request.urlopen(request)
1957 if urlh.headers.get('Content-Type', '').startswith('video/'): # Direct download
1958 basename = url.split('/')[-1]
1959 title,ext = os.path.splitext(basename)
1960 title = title.decode('UTF-8')
1961 ext = ext.replace('.', '')
1962 self.report_direct_download(title)
1967 'upload_date': None,
1972 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
1973 raise ExtractorError(u'ERROR: unable to download video info webpage: %s' % compat_str(err))
1974 if info is None: # Regular URL
1976 json_code_bytes = urlh.read()
1977 json_code = json_code_bytes.decode('utf-8')
1978 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
1979 raise ExtractorError(u'Unable to read video info webpage: %s' % compat_str(err))
1982 json_data = json.loads(json_code)
1983 if 'Post' in json_data:
1984 data = json_data['Post']
1988 upload_date = datetime.datetime.strptime(data['datestamp'], '%m-%d-%y %H:%M%p').strftime('%Y%m%d')
1989 video_url = data['media']['url']
1990 umobj = re.match(self._URL_EXT, video_url)
1992 raise ValueError('Can not determine filename extension')
1993 ext = umobj.group(1)
1996 'id': data['item_id'],
1998 'uploader': data['display_name'],
1999 'upload_date': upload_date,
2000 'title': data['title'],
2002 'format': data['media']['mimeType'],
2003 'thumbnail': data['thumbnailUrl'],
2004 'description': data['description'],
2005 'player_url': data['embedUrl'],
2006 'user_agent': 'iTunes/10.6.1',
2008 except (ValueError,KeyError) as err:
2009 raise ExtractorError(u'Unable to parse video information: %s' % repr(err))
2014 class MyVideoIE(InfoExtractor):
2015 """Information Extractor for myvideo.de."""
2017 _VALID_URL = r'(?:http://)?(?:www\.)?myvideo\.de/watch/([0-9]+)/([^?/]+).*'
2018 IE_NAME = u'myvideo'
2020 # Original Code from: https://github.com/dersphere/plugin.video.myvideo_de.git
2021 # Released into the Public Domain by Tristan Fischer on 2013-05-19
2022 # https://github.com/rg3/youtube-dl/pull/842
2023 def __rc4crypt(self,data, key):
2025 box = list(range(256))
2026 for i in list(range(256)):
2027 x = (x + box[i] + compat_ord(key[i % len(key)])) % 256
2028 box[i], box[x] = box[x], box[i]
2034 y = (y + box[x]) % 256
2035 box[x], box[y] = box[y], box[x]
2036 out += chr(compat_ord(char) ^ box[(box[x] + box[y]) % 256])
2040 return hashlib.md5(s).hexdigest().encode()
2042 def _real_extract(self,url):
2043 mobj = re.match(self._VALID_URL, url)
2045 raise ExtractorError(u'invalid URL: %s' % url)
2047 video_id = mobj.group(1)
2050 b'WXpnME1EZGhNRGhpTTJNM01XVmhOREU0WldNNVpHTTJOakpt'
2051 b'TW1FMU5tVTBNR05pWkRaa05XRXhNVFJoWVRVd1ptSXhaVEV3'
2052 b'TnpsbA0KTVRkbU1tSTRNdz09'
2056 webpage_url = 'http://www.myvideo.de/watch/%s' % video_id
2057 webpage = self._download_webpage(webpage_url, video_id)
2059 mobj = re.search('source src=\'(.+?)[.]([^.]+)\'', webpage)
2060 if mobj is not None:
2061 self.report_extraction(video_id)
2062 video_url = mobj.group(1) + '.flv'
2064 mobj = re.search('<title>([^<]+)</title>', webpage)
2066 raise ExtractorError(u'Unable to extract title')
2067 video_title = mobj.group(1)
2069 mobj = re.search('[.](.+?)$', video_url)
2071 raise ExtractorError(u'Unable to extract extention')
2072 video_ext = mobj.group(1)
2078 'upload_date': None,
2079 'title': video_title,
2084 mobj = re.search('var flashvars={(.+?)}', webpage)
2086 raise ExtractorError(u'Unable to extract video')
2091 for (a, b) in re.findall('(.+?):\'(.+?)\',?', sec):
2092 if not a == '_encxml':
2095 encxml = compat_urllib_parse.unquote(b)
2096 if not params.get('domain'):
2097 params['domain'] = 'www.myvideo.de'
2098 xmldata_url = '%s?%s' % (encxml, compat_urllib_parse.urlencode(params))
2099 if 'flash_playertype=MTV' in xmldata_url:
2100 self._downloader.report_warning(u'avoiding MTV player')
2102 'http://www.myvideo.de/dynamic/get_player_video_xml.php'
2103 '?flash_playertype=D&ID=%s&_countlimit=4&autorun=yes'
2107 enc_data = self._download_webpage(xmldata_url, video_id).split('=')[1]
2108 enc_data_b = binascii.unhexlify(enc_data)
2110 base64.b64decode(base64.b64decode(GK)) +
2112 str(video_id).encode('utf-8')
2115 dec_data = self.__rc4crypt(enc_data_b, sk)
2118 self.report_extraction(video_id)
2120 mobj = re.search('connectionurl=\'(.*?)\'', dec_data)
2122 raise ExtractorError(u'unable to extract rtmpurl')
2123 video_rtmpurl = compat_urllib_parse.unquote(mobj.group(1))
2124 if 'myvideo2flash' in video_rtmpurl:
2125 self._downloader.report_warning(u'forcing RTMPT ...')
2126 video_rtmpurl = video_rtmpurl.replace('rtmpe://', 'rtmpt://')
2128 # extract non rtmp videos
2129 if (video_rtmpurl is None) or (video_rtmpurl == ''):
2130 mobj = re.search('path=\'(http.*?)\' source=\'(.*?)\'', dec_data)
2132 raise ExtractorError(u'unable to extract url')
2133 video_rtmpurl = compat_urllib_parse.unquote(mobj.group(1)) + compat_urllib_parse.unquote(mobj.group(2))
2135 mobj = re.search('source=\'(.*?)\'', dec_data)
2137 raise ExtractorError(u'unable to extract swfobj')
2138 video_file = compat_urllib_parse.unquote(mobj.group(1))
2140 if not video_file.endswith('f4m'):
2141 ppath, prefix = video_file.split('.')
2142 video_playpath = '%s:%s' % (prefix, ppath)
2143 video_hls_playlist = ''
2146 video_hls_playlist = (
2147 video_filepath + video_file
2148 ).replace('.f4m', '.m3u8')
2150 mobj = re.search('swfobject.embedSWF\(\'(.+?)\'', webpage)
2152 raise ExtractorError(u'unable to extract swfobj')
2153 video_swfobj = compat_urllib_parse.unquote(mobj.group(1))
2155 mobj = re.search("<h1(?: class='globalHd')?>(.*?)</h1>", webpage)
2157 raise ExtractorError(u'unable to extract title')
2158 video_title = mobj.group(1)
2162 'url': video_rtmpurl,
2163 'tc_url': video_rtmpurl,
2165 'upload_date': None,
2166 'title': video_title,
2168 'play_path': video_playpath,
2169 'video_file': video_file,
2170 'video_hls_playlist': video_hls_playlist,
2171 'player_url': video_swfobj,
2174 class ComedyCentralIE(InfoExtractor):
2175 """Information extractor for The Daily Show and Colbert Report """
2177 # urls can be abbreviations like :thedailyshow or :colbert
2178 # urls for episodes like:
2179 # or urls for clips like: http://www.thedailyshow.com/watch/mon-december-10-2012/any-given-gun-day
2180 # or: http://www.colbertnation.com/the-colbert-report-videos/421667/november-29-2012/moon-shattering-news
2181 # or: http://www.colbertnation.com/the-colbert-report-collections/422008/festival-of-lights/79524
2182 _VALID_URL = r"""^(:(?P<shortname>tds|thedailyshow|cr|colbert|colbertnation|colbertreport)
2183 |(https?://)?(www\.)?
2184 (?P<showname>thedailyshow|colbertnation)\.com/
2185 (full-episodes/(?P<episode>.*)|
2187 (the-colbert-report-(videos|collections)/(?P<clipID>[0-9]+)/[^/]*/(?P<cntitle>.*?))
2188 |(watch/(?P<date>[^/]*)/(?P<tdstitle>.*)))))
2191 _available_formats = ['3500', '2200', '1700', '1200', '750', '400']
2193 _video_extensions = {
2201 _video_dimensions = {
2211 def suitable(cls, url):
2212 """Receives a URL and returns True if suitable for this IE."""
2213 return re.match(cls._VALID_URL, url, re.VERBOSE) is not None
2215 def _print_formats(self, formats):
2216 print('Available formats:')
2218 print('%s\t:\t%s\t[%s]' %(x, self._video_extensions.get(x, 'mp4'), self._video_dimensions.get(x, '???')))
2221 def _real_extract(self, url):
2222 mobj = re.match(self._VALID_URL, url, re.VERBOSE)
2224 raise ExtractorError(u'Invalid URL: %s' % url)
2226 if mobj.group('shortname'):
2227 if mobj.group('shortname') in ('tds', 'thedailyshow'):
2228 url = u'http://www.thedailyshow.com/full-episodes/'
2230 url = u'http://www.colbertnation.com/full-episodes/'
2231 mobj = re.match(self._VALID_URL, url, re.VERBOSE)
2232 assert mobj is not None
2234 if mobj.group('clip'):
2235 if mobj.group('showname') == 'thedailyshow':
2236 epTitle = mobj.group('tdstitle')
2238 epTitle = mobj.group('cntitle')
2241 dlNewest = not mobj.group('episode')
2243 epTitle = mobj.group('showname')
2245 epTitle = mobj.group('episode')
2247 self.report_extraction(epTitle)
2248 webpage,htmlHandle = self._download_webpage_handle(url, epTitle)
2250 url = htmlHandle.geturl()
2251 mobj = re.match(self._VALID_URL, url, re.VERBOSE)
2253 raise ExtractorError(u'Invalid redirected URL: ' + url)
2254 if mobj.group('episode') == '':
2255 raise ExtractorError(u'Redirected URL is still not specific: ' + url)
2256 epTitle = mobj.group('episode')
2258 mMovieParams = re.findall('(?:<param name="movie" value="|var url = ")(http://media.mtvnservices.com/([^"]*(?:episode|video).*?:.*?))"', webpage)
2260 if len(mMovieParams) == 0:
2261 # The Colbert Report embeds the information in a without
2262 # a URL prefix; so extract the alternate reference
2263 # and then add the URL prefix manually.
