2 # -*- coding: utf-8 -*-
4 from __future__ import absolute_import
13 import xml.etree.ElementTree
20 class InfoExtractor(object):
21 """Information Extractor class.
23 Information extractors are the classes that, given a URL, extract
24 information about the video (or videos) the URL refers to. This
25 information includes the real video URL, the video title, author and
26 others. The information is stored in a dictionary which is then
27 passed to the FileDownloader. The FileDownloader processes this
28 information possibly downloading the video to the file system, among
29 other possible outcomes.
31 The dictionaries must include the following fields:
35 uploader: Nickname of the video uploader, unescaped.
36 upload_date: Video upload date (YYYYMMDD).
37 title: Video title, unescaped.
38 ext: Video filename extension.
40 The following fields are optional:
42 format: The video format, defaults to ext (used for --get-format)
43 thumbnail: Full URL to a video thumbnail image.
44 description: One-line video description.
45 player_url: SWF Player URL (used for rtmpdump).
46 subtitles: The .srt file contents.
47 urlhandle: [internal] The urlHandle to be used to download the file,
48 like returned by urllib.request.urlopen
50 The fields should all be Unicode strings.
52 Subclasses of this one should re-define the _real_initialize() and
53 _real_extract() methods and define a _VALID_URL regexp.
54 Probably, they should also be added to the list of extractors.
56 _real_extract() must return a *list* of information dictionaries as
59 Finally, the _WORKING attribute should be set to False for broken IEs
60 in order to warn the users and skip the tests.
67 def __init__(self, downloader=None):
68 """Constructor. Receives an optional downloader."""
70 self.set_downloader(downloader)
72 def suitable(self, url):
73 """Receives a URL and returns True if suitable for this IE."""
74 return re.match(self._VALID_URL, url) is not None
77 """Getter method for _WORKING."""
81 """Initializes an instance (authentication, etc)."""
83 self._real_initialize()
86 def extract(self, url):
87 """Extracts URL information and returns it in list of dicts."""
89 return self._real_extract(url)
91 def set_downloader(self, downloader):
92 """Sets the downloader for this IE."""
93 self._downloader = downloader
95 def _real_initialize(self):
96 """Real initialization process. Redefine in subclasses."""
99 def _real_extract(self, url):
100 """Real extraction process. Redefine in subclasses."""
104 class YoutubeIE(InfoExtractor):
105 """Information extractor for youtube.com."""
109 (?:https?://)? # http(s):// (optional)
110 (?:youtu\.be/|(?:\w+\.)?youtube(?:-nocookie)?\.com/|
111 tube\.majestyc\.net/) # the various hostnames, with wildcard subdomains
112 (?:.*?\#/)? # handle anchor (#/) redirect urls
113 (?!view_play_list|my_playlists|artist|playlist) # ignore playlist URLs
114 (?: # the various things that can precede the ID:
115 (?:(?:v|embed|e)/) # v/ or embed/ or e/
116 |(?: # or the v= param in all its forms
117 (?:watch(?:_popup)?(?:\.php)?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
118 (?:\?|\#!?) # the params delimiter ? or # or #!
119 (?:.+&)? # any other preceding param (like /?s=tuff&v=xxxx)
122 )? # optional -> youtube.com/xxxx is OK
123 )? # all until now is optional -> you can pass the naked ID
124 ([0-9A-Za-z_-]+) # here is it! the YouTube video ID
125 (?(1).+)? # if we found the ID, everything can follow
127 _LANG_URL = r'http://www.youtube.com/?hl=en&persist_hl=1&gl=US&persist_gl=1&opt_out_ackd=1'
128 _LOGIN_URL = 'https://www.youtube.com/signup?next=/&gl=US&hl=en'
129 _AGE_URL = 'http://www.youtube.com/verify_age?next_url=/&gl=US&hl=en'
130 _NEXT_URL_RE = r'[\?&]next_url=([^&]+)'
131 _NETRC_MACHINE = 'youtube'
132 # Listed in order of quality
133 _available_formats = ['38', '37', '46', '22', '45', '35', '44', '34', '18', '43', '6', '5', '17', '13']
134 _available_formats_prefer_free = ['38', '46', '37', '45', '22', '44', '35', '43', '34', '18', '6', '5', '17', '13']
135 _video_extensions = {
141 '38': 'video', # You actually don't know if this will be MOV, AVI or whatever
147 _video_dimensions = {
165 def suitable(self, url):
166 """Receives a URL and returns True if suitable for this IE."""
167 return re.match(self._VALID_URL, url, re.VERBOSE) is not None
169 def report_lang(self):
170 """Report attempt to set language."""
171 self._downloader.to_screen(u'[youtube] Setting language')
173 def report_login(self):
174 """Report attempt to log in."""
175 self._downloader.to_screen(u'[youtube] Logging in')
177 def report_age_confirmation(self):
178 """Report attempt to confirm age."""
179 self._downloader.to_screen(u'[youtube] Confirming age')
181 def report_video_webpage_download(self, video_id):
182 """Report attempt to download video webpage."""
183 self._downloader.to_screen(u'[youtube] %s: Downloading video webpage' % video_id)
185 def report_video_info_webpage_download(self, video_id):
186 """Report attempt to download video info webpage."""
187 self._downloader.to_screen(u'[youtube] %s: Downloading video info webpage' % video_id)
189 def report_video_subtitles_download(self, video_id):
190 """Report attempt to download video info webpage."""
191 self._downloader.to_screen(u'[youtube] %s: Downloading video subtitles' % video_id)
193 def report_information_extraction(self, video_id):
194 """Report attempt to extract video information."""
195 self._downloader.to_screen(u'[youtube] %s: Extracting video information' % video_id)
197 def report_unavailable_format(self, video_id, format):
198 """Report extracted video URL."""
199 self._downloader.to_screen(u'[youtube] %s: Format %s not available' % (video_id, format))
201 def report_rtmp_download(self):
202 """Indicate the download will use the RTMP protocol."""
203 self._downloader.to_screen(u'[youtube] RTMP download detected')
205 def _closed_captions_xml_to_srt(self, xml_string):
207 texts = re.findall(r'<text start="([\d\.]+)"( dur="([\d\.]+)")?>([^<]+)</text>', xml_string, re.MULTILINE)
208 # TODO parse xml instead of regex
209 for n, (start, dur_tag, dur, caption) in enumerate(texts):
210 if not dur: dur = '4'
212 end = start + float(dur)
213 start = "%02i:%02i:%02i,%03i" %(start/(60*60), start/60%60, start%60, start%1*1000)
214 end = "%02i:%02i:%02i,%03i" %(end/(60*60), end/60%60, end%60, end%1*1000)
215 caption = unescapeHTML(caption)
216 caption = unescapeHTML(caption) # double cycle, intentional
217 srt += str(n+1) + '\n'
218 srt += start + ' --> ' + end + '\n'
219 srt += caption + '\n\n'
222 def _print_formats(self, formats):
223 print('Available formats:')
225 print('%s\t:\t%s\t[%s]' %(x, self._video_extensions.get(x, 'flv'), self._video_dimensions.get(x, '???')))
227 def _real_initialize(self):
228 if self._downloader is None:
233 downloader_params = self._downloader.params
235 # Attempt to use provided username and password or .netrc data
236 if downloader_params.get('username', None) is not None:
237 username = downloader_params['username']
238 password = downloader_params['password']
239 elif downloader_params.get('usenetrc', False):
241 info = netrc.netrc().authenticators(self._NETRC_MACHINE)
246 raise netrc.NetrcParseError('No authenticators for %s' % self._NETRC_MACHINE)
247 except (IOError, netrc.NetrcParseError) as err:
248 self._downloader.to_stderr(u'WARNING: parsing .netrc: %s' % compat_str(err))
252 request = compat_urllib_request.Request(self._LANG_URL)
255 compat_urllib_request.urlopen(request).read()
256 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
257 self._downloader.to_stderr(u'WARNING: unable to set language: %s' % compat_str(err))
260 # No authentication to be performed
266 'current_form': 'loginForm',
268 'action_login': 'Log In',
269 'username': username,
270 'password': password,
272 request = compat_urllib_request.Request(self._LOGIN_URL, compat_urllib_parse.urlencode(login_form))
275 login_results = compat_urllib_request.urlopen(request).read()
276 if re.search(r'(?i)<form[^>]* name="loginForm"', login_results) is not None:
277 self._downloader.to_stderr(u'WARNING: unable to log in: bad username or password')
279 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
280 self._downloader.to_stderr(u'WARNING: unable to log in: %s' % compat_str(err))
286 'action_confirm': 'Confirm',
288 request = compat_urllib_request.Request(self._AGE_URL, compat_urllib_parse.urlencode(age_form))
290 self.report_age_confirmation()
291 age_results = compat_urllib_request.urlopen(request).read()
292 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
293 self._downloader.trouble(u'ERROR: unable to confirm age: %s' % compat_str(err))
296 def _real_extract(self, url):
297 # Extract original video URL from URL with redirection, like age verification, using next_url parameter
298 mobj = re.search(self._NEXT_URL_RE, url)
300 url = 'http://www.youtube.com/' + compat_urllib_parse.unquote(mobj.group(1)).lstrip('/')
302 # Extract video id from URL
303 mobj = re.match(self._VALID_URL, url, re.VERBOSE)
305 self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
307 video_id = mobj.group(2)
310 self.report_video_webpage_download(video_id)
311 request = compat_urllib_request.Request('http://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1' % video_id)
313 video_webpage_bytes = compat_urllib_request.urlopen(request).read()
314 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
315 self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % compat_str(err))
318 video_webpage = video_webpage_bytes.decode('utf-8', 'ignore')
320 # Attempt to extract SWF player URL
321 mobj = re.search(r'swfConfig.*?"(http:\\/\\/.*?watch.*?-.*?\.swf)"', video_webpage)
323 player_url = re.sub(r'\\(.)', r'\1', mobj.group(1))
328 self.report_video_info_webpage_download(video_id)
329 for el_type in ['&el=embedded', '&el=detailpage', '&el=vevo', '']:
330 video_info_url = ('http://www.youtube.com/get_video_info?&video_id=%s%s&ps=default&eurl=&gl=US&hl=en'
331 % (video_id, el_type))
332 request = compat_urllib_request.Request(video_info_url)
334 video_info_webpage_bytes = compat_urllib_request.urlopen(request).read()
335 video_info_webpage = video_info_webpage_bytes.decode('utf-8', 'ignore')
336 video_info = compat_parse_qs(video_info_webpage)
337 if 'token' in video_info:
339 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
340 self._downloader.trouble(u'ERROR: unable to download video info webpage: %s' % compat_str(err))
342 if 'token' not in video_info:
343 if 'reason' in video_info:
344 self._downloader.trouble(u'ERROR: YouTube said: %s' % video_info['reason'][0])
346 self._downloader.trouble(u'ERROR: "token" parameter not in video info for unknown reason')
349 # Check for "rental" videos
350 if 'ypc_video_rental_bar_text' in video_info and 'author' not in video_info:
351 self._downloader.trouble(u'ERROR: "rental" videos not supported')
354 # Start extracting information
355 self.report_information_extraction(video_id)
358 if 'author' not in video_info:
359 self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
361 video_uploader = compat_urllib_parse.unquote_plus(video_info['author'][0])
364 if 'title' not in video_info:
365 self._downloader.trouble(u'ERROR: unable to extract video title')
367 video_title = compat_urllib_parse.unquote_plus(video_info['title'][0])
370 if 'thumbnail_url' not in video_info:
371 self._downloader.trouble(u'WARNING: unable to extract video thumbnail')
373 else: # don't panic if we can't find it
374 video_thumbnail = compat_urllib_parse.unquote_plus(video_info['thumbnail_url'][0])
378 mobj = re.search(r'id="eow-date.*?>(.*?)</span>', video_webpage, re.DOTALL)
380 upload_date = ' '.join(re.sub(r'[/,-]', r' ', mobj.group(1)).split())
381 format_expressions = ['%d %B %Y', '%B %d %Y', '%b %d %Y']
382 for expression in format_expressions:
384 upload_date = datetime.datetime.strptime(upload_date, expression).strftime('%Y%m%d')
389 video_description = get_element_by_id("eow-description", video_webpage)
390 if video_description:
391 video_description = clean_html(video_description)
393 video_description = ''
396 video_subtitles = None
397 if self._downloader.params.get('writesubtitles', False):
399 self.report_video_subtitles_download(video_id)
400 request = compat_urllib_request.Request('http://video.google.com/timedtext?hl=en&type=list&v=%s' % video_id)
402 srt_list = compat_urllib_request.urlopen(request).read()
403 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
404 raise Trouble(u'WARNING: unable to download video subtitles: %s' % compat_str(err))
405 srt_lang_list = re.findall(r'name="([^"]*)"[^>]+lang_code="([\w\-]+)"', srt_list)
406 srt_lang_list = dict((l[1], l[0]) for l in srt_lang_list)
407 if not srt_lang_list:
408 raise Trouble(u'WARNING: video has no closed captions')
409 if self._downloader.params.get('subtitleslang', False):
410 srt_lang = self._downloader.params.get('subtitleslang')
411 elif 'en' in srt_lang_list:
414 srt_lang = srt_lang_list.keys()[0]
415 if not srt_lang in srt_lang_list:
416 raise Trouble(u'WARNING: no closed captions found in the specified language')
417 request = compat_urllib_request.Request('http://www.youtube.com/api/timedtext?lang=%s&name=%s&v=%s' % (srt_lang, srt_lang_list[srt_lang], video_id))
419 srt_xml = compat_urllib_request.urlopen(request).read()
420 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
421 raise Trouble(u'WARNING: unable to download video subtitles: %s' % compat_str(err))
423 raise Trouble(u'WARNING: unable to download video subtitles')
424 video_subtitles = self._closed_captions_xml_to_srt(srt_xml.decode('utf-8'))
425 except Trouble as trouble:
426 self._downloader.trouble(trouble[0])
428 if 'length_seconds' not in video_info:
429 self._downloader.trouble(u'WARNING: unable to extract video duration')
432 video_duration = compat_urllib_parse.unquote_plus(video_info['length_seconds'][0])
435 video_token = compat_urllib_parse.unquote_plus(video_info['token'][0])
437 # Decide which formats to download
438 req_format = self._downloader.params.get('format', None)
440 if 'conn' in video_info and video_info['conn'][0].startswith('rtmp'):
441 self.report_rtmp_download()
442 video_url_list = [(None, video_info['conn'][0])]
443 elif 'url_encoded_fmt_stream_map' in video_info and len(video_info['url_encoded_fmt_stream_map']) >= 1:
444 url_data_strs = video_info['url_encoded_fmt_stream_map'][0].split(',')
445 url_data = [compat_parse_qs(uds) for uds in url_data_strs]
446 url_data = filter(lambda ud: 'itag' in ud and 'url' in ud, url_data)
447 url_map = dict((ud['itag'][0], ud['url'][0] + '&signature=' + ud['sig'][0]) for ud in url_data)
449 format_limit = self._downloader.params.get('format_limit', None)
450 available_formats = self._available_formats_prefer_free if self._downloader.params.get('prefer_free_formats', False) else self._available_formats
451 if format_limit is not None and format_limit in available_formats:
452 format_list = available_formats[available_formats.index(format_limit):]
454 format_list = available_formats
455 existing_formats = [x for x in format_list if x in url_map]
456 if len(existing_formats) == 0:
457 self._downloader.trouble(u'ERROR: no known formats available for video')
459 if self._downloader.params.get('listformats', None):
460 self._print_formats(existing_formats)
462 if req_format is None or req_format == 'best':
463 video_url_list = [(existing_formats[0], url_map[existing_formats[0]])] # Best quality
464 elif req_format == 'worst':
465 video_url_list = [(existing_formats[len(existing_formats)-1], url_map[existing_formats[len(existing_formats)-1]])] # worst quality
466 elif req_format in ('-1', 'all'):
467 video_url_list = [(f, url_map[f]) for f in existing_formats] # All formats
469 # Specific formats. We pick the first in a slash-delimeted sequence.
470 # For example, if '1/2/3/4' is requested and '2' and '4' are available, we pick '2'.
471 req_formats = req_format.split('/')
472 video_url_list = None
473 for rf in req_formats:
475 video_url_list = [(rf, url_map[rf])]
477 if video_url_list is None:
478 self._downloader.trouble(u'ERROR: requested format not available')
481 self._downloader.trouble(u'ERROR: no conn or url_encoded_fmt_stream_map information found in video info')
485 for format_param, video_real_url in video_url_list:
487 video_extension = self._video_extensions.get(format_param, 'flv')
489 video_format = '{} - {}'.format(format_param if format_param else video_extension,
490 self._video_dimensions.get(format_param, '???'))
494 'url': video_real_url,
495 'uploader': video_uploader,
496 'upload_date': upload_date,
497 'title': video_title,
498 'ext': video_extension,
499 'format': video_format,
500 'thumbnail': video_thumbnail,
501 'description': video_description,
502 'player_url': player_url,
503 'subtitles': video_subtitles,
504 'duration': video_duration
509 class MetacafeIE(InfoExtractor):
510 """Information Extractor for metacafe.com."""
512 _VALID_URL = r'(?:http://)?(?:www\.)?metacafe\.com/watch/([^/]+)/([^/]+)/.*'
513 _DISCLAIMER = 'http://www.metacafe.com/family_filter/'
514 _FILTER_POST = 'http://www.metacafe.com/f/index.php?inputType=filter&controllerGroup=user'
515 IE_NAME = u'metacafe'
517 def __init__(self, downloader=None):
518 InfoExtractor.__init__(self, downloader)
520 def report_disclaimer(self):
521 """Report disclaimer retrieval."""
522 self._downloader.to_screen(u'[metacafe] Retrieving disclaimer')
524 def report_age_confirmation(self):
525 """Report attempt to confirm age."""
526 self._downloader.to_screen(u'[metacafe] Confirming age')
528 def report_download_webpage(self, video_id):
529 """Report webpage download."""