2265 altMovieParams = re.findall('data-mgid="([^"]*(?:episode|video).*?:.*?)"', webpage)
2266 if len(altMovieParams) == 0:
2267 raise ExtractorError(u'unable to find Flash URL in webpage ' + url)
2269 mMovieParams = [("http://media.mtvnservices.com/" + altMovieParams[0], altMovieParams[0])]
2271 uri = mMovieParams[0][1]
2272 indexUrl = 'http://shadow.comedycentral.com/feeds/video_player/mrss/?' + compat_urllib_parse.urlencode({'uri': uri})
2273 indexXml = self._download_webpage(indexUrl, epTitle,
2274 u'Downloading show index',
2275 u'unable to download episode index')
2279 idoc = xml.etree.ElementTree.fromstring(indexXml)
2280 itemEls = idoc.findall('.//item')
2281 for partNum,itemEl in enumerate(itemEls):
2282 mediaId = itemEl.findall('./guid')[0].text
2283 shortMediaId = mediaId.split(':')[-1]
2284 showId = mediaId.split(':')[-2].replace('.com', '')
2285 officialTitle = itemEl.findall('./title')[0].text
2286 officialDate = unified_strdate(itemEl.findall('./pubDate')[0].text)
2288 configUrl = ('http://www.comedycentral.com/global/feeds/entertainment/media/mediaGenEntertainment.jhtml?' +
2289 compat_urllib_parse.urlencode({'uri': mediaId}))
2290 configXml = self._download_webpage(configUrl, epTitle,
2291 u'Downloading configuration for %s' % shortMediaId)
2293 cdoc = xml.etree.ElementTree.fromstring(configXml)
2295 for rendition in cdoc.findall('.//rendition'):
2296 finfo = (rendition.attrib['bitrate'], rendition.findall('./src')[0].text)
2300 self._downloader.report_error(u'unable to download ' + mediaId + ': No videos found')
2303 if self._downloader.params.get('listformats', None):
2304 self._print_formats([i[0] for i in turls])
2307 # For now, just pick the highest bitrate
2308 format,rtmp_video_url = turls[-1]
2310 # Get the format arg from the arg stream
2311 req_format = self._downloader.params.get('format', None)
2313 # Select format if we can find one
2316 format, rtmp_video_url = f, v
2319 m = re.match(r'^rtmpe?://.*?/(?P<finalid>gsp.comedystor/.*)$', rtmp_video_url)
2321 raise ExtractorError(u'Cannot transform RTMP url')
2322 base = 'http://mtvnmobile.vo.llnwd.net/kip0/_pxn=1+_pxI0=Ripod-h264+_pxL0=undefined+_pxM0=+_pxK=18639+_pxE=mp4/44620/mtvnorigin/'
2323 video_url = base + m.group('finalid')
2325 effTitle = showId + u'-' + epTitle + u' part ' + compat_str(partNum+1)
2330 'upload_date': officialDate,
2335 'description': officialTitle,
2337 results.append(info)
2342 class EscapistIE(InfoExtractor):
2343 """Information extractor for The Escapist """
2345 _VALID_URL = r'^(https?://)?(www\.)?escapistmagazine\.com/videos/view/(?P<showname>[^/]+)/(?P<episode>[^/?]+)[/?]?.*$'
2346 IE_NAME = u'escapist'
2348 def _real_extract(self, url):
2349 mobj = re.match(self._VALID_URL, url)
2351 raise ExtractorError(u'Invalid URL: %s' % url)
2352 showName = mobj.group('showname')
2353 videoId = mobj.group('episode')
2355 self.report_extraction(showName)
2356 webPage = self._download_webpage(url, showName)
2358 descMatch = re.search('<meta name="description" content="([^"]*)"', webPage)
2359 description = unescapeHTML(descMatch.group(1))
2360 imgMatch = re.search('<meta property="og:image" content="([^"]*)"', webPage)
2361 imgUrl = unescapeHTML(imgMatch.group(1))
2362 playerUrlMatch = re.search('<meta property="og:video" content="([^"]*)"', webPage)
2363 playerUrl = unescapeHTML(playerUrlMatch.group(1))
2364 configUrlMatch = re.search('config=(.*)$', playerUrl)
2365 configUrl = compat_urllib_parse.unquote(configUrlMatch.group(1))
2367 configJSON = self._download_webpage(configUrl, showName,
2368 u'Downloading configuration',
2369 u'unable to download configuration')
2371 # Technically, it's JavaScript, not JSON
2372 configJSON = configJSON.replace("'", '"')
2375 config = json.loads(configJSON)
2376 except (ValueError,) as err:
2377 raise ExtractorError(u'Invalid JSON in configuration file: ' + compat_str(err))
2379 playlist = config['playlist']
2380 videoUrl = playlist[1]['url']
2385 'uploader': showName,
2386 'upload_date': None,
2389 'thumbnail': imgUrl,
2390 'description': description,
2391 'player_url': playerUrl,
2396 class CollegeHumorIE(InfoExtractor):
2397 """Information extractor for collegehumor.com"""
2400 _VALID_URL = r'^(?:https?://)?(?:www\.)?collegehumor\.com/video/(?P<videoid>[0-9]+)/(?P<shorttitle>.*)$'
2401 IE_NAME = u'collegehumor'
2403 def report_manifest(self, video_id):
2404 """Report information extraction."""
2405 self.to_screen(u'%s: Downloading XML manifest' % video_id)
2407 def _real_extract(self, url):
2408 mobj = re.match(self._VALID_URL, url)
2410 raise ExtractorError(u'Invalid URL: %s' % url)
2411 video_id = mobj.group('videoid')
2416 'upload_date': None,
2419 self.report_extraction(video_id)
2420 xmlUrl = 'http://www.collegehumor.com/moogaloop/video/' + video_id
2422 metaXml = compat_urllib_request.urlopen(xmlUrl).read()
2423 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
2424 raise ExtractorError(u'Unable to download video info XML: %s' % compat_str(err))
2426 mdoc = xml.etree.ElementTree.fromstring(metaXml)
2428 videoNode = mdoc.findall('./video')[0]
2429 info['description'] = videoNode.findall('./description')[0].text
2430 info['title'] = videoNode.findall('./caption')[0].text
2431 info['thumbnail'] = videoNode.findall('./thumbnail')[0].text
2432 manifest_url = videoNode.findall('./file')[0].text
2434 raise ExtractorError(u'Invalid metadata XML file')
2436 manifest_url += '?hdcore=2.10.3'
2437 self.report_manifest(video_id)
2439 manifestXml = compat_urllib_request.urlopen(manifest_url).read()
2440 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
2441 raise ExtractorError(u'Unable to download video info XML: %s' % compat_str(err))
2443 adoc = xml.etree.ElementTree.fromstring(manifestXml)
2445 media_node = adoc.findall('./{http://ns.adobe.com/f4m/1.0}media')[0]
2446 node_id = media_node.attrib['url']
2447 video_id = adoc.findall('./{http://ns.adobe.com/f4m/1.0}id')[0].text
2448 except IndexError as err:
2449 raise ExtractorError(u'Invalid manifest file')
2451 url_pr = compat_urllib_parse_urlparse(manifest_url)
2452 url = url_pr.scheme + '://' + url_pr.netloc + '/z' + video_id[:-2] + '/' + node_id + 'Seg1-Frag1'
2459 class XVideosIE(InfoExtractor):
2460 """Information extractor for xvideos.com"""
2462 _VALID_URL = r'^(?:https?://)?(?:www\.)?xvideos\.com/video([0-9]+)(?:.*)'
2463 IE_NAME = u'xvideos'
2465 def _real_extract(self, url):
2466 mobj = re.match(self._VALID_URL, url)
2468 raise ExtractorError(u'Invalid URL: %s' % url)
2469 video_id = mobj.group(1)
2471 webpage = self._download_webpage(url, video_id)
2473 self.report_extraction(video_id)
2477 mobj = re.search(r'flv_url=(.+?)&', webpage)
2479 raise ExtractorError(u'Unable to extract video url')
2480 video_url = compat_urllib_parse.unquote(mobj.group(1))
2484 mobj = re.search(r'<title>(.*?)\s+-\s+XVID', webpage)
2486 raise ExtractorError(u'Unable to extract video title')
2487 video_title = mobj.group(1)
2490 # Extract video thumbnail
2491 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)
2493 raise ExtractorError(u'Unable to extract video thumbnail')
2494 video_thumbnail = mobj.group(0)
2500 'upload_date': None,
2501 'title': video_title,
2503 'thumbnail': video_thumbnail,
2504 'description': None,
2510 class SoundcloudIE(InfoExtractor):
2511 """Information extractor for soundcloud.com
2512 To access the media, the uid of the song and a stream token
2513 must be extracted from the page source and the script must make
2514 a request to media.soundcloud.com/crossdomain.xml. Then
2515 the media can be grabbed by requesting from an url composed
2516 of the stream token and uid
2519 _VALID_URL = r'^(?:https?://)?(?:www\.)?soundcloud\.com/([\w\d-]+)/([\w\d-]+)'
2520 IE_NAME = u'soundcloud'
2522 def report_resolve(self, video_id):
2523 """Report information extraction."""
2524 self.to_screen(u'%s: Resolving id' % video_id)
2526 def _real_extract(self, url):
2527 mobj = re.match(self._VALID_URL, url)
2529 raise ExtractorError(u'Invalid URL: %s' % url)
2531 # extract uploader (which is in the url)
2532 uploader = mobj.group(1)
2533 # extract simple title (uploader + slug of song title)
2534 slug_title = mobj.group(2)
2535 simple_title = uploader + u'-' + slug_title
2536 full_title = '%s/%s' % (uploader, slug_title)
2538 self.report_resolve(full_title)
2540 url = 'http://soundcloud.com/%s/%s' % (uploader, slug_title)
2541 resolv_url = 'http://api.soundcloud.com/resolve.json?url=' + url + '&client_id=b45b1aa10f1ac2941910a7f0d10f8e28'
2542 info_json = self._download_webpage(resolv_url, full_title, u'Downloading info JSON')
2544 info = json.loads(info_json)
2545 video_id = info['id']
2546 self.report_extraction(full_title)
2548 streams_url = 'https://api.sndcdn.com/i1/tracks/' + str(video_id) + '/streams?client_id=b45b1aa10f1ac2941910a7f0d10f8e28'
2549 stream_json = self._download_webpage(streams_url, full_title,
2550 u'Downloading stream definitions',
2551 u'unable to download stream definitions')
2553 streams = json.loads(stream_json)
2554 mediaURL = streams['http_mp3_128_url']
2555 upload_date = unified_strdate(info['created_at'])
2560 'uploader': info['user']['username'],
2561 'upload_date': upload_date,
2562 'title': info['title'],
2564 'description': info['description'],
2567 class SoundcloudSetIE(InfoExtractor):
2568 """Information extractor for soundcloud.com sets
2569 To access the media, the uid of the song and a stream token
2570 must be extracted from the page source and the script must make
2571 a request to media.soundcloud.com/crossdomain.xml. Then
2572 the media can be grabbed by requesting from an url composed
2573 of the stream token and uid
2576 _VALID_URL = r'^(?:https?://)?(?:www\.)?soundcloud\.com/([\w\d-]+)/sets/([\w\d-]+)'
2577 IE_NAME = u'soundcloud:set'
2579 def report_resolve(self, video_id):
2580 """Report information extraction."""