530 self._downloader.to_screen(u'[metacafe] %s: Downloading webpage' % video_id)
532 def report_extraction(self, video_id):
533 """Report information extraction."""
534 self._downloader.to_screen(u'[metacafe] %s: Extracting information' % video_id)
536 def _real_initialize(self):
537 # Retrieve disclaimer
538 request = compat_urllib_request.Request(self._DISCLAIMER)
540 self.report_disclaimer()
541 disclaimer = compat_urllib_request.urlopen(request).read()
542 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
543 self._downloader.trouble(u'ERROR: unable to retrieve disclaimer: %s' % compat_str(err))
549 'submit': "Continue - I'm over 18",
551 request = compat_urllib_request.Request(self._FILTER_POST, compat_urllib_parse.urlencode(disclaimer_form))
553 self.report_age_confirmation()
554 disclaimer = compat_urllib_request.urlopen(request).read()
555 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
556 self._downloader.trouble(u'ERROR: unable to confirm age: %s' % compat_str(err))
559 def _real_extract(self, url):
560 # Extract id and simplified title from URL
561 mobj = re.match(self._VALID_URL, url)
563 self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
566 video_id = mobj.group(1)
568 # Check if video comes from YouTube
569 mobj2 = re.match(r'^yt-(.*)$', video_id)
570 if mobj2 is not None:
571 self._downloader.download(['http://www.youtube.com/watch?v=%s' % mobj2.group(1)])
574 # Retrieve video webpage to extract further information
575 request = compat_urllib_request.Request('http://www.metacafe.com/watch/%s/' % video_id)
577 self.report_download_webpage(video_id)
578 webpage = compat_urllib_request.urlopen(request).read()
579 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
580 self._downloader.trouble(u'ERROR: unable retrieve video webpage: %s' % compat_str(err))
583 # Extract URL, uploader and title from webpage
584 self.report_extraction(video_id)
585 mobj = re.search(r'(?m)&mediaURL=([^&]+)', webpage)
587 mediaURL = compat_urllib_parse.unquote(mobj.group(1))
588 video_extension = mediaURL[-3:]
590 # Extract gdaKey if available
591 mobj = re.search(r'(?m)&gdaKey=(.*?)&', webpage)
595 gdaKey = mobj.group(1)
596 video_url = '%s?__gda__=%s' % (mediaURL, gdaKey)
598 mobj = re.search(r' name="flashvars" value="(.*?)"', webpage)
600 self._downloader.trouble(u'ERROR: unable to extract media URL')
602 vardict = compat_parse_qs(mobj.group(1))
603 if 'mediaData' not in vardict:
604 self._downloader.trouble(u'ERROR: unable to extract media URL')
606 mobj = re.search(r'"mediaURL":"(http.*?)","key":"(.*?)"', vardict['mediaData'][0])
608 self._downloader.trouble(u'ERROR: unable to extract media URL')
610 mediaURL = mobj.group(1).replace('\\/', '/')
611 video_extension = mediaURL[-3:]
612 video_url = '%s?__gda__=%s' % (mediaURL, mobj.group(2))
614 mobj = re.search(r'(?im)<title>(.*) - Video</title>', webpage)
616 self._downloader.trouble(u'ERROR: unable to extract title')
618 video_title = mobj.group(1).decode('utf-8')
620 mobj = re.search(r'submitter=(.*?);', webpage)
622 self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
624 video_uploader = mobj.group(1)
627 'id': video_id.decode('utf-8'),
628 'url': video_url.decode('utf-8'),
629 'uploader': video_uploader.decode('utf-8'),
631 'title': video_title,
632 'ext': video_extension.decode('utf-8'),
636 class DailymotionIE(InfoExtractor):
637 """Information Extractor for Dailymotion"""
639 _VALID_URL = r'(?i)(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/video/([^/]+)'
640 IE_NAME = u'dailymotion'
642 def __init__(self, downloader=None):
643 InfoExtractor.__init__(self, downloader)
645 def report_download_webpage(self, video_id):
646 """Report webpage download."""
647 self._downloader.to_screen(u'[dailymotion] %s: Downloading webpage' % video_id)
649 def report_extraction(self, video_id):
650 """Report information extraction."""
651 self._downloader.to_screen(u'[dailymotion] %s: Extracting information' % video_id)
653 def _real_extract(self, url):
654 # Extract id and simplified title from URL
655 mobj = re.match(self._VALID_URL, url)
657 self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
660 video_id = mobj.group(1).split('_')[0].split('?')[0]
662 video_extension = 'mp4'
664 # Retrieve video webpage to extract further information
665 request = compat_urllib_request.Request(url)
666 request.add_header('Cookie', 'family_filter=off')
668 self.report_download_webpage(video_id)
669 webpage = compat_urllib_request.urlopen(request).read()
670 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
671 self._downloader.trouble(u'ERROR: unable retrieve video webpage: %s' % compat_str(err))
674 # Extract URL, uploader and title from webpage
675 self.report_extraction(video_id)
676 mobj = re.search(r'\s*var flashvars = (.*)', webpage)
678 self._downloader.trouble(u'ERROR: unable to extract media URL')
680 flashvars = compat_urllib_parse.unquote(mobj.group(1))
682 for key in ['hd1080URL', 'hd720URL', 'hqURL', 'sdURL', 'ldURL', 'video_url']:
685 self._downloader.to_screen(u'[dailymotion] Using %s' % key)
688 self._downloader.trouble(u'ERROR: unable to extract video URL')
691 mobj = re.search(r'"' + max_quality + r'":"(.+?)"', flashvars)
693 self._downloader.trouble(u'ERROR: unable to extract video URL')
696 video_url = compat_urllib_parse.unquote(mobj.group(1)).replace('\\/', '/')
698 # TODO: support choosing qualities
700 mobj = re.search(r'<meta property="og:title" content="(?P<title>[^"]*)" />', webpage)
702 self._downloader.trouble(u'ERROR: unable to extract title')
704 video_title = unescapeHTML(mobj.group('title').decode('utf-8'))
706 video_uploader = None
707 mobj = re.search(r'(?im)<span class="owner[^\"]+?">[^<]+?<a [^>]+?>([^<]+?)</a>', webpage)
709 # lookin for official user
710 mobj_official = re.search(r'<span rel="author"[^>]+?>([^<]+?)</span>', webpage)
711 if mobj_official is None:
712 self._downloader.trouble(u'WARNING: unable to extract uploader nickname')
714 video_uploader = mobj_official.group(1)
716 video_uploader = mobj.group(1)
718 video_upload_date = None
719 mobj = re.search(r'<div class="[^"]*uploaded_cont[^"]*" title="[^"]*">([0-9]{2})-([0-9]{2})-([0-9]{4})</div>', webpage)
721 video_upload_date = mobj.group(3) + mobj.group(2) + mobj.group(1)
724 'id': video_id.decode('utf-8'),
725 'url': video_url.decode('utf-8'),
726 'uploader': video_uploader.decode('utf-8'),
727 'upload_date': video_upload_date,
728 'title': video_title,
729 'ext': video_extension.decode('utf-8'),
733 class GoogleIE(InfoExtractor):
734 """Information extractor for video.google.com."""
736 _VALID_URL = r'(?:http://)?video\.google\.(?:com(?:\.au)?|co\.(?:uk|jp|kr|cr)|ca|de|es|fr|it|nl|pl)/videoplay\?docid=([^\&]+).*'
737 IE_NAME = u'video.google'
739 def __init__(self, downloader=None):
740 InfoExtractor.__init__(self, downloader)
742 def report_download_webpage(self, video_id):
743 """Report webpage download."""
744 self._downloader.to_screen(u'[video.google] %s: Downloading webpage' % video_id)
746 def report_extraction(self, video_id):
747 """Report information extraction."""
748 self._downloader.to_screen(u'[video.google] %s: Extracting information' % video_id)
750 def _real_extract(self, url):
751 # Extract id from URL
752 mobj = re.match(self._VALID_URL, url)
754 self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
757 video_id = mobj.group(1)
759 video_extension = 'mp4'
761 # Retrieve video webpage to extract further information
762 request = compat_urllib_request.Request('http://video.google.com/videoplay?docid=%s&hl=en&oe=utf-8' % video_id)
764 self.report_download_webpage(video_id)
765 webpage = compat_urllib_request.urlopen(request).read()
766 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
767 self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err))
770 # Extract URL, uploader, and title from webpage
771 self.report_extraction(video_id)
772 mobj = re.search(r"download_url:'([^']+)'", webpage)
774 video_extension = 'flv'
775 mobj = re.search(r"(?i)videoUrl\\x3d(.+?)\\x26", webpage)
777 self._downloader.trouble(u'ERROR: unable to extract media URL')
779 mediaURL = compat_urllib_parse.unquote(mobj.group(1))
780 mediaURL = mediaURL.replace('\\x3d', '\x3d')
781 mediaURL = mediaURL.replace('\\x26', '\x26')
785 mobj = re.search(r'<title>(.*)</title>', webpage)
787 self._downloader.trouble(u'ERROR: unable to extract title')
789 video_title = mobj.group(1).decode('utf-8')
791 # Extract video description
792 mobj = re.search(r'<span id=short-desc-content>([^<]*)</span>', webpage)
794 self._downloader.trouble(u'ERROR: unable to extract video description')
796 video_description = mobj.group(1).decode('utf-8')
797 if not video_description:
798 video_description = 'No description available.'
800 # Extract video thumbnail
801 if self._downloader.params.get('forcethumbnail', False):
802 request = compat_urllib_request.Request('http://video.google.com/videosearch?q=%s+site:video.google.com&hl=en' % abs(int(video_id)))
804 webpage = compat_urllib_request.urlopen(request).read()
805 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
806 self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err))
808 mobj = re.search(r'<img class=thumbnail-img (?:.* )?src=(http.*)>', webpage)
810 self._downloader.trouble(u'ERROR: unable to extract video thumbnail')
812 video_thumbnail = mobj.group(1)
813 else: # we need something to pass to process_info
817 'id': video_id.decode('utf-8'),
818 'url': video_url.decode('utf-8'),
821 'title': video_title,
822 'ext': video_extension.decode('utf-8'),
826 class PhotobucketIE(InfoExtractor):
827 """Information extractor for photobucket.com."""
829 _VALID_URL = r'(?:http://)?(?:[a-z0-9]+\.)?photobucket\.com/.*[\?\&]current=(.*\.flv)'
830 IE_NAME = u'photobucket'
832 def __init__(self, downloader=None):
833 InfoExtractor.__init__(self, downloader)
835 def report_download_webpage(self, video_id):
836 """Report webpage download."""
837 self._downloader.to_screen(u'[photobucket] %s: Downloading webpage' % video_id)
839 def report_extraction(self, video_id):
840 """Report information extraction."""
841 self._downloader.to_screen(u'[photobucket] %s: Extracting information' % video_id)
843 def _real_extract(self, url):
844 # Extract id from URL
845 mobj = re.match(self._VALID_URL, url)
847 self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
850 video_id = mobj.group(1)
852 video_extension = 'flv'
854 # Retrieve video webpage to extract further information
855 request = compat_urllib_request.Request(url)
857 self.report_download_webpage(video_id)
858 webpage = compat_urllib_request.urlopen(request).read()
859 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
860 self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err))
863 # Extract URL, uploader, and title from webpage
864 self.report_extraction(video_id)
865 mobj = re.search(r'<link rel="video_src" href=".*\?file=([^"]+)" />', webpage)
867 self._downloader.trouble(u'ERROR: unable to extract media URL')
869 mediaURL = compat_urllib_parse.unquote(mobj.group(1))
873 mobj = re.search(r'<title>(.*) video by (.*) - Photobucket</title>', webpage)
875 self._downloader.trouble(u'ERROR: unable to extract title')
877 video_title = mobj.group(1).decode('utf-8')
879 video_uploader = mobj.group(2).decode('utf-8')
882 'id': video_id.decode('utf-8'),
883 'url': video_url.decode('utf-8'),
884 'uploader': video_uploader,
886 'title': video_title,
887 'ext': video_extension.decode('utf-8'),
891 class YahooIE(InfoExtractor):
892 """Information extractor for video.yahoo.com."""
894 # _VALID_URL matches all Yahoo! Video URLs
895 # _VPAGE_URL matches only the extractable '/watch/' URLs
896 _VALID_URL = r'(?:http://)?(?:[a-z]+\.)?video\.yahoo\.com/(?:watch|network)/([0-9]+)(?:/|\?v=)([0-9]+)(?:[#\?].*)?'
897 _VPAGE_URL = r'(?:http://)?video\.yahoo\.com/watch/([0-9]+)/([0-9]+)(?:[#\?].*)?'
898 IE_NAME = u'video.yahoo'
900 def __init__(self, downloader=None):
901 InfoExtractor.__init__(self, downloader)
903 def report_download_webpage(self, video_id):
904 """Report webpage download."""
905 self._downloader.to_screen(u'[video.yahoo] %s: Downloading webpage' % video_id)
907 def report_extraction(self, video_id):
908 """Report information extraction."""
909 self._downloader.to_screen(u'[video.yahoo] %s: Extracting information' % video_id)
911 def _real_extract(self, url, new_video=True):
912 # Extract ID from URL
913 mobj = re.match(self._VALID_URL, url)
915 self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
918 video_id = mobj.group(2)
919 video_extension = 'flv'
921 # Rewrite valid but non-extractable URLs as
922 # extractable English language /watch/ URLs
923 if re.match(self._VPAGE_URL, url) is None:
924 request = compat_urllib_request.Request(url)
926 webpage = compat_urllib_request.urlopen(request).read()
927 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
928 self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err))
931 mobj = re.search(r'\("id", "([0-9]+)"\);', webpage)
933 self._downloader.trouble(u'ERROR: Unable to extract id field')
935 yahoo_id = mobj.group(1)
937 mobj = re.search(r'\("vid", "([0-9]+)"\);', webpage)
939 self._downloader.trouble(u'ERROR: Unable to extract vid field')
941 yahoo_vid = mobj.group(1)
943 url = 'http://video.yahoo.com/watch/%s/%s' % (yahoo_vid, yahoo_id)
944 return self._real_extract(url, new_video=False)
946 # Retrieve video webpage to extract further information
947 request = compat_urllib_request.Request(url)
949 self.report_download_webpage(video_id)
950 webpage = compat_urllib_request.urlopen(request).read()
951 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
952 self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err))
955 # Extract uploader and title from webpage
956 self.report_extraction(video_id)
957 mobj = re.search(r'<meta name="title" content="(.*)" />', webpage)
959 self._downloader.trouble(u'ERROR: unable to extract video title')
961 video_title = mobj.group(1).decode('utf-8')
963 mobj = re.search(r'<h2 class="ti-5"><a href="http://video\.yahoo\.com/(people|profile)/[0-9]+" beacon=".*">(.*)</a></h2>', webpage)
965 self._downloader.trouble(u'ERROR: unable to extract video uploader')
967 video_uploader = mobj.group(1).decode('utf-8')
969 # Extract video thumbnail
970 mobj = re.search(r'<link rel="image_src" href="(.*)" />', webpage)
972 self._downloader.trouble(u'ERROR: unable to extract video thumbnail')
974 video_thumbnail = mobj.group(1).decode('utf-8')
976 # Extract video description
977 mobj = re.search(r'<meta name="description" content="(.*)" />', webpage)
979 self._downloader.trouble(u'ERROR: unable to extract video description')
981 video_description = mobj.group(1).decode('utf-8')
982 if not video_description:
983 video_description = 'No description available.'
985 # Extract video height and width
986 mobj = re.search(r'<meta name="video_height" content="([0-9]+)" />', webpage)
988 self._downloader.trouble(u'ERROR: unable to extract video height')
990 yv_video_height = mobj.group(1)
992 mobj = re.search(r'<meta name="video_width" content="([0-9]+)" />', webpage)
994 self._downloader.trouble(u'ERROR: unable to extract video width')
996 yv_video_width = mobj.group(1)
998 # Retrieve video playlist to extract media URL
999 # I'm not completely sure what all these options are, but we
1000 # seem to need most of them, otherwise the server sends a 401.
1001 yv_lg = 'R0xx6idZnW2zlrKP8xxAIR' # not sure what this represents
1002 yv_bitrate = '700' # according to Wikipedia this is hard-coded
1003 request = compat_urllib_request.Request('http://cosmos.bcst.yahoo.com/up/yep/process/getPlaylistFOP.php?node_id=' + video_id +
1004 '&tech=flash&mode=playlist&lg=' + yv_lg + '&bitrate=' + yv_bitrate + '&vidH=' + yv_video_height +
1005 '&vidW=' + yv_video_width + '&swf=as3&rd=video.yahoo.com&tk=null&adsupported=v1,v2,&eventid=1301797')
1007 self.report_download_webpage(video_id)
1008 webpage = compat_urllib_request.urlopen(request).read()
1009 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
1010 self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err))
1013 # Extract media URL from playlist XML
1014 mobj = re.search(r'<STREAM APP="(http://.*)" FULLPATH="/?(/.*\.flv\?[^"]*)"', webpage)
1016 self._downloader.trouble(u'ERROR: Unable to extract media URL')
1018 video_url = compat_urllib_parse.unquote(mobj.group(1) + mobj.group(2)).decode('utf-8')
1019 video_url = unescapeHTML(video_url)
1022 'id': video_id.decode('utf-8'),
1024 'uploader': video_uploader,
1025 'upload_date': None,
1026 'title': video_title,
1027 'ext': video_extension.decode('utf-8'),
1028 'thumbnail': video_thumbnail.decode('utf-8'),
1029 'description': video_description,
1033 class VimeoIE(InfoExtractor):
1034 """Information extractor for vimeo.com."""
1036 # _VALID_URL matches Vimeo URLs
1037 _VALID_URL = r'(?:https?://)?(?:(?:www|player).)?vimeo\.com/(?:(?:groups|album)/[^/]+/)?(?:videos?/)?([0-9]+)'
1040 def __init__(self, downloader=None):
1041 InfoExtractor.__init__(self, downloader)
1043 def report_download_webpage(self, video_id):
1044 """Report webpage download."""