2581 self.to_screen(u'%s: Resolving id' % video_id)
2583 def _real_extract(self, url):
2584 mobj = re.match(self._VALID_URL, url)
2586 raise ExtractorError(u'Invalid URL: %s' % url)
2588 # extract uploader (which is in the url)
2589 uploader = mobj.group(1)
2590 # extract simple title (uploader + slug of song title)
2591 slug_title = mobj.group(2)
2592 simple_title = uploader + u'-' + slug_title
2593 full_title = '%s/sets/%s' % (uploader, slug_title)
2595 self.report_resolve(full_title)
2597 url = 'http://soundcloud.com/%s/sets/%s' % (uploader, slug_title)
2598 resolv_url = 'http://api.soundcloud.com/resolve.json?url=' + url + '&client_id=b45b1aa10f1ac2941910a7f0d10f8e28'
2599 info_json = self._download_webpage(resolv_url, full_title)
2602 info = json.loads(info_json)
2603 if 'errors' in info:
2604 for err in info['errors']:
2605 self._downloader.report_error(u'unable to download video webpage: %s' % compat_str(err['error_message']))
2608 self.report_extraction(full_title)
2609 for track in info['tracks']:
2610 video_id = track['id']
2612 streams_url = 'https://api.sndcdn.com/i1/tracks/' + str(video_id) + '/streams?client_id=b45b1aa10f1ac2941910a7f0d10f8e28'
2613 stream_json = self._download_webpage(streams_url, video_id, u'Downloading track info JSON')
2615 self.report_extraction(video_id)
2616 streams = json.loads(stream_json)
2617 mediaURL = streams['http_mp3_128_url']
2622 'uploader': track['user']['username'],
2623 'upload_date': unified_strdate(track['created_at']),
2624 'title': track['title'],
2626 'description': track['description'],
2631 class InfoQIE(InfoExtractor):
2632 """Information extractor for infoq.com"""
2633 _VALID_URL = r'^(?:https?://)?(?:www\.)?infoq\.com/[^/]+/[^/]+$'
2635 def _real_extract(self, url):
2636 mobj = re.match(self._VALID_URL, url)
2638 raise ExtractorError(u'Invalid URL: %s' % url)
2640 webpage = self._download_webpage(url, video_id=url)
2641 self.report_extraction(url)
2644 mobj = re.search(r"jsclassref ?= ?'([^']*)'", webpage)
2646 raise ExtractorError(u'Unable to extract video url')
2647 real_id = compat_urllib_parse.unquote(base64.b64decode(mobj.group(1).encode('ascii')).decode('utf-8'))
2648 video_url = 'rtmpe://video.infoq.com/cfx/st/' + real_id
2651 mobj = re.search(r'contentTitle = "(.*?)";', webpage)
2653 raise ExtractorError(u'Unable to extract video title')
2654 video_title = mobj.group(1)
2656 # Extract description
2657 video_description = u'No description available.'
2658 mobj = re.search(r'<meta name="description" content="(.*)"(?:\s*/)?>', webpage)
2659 if mobj is not None:
2660 video_description = mobj.group(1)
2662 video_filename = video_url.split('/')[-1]
2663 video_id, extension = video_filename.split('.')
2669 'upload_date': None,
2670 'title': video_title,
2671 'ext': extension, # Extension is always(?) mp4, but seems to be flv
2673 'description': video_description,
2678 class MixcloudIE(InfoExtractor):
2679 """Information extractor for www.mixcloud.com"""
2681 _WORKING = False # New API, but it seems good http://www.mixcloud.com/developers/documentation/
2682 _VALID_URL = r'^(?:https?://)?(?:www\.)?mixcloud\.com/([\w\d-]+)/([\w\d-]+)'
2683 IE_NAME = u'mixcloud'
2685 def report_download_json(self, file_id):
2686 """Report JSON download."""
2687 self.to_screen(u'Downloading json')
2689 def get_urls(self, jsonData, fmt, bitrate='best'):
2690 """Get urls from 'audio_formats' section in json"""
2693 bitrate_list = jsonData[fmt]
2694 if bitrate is None or bitrate == 'best' or bitrate not in bitrate_list:
2695 bitrate = max(bitrate_list) # select highest
2697 url_list = jsonData[fmt][bitrate]
2698 except TypeError: # we have no bitrate info.
2699 url_list = jsonData[fmt]
2702 def check_urls(self, url_list):
2703 """Returns 1st active url from list"""
2704 for url in url_list:
2706 compat_urllib_request.urlopen(url)
2708 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
2713 def _print_formats(self, formats):
2714 print('Available formats:')
2715 for fmt in formats.keys():
2716 for b in formats[fmt]:
2718 ext = formats[fmt][b][0]
2719 print('%s\t%s\t[%s]' % (fmt, b, ext.split('.')[-1]))
2720 except TypeError: # we have no bitrate info
2721 ext = formats[fmt][0]
2722 print('%s\t%s\t[%s]' % (fmt, '??', ext.split('.')[-1]))
2725 def _real_extract(self, url):
2726 mobj = re.match(self._VALID_URL, url)
2728 raise ExtractorError(u'Invalid URL: %s' % url)
2729 # extract uploader & filename from url
2730 uploader = mobj.group(1).decode('utf-8')
2731 file_id = uploader + "-" + mobj.group(2).decode('utf-8')
2733 # construct API request
2734 file_url = 'http://www.mixcloud.com/api/1/cloudcast/' + '/'.join(url.split('/')[-3:-1]) + '.json'
2735 # retrieve .json file with links to files
2736 request = compat_urllib_request.Request(file_url)
2738 self.report_download_json(file_url)
2739 jsonData = compat_urllib_request.urlopen(request).read()
2740 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
2741 raise ExtractorError(u'Unable to retrieve file: %s' % compat_str(err))
2744 json_data = json.loads(jsonData)
2745 player_url = json_data['player_swf_url']
2746 formats = dict(json_data['audio_formats'])
2748 req_format = self._downloader.params.get('format', None)
2751 if self._downloader.params.get('listformats', None):
2752 self._print_formats(formats)
2755 if req_format is None or req_format == 'best':
2756 for format_param in formats.keys():
2757 url_list = self.get_urls(formats, format_param)
2759 file_url = self.check_urls(url_list)
2760 if file_url is not None:
2763 if req_format not in formats:
2764 raise ExtractorError(u'Format is not available')
2766 url_list = self.get_urls(formats, req_format)
2767 file_url = self.check_urls(url_list)
2768 format_param = req_format
2771 'id': file_id.decode('utf-8'),
2772 'url': file_url.decode('utf-8'),
2773 'uploader': uploader.decode('utf-8'),
2774 'upload_date': None,
2775 'title': json_data['name'],
2776 'ext': file_url.split('.')[-1].decode('utf-8'),
2777 'format': (format_param is None and u'NA' or format_param.decode('utf-8')),
2778 'thumbnail': json_data['thumbnail_url'],
2779 'description': json_data['description'],
2780 'player_url': player_url.decode('utf-8'),
2783 class StanfordOpenClassroomIE(InfoExtractor):
2784 """Information extractor for Stanford's Open ClassRoom"""
2786 _VALID_URL = r'^(?:https?://)?openclassroom.stanford.edu(?P<path>/?|(/MainFolder/(?:HomePage|CoursePage|VideoPage)\.php([?]course=(?P<course>[^&]+)(&video=(?P<video>[^&]+))?(&.*)?)?))$'
2787 IE_NAME = u'stanfordoc'
2789 def _real_extract(self, url):
2790 mobj = re.match(self._VALID_URL, url)
2792 raise ExtractorError(u'Invalid URL: %s' % url)
2794 if mobj.group('course') and mobj.group('video'): # A specific video
2795 course = mobj.group('course')
2796 video = mobj.group('video')
2798 'id': course + '_' + video,
2800 'upload_date': None,
2803 self.report_extraction(info['id'])
2804 baseUrl = 'http://openclassroom.stanford.edu/MainFolder/courses/' + course + '/videos/'
2805 xmlUrl = baseUrl + video + '.xml'
2807 metaXml = compat_urllib_request.urlopen(xmlUrl).read()
2808 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
2809 raise ExtractorError(u'Unable to download video info XML: %s' % compat_str(err))
2810 mdoc = xml.etree.ElementTree.fromstring(metaXml)
2812 info['title'] = mdoc.findall('./title')[0].text
2813 info['url'] = baseUrl + mdoc.findall('./videoFile')[0].text
2815 raise ExtractorError(u'Invalid metadata XML file')
2816 info['ext'] = info['url'].rpartition('.')[2]
2818 elif mobj.group('course'): # A course page
2819 course = mobj.group('course')
2824 'upload_date': None,
2827 coursepage = self._download_webpage(url, info['id'],
2828 note='Downloading course info page',
2829 errnote='Unable to download course info page')
2831 m = re.search('<h1>([^<]+)</h1>', coursepage)
2833 info['title'] = unescapeHTML(m.group(1))
2835 info['title'] = info['id']
2837 m = re.search('<description>([^<]+)</description>', coursepage)
2839 info['description'] = unescapeHTML(m.group(1))
2841 links = orderedSet(re.findall('<a href="(VideoPage.php\?[^"]+)">', coursepage))
2844 'type': 'reference',
2845 'url': 'http://openclassroom.stanford.edu/MainFolder/' + unescapeHTML(vpage),
2849 for entry in info['list']:
2850 assert entry['type'] == 'reference'
2851 results += self.extract(entry['url'])
2855 'id': 'Stanford OpenClassroom',
2858 'upload_date': None,
2861 self.report_download_webpage(info['id'])
2862 rootURL = 'http://openclassroom.stanford.edu/MainFolder/HomePage.php'
2864 rootpage = compat_urllib_request.urlopen(rootURL).read()
2865 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
2866 raise ExtractorError(u'Unable to download course info page: ' + compat_str(err))
2868 info['title'] = info['id']
2870 links = orderedSet(re.findall('<a href="(CoursePage.php\?[^"]+)">', rootpage))
2873 'type': 'reference',
2874 'url': 'http://openclassroom.stanford.edu/MainFolder/' + unescapeHTML(cpage),
2879 for entry in info['list']:
2880 assert entry['type'] == 'reference'
2881 results += self.extract(entry['url'])
2884 class MTVIE(InfoExtractor):
2885 """Information extractor for MTV.com"""
2887 _VALID_URL = r'^(?P<proto>https?://)?(?:www\.)?mtv\.com/videos/[^/]+/(?P<videoid>[0-9]+)/[^/]+$'
2890 def _real_extract(self, url):
2891 mobj = re.match(self._VALID_URL, url)
2893 raise ExtractorError(u'Invalid URL: %s' % url)
2894 if not mobj.group('proto'):
2895 url = 'http://' + url
2896 video_id = mobj.group('videoid')
2898 webpage = self._download_webpage(url, video_id)
2900 mobj = re.search(r'<meta name="mtv_vt" content="([^"]+)"/>', webpage)
2902 raise ExtractorError(u'Unable to extract song name')
2903 song_name = unescapeHTML(mobj.group(1).decode('iso-8859-1'))
2904 mobj = re.search(r'<meta name="mtv_an" content="([^"]+)"/>', webpage)
2906 raise ExtractorError(u'Unable to extract performer')
2907 performer = unescapeHTML(mobj.group(1).decode('iso-8859-1'))
2908 video_title = performer + ' - ' + song_name
2910 mobj = re.search(r'<meta name="mtvn_uri" content="([^"]+)"/>', webpage)
2912 raise ExtractorError(u'Unable to mtvn_uri')
2913 mtvn_uri = mobj.group(1)
2915 mobj = re.search(r'MTVN.Player.defaultPlaylistId = ([0-9]+);', webpage)
2917 raise ExtractorError(u'Unable to extract content id')
2918 content_id = mobj.group(1)
2920 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
2921 self.report_extraction(video_id)
2922 request = compat_urllib_request.Request(videogen_url)
2924 metadataXml = compat_urllib_request.urlopen(request).read()
2925 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
2926 raise ExtractorError(u'Unable to download video metadata: %s' % compat_str(err))
2928 mdoc = xml.etree.ElementTree.fromstring(metadataXml)
2929 renditions = mdoc.findall('.//rendition')
2931 # For now, always pick the highest quality.
2932 rendition = renditions[-1]
2935 _,_,ext = rendition.attrib['type'].partition('/')
2936 format = ext + '-' + rendition.attrib['width'] + 'x' + rendition.attrib['height'] + '_' + rendition.attrib['bitrate']
2937 video_url = rendition.find('./src').text
2939 raise ExtractorError('Invalid rendition field.')
2944 'uploader': performer,
2945 'upload_date': None,
2946 'title': video_title,
2954 class YoukuIE(InfoExtractor):
2955 _VALID_URL = r'(?:http://)?v\.youku\.com/v_show/id_(?P<ID>[A-Za-z0-9]+)\.html'
2958 nowTime = int(time.time() * 1000)
2959 random1 = random.randint(1000,1998)
2960 random2 = random.randint(1000,9999)
2962 return "%d%d%d" %(nowTime,random1,random2)
2964 def _get_file_ID_mix_string(self, seed):
2966 source = list("abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ/\:._-1234567890")
2968 for i in range(len(source)):
2969 seed = (seed * 211 + 30031 ) % 65536
2970 index = math.floor(seed / 65536 * len(source) )
2971 mixed.append(source[int(index)])
2972 source.remove(source[int(index)])
2973 #return ''.join(mixed)
2976 def _get_file_id(self, fileId, seed):
2977 mixed = self._get_file_ID_mix_string(seed)
2978 ids = fileId.split('*')
2982 realId.append(mixed[int(ch)])
2983 return ''.join(realId)
2985 def _real_extract(self, url):
2986 mobj = re.match(self._VALID_URL, url)
2988 raise ExtractorError(u'Invalid URL: %s' % url)
2989 video_id = mobj.group('ID')
2991 info_url = 'http://v.youku.com/player/getPlayList/VideoIDS/' + video_id
2993 jsondata = self._download_webpage(info_url, video_id)
2995 self.report_extraction(video_id)
2997 config = json.loads(jsondata)
2999 video_title = config['data'][0]['title']
3000 seed = config['data'][0]['seed']
3002 format = self._downloader.params.get('format', None)
3003 supported_format = list(config['data'][0]['streamfileids'].keys())
3005 if format is None or format == 'best':
3006 if 'hd2' in supported_format:
3011 elif format == 'worst':
3019 fileid = config['data'][0]['streamfileids'][format]
3020 keys = [s['k'] for s in config['data'][0]['segs'][format]]
3021 except (UnicodeDecodeError, ValueError, KeyError):
3022 raise ExtractorError(u'Unable to extract info section')
3025 sid = self._gen_sid()
3026 fileid = self._get_file_id(fileid, seed)
3028 #column 8,9 of fileid represent the segment number
3029 #fileid[7:9] should be changed
3030 for index, key in enumerate(keys):
3032 temp_fileid = '%s%02X%s' % (fileid[0:8], index, fileid[10:])
3033 download_url = 'http://f.youku.com/player/getFlvPath/sid/%s_%02X/st/flv/fileid/%s?k=%s' % (sid, index, temp_fileid, key)
3036 'id': '%s_part%02d' % (video_id, index),
3037 'url': download_url,
3039 'upload_date': None,
3040 'title': video_title,
3043 files_info.append(info)
3048 class XNXXIE(InfoExtractor):
3049 """Information extractor for xnxx.com"""
3051 _VALID_URL = r'^(?:https?://)?video\.xnxx\.com/video([0-9]+)/(.*)'
3053 VIDEO_URL_RE = r'flv_url=(.*?)&'
3054 VIDEO_TITLE_RE = r'<title>(.*?)\s+-\s+XNXX.COM'
3055 VIDEO_THUMB_RE = r'url_bigthumb=(.*?)&'
3057 def _real_extract(self, url):
3058 mobj = re.match(self._VALID_URL, url)
3060 raise ExtractorError(u'Invalid URL: %s' % url)
3061 video_id = mobj.group(1)
3063 # Get webpage content
3064 webpage = self._download_webpage(url, video_id)
3066 result = re.search(self.VIDEO_URL_RE, webpage)
3068 raise ExtractorError(u'Unable to extract video url')
3069 video_url = compat_urllib_parse.unquote(result.group(1))
3071 result = re.search(self.VIDEO_TITLE_RE, webpage)
3073 raise ExtractorError(u'Unable to extract video title')
3074 video_title = result.group(1)
3076 result = re.search(self.VIDEO_THUMB_RE, webpage)
3078 raise ExtractorError(u'Unable to extract video thumbnail')
3079 video_thumbnail = result.group(1)
3085 'upload_date': None,
3086 'title': video_title,
3088 'thumbnail': video_thumbnail,
3089 'description': None,
3093 class GooglePlusIE(InfoExtractor):
3094 """Information extractor for plus.google.com."""
3096 _VALID_URL = r'(?:https://)?plus\.google\.com/(?:[^/]+/)*?posts/(\w+)'
3097 IE_NAME = u'plus.google'
3099 def report_extract_entry(self, url):
3100 """Report downloading extry"""
3101 self.to_screen(u'Downloading entry: %s' % url)
3103 def report_date(self, upload_date):
3104 """Report downloading extry"""
3105 self.to_screen(u'Entry date: %s' % upload_date)
3107 def report_uploader(self, uploader):
3108 """Report downloading extry"""
3109 self.to_screen(u'Uploader: %s' % uploader)
3111 def report_title(self, video_title):
3112 """Report downloading extry"""
3113 self.to_screen(u'Title: %s' % video_title)
3115 def report_extract_vid_page(self, video_page):
3116 """Report information extraction."""
3117 self.to_screen(u'Extracting video page: %s' % video_page)
3119 def _real_extract(self, url):
3120 # Extract id from URL
3121 mobj = re.match(self._VALID_URL, url)
3123 raise ExtractorError(u'Invalid URL: %s' % url)
3125 post_url = mobj.group(0)
3126 video_id = mobj.group(1)
3128 video_extension = 'flv'
3130 # Step 1, Retrieve post webpage to extract further information
3131 self.report_extract_entry(post_url)
3132 webpage = self._download_webpage(post_url, video_id, u'Downloading entry webpage')
3134 # Extract update date
3136 pattern = 'title="Timestamp">(.*?)</a>'
3137 mobj = re.search(pattern, webpage)
3139 upload_date = mobj.group(1)
3140 # Convert timestring to a format suitable for filename
3141 upload_date = datetime.datetime.strptime(upload_date, "%Y-%m-%d")
3142 upload_date = upload_date.strftime('%Y%m%d')
3143 self.report_date(upload_date)
3147 pattern = r'rel\="author".*?>(.*?)</a>'
3148 mobj = re.search(pattern, webpage)
3150 uploader = mobj.group(1)
3151 self.report_uploader(uploader)
3154 # Get the first line for title
3156 pattern = r'<meta name\=\"Description\" content\=\"(.*?)[\n<"]'
3157 mobj = re.search(pattern, webpage)
3159 video_title = mobj.group(1)
3160 self.report_title(video_title)
3162 # Step 2, Stimulate clicking the image box to launch video
3163 pattern = '"(https\://plus\.google\.com/photos/.*?)",,"image/jpeg","video"\]'
3164 mobj = re.search(pattern, webpage)
3166 raise ExtractorError(u'Unable to extract video page URL')
3168 video_page = mobj.group(1)
3169 webpage = self._download_webpage(video_page, video_id, u'Downloading video page')
3170 self.report_extract_vid_page(video_page)
3173 # Extract video links on video page
3174 """Extract video links of all sizes"""
3175 pattern = '\d+,\d+,(\d+),"(http\://redirector\.googlevideo\.com.*?)"'
3176 mobj = re.findall(pattern, webpage)
3178 raise ExtractorError(u'Unable to extract video links')
3180 # Sort in resolution
3181 links = sorted(mobj)
3183 # Choose the lowest of the sort, i.e. highest resolution
3184 video_url = links[-1]
3185 # Only get the url. The resolution part in the tuple has no use anymore
3186 video_url = video_url[-1]
3187 # Treat escaped \u0026 style hex
3189 video_url = video_url.decode("unicode_escape")
3190 except AttributeError: # Python 3
3191 video_url = bytes(video_url, 'ascii').decode('unicode-escape')
3197 'uploader': uploader,
3198 'upload_date': upload_date,
3199 'title': video_title,
3200 'ext': video_extension,
3203 class NBAIE(InfoExtractor):
3204 _VALID_URL = r'^(?:https?://)?(?:watch\.|www\.)?nba\.com/(?:nba/)?video(/[^?]*)(\?.*)?$'
3207 def _real_extract(self, url):
3208 mobj = re.match(self._VALID_URL, url)
3210 raise ExtractorError(u'Invalid URL: %s' % url)
3212 video_id = mobj.group(1)
3213 if video_id.endswith('/index.html'):
3214 video_id = video_id[:-len('/index.html')]
3216 webpage = self._download_webpage(url, video_id)
3218 video_url = u'http://ht-mobile.cdn.turner.com/nba/big' + video_id + '_nba_1280x720.mp4'
3219 def _findProp(rexp, default=None):
3220 m = re.search(rexp, webpage)
3222 return unescapeHTML(m.group(1))
3226 shortened_video_id = video_id.rpartition('/')[2]
3227 title = _findProp(r'<meta property="og:title" content="(.*?)"', shortened_video_id).replace('NBA.com: ', '')
3229 'id': shortened_video_id,
3233 'uploader_date': _findProp(r'<b>Date:</b> (.*?)</div>'),
3234 'description': _findProp(r'<div class="description">(.*?)</h1>'),
3238 class JustinTVIE(InfoExtractor):
3239 """Information extractor for justin.tv and twitch.tv"""
3240 # TODO: One broadcast may be split into multiple videos. The key
3241 # 'broadcast_id' is the same for all parts, and 'broadcast_part'
3242 # starts at 1 and increases. Can we treat all parts as one video?
3244 _VALID_URL = r"""(?x)^(?:http://)?(?:www\.)?(?:twitch|justin)\.tv/
3246 (?P<channelid>[^/]+)|
3247 (?:(?:[^/]+)/b/(?P<videoid>[^/]+))|
3248 (?:(?:[^/]+)/c/(?P<chapterid>[^/]+))
3252 _JUSTIN_PAGE_LIMIT = 100
3253 IE_NAME = u'justin.tv'
3255 def report_download_page(self, channel, offset):
3256 """Report attempt to download a single page of videos."""