1045 self._downloader.to_screen(u'[vimeo] %s: Downloading webpage' % video_id)
1047 def report_extraction(self, video_id):
1048 """Report information extraction."""
1049 self._downloader.to_screen(u'[vimeo] %s: Extracting information' % video_id)
1051 def _real_extract(self, url, new_video=True):
1052 # Extract ID from URL
1053 mobj = re.match(self._VALID_URL, url)
1055 self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
1058 video_id = mobj.group(1)
1060 # Retrieve video webpage to extract further information
1061 request = compat_urllib_request.Request(url, None, std_headers)
1063 self.report_download_webpage(video_id)
1064 webpage = compat_urllib_request.urlopen(request).read()
1065 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
1066 self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err))
1069 # Now we begin extracting as much information as we can from what we
1070 # retrieved. First we extract the information common to all extractors,
1071 # and latter we extract those that are Vimeo specific.
1072 self.report_extraction(video_id)
1074 # Extract the config JSON
1075 config = webpage.split(' = {config:')[1].split(',assets:')[0]
1077 config = json.loads(config)
1079 self._downloader.trouble(u'ERROR: unable to extract info section')
1083 video_title = config["video"]["title"]
1086 video_uploader = config["video"]["owner"]["name"]
1088 # Extract video thumbnail
1089 video_thumbnail = config["video"]["thumbnail"]
1091 # Extract video description
1092 video_description = get_element_by_id("description", webpage.decode('utf8'))
1093 if video_description: video_description = clean_html(video_description)
1094 else: video_description = ''
1096 # Extract upload date
1097 video_upload_date = None
1098 mobj = re.search(r'<span id="clip-date" style="display:none">[^:]*: (.*?)( \([^\(]*\))?</span>', webpage)
1099 if mobj is not None:
1100 video_upload_date = mobj.group(1)
1102 # Vimeo specific: extract request signature and timestamp
1103 sig = config['request']['signature']
1104 timestamp = config['request']['timestamp']
1106 # Vimeo specific: extract video codec and quality information
1107 # First consider quality, then codecs, then take everything
1108 # TODO bind to format param
1109 codecs = [('h264', 'mp4'), ('vp8', 'flv'), ('vp6', 'flv')]
1110 files = { 'hd': [], 'sd': [], 'other': []}
1111 for codec_name, codec_extension in codecs:
1112 if codec_name in config["video"]["files"]:
1113 if 'hd' in config["video"]["files"][codec_name]:
1114 files['hd'].append((codec_name, codec_extension, 'hd'))
1115 elif 'sd' in config["video"]["files"][codec_name]:
1116 files['sd'].append((codec_name, codec_extension, 'sd'))
1118 files['other'].append((codec_name, codec_extension, config["video"]["files"][codec_name][0]))
1120 for quality in ('hd', 'sd', 'other'):
1121 if len(files[quality]) > 0:
1122 video_quality = files[quality][0][2]
1123 video_codec = files[quality][0][0]
1124 video_extension = files[quality][0][1]
1125 self._downloader.to_screen(u'[vimeo] %s: Downloading %s file at %s quality' % (video_id, video_codec.upper(), video_quality))
1128 self._downloader.trouble(u'ERROR: no known codec found')
1131 video_url = "http://player.vimeo.com/play_redirect?clip_id=%s&sig=%s&time=%s&quality=%s&codecs=%s&type=moogaloop_local&embed_location=" \
1132 %(video_id, sig, timestamp, video_quality, video_codec.upper())
1137 'uploader': video_uploader,
1138 'upload_date': video_upload_date,
1139 'title': video_title,
1140 'ext': video_extension,
1141 'thumbnail': video_thumbnail,
1142 'description': video_description,
1146 class ArteTvIE(InfoExtractor):
1147 """arte.tv information extractor."""
1149 _VALID_URL = r'(?:http://)?videos\.arte\.tv/(?:fr|de)/videos/.*'
1150 _LIVE_URL = r'index-[0-9]+\.html$'
1152 IE_NAME = u'arte.tv'
1154 def __init__(self, downloader=None):
1155 InfoExtractor.__init__(self, downloader)
1157 def report_download_webpage(self, video_id):
1158 """Report webpage download."""
1159 self._downloader.to_screen(u'[arte.tv] %s: Downloading webpage' % video_id)
1161 def report_extraction(self, video_id):
1162 """Report information extraction."""
1163 self._downloader.to_screen(u'[arte.tv] %s: Extracting information' % video_id)
1165 def fetch_webpage(self, url):
1166 self._downloader.increment_downloads()
1167 request = compat_urllib_request.Request(url)
1169 self.report_download_webpage(url)
1170 webpage = compat_urllib_request.urlopen(request).read()
1171 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
1172 self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err))
1174 except ValueError as err:
1175 self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
1179 def grep_webpage(self, url, regex, regexFlags, matchTuples):
1180 page = self.fetch_webpage(url)
1181 mobj = re.search(regex, page, regexFlags)
1185 self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
1188 for (i, key, err) in matchTuples:
1189 if mobj.group(i) is None:
1190 self._downloader.trouble(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'ERROR: 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'ERROR: could not extract video path: %s' % url),
1217 (2, 'player', u'ERROR: could not extract video player: %s' % url),
1218 (3, 'url', u'ERROR: 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'ERROR: 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'ERROR: 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'ERROR: could not extract video id: %s' % url),
1253 (2, 'title', u'ERROR: could not extract video title: %s' % url),
1254 (3, 'date', u'ERROR: could not extract video date: %s' % url),
1255 (4, 'url', u'ERROR: 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': info.get('date'),
1264 'title': info.get('title'),
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 __init__(self, downloader=None):
1290 InfoExtractor.__init__(self, downloader)
1292 def report_download_webpage(self, video_id):
1293 """Report webpage download."""
1294 self._downloader.to_screen(u'WARNING: Falling back on generic information extractor.')
1295 self._downloader.to_screen(u'[generic] %s: Downloading webpage' % video_id)
1297 def report_extraction(self, video_id):
1298 """Report information extraction."""
1299 self._downloader.to_screen(u'[generic] %s: Extracting information' % video_id)
1301 def report_following_redirect(self, new_url):
1302 """Report information extraction."""
1303 self._downloader.to_screen(u'[redirect] Following redirect to %s' % new_url)
1305 def _test_redirect(self, url):
1306 """Check if it is a redirect, like url shorteners, in case restart chain."""
1307 class HeadRequest(compat_urllib_request.Request):
1308 def get_method(self):
1311 class HEADRedirectHandler(compat_urllib_request.HTTPRedirectHandler):
1313 Subclass the HTTPRedirectHandler to make it use our
1314 HeadRequest also on the redirected URL
1316 def redirect_request(self, req, fp, code, msg, headers, newurl):
1317 if code in (301, 302, 303, 307):
1318 newurl = newurl.replace(' ', '%20')
1319 newheaders = dict((k,v) for k,v in req.headers.items()
1320 if k.lower() not in ("content-length", "content-type"))
1321 return HeadRequest(newurl,
1323 origin_req_host=req.get_origin_req_host(),
1326 raise compat_urllib_error.HTTPError(req.get_full_url(), code, msg, headers, fp)
1328 class HTTPMethodFallback(compat_urllib_request.BaseHandler):
1330 Fallback to GET if HEAD is not allowed (405 HTTP error)
1332 def http_error_405(self, req, fp, code, msg, headers):
1336 newheaders = dict((k,v) for k,v in req.headers.items()
1337 if k.lower() not in ("content-length", "content-type"))
1338 return self.parent.open(compat_urllib_request.Request(req.get_full_url(),
1340 origin_req_host=req.get_origin_req_host(),
1344 opener = compat_urllib_request.OpenerDirector()
1345 for handler in [compat_urllib_request.HTTPHandler, compat_urllib_request.HTTPDefaultErrorHandler,
1346 HTTPMethodFallback, HEADRedirectHandler,
1347 compat_urllib_error.HTTPErrorProcessor, compat_urllib_request.HTTPSHandler]:
1348 opener.add_handler(handler())
1350 response = opener.open(HeadRequest(url))
1351 new_url = response.geturl()
1356 self.report_following_redirect(new_url)
1357 self._downloader.download([new_url])
1360 def _real_extract(self, url):
1361 if self._test_redirect(url): return
1363 video_id = url.split('/')[-1]
1364 request = compat_urllib_request.Request(url)
1366 self.report_download_webpage(video_id)
1367 webpage = compat_urllib_request.urlopen(request).read()
1368 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
1369 self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err))
1371 except ValueError as err:
1372 # since this is the last-resort InfoExtractor, if
1373 # this error is thrown, it'll be thrown here
1374 self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
1377 self.report_extraction(video_id)
1378 # Start with something easy: JW Player in SWFObject
1379 mobj = re.search(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage)
1381 # Broaden the search a little bit
1382 mobj = re.search(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage)
1384 self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
1387 # It's possible that one of the regexes
1388 # matched, but returned an empty group:
1389 if mobj.group(1) is None:
1390 self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
1393 video_url = compat_urllib_parse.unquote(mobj.group(1))
1394 video_id = os.path.basename(video_url)
1396 # here's a fun little line of code for you:
1397 video_extension = os.path.splitext(video_id)[1][1:]
1398 video_id = os.path.splitext(video_id)[0]
1400 # it's tempting to parse this further, but you would
1401 # have to take into account all the variations like
1402 # Video Title - Site Name
1403 # Site Name | Video Title
1404 # Video Title - Tagline | Site Name
1405 # and so on and so forth; it's just not practical
1406 mobj = re.search(r'<title>(.*)</title>', webpage)
1408 self._downloader.trouble(u'ERROR: unable to extract title')
1410 video_title = mobj.group(1).decode('utf-8')
1412 # video uploader is domain name
1413 mobj = re.match(r'(?:https?://)?([^/]*)/.*', url)
1415 self._downloader.trouble(u'ERROR: unable to extract title')
1417 video_uploader = mobj.group(1).decode('utf-8')
1420 'id': video_id.decode('utf-8'),
1421 'url': video_url.decode('utf-8'),
1422 'uploader': video_uploader,
1423 'upload_date': None,
1424 'title': video_title,
1425 'ext': video_extension.decode('utf-8'),
1429 class YoutubeSearchIE(InfoExtractor):
1430 """Information Extractor for YouTube search queries."""