3257 self.to_screen(u'%s: Downloading video information from %d to %d' %
3258 (channel, offset, offset + self._JUSTIN_PAGE_LIMIT))
3260 # Return count of items, list of *valid* items
3261 def _parse_page(self, url, video_id):
3262 webpage = self._download_webpage(url, video_id,
3263 u'Downloading video info JSON',
3264 u'unable to download video info JSON')
3266 response = json.loads(webpage)
3267 if type(response) != list:
3268 error_text = response.get('error', 'unknown error')
3269 raise ExtractorError(u'Justin.tv API: %s' % error_text)
3271 for clip in response:
3272 video_url = clip['video_file_url']
3274 video_extension = os.path.splitext(video_url)[1][1:]
3275 video_date = re.sub('-', '', clip['start_time'][:10])
3276 video_uploader_id = clip.get('user_id', clip.get('channel_id'))
3277 video_id = clip['id']
3278 video_title = clip.get('title', video_id)
3282 'title': video_title,
3283 'uploader': clip.get('channel_name', video_uploader_id),
3284 'uploader_id': video_uploader_id,
3285 'upload_date': video_date,
3286 'ext': video_extension,
3288 return (len(response), info)
3290 def _real_extract(self, url):
3291 mobj = re.match(self._VALID_URL, url)
3293 raise ExtractorError(u'invalid URL: %s' % url)
3295 api_base = 'http://api.justin.tv'
3297 if mobj.group('channelid'):
3299 video_id = mobj.group('channelid')
3300 api = api_base + '/channel/archives/%s.json' % video_id
3301 elif mobj.group('chapterid'):
3302 chapter_id = mobj.group('chapterid')
3304 webpage = self._download_webpage(url, chapter_id)
3305 m = re.search(r'PP\.archive_id = "([0-9]+)";', webpage)
3307 raise ExtractorError(u'Cannot find archive of a chapter')
3308 archive_id = m.group(1)
3310 api = api_base + '/broadcast/by_chapter/%s.xml' % chapter_id
3311 chapter_info_xml = self._download_webpage(api, chapter_id,
3312 note=u'Downloading chapter information',
3313 errnote=u'Chapter information download failed')
3314 doc = xml.etree.ElementTree.fromstring(chapter_info_xml)
3315 for a in doc.findall('.//archive'):
3316 if archive_id == a.find('./id').text:
3319 raise ExtractorError(u'Could not find chapter in chapter information')
3321 video_url = a.find('./video_file_url').text
3322 video_ext = video_url.rpartition('.')[2] or u'flv'
3324 chapter_api_url = u'https://api.twitch.tv/kraken/videos/c' + chapter_id
3325 chapter_info_json = self._download_webpage(chapter_api_url, u'c' + chapter_id,
3326 note='Downloading chapter metadata',
3327 errnote='Download of chapter metadata failed')
3328 chapter_info = json.loads(chapter_info_json)
3330 bracket_start = int(doc.find('.//bracket_start').text)
3331 bracket_end = int(doc.find('.//bracket_end').text)
3333 # TODO determine start (and probably fix up file)
3334 # youtube-dl -v http://www.twitch.tv/firmbelief/c/1757457
3335 #video_url += u'?start=' + TODO:start_timestamp
3336 # bracket_start is 13290, but we want 51670615
3337 self._downloader.report_warning(u'Chapter detected, but we can just download the whole file. '
3338 u'Chapter starts at %s and ends at %s' % (formatSeconds(bracket_start), formatSeconds(bracket_end)))
3341 'id': u'c' + chapter_id,
3344 'title': chapter_info['title'],
3345 'thumbnail': chapter_info['preview'],
3346 'description': chapter_info['description'],
3347 'uploader': chapter_info['channel']['display_name'],
3348 'uploader_id': chapter_info['channel']['name'],
3352 video_id = mobj.group('videoid')
3353 api = api_base + '/broadcast/by_archive/%s.json' % video_id
3355 self.report_extraction(video_id)
3359 limit = self._JUSTIN_PAGE_LIMIT
3362 self.report_download_page(video_id, offset)
3363 page_url = api + ('?offset=%d&limit=%d' % (offset, limit))
3364 page_count, page_info = self._parse_page(page_url, video_id)
3365 info.extend(page_info)
3366 if not paged or page_count != limit:
3371 class FunnyOrDieIE(InfoExtractor):
3372 _VALID_URL = r'^(?:https?://)?(?:www\.)?funnyordie\.com/videos/(?P<id>[0-9a-f]+)/.*$'
3374 def _real_extract(self, url):
3375 mobj = re.match(self._VALID_URL, url)
3377 raise ExtractorError(u'invalid URL: %s' % url)
3379 video_id = mobj.group('id')
3380 webpage = self._download_webpage(url, video_id)
3382 m = re.search(r'<video[^>]*>\s*<source[^>]*>\s*<source src="(?P<url>[^"]+)"', webpage, re.DOTALL)
3384 raise ExtractorError(u'Unable to find video information')
3385 video_url = unescapeHTML(m.group('url'))
3387 m = re.search(r"<h1 class='player_page_h1'.*?>(?P<title>.*?)</h1>", webpage, flags=re.DOTALL)
3389 m = re.search(r'<title>(?P<title>[^<]+?)</title>', webpage)
3391 raise ExtractorError(u'Cannot find video title')
3392 title = clean_html(m.group('title'))
3394 m = re.search(r'<meta property="og:description" content="(?P<desc>.*?)"', webpage)
3396 desc = unescapeHTML(m.group('desc'))
3405 'description': desc,
3409 class SteamIE(InfoExtractor):
3410 _VALID_URL = r"""http://store\.steampowered\.com/
3412 (?P<urltype>video|app)/ #If the page is only for videos or for a game
3414 (?P<videoID>\d*)(?P<extra>\??) #For urltype == video we sometimes get the videoID
3418 def suitable(cls, url):
3419 """Receives a URL and returns True if suitable for this IE."""
3420 return re.match(cls._VALID_URL, url, re.VERBOSE) is not None
3422 def _real_extract(self, url):
3423 m = re.match(self._VALID_URL, url, re.VERBOSE)
3424 gameID = m.group('gameID')
3425 videourl = 'http://store.steampowered.com/agecheck/video/%s/?snr=1_agecheck_agecheck__age-gate&ageDay=1&ageMonth=January&ageYear=1970' % gameID
3426 self.report_age_confirmation()
3427 webpage = self._download_webpage(videourl, gameID)
3428 game_title = re.search(r'<h2 class="pageheader">(?P<game_title>.*?)</h2>', webpage).group('game_title')
3430 urlRE = r"'movie_(?P<videoID>\d+)': \{\s*FILENAME: \"(?P<videoURL>[\w:/\.\?=]+)\"(,\s*MOVIE_NAME: \"(?P<videoName>[\w:/\.\?=\+-]+)\")?\s*\},"
3431 mweb = re.finditer(urlRE, webpage)
3432 namesRE = r'<span class="title">(?P<videoName>.+?)</span>'
3433 titles = re.finditer(namesRE, webpage)
3434 thumbsRE = r'<img class="movie_thumb" src="(?P<thumbnail>.+?)">'
3435 thumbs = re.finditer(thumbsRE, webpage)
3437 for vid,vtitle,thumb in zip(mweb,titles,thumbs):
3438 video_id = vid.group('videoID')
3439 title = vtitle.group('videoName')
3440 video_url = vid.group('videoURL')
3441 video_thumb = thumb.group('thumbnail')
3443 raise ExtractorError(u'Cannot find video url for %s' % video_id)
3448 'title': unescapeHTML(title),
3449 'thumbnail': video_thumb
3452 return [self.playlist_result(videos, gameID, game_title)]
3454 class UstreamIE(InfoExtractor):
3455 _VALID_URL = r'https?://www\.ustream\.tv/recorded/(?P<videoID>\d+)'
3456 IE_NAME = u'ustream'
3458 def _real_extract(self, url):
3459 m = re.match(self._VALID_URL, url)
3460 video_id = m.group('videoID')
3461 video_url = u'http://tcdn.ustream.tv/video/%s' % video_id
3462 webpage = self._download_webpage(url, video_id)
3463 self.report_extraction(video_id)
3465 m = re.search(r'data-title="(?P<title>.+)"',webpage)
3466 title = m.group('title')
3467 m = re.search(r'data-content-type="channel".*?>(?P<uploader>.*?)</a>',
3469 uploader = unescapeHTML(m.group('uploader').strip())
3470 m = re.search(r'<link rel="image_src" href="(?P<thumb>.*?)"', webpage)
3471 thumb = m.group('thumb')
3472 except AttributeError:
3473 raise ExtractorError(u'Unable to extract info')
3479 'uploader': uploader,
3484 class WorldStarHipHopIE(InfoExtractor):
3485 _VALID_URL = r'https?://(?:www|m)\.worldstar(?:candy|hiphop)\.com/videos/video\.php\?v=(?P<id>.*)'
3486 IE_NAME = u'WorldStarHipHop'
3488 def _real_extract(self, url):
3489 _src_url = r'so\.addVariable\("file","(.*?)"\)'
3491 m = re.match(self._VALID_URL, url)
3492 video_id = m.group('id')
3494 webpage_src = self._download_webpage(url, video_id)
3496 mobj = re.search(_src_url, webpage_src)
3498 if mobj is not None:
3499 video_url = mobj.group(1)
3500 if 'mp4' in video_url:
3505 raise ExtractorError(u'Cannot find video url for %s' % video_id)
3507 mobj = re.search(r"<title>(.*)</title>", webpage_src)
3510 raise ExtractorError(u'Cannot determine title')
3511 title = mobj.group(1)
3513 mobj = re.search(r'rel="image_src" href="(.*)" />', webpage_src)
3514 # Getting thumbnail and if not thumbnail sets correct title for WSHH candy video.
3515 if mobj is not None:
3516 thumbnail = mobj.group(1)
3518 _title = r"""candytitles.*>(.*)</span>"""
3519 mobj = re.search(_title, webpage_src)
3520 if mobj is not None:
3521 title = mobj.group(1)
3528 'thumbnail' : thumbnail,
3533 class RBMARadioIE(InfoExtractor):
3534 _VALID_URL = r'https?://(?:www\.)?rbmaradio\.com/shows/(?P<videoID>[^/]+)$'
3536 def _real_extract(self, url):
3537 m = re.match(self._VALID_URL, url)
3538 video_id = m.group('videoID')
3540 webpage = self._download_webpage(url, video_id)
3541 m = re.search(r'<script>window.gon = {.*?};gon\.show=(.+?);</script>', webpage)
3543 raise ExtractorError(u'Cannot find metadata')
3544 json_data = m.group(1)
3547 data = json.loads(json_data)
3548 except ValueError as e:
3549 raise ExtractorError(u'Invalid JSON: ' + str(e))
3551 video_url = data['akamai_url'] + '&cbr=256'
3552 url_parts = compat_urllib_parse_urlparse(video_url)
3553 video_ext = url_parts.path.rpartition('.')[2]
3558 'title': data['title'],
3559 'description': data.get('teaser_text'),
3560 'location': data.get('country_of_origin'),
3561 'uploader': data.get('host', {}).get('name'),
3562 'uploader_id': data.get('host', {}).get('slug'),
3563 'thumbnail': data.get('image', {}).get('large_url_2x'),
3564 'duration': data.get('duration'),
3569 class YouPornIE(InfoExtractor):
3570 """Information extractor for youporn.com."""
3571 _VALID_URL = r'^(?:https?://)?(?:\w+\.)?youporn\.com/watch/(?P<videoid>[0-9]+)/(?P<title>[^/]+)'
3573 def _print_formats(self, formats):
3574 """Print all available formats"""
3575 print(u'Available formats:')
3576 print(u'ext\t\tformat')
3577 print(u'---------------------------------')
3578 for format in formats:
3579 print(u'%s\t\t%s' % (format['ext'], format['format']))
3581 def _specific(self, req_format, formats):
3583 if(x["format"]==req_format):
3587 def _real_extract(self, url):
3588 mobj = re.match(self._VALID_URL, url)
3590 raise ExtractorError(u'Invalid URL: %s' % url)
3592 video_id = mobj.group('videoid')
3594 req = compat_urllib_request.Request(url)
3595 req.add_header('Cookie', 'age_verified=1')
3596 webpage = self._download_webpage(req, video_id)
3598 # Get the video title
3599 result = re.search(r'<h1.*?>(?P<title>.*)</h1>', webpage)
3601 raise ExtractorError(u'Unable to extract video title')
3602 video_title = result.group('title').strip()
3604 # Get the video date
3605 result = re.search(r'Date:</label>(?P<date>.*) </li>', webpage)
3607 self._downloader.report_warning(u'unable to extract video date')
3610 upload_date = unified_strdate(result.group('date').strip())
3612 # Get the video uploader
3613 result = re.search(r'Submitted:</label>(?P<uploader>.*)</li>', webpage)
3615 self._downloader.report_warning(u'unable to extract uploader')
3616 video_uploader = None
3618 video_uploader = result.group('uploader').strip()
3619 video_uploader = clean_html( video_uploader )
3621 # Get all of the formats available
3622 DOWNLOAD_LIST_RE = r'(?s)<ul class="downloadList">(?P<download_list>.*?)</ul>'
3623 result = re.search(DOWNLOAD_LIST_RE, webpage)
3625 raise ExtractorError(u'Unable to extract download list')
3626 download_list_html = result.group('download_list').strip()
3628 # Get all of the links from the page
3629 LINK_RE = r'(?s)<a href="(?P<url>[^"]+)">'
3630 links = re.findall(LINK_RE, download_list_html)
3631 if(len(links) == 0):
3632 raise ExtractorError(u'ERROR: no known formats available for video')
3634 self.to_screen(u'Links found: %d' % len(links))
3639 # A link looks like this:
3640 # 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
3641 # A path looks like this:
3642 # /201210/31/8004515/480p_370k_8004515/YouPorn%20-%20Nubile%20Films%20The%20Pillow%20Fight.mp4
3643 video_url = unescapeHTML( link )
3644 path = compat_urllib_parse_urlparse( video_url ).path
3645 extension = os.path.splitext( path )[1][1:]
3646 format = path.split('/')[4].split('_')[:2]
3649 format = "-".join( format )
3650 title = u'%s-%s-%s' % (video_title, size, bitrate)
3655 'uploader': video_uploader,
3656 'upload_date': upload_date,
3661 'description': None,
3665 if self._downloader.params.get('listformats', None):
3666 self._print_formats(formats)
3669 req_format = self._downloader.params.get('format', None)
3670 self.to_screen(u'Format: %s' % req_format)
3672 if req_format is None or req_format == 'best':
3674 elif req_format == 'worst':
3675 return [formats[-1]]
3676 elif req_format in ('-1', 'all'):
3679 format = self._specific( req_format, formats )
3681 raise ExtractorError(u'Requested format not available')
3686 class PornotubeIE(InfoExtractor):
3687 """Information extractor for pornotube.com."""
3688 _VALID_URL = r'^(?:https?://)?(?:\w+\.)?pornotube\.com(/c/(?P<channel>[0-9]+))?(/m/(?P<videoid>[0-9]+))(/(?P<title>.+))$'
3690 def _real_extract(self, url):
3691 mobj = re.match(self._VALID_URL, url)
3693 raise ExtractorError(u'Invalid URL: %s' % url)
3695 video_id = mobj.group('videoid')
3696 video_title = mobj.group('title')
3698 # Get webpage content
3699 webpage = self._download_webpage(url, video_id)
3702 VIDEO_URL_RE = r'url: "(?P<url>http://video[0-9].pornotube.com/.+\.flv)",'
3703 result = re.search(VIDEO_URL_RE, webpage)
3705 raise ExtractorError(u'Unable to extract video url')
3706 video_url = compat_urllib_parse.unquote(result.group('url'))
3708 #Get the uploaded date
3709 VIDEO_UPLOADED_RE = r'<div class="video_added_by">Added (?P<date>[0-9\/]+) by'
3710 result = re.search(VIDEO_UPLOADED_RE, webpage)
3712 raise ExtractorError(u'Unable to extract video title')
3713 upload_date = unified_strdate(result.group('date'))
3715 info = {'id': video_id,
3718 'upload_date': upload_date,
3719 'title': video_title,
3725 class YouJizzIE(InfoExtractor):
3726 """Information extractor for youjizz.com."""
3727 _VALID_URL = r'^(?:https?://)?(?:\w+\.)?youjizz\.com/videos/(?P<videoid>[^.]+).html$'
3729 def _real_extract(self, url):
3730 mobj = re.match(self._VALID_URL, url)
3732 raise ExtractorError(u'Invalid URL: %s' % url)
3734 video_id = mobj.group('videoid')
3736 # Get webpage content
3737 webpage = self._download_webpage(url, video_id)
3739 # Get the video title
3740 result = re.search(r'<title>(?P<title>.*)</title>', webpage)
3742 raise ExtractorError(u'ERROR: unable to extract video title')
3743 video_title = result.group('title').strip()
3745 # Get the embed page
3746 result = re.search(r'https?://www.youjizz.com/videos/embed/(?P<videoid>[0-9]+)', webpage)
3748 raise ExtractorError(u'ERROR: unable to extract embed page')
3750 embed_page_url = result.group(0).strip()
3751 video_id = result.group('videoid')
3753 webpage = self._download_webpage(embed_page_url, video_id)
3756 result = re.search(r'so.addVariable\("file",encodeURIComponent\("(?P<source>[^"]+)"\)\);', webpage)
3758 raise ExtractorError(u'ERROR: unable to extract video url')
3759 video_url = result.group('source')
3761 info = {'id': video_id,
3763 'title': video_title,
3766 'player_url': embed_page_url}
3770 class EightTracksIE(InfoExtractor):
3772 _VALID_URL = r'https?://8tracks.com/(?P<user>[^/]+)/(?P<id>[^/#]+)(?:#.*)?$'
3774 def _real_extract(self, url):
3775 mobj = re.match(self._VALID_URL, url)
3777 raise ExtractorError(u'Invalid URL: %s' % url)
3778 playlist_id = mobj.group('id')
3780 webpage = self._download_webpage(url, playlist_id)
3782 m = re.search(r"PAGE.mix = (.*?);\n", webpage, flags=re.DOTALL)
3784 raise ExtractorError(u'Cannot find trax information')
3785 json_like = m.group(1)
3786 data = json.loads(json_like)
3788 session = str(random.randint(0, 1000000000))
3790 track_count = data['tracks_count']
3791 first_url = 'http://8tracks.com/sets/%s/play?player=sm&mix_id=%s&format=jsonh' % (session, mix_id)
3792 next_url = first_url
3794 for i in itertools.count():
3795 api_json = self._download_webpage(next_url, playlist_id,
3796 note=u'Downloading song information %s/%s' % (str(i+1), track_count),
3797 errnote=u'Failed to download song information')
3798 api_data = json.loads(api_json)
3799 track_data = api_data[u'set']['track']
3801 'id': track_data['id'],
3802 'url': track_data['track_file_stream_url'],
3803 'title': track_data['performer'] + u' - ' + track_data['name'],
3804 'raw_title': track_data['name'],
3805 'uploader_id': data['user']['login'],
3809 if api_data['set']['at_last_track']:
3811 next_url = 'http://8tracks.com/sets/%s/next?player=sm&mix_id=%s&format=jsonh&track_id=%s' % (session, mix_id, track_data['id'])
3814 class KeekIE(InfoExtractor):
3815 _VALID_URL = r'http://(?:www\.)?keek\.com/(?:!|\w+/keeks/)(?P<videoID>\w+)'
3818 def _real_extract(self, url):
3819 m = re.match(self._VALID_URL, url)
3820 video_id = m.group('videoID')
3821 video_url = u'http://cdn.keek.com/keek/video/%s' % video_id
3822 thumbnail = u'http://cdn.keek.com/keek/thumbnail/%s/w100/h75' % video_id
3823 webpage = self._download_webpage(url, video_id)
3824 m = re.search(r'<meta property="og:title" content="(?P<title>.*?)"', webpage)
3825 title = unescapeHTML(m.group('title'))
3826 m = re.search(r'<div class="user-name-and-bio">[\S\s]+?<h2>(?P<uploader>.+?)</h2>', webpage)
3827 uploader = clean_html(m.group('uploader'))
3833 'thumbnail': thumbnail,
3834 'uploader': uploader
3838 class TEDIE(InfoExtractor):
3839 _VALID_URL=r'''http://www\.ted\.com/
3841 ((?P<type_playlist>playlists)/(?P<playlist_id>\d+)) # We have a playlist
3843 ((?P<type_talk>talks)) # We have a simple talk
3845 (/lang/(.*?))? # The url may contain the language
3846 /(?P<name>\w+) # Here goes the name and then ".html"
3850 def suitable(cls, url):
3851 """Receives a URL and returns True if suitable for this IE."""
3852 return re.match(cls._VALID_URL, url, re.VERBOSE) is not None
3854 def _real_extract(self, url):
3855 m=re.match(self._VALID_URL, url, re.VERBOSE)
3856 if m.group('type_talk'):
3857 return [self._talk_info(url)]
3859 playlist_id=m.group('playlist_id')
3860 name=m.group('name')
3861 self.to_screen(u'Getting info of playlist %s: "%s"' % (playlist_id,name))
3862 return [self._playlist_videos_info(url,name,playlist_id)]
3864 def _talk_video_link(self,mediaSlug):
3865 '''Returns the video link for that mediaSlug'''
3866 return 'http://download.ted.com/talks/%s.mp4' % mediaSlug
3868 def _playlist_videos_info(self,url,name,playlist_id=0):
3869 '''Returns the videos of the playlist'''
3871 <li\ id="talk_(\d+)"([.\s]*?)data-id="(?P<video_id>\d+)"
3872 ([.\s]*?)data-playlist_item_id="(\d+)"
3873 ([.\s]*?)data-mediaslug="(?P<mediaSlug>.+?)"