1431 _VALID_URL = r'ytsearch(\d+|all)?:[\s\S]+'
1432 _API_URL = 'https://gdata.youtube.com/feeds/api/videos?q=%s&start-index=%i&max-results=50&v=2&alt=jsonc'
1433 _max_youtube_results = 1000
1434 IE_NAME = u'youtube:search'
1436 def __init__(self, downloader=None):
1437 InfoExtractor.__init__(self, downloader)
1439 def report_download_page(self, query, pagenum):
1440 """Report attempt to download search page with given number."""
1441 query = query.decode(preferredencoding())
1442 self._downloader.to_screen(u'[youtube] query "%s": Downloading page %s' % (query, pagenum))
1444 def _real_extract(self, query):
1445 mobj = re.match(self._VALID_URL, query)
1447 self._downloader.trouble(u'ERROR: invalid search query "%s"' % query)
1450 prefix, query = query.split(':')
1452 query = query.encode('utf-8')
1454 self._download_n_results(query, 1)
1456 elif prefix == 'all':
1457 self._download_n_results(query, self._max_youtube_results)
1463 self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query))
1465 elif n > self._max_youtube_results:
1466 self._downloader.to_stderr(u'WARNING: ytsearch returns max %i results (you requested %i)' % (self._max_youtube_results, n))
1467 n = self._max_youtube_results
1468 self._download_n_results(query, n)
1470 except ValueError: # parsing prefix as integer fails
1471 self._download_n_results(query, 1)
1474 def _download_n_results(self, query, n):
1475 """Downloads a specified number of results for a query"""
1481 while (50 * pagenum) < limit:
1482 self.report_download_page(query, pagenum+1)
1483 result_url = self._API_URL % (compat_urllib_parse.quote_plus(query), (50*pagenum)+1)
1484 request = compat_urllib_request.Request(result_url)
1486 data = compat_urllib_request.urlopen(request).read()
1487 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
1488 self._downloader.trouble(u'ERROR: unable to download API page: %s' % compat_str(err))
1490 api_response = json.loads(data)['data']
1492 new_ids = list(video['id'] for video in api_response['items'])
1493 video_ids += new_ids
1495 limit = min(n, api_response['totalItems'])
1498 if len(video_ids) > n:
1499 video_ids = video_ids[:n]
1500 for id in video_ids:
1501 self._downloader.download(['http://www.youtube.com/watch?v=%s' % id])
1505 class GoogleSearchIE(InfoExtractor):
1506 """Information Extractor for Google Video search queries."""
1507 _VALID_URL = r'gvsearch(\d+|all)?:[\s\S]+'
1508 _TEMPLATE_URL = 'http://video.google.com/videosearch?q=%s+site:video.google.com&start=%s&hl=en'
1509 _VIDEO_INDICATOR = r'<a href="http://video\.google\.com/videoplay\?docid=([^"\&]+)'
1510 _MORE_PAGES_INDICATOR = r'class="pn" id="pnnext"'
1511 _max_google_results = 1000
1512 IE_NAME = u'video.google:search'
1514 def __init__(self, downloader=None):
1515 InfoExtractor.__init__(self, downloader)
1517 def report_download_page(self, query, pagenum):
1518 """Report attempt to download playlist page with given number."""
1519 query = query.decode(preferredencoding())
1520 self._downloader.to_screen(u'[video.google] query "%s": Downloading page %s' % (query, pagenum))
1522 def _real_extract(self, query):
1523 mobj = re.match(self._VALID_URL, query)
1525 self._downloader.trouble(u'ERROR: invalid search query "%s"' % query)
1528 prefix, query = query.split(':')
1530 query = query.encode('utf-8')
1532 self._download_n_results(query, 1)
1534 elif prefix == 'all':
1535 self._download_n_results(query, self._max_google_results)
1541 self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query))
1543 elif n > self._max_google_results:
1544 self._downloader.to_stderr(u'WARNING: gvsearch returns max %i results (you requested %i)' % (self._max_google_results, n))
1545 n = self._max_google_results
1546 self._download_n_results(query, n)
1548 except ValueError: # parsing prefix as integer fails
1549 self._download_n_results(query, 1)
1552 def _download_n_results(self, query, n):
1553 """Downloads a specified number of results for a query"""
1559 self.report_download_page(query, pagenum)
1560 result_url = self._TEMPLATE_URL % (compat_urllib_parse.quote_plus(query), pagenum*10)
1561 request = compat_urllib_request.Request(result_url)
1563 page = compat_urllib_request.urlopen(request).read()
1564 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
1565 self._downloader.trouble(u'ERROR: unable to download webpage: %s' % compat_str(err))
1568 # Extract video identifiers
1569 for mobj in re.finditer(self._VIDEO_INDICATOR, page):
1570 video_id = mobj.group(1)
1571 if video_id not in video_ids:
1572 video_ids.append(video_id)
1573 if len(video_ids) == n:
1574 # Specified n videos reached
1575 for id in video_ids:
1576 self._downloader.download(['http://video.google.com/videoplay?docid=%s' % id])
1579 if re.search(self._MORE_PAGES_INDICATOR, page) is None:
1580 for id in video_ids:
1581 self._downloader.download(['http://video.google.com/videoplay?docid=%s' % id])
1584 pagenum = pagenum + 1
1587 class YahooSearchIE(InfoExtractor):
1588 """Information Extractor for Yahoo! Video search queries."""
1589 _VALID_URL = r'yvsearch(\d+|all)?:[\s\S]+'
1590 _TEMPLATE_URL = 'http://video.yahoo.com/search/?p=%s&o=%s'
1591 _VIDEO_INDICATOR = r'href="http://video\.yahoo\.com/watch/([0-9]+/[0-9]+)"'
1592 _MORE_PAGES_INDICATOR = r'\s*Next'
1593 _max_yahoo_results = 1000
1594 IE_NAME = u'video.yahoo:search'
1596 def __init__(self, downloader=None):
1597 InfoExtractor.__init__(self, downloader)
1599 def report_download_page(self, query, pagenum):
1600 """Report attempt to download playlist page with given number."""
1601 query = query.decode(preferredencoding())
1602 self._downloader.to_screen(u'[video.yahoo] query "%s": Downloading page %s' % (query, pagenum))
1604 def _real_extract(self, query):
1605 mobj = re.match(self._VALID_URL, query)
1607 self._downloader.trouble(u'ERROR: invalid search query "%s"' % query)
1610 prefix, query = query.split(':')
1612 query = query.encode('utf-8')
1614 self._download_n_results(query, 1)
1616 elif prefix == 'all':
1617 self._download_n_results(query, self._max_yahoo_results)
1623 self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query))
1625 elif n > self._max_yahoo_results:
1626 self._downloader.to_stderr(u'WARNING: yvsearch returns max %i results (you requested %i)' % (self._max_yahoo_results, n))
1627 n = self._max_yahoo_results
1628 self._download_n_results(query, n)
1630 except ValueError: # parsing prefix as integer fails
1631 self._download_n_results(query, 1)
1634 def _download_n_results(self, query, n):
1635 """Downloads a specified number of results for a query"""
1638 already_seen = set()
1642 self.report_download_page(query, pagenum)
1643 result_url = self._TEMPLATE_URL % (compat_urllib_parse.quote_plus(query), pagenum)
1644 request = compat_urllib_request.Request(result_url)
1646 page = compat_urllib_request.urlopen(request).read()
1647 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
1648 self._downloader.trouble(u'ERROR: unable to download webpage: %s' % compat_str(err))
1651 # Extract video identifiers
1652 for mobj in re.finditer(self._VIDEO_INDICATOR, page):
1653 video_id = mobj.group(1)
1654 if video_id not in already_seen:
1655 video_ids.append(video_id)
1656 already_seen.add(video_id)
1657 if len(video_ids) == n:
1658 # Specified n videos reached
1659 for id in video_ids:
1660 self._downloader.download(['http://video.yahoo.com/watch/%s' % id])
1663 if re.search(self._MORE_PAGES_INDICATOR, page) is None:
1664 for id in video_ids:
1665 self._downloader.download(['http://video.yahoo.com/watch/%s' % id])
1668 pagenum = pagenum + 1
1671 class YoutubePlaylistIE(InfoExtractor):
1672 """Information Extractor for YouTube playlists."""
1674 _VALID_URL = r'(?:(?:https?://)?(?:\w+\.)?youtube\.com/(?:(?:course|view_play_list|my_playlists|artist|playlist)\?.*?(p|a|list)=|user/.*?/user/|p/|user/.*?#[pg]/c/)(?:PL|EC)?|PL|EC)([0-9A-Za-z-_]+)(?:/.*?/([0-9A-Za-z_-]+))?.*'
1675 _TEMPLATE_URL = 'http://www.youtube.com/%s?%s=%s&page=%s&gl=US&hl=en'
1676 _VIDEO_INDICATOR_TEMPLATE = r'/watch\?v=(.+?)&([^&"]+&)*list=.*?%s'
1677 _MORE_PAGES_INDICATOR = r'yt-uix-pager-next'
1678 IE_NAME = u'youtube:playlist'
1680 def __init__(self, downloader=None):
1681 InfoExtractor.__init__(self, downloader)
1683 def report_download_page(self, playlist_id, pagenum):
1684 """Report attempt to download playlist page with given number."""
1685 self._downloader.to_screen(u'[youtube] PL %s: Downloading page #%s' % (playlist_id, pagenum))
1687 def _real_extract(self, url):
1688 # Extract playlist id
1689 mobj = re.match(self._VALID_URL, url)
1691 self._downloader.trouble(u'ERROR: invalid url: %s' % url)
1695 if mobj.group(3) is not None:
1696 self._downloader.download([mobj.group(3)])
1699 # Download playlist pages
1700 # prefix is 'p' as default for playlists but there are other types that need extra care
1701 playlist_prefix = mobj.group(1)
1702 if playlist_prefix == 'a':
1703 playlist_access = 'artist'
1705 playlist_prefix = 'p'
1706 playlist_access = 'view_play_list'
1707 playlist_id = mobj.group(2)
1712 self.report_download_page(playlist_id, pagenum)
1713 url = self._TEMPLATE_URL % (playlist_access, playlist_prefix, playlist_id, pagenum)
1714 request = compat_urllib_request.Request(url)
1716 page = compat_urllib_request.urlopen(request).read()
1717 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
1718 self._downloader.trouble(u'ERROR: unable to download webpage: %s' % compat_str(err))
1721 # Extract video identifiers
1723 for mobj in re.finditer(self._VIDEO_INDICATOR_TEMPLATE % playlist_id, page):
1724 if mobj.group(1) not in ids_in_page:
1725 ids_in_page.append(mobj.group(1))
1726 video_ids.extend(ids_in_page)
1728 if re.search(self._MORE_PAGES_INDICATOR, page) is None:
1730 pagenum = pagenum + 1
1732 playliststart = self._downloader.params.get('playliststart', 1) - 1
1733 playlistend = self._downloader.params.get('playlistend', -1)
1734 if playlistend == -1:
1735 video_ids = video_ids[playliststart:]
1737 video_ids = video_ids[playliststart:playlistend]
1739 for id in video_ids:
1740 self._downloader.download(['http://www.youtube.com/watch?v=%s' % id])
1744 class YoutubeChannelIE(InfoExtractor):
1745 """Information Extractor for YouTube channels."""
1747 _VALID_URL = r"^(?:https?://)?(?:youtu\.be|(?:\w+\.)?youtube(?:-nocookie)?\.com)/channel/([0-9A-Za-z_-]+)(?:/.*)?$"
1748 _TEMPLATE_URL = 'http://www.youtube.com/channel/%s/videos?sort=da&flow=list&view=0&page=%s&gl=US&hl=en'
1749 _MORE_PAGES_INDICATOR = r'yt-uix-button-content">Next' # TODO
1750 IE_NAME = u'youtube:channel'
1752 def report_download_page(self, channel_id, pagenum):
1753 """Report attempt to download channel page with given number."""
1754 self._downloader.to_screen(u'[youtube] Channel %s: Downloading page #%s' % (channel_id, pagenum))
1756 def _real_extract(self, url):
1757 # Extract channel id
1758 mobj = re.match(self._VALID_URL, url)
1760 self._downloader.trouble(u'ERROR: invalid url: %s' % url)
1763 # Download channel pages
1764 channel_id = mobj.group(1)
1769 self.report_download_page(channel_id, pagenum)
1770 url = self._TEMPLATE_URL % (channel_id, pagenum)
1771 request = compat_urllib_request.Request(url)
1773 page = compat_urllib_request.urlopen(request).read()
1774 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
1775 self._downloader.trouble(u'ERROR: unable to download webpage: %s' % compat_str(err))
1778 # Extract video identifiers
1780 for mobj in re.finditer(r'href="/watch\?v=([0-9A-Za-z_-]+)&', page):
1781 if mobj.group(1) not in ids_in_page:
1782 ids_in_page.append(mobj.group(1))
1783 video_ids.extend(ids_in_page)
1785 if re.search(self._MORE_PAGES_INDICATOR, page) is None:
1787 pagenum = pagenum + 1
1789 for id in video_ids:
1790 self._downloader.download(['http://www.youtube.com/watch?v=%s' % id])
1794 class YoutubeUserIE(InfoExtractor):
1795 """Information Extractor for YouTube users."""
1797 _VALID_URL = r'(?:(?:(?:https?://)?(?:\w+\.)?youtube\.com/user/)|ytuser:)([A-Za-z0-9_-]+)'
1798 _TEMPLATE_URL = 'http://gdata.youtube.com/feeds/api/users/%s'
1799 _GDATA_PAGE_SIZE = 50
1800 _GDATA_URL = 'http://gdata.youtube.com/feeds/api/users/%s/uploads?max-results=%d&start-index=%d'
1801 _VIDEO_INDICATOR = r'/watch\?v=(.+?)[\<&]'
1802 IE_NAME = u'youtube:user'
1804 def __init__(self, downloader=None):
1805 InfoExtractor.__init__(self, downloader)
1807 def report_download_page(self, username, start_index):
1808 """Report attempt to download user page."""
1809 self._downloader.to_screen(u'[youtube] user %s: Downloading video ids from %d to %d' %
1810 (username, start_index, start_index + self._GDATA_PAGE_SIZE))
1812 def _real_extract(self, url):
1814 mobj = re.match(self._VALID_URL, url)
1816 self._downloader.trouble(u'ERROR: invalid url: %s' % url)
1819 username = mobj.group(1)
1821 # Download video ids using YouTube Data API. Result size per
1822 # query is limited (currently to 50 videos) so we need to query
1823 # page by page until there are no video ids - it means we got
1830 start_index = pagenum * self._GDATA_PAGE_SIZE + 1
1831 self.report_download_page(username, start_index)
1833 request = compat_urllib_request.Request(self._GDATA_URL % (username, self._GDATA_PAGE_SIZE, start_index))
1836 page = compat_urllib_request.urlopen(request).read()
1837 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
1838 self._downloader.trouble(u'ERROR: unable to download webpage: %s' % compat_str(err))
1841 # Extract video identifiers
1844 for mobj in re.finditer(self._VIDEO_INDICATOR, page):
1845 if mobj.group(1) not in ids_in_page:
1846 ids_in_page.append(mobj.group(1))
1848 video_ids.extend(ids_in_page)
1850 # A little optimization - if current page is not
1851 # "full", ie. does not contain PAGE_SIZE video ids then
1852 # we can assume that this page is the last one - there
1853 # are no more ids on further pages - no need to query
1856 if len(ids_in_page) < self._GDATA_PAGE_SIZE:
1861 all_ids_count = len(video_ids)
1862 playliststart = self._downloader.params.get('playliststart', 1) - 1
1863 playlistend = self._downloader.params.get('playlistend', -1)
1865 if playlistend == -1:
1866 video_ids = video_ids[playliststart:]
1868 video_ids = video_ids[playliststart:playlistend]
1870 self._downloader.to_screen(u"[youtube] user %s: Collected %d video ids (downloading %d of them)" %
1871 (username, all_ids_count, len(video_ids)))
1873 for video_id in video_ids:
1874 self._downloader.download(['http://www.youtube.com/watch?v=%s' % video_id])
1877 class BlipTVUserIE(InfoExtractor):
1878 """Information Extractor for blip.tv users."""
1880 _VALID_URL = r'(?:(?:(?:https?://)?(?:\w+\.)?blip\.tv/)|bliptvuser:)([^/]+)/*$'
1882 IE_NAME = u'blip.tv:user'
1884 def __init__(self, downloader=None):
1885 InfoExtractor.__init__(self, downloader)
1887 def report_download_page(self, username, pagenum):
1888 """Report attempt to download user page."""