3875 video_name_RE=r'<p\ class="talk-title"><a href="(?P<talk_url>/talks/(.+).html)">(?P<fullname>.+?)</a></p>'
3876 webpage=self._download_webpage(url, playlist_id, 'Downloading playlist webpage')
3877 m_videos=re.finditer(video_RE,webpage,re.VERBOSE)
3878 m_names=re.finditer(video_name_RE,webpage)
3880 playlist_RE = r'div class="headline">(\s*?)<h1>(\s*?)<span>(?P<playlist_title>.*?)</span>'
3881 m_playlist = re.search(playlist_RE, webpage)
3882 playlist_title = m_playlist.group('playlist_title')
3884 playlist_entries = []
3885 for m_video, m_name in zip(m_videos,m_names):
3886 video_id=m_video.group('video_id')
3887 talk_url='http://www.ted.com%s' % m_name.group('talk_url')
3888 playlist_entries.append(self.url_result(talk_url, 'TED'))
3889 return self.playlist_result(playlist_entries, playlist_id = playlist_id, playlist_title = playlist_title)
3891 def _talk_info(self, url, video_id=0):
3892 """Return the video for the talk in the url"""
3893 m=re.match(self._VALID_URL, url,re.VERBOSE)
3894 videoName=m.group('name')
3895 webpage=self._download_webpage(url, video_id, 'Downloading \"%s\" page' % videoName)
3896 # If the url includes the language we get the title translated
3897 title_RE=r'<span id="altHeadline" >(?P<title>.*)</span>'
3898 title=re.search(title_RE, webpage).group('title')
3899 info_RE=r'''<script\ type="text/javascript">var\ talkDetails\ =(.*?)
3900 "id":(?P<videoID>[\d]+).*?
3901 "mediaSlug":"(?P<mediaSlug>[\w\d]+?)"'''
3902 thumb_RE=r'</span>[\s.]*</div>[\s.]*<img src="(?P<thumbnail>.*?)"'
3903 thumb_match=re.search(thumb_RE,webpage)
3904 info_match=re.search(info_RE,webpage,re.VERBOSE)
3905 video_id=info_match.group('videoID')
3906 mediaSlug=info_match.group('mediaSlug')
3907 video_url=self._talk_video_link(mediaSlug)
3913 'thumbnail': thumb_match.group('thumbnail')
3917 class MySpassIE(InfoExtractor):
3918 _VALID_URL = r'http://www.myspass.de/.*'
3920 def _real_extract(self, url):
3921 META_DATA_URL_TEMPLATE = 'http://www.myspass.de/myspass/includes/apps/video/getvideometadataxml.php?id=%s'
3923 # video id is the last path element of the URL
3924 # usually there is a trailing slash, so also try the second but last
3925 url_path = compat_urllib_parse_urlparse(url).path
3926 url_parent_path, video_id = os.path.split(url_path)
3928 _, video_id = os.path.split(url_parent_path)
3931 metadata_url = META_DATA_URL_TEMPLATE % video_id
3932 metadata_text = self._download_webpage(metadata_url, video_id)
3933 metadata = xml.etree.ElementTree.fromstring(metadata_text.encode('utf-8'))
3935 # extract values from metadata
3936 url_flv_el = metadata.find('url_flv')
3937 if url_flv_el is None:
3938 raise ExtractorError(u'Unable to extract download url')
3939 video_url = url_flv_el.text
3940 extension = os.path.splitext(video_url)[1][1:]
3941 title_el = metadata.find('title')
3942 if title_el is None:
3943 raise ExtractorError(u'Unable to extract title')
3944 title = title_el.text
3945 format_id_el = metadata.find('format_id')
3946 if format_id_el is None:
3949 format = format_id_el.text
3950 description_el = metadata.find('description')
3951 if description_el is not None:
3952 description = description_el.text
3955 imagePreview_el = metadata.find('imagePreview')
3956 if imagePreview_el is not None:
3957 thumbnail = imagePreview_el.text
3966 'thumbnail': thumbnail,
3967 'description': description
3971 class SpiegelIE(InfoExtractor):
3972 _VALID_URL = r'https?://(?:www\.)?spiegel\.de/video/[^/]*-(?P<videoID>[0-9]+)(?:\.html)?(?:#.*)?$'
3974 def _real_extract(self, url):
3975 m = re.match(self._VALID_URL, url)
3976 video_id = m.group('videoID')
3978 webpage = self._download_webpage(url, video_id)
3979 m = re.search(r'<div class="spVideoTitle">(.*?)</div>', webpage)
3981 raise ExtractorError(u'Cannot find title')
3982 video_title = unescapeHTML(m.group(1))
3984 xml_url = u'http://video2.spiegel.de/flash/' + video_id + u'.xml'
3985 xml_code = self._download_webpage(xml_url, video_id,
3986 note=u'Downloading XML', errnote=u'Failed to download XML')
3988 idoc = xml.etree.ElementTree.fromstring(xml_code)
3989 last_type = idoc[-1]
3990 filename = last_type.findall('./filename')[0].text
3991 duration = float(last_type.findall('./duration')[0].text)
3993 video_url = 'http://video2.spiegel.de/flash/' + filename
3994 video_ext = filename.rpartition('.')[2]
3999 'title': video_title,
4000 'duration': duration,
4004 class LiveLeakIE(InfoExtractor):
4006 _VALID_URL = r'^(?:http?://)?(?:\w+\.)?liveleak\.com/view\?(?:.*?)i=(?P<video_id>[\w_]+)(?:.*)'
4007 IE_NAME = u'liveleak'
4009 def _real_extract(self, url):
4010 mobj = re.match(self._VALID_URL, url)
4012 raise ExtractorError(u'Invalid URL: %s' % url)
4014 video_id = mobj.group('video_id')
4016 webpage = self._download_webpage(url, video_id)
4018 m = re.search(r'file: "(.*?)",', webpage)
4020 raise ExtractorError(u'Unable to find video url')
4021 video_url = m.group(1)
4023 m = re.search(r'<meta property="og:title" content="(?P<title>.*?)"', webpage)
4025 raise ExtractorError(u'Cannot find video title')
4026 title = unescapeHTML(m.group('title')).replace('LiveLeak.com -', '').strip()
4028 m = re.search(r'<meta property="og:description" content="(?P<desc>.*?)"', webpage)
4030 desc = unescapeHTML(m.group('desc'))
4034 m = re.search(r'By:.*?(\w+)</a>', webpage)
4036 uploader = clean_html(m.group(1))
4045 'description': desc,
4046 'uploader': uploader
4051 class ARDIE(InfoExtractor):
4052 _VALID_URL = r'^(?:https?://)?(?:(?:www\.)?ardmediathek\.de|mediathek\.daserste\.de)/(?:.*/)(?P<video_id>[^/\?]+)(?:\?.*)?'
4053 _TITLE = r'<h1(?: class="boxTopHeadline")?>(?P<title>.*)</h1>'
4054 _MEDIA_STREAM = r'mediaCollection\.addMediaStream\((?P<media_type>\d+), (?P<quality>\d+), "(?P<rtmp_url>[^"]*)", "(?P<video_url>[^"]*)", "[^"]*"\)'
4056 def _real_extract(self, url):
4057 # determine video id from url
4058 m = re.match(self._VALID_URL, url)
4060 numid = re.search(r'documentId=([0-9]+)', url)
4062 video_id = numid.group(1)
4064 video_id = m.group('video_id')
4066 # determine title and media streams from webpage
4067 html = self._download_webpage(url, video_id)
4068 title = re.search(self._TITLE, html).group('title')
4069 streams = [m.groupdict() for m in re.finditer(self._MEDIA_STREAM, html)]
4071 assert '"fsk"' in html
4072 raise ExtractorError(u'This video is only available after 8:00 pm')
4074 # choose default media type and highest quality for now
4075 stream = max([s for s in streams if int(s["media_type"]) == 0],
4076 key=lambda s: int(s["quality"]))
4078 # there's two possibilities: RTMP stream or HTTP download
4079 info = {'id': video_id, 'title': title, 'ext': 'mp4'}
4080 if stream['rtmp_url']:
4081 self.to_screen(u'RTMP download detected')
4082 assert stream['video_url'].startswith('mp4:')
4083 info["url"] = stream["rtmp_url"]
4084 info["play_path"] = stream['video_url']
4086 assert stream["video_url"].endswith('.mp4')
4087 info["url"] = stream["video_url"]
4090 class TumblrIE(InfoExtractor):
4091 _VALID_URL = r'http://(?P<blog_name>.*?)\.tumblr\.com/((post)|(video))/(?P<id>\d*)/(.*?)'
4093 def _real_extract(self, url):
4094 m_url = re.match(self._VALID_URL, url)
4095 video_id = m_url.group('id')
4096 blog = m_url.group('blog_name')
4098 url = 'http://%s.tumblr.com/post/%s/' % (blog, video_id)
4099 webpage = self._download_webpage(url, video_id)
4101 re_video = r'src=\\x22(?P<video_url>http://%s\.tumblr\.com/video_file/%s/(.*?))\\x22 type=\\x22video/(?P<ext>.*?)\\x22' % (blog, video_id)
4102 video = re.search(re_video, webpage)
4104 self.to_screen("No video found")
4106 video_url = video.group('video_url')
4107 ext = video.group('ext')
4109 re_thumb = r'posters(.*?)\[\\x22(?P<thumb>.*?)\\x22' # We pick the first poster
4110 thumb = re.search(re_thumb, webpage).group('thumb').replace('\\', '')
4112 # The only place where you can get a title, it's not complete,
4113 # but searching in other places doesn't work for all videos
4114 re_title = r'<title>(?P<title>.*?)</title>'
4115 title = unescapeHTML(re.search(re_title, webpage, re.DOTALL).group('title'))
4117 return [{'id': video_id,
4124 class BandcampIE(InfoExtractor):
4125 _VALID_URL = r'http://.*?\.bandcamp\.com/track/(?P<title>.*)'
4127 def _real_extract(self, url):
4128 mobj = re.match(self._VALID_URL, url)
4129 title = mobj.group('title')
4130 webpage = self._download_webpage(url, title)
4131 # We get the link to the free download page
4132 m_download = re.search(r'freeDownloadPage: "(.*?)"', webpage)
4133 if m_download is None:
4134 raise ExtractorError(u'No free songs founded')
4136 download_link = m_download.group(1)
4137 id = re.search(r'var TralbumData = {(.*?)id: (?P<id>\d*?)$',
4138 webpage, re.MULTILINE|re.DOTALL).group('id')
4140 download_webpage = self._download_webpage(download_link, id,
4141 'Downloading free downloads page')
4142 # We get the dictionary of the track from some javascrip code
4143 info = re.search(r'items: (.*?),$',
4144 download_webpage, re.MULTILINE).group(1)
4145 info = json.loads(info)[0]
4146 # We pick mp3-320 for now, until format selection can be easily implemented.
4147 mp3_info = info[u'downloads'][u'mp3-320']
4148 # If we try to use this url it says the link has expired
4149 initial_url = mp3_info[u'url']
4150 re_url = r'(?P<server>http://(.*?)\.bandcamp\.com)/download/track\?enc=mp3-320&fsig=(?P<fsig>.*?)&id=(?P<id>.*?)&ts=(?P<ts>.*)$'
4151 m_url = re.match(re_url, initial_url)
4152 #We build the url we will use to get the final track url
4153 # This url is build in Bandcamp in the script download_bunde_*.js
4154 request_url = '%s/statdownload/track?enc=mp3-320&fsig=%s&id=%s&ts=%s&.rand=665028774616&.vrs=1' % (m_url.group('server'), m_url.group('fsig'), id, m_url.group('ts'))
4155 final_url_webpage = self._download_webpage(request_url, id, 'Requesting download url')
4156 # If we could correctly generate the .rand field the url would be
4157 #in the "download_url" key
4158 final_url = re.search(r'"retry_url":"(.*?)"', final_url_webpage).group(1)
4160 track_info = {'id':id,
4161 'title' : info[u'title'],
4164 'thumbnail' : info[u'thumb_url'],
4165 'uploader' : info[u'artist']
4170 class RedTubeIE(InfoExtractor):
4171 """Information Extractor for redtube"""
4172 _VALID_URL = r'(?:http://)?(?:www\.)?redtube\.com/(?P<id>[0-9]+)'
4174 def _real_extract(self,url):
4175 mobj = re.match(self._VALID_URL, url)
4177 raise ExtractorError(u'Invalid URL: %s' % url)
4179 video_id = mobj.group('id')
4180 video_extension = 'mp4'
4181 webpage = self._download_webpage(url, video_id)
4182 self.report_extraction(video_id)
4183 mobj = re.search(r'<source src="'+'(.+)'+'" type="video/mp4">',webpage)
4186 raise ExtractorError(u'Unable to extract media URL')
4188 video_url = mobj.group(1)
4189 mobj = re.search('<h1 class="videoTitle slidePanelMovable">(.+)</h1>',webpage)
4191 raise ExtractorError(u'Unable to extract title')
4192 video_title = mobj.group(1)
4197 'ext': video_extension,
4198 'title': video_title,
4201 class InaIE(InfoExtractor):
4202 """Information Extractor for Ina.fr"""
4203 _VALID_URL = r'(?:http://)?(?:www\.)?ina\.fr/video/(?P<id>I[0-9]+)/.*'
4205 def _real_extract(self,url):
4206 mobj = re.match(self._VALID_URL, url)
4208 video_id = mobj.group('id')
4209 mrss_url='http://player.ina.fr/notices/%s.mrss' % video_id
4210 video_extension = 'mp4'
4211 webpage = self._download_webpage(mrss_url, video_id)
4213 mobj = re.search(r'<media:player url="(?P<mp4url>http://mp4.ina.fr/[^"]+\.mp4)', webpage)
4215 raise ExtractorError(u'Unable to extract media URL')
4216 video_url = mobj.group(1)
4218 mobj = re.search(r'<title><!\[CDATA\[(?P<titre>.*?)]]></title>', webpage)
4220 raise ExtractorError(u'Unable to extract title')
4221 video_title = mobj.group(1)
4226 'ext': video_extension,
4227 'title': video_title,
4230 class HowcastIE(InfoExtractor):
4231 """Information Extractor for Howcast.com"""
4232 _VALID_URL = r'(?:https?://)?(?:www\.)?howcast\.com/videos/(?P<id>\d+)'
4234 def _real_extract(self, url):
4235 mobj = re.match(self._VALID_URL, url)
4237 video_id = mobj.group('id')
4238 webpage_url = 'http://www.howcast.com/videos/' + video_id
4239 webpage = self._download_webpage(webpage_url, video_id)
4241 self.report_extraction(video_id)
4243 mobj = re.search(r'\'?file\'?: "(http://mobile-media\.howcast\.com/[0-9]+\.mp4)"', webpage)
4245 raise ExtractorError(u'Unable to extract video URL')
4246 video_url = mobj.group(1)
4248 mobj = re.search(r'<meta content=(?:"([^"]+)"|\'([^\']+)\') property=\'og:title\'', webpage)
4250 raise ExtractorError(u'Unable to extract title')
4251 video_title = mobj.group(1) or mobj.group(2)
4253 mobj = re.search(r'<meta content=(?:"([^"]+)"|\'([^\']+)\') name=\'description\'', webpage)
4255 self._downloader.report_warning(u'unable to extract description')
4256 video_description = None
4258 video_description = mobj.group(1) or mobj.group(2)
4260 mobj = re.search(r'<meta content=\'(.+?)\' property=\'og:image\'', webpage)
4262 raise ExtractorError(u'Unable to extract thumbnail')
4263 thumbnail = mobj.group(1)
4269 'title': video_title,
4270 'description': video_description,
4271 'thumbnail': thumbnail,
4274 class VineIE(InfoExtractor):
4275 """Information Extractor for Vine.co"""
4276 _VALID_URL = r'(?:https?://)?(?:www\.)?vine\.co/v/(?P<id>\w+)'
4278 def _real_extract(self, url):
4280 mobj = re.match(self._VALID_URL, url)
4282 video_id = mobj.group('id')
4283 webpage_url = 'https://vine.co/v/' + video_id
4284 webpage = self._download_webpage(webpage_url, video_id)
4286 self.report_extraction(video_id)
4288 mobj = re.search(r'<meta property="twitter:player:stream" content="(.+?)"', webpage)
4290 raise ExtractorError(u'Unable to extract video URL')
4291 video_url = mobj.group(1)
4293 mobj = re.search(r'<meta property="og:title" content="(.+?)"', webpage)
4295 raise ExtractorError(u'Unable to extract title')
4296 video_title = mobj.group(1)
4298 mobj = re.search(r'<meta property="og:image" content="(.+?)(\?.*?)?"', webpage)
4300 raise ExtractorError(u'Unable to extract thumbnail')
4301 thumbnail = mobj.group(1)
4303 mobj = re.search(r'<div class="user">.*?<h2>(.+?)</h2>', webpage, re.DOTALL)
4305 raise ExtractorError(u'Unable to extract uploader')
4306 uploader = mobj.group(1)
4312 'title': video_title,
4313 'thumbnail': thumbnail,
4314 'uploader': uploader,
4317 class FlickrIE(InfoExtractor):
4318 """Information Extractor for Flickr videos"""
4319 _VALID_URL = r'(?:https?://)?(?:www\.)?flickr\.com/photos/(?P<uploader_id>[\w\-_@]+)/(?P<id>\d+).*'
4321 def _real_extract(self, url):
4322 mobj = re.match(self._VALID_URL, url)
4324 video_id = mobj.group('id')
4325 video_uploader_id = mobj.group('uploader_id')
4326 webpage_url = 'http://www.flickr.com/photos/' + video_uploader_id + '/' + video_id
4327 webpage = self._download_webpage(webpage_url, video_id)
4329 mobj = re.search(r"photo_secret: '(\w+)'", webpage)
4331 raise ExtractorError(u'Unable to extract video secret')
4332 secret = mobj.group(1)
4334 first_url = 'https://secure.flickr.com/apps/video/video_mtl_xml.gne?v=x&photo_id=' + video_id + '&secret=' + secret + '&bitrate=700&target=_self'
4335 first_xml = self._download_webpage(first_url, video_id, 'Downloading first data webpage')
4337 mobj = re.search(r'<Item id="id">(\d+-\d+)</Item>', first_xml)
4339 raise ExtractorError(u'Unable to extract node_id')
4340 node_id = mobj.group(1)
4342 second_url = 'https://secure.flickr.com/video_playlist.gne?node_id=' + node_id + '&tech=flash&mode=playlist&bitrate=700&secret=' + secret + '&rd=video.yahoo.com&noad=1'
4343 second_xml = self._download_webpage(second_url, video_id, 'Downloading second data webpage')
4345 self.report_extraction(video_id)
4347 mobj = re.search(r'<STREAM APP="(.+?)" FULLPATH="(.+?)"', second_xml)
4349 raise ExtractorError(u'Unable to extract video url')
4350 video_url = mobj.group(1) + unescapeHTML(mobj.group(2))
4352 mobj = re.search(r'<meta property="og:title" content=(?:"([^"]+)"|\'([^\']+)\')', webpage)
4354 raise ExtractorError(u'Unable to extract title')
4355 video_title = mobj.group(1) or mobj.group(2)
4357 mobj = re.search(r'<meta property="og:description" content=(?:"([^"]+)"|\'([^\']+)\')', webpage)
4359 self._downloader.report_warning(u'unable to extract description')
4360 video_description = None
4362 video_description = mobj.group(1) or mobj.group(2)
4364 mobj = re.search(r'<meta property="og:image" content=(?:"([^"]+)"|\'([^\']+)\')', webpage)
4366 raise ExtractorError(u'Unable to extract thumbnail')
4367 thumbnail = mobj.group(1) or mobj.group(2)
4373 'title': video_title,
4374 'description': video_description,
4375 'thumbnail': thumbnail,
4376 'uploader_id': video_uploader_id,
4379 class TeamcocoIE(InfoExtractor):
4380 _VALID_URL = r'http://teamcoco\.com/video/(?P<url_title>.*)'
4382 def _real_extract(self, url):
4383 mobj = re.match(self._VALID_URL, url)
4385 raise ExtractorError(u'Invalid URL: %s' % url)
4386 url_title = mobj.group('url_title')
4387 webpage = self._download_webpage(url, url_title)
4389 mobj = re.search(r'<article class="video" data-id="(\d+?)"', webpage)
4390 video_id = mobj.group(1)
4392 self.report_extraction(video_id)
4394 mobj = re.search(r'<meta property="og:title" content="(.+?)"', webpage)
4396 raise ExtractorError(u'Unable to extract title')
4397 video_title = mobj.group(1)
4399 mobj = re.search(r'<meta property="og:image" content="(.+?)"', webpage)
4401 raise ExtractorError(u'Unable to extract thumbnail')
4402 thumbnail = mobj.group(1)
4404 mobj = re.search(r'<meta property="og:description" content="(.*?)"', webpage)
4406 raise ExtractorError(u'Unable to extract description')
4407 description = mobj.group(1)
4409 data_url = 'http://teamcoco.com/cvp/2.0/%s.xml' % video_id
4410 data = self._download_webpage(data_url, video_id, 'Downloading data webpage')
4411 mobj = re.search(r'<file type="high".*?>(.*?)</file>', data)
4413 raise ExtractorError(u'Unable to extract video url')
4414 video_url = mobj.group(1)
4420 'title': video_title,
4421 'thumbnail': thumbnail,
4422 'description': description,
4425 def gen_extractors():
4426 """ Return a list of an instance of every supported extractor.
4427 The order does matter; the first extractor matched is the one handling the URL.
4430 YoutubePlaylistIE(),
4455 StanfordOpenClassroomIE(),
4465 WorldStarHipHopIE(),
4489 def get_info_extractor(ie_name):
4490 """Returns the info extractor class with the given ie_name"""
4491 return globals()[ie_name+'IE']