1889 self._downloader.to_screen(u'[%s] user %s: Downloading video ids from page %d' %
1890 (self.IE_NAME, username, pagenum))
1892 def _real_extract(self, url):
1894 mobj = re.match(self._VALID_URL, url)
1896 self._downloader.trouble(u'ERROR: invalid url: %s' % url)
1899 username = mobj.group(1)
1901 page_base = 'http://m.blip.tv/pr/show_get_full_episode_list?users_id=%s&lite=0&esi=1'
1903 request = compat_urllib_request.Request(url)
1906 page = compat_urllib_request.urlopen(request).read().decode('utf-8')
1907 mobj = re.search(r'data-users-id="([^"]+)"', page)
1908 page_base = page_base % mobj.group(1)
1909 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
1910 self._downloader.trouble(u'ERROR: unable to download webpage: %s' % compat_str(err))
1914 # Download video ids using BlipTV Ajax calls. Result size per
1915 # query is limited (currently to 12 videos) so we need to query
1916 # page by page until there are no video ids - it means we got
1923 self.report_download_page(username, pagenum)
1925 request = compat_urllib_request.Request( page_base + "&page=" + str(pagenum) )
1928 page = compat_urllib_request.urlopen(request).read().decode('utf-8')
1929 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
1930 self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err))
1933 # Extract video identifiers
1936 for mobj in re.finditer(r'href="/([^"]+)"', page):
1937 if mobj.group(1) not in ids_in_page:
1938 ids_in_page.append(unescapeHTML(mobj.group(1)))
1940 video_ids.extend(ids_in_page)
1942 # A little optimization - if current page is not
1943 # "full", ie. does not contain PAGE_SIZE video ids then
1944 # we can assume that this page is the last one - there
1945 # are no more ids on further pages - no need to query
1948 if len(ids_in_page) < self._PAGE_SIZE:
1953 all_ids_count = len(video_ids)
1954 playliststart = self._downloader.params.get('playliststart', 1) - 1
1955 playlistend = self._downloader.params.get('playlistend', -1)
1957 if playlistend == -1:
1958 video_ids = video_ids[playliststart:]
1960 video_ids = video_ids[playliststart:playlistend]
1962 self._downloader.to_screen(u"[%s] user %s: Collected %d video ids (downloading %d of them)" %
1963 (self.IE_NAME, username, all_ids_count, len(video_ids)))
1965 for video_id in video_ids:
1966 self._downloader.download([u'http://blip.tv/'+video_id])
1969 class DepositFilesIE(InfoExtractor):
1970 """Information extractor for depositfiles.com"""
1972 _VALID_URL = r'(?:http://)?(?:\w+\.)?depositfiles\.com/(?:../(?#locale))?files/(.+)'
1973 IE_NAME = u'DepositFiles'
1975 def __init__(self, downloader=None):
1976 InfoExtractor.__init__(self, downloader)
1978 def report_download_webpage(self, file_id):
1979 """Report webpage download."""
1980 self._downloader.to_screen(u'[DepositFiles] %s: Downloading webpage' % file_id)
1982 def report_extraction(self, file_id):
1983 """Report information extraction."""
1984 self._downloader.to_screen(u'[DepositFiles] %s: Extracting information' % file_id)
1986 def _real_extract(self, url):
1987 file_id = url.split('/')[-1]
1988 # Rebuild url in english locale
1989 url = 'http://depositfiles.com/en/files/' + file_id
1991 # Retrieve file webpage with 'Free download' button pressed
1992 free_download_indication = { 'gateway_result' : '1' }
1993 request = compat_urllib_request.Request(url, compat_urllib_parse.urlencode(free_download_indication))
1995 self.report_download_webpage(file_id)
1996 webpage = compat_urllib_request.urlopen(request).read()
1997 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
1998 self._downloader.trouble(u'ERROR: Unable to retrieve file webpage: %s' % compat_str(err))
2001 # Search for the real file URL
2002 mobj = re.search(r'<form action="(http://fileshare.+?)"', webpage)
2003 if (mobj is None) or (mobj.group(1) is None):
2004 # Try to figure out reason of the error.
2005 mobj = re.search(r'<strong>(Attention.*?)</strong>', webpage, re.DOTALL)
2006 if (mobj is not None) and (mobj.group(1) is not None):
2007 restriction_message = re.sub('\s+', ' ', mobj.group(1)).strip()
2008 self._downloader.trouble(u'ERROR: %s' % restriction_message)
2010 self._downloader.trouble(u'ERROR: unable to extract download URL from: %s' % url)
2013 file_url = mobj.group(1)
2014 file_extension = os.path.splitext(file_url)[1][1:]
2016 # Search for file title
2017 mobj = re.search(r'<b title="(.*?)">', webpage)
2019 self._downloader.trouble(u'ERROR: unable to extract title')
2021 file_title = mobj.group(1).decode('utf-8')
2024 'id': file_id.decode('utf-8'),
2025 'url': file_url.decode('utf-8'),
2027 'upload_date': None,
2028 'title': file_title,
2029 'ext': file_extension.decode('utf-8'),
2033 class FacebookIE(InfoExtractor):
2034 """Information Extractor for Facebook"""
2037 _VALID_URL = r'^(?:https?://)?(?:\w+\.)?facebook\.com/(?:video/video|photo)\.php\?(?:.*?)v=(?P<ID>\d+)(?:.*)'
2038 _LOGIN_URL = 'https://login.facebook.com/login.php?m&next=http%3A%2F%2Fm.facebook.com%2Fhome.php&'
2039 _NETRC_MACHINE = 'facebook'
2040 _available_formats = ['video', 'highqual', 'lowqual']
2041 _video_extensions = {
2046 IE_NAME = u'facebook'
2048 def __init__(self, downloader=None):
2049 InfoExtractor.__init__(self, downloader)
2051 def _reporter(self, message):
2052 """Add header and report message."""
2053 self._downloader.to_screen(u'[facebook] %s' % message)
2055 def report_login(self):
2056 """Report attempt to log in."""
2057 self._reporter(u'Logging in')
2059 def report_video_webpage_download(self, video_id):
2060 """Report attempt to download video webpage."""
2061 self._reporter(u'%s: Downloading video webpage' % video_id)
2063 def report_information_extraction(self, video_id):
2064 """Report attempt to extract video information."""
2065 self._reporter(u'%s: Extracting video information' % video_id)
2067 def _parse_page(self, video_webpage):
2068 """Extract video information from page"""
2070 data = {'title': r'\("video_title", "(.*?)"\)',
2071 'description': r'<div class="datawrap">(.*?)</div>',
2072 'owner': r'\("video_owner_name", "(.*?)"\)',
2073 'thumbnail': r'\("thumb_url", "(?P<THUMB>.*?)"\)',
2076 for piece in data.keys():
2077 mobj = re.search(data[piece], video_webpage)
2078 if mobj is not None:
2079 video_info[piece] = compat_urllib_parse.unquote_plus(mobj.group(1).decode("unicode_escape"))
2083 for fmt in self._available_formats:
2084 mobj = re.search(r'\("%s_src\", "(.+?)"\)' % fmt, video_webpage)
2085 if mobj is not None:
2086 # URL is in a Javascript segment inside an escaped Unicode format within
2087 # the generally utf-8 page
2088 video_urls[fmt] = compat_urllib_parse.unquote_plus(mobj.group(1).decode("unicode_escape"))
2089 video_info['video_urls'] = video_urls
2093 def _real_initialize(self):
2094 if self._downloader is None:
2099 downloader_params = self._downloader.params
2101 # Attempt to use provided username and password or .netrc data
2102 if downloader_params.get('username', None) is not None:
2103 useremail = downloader_params['username']
2104 password = downloader_params['password']
2105 elif downloader_params.get('usenetrc', False):
2107 info = netrc.netrc().authenticators(self._NETRC_MACHINE)
2108 if info is not None:
2112 raise netrc.NetrcParseError('No authenticators for %s' % self._NETRC_MACHINE)
2113 except (IOError, netrc.NetrcParseError) as err:
2114 self._downloader.to_stderr(u'WARNING: parsing .netrc: %s' % compat_str(err))
2117 if useremail is None:
2126 request = compat_urllib_request.Request(self._LOGIN_URL, compat_urllib_parse.urlencode(login_form))
2129 login_results = compat_urllib_request.urlopen(request).read()
2130 if re.search(r'<form(.*)name="login"(.*)</form>', login_results) is not None:
2131 self._downloader.to_stderr(u'WARNING: unable to log in: bad username/password, or exceded login rate limit (~3/min). Check credentials or wait.')
2133 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
2134 self._downloader.to_stderr(u'WARNING: unable to log in: %s' % compat_str(err))
2137 def _real_extract(self, url):
2138 mobj = re.match(self._VALID_URL, url)
2140 self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
2142 video_id = mobj.group('ID')
2145 self.report_video_webpage_download(video_id)
2146 request = compat_urllib_request.Request('https://www.facebook.com/video/video.php?v=%s' % video_id)
2148 page = compat_urllib_request.urlopen(request)
2149 video_webpage = page.read()
2150 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
2151 self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % compat_str(err))
2154 # Start extracting information
2155 self.report_information_extraction(video_id)
2157 # Extract information
2158 video_info = self._parse_page(video_webpage)
2161 if 'owner' not in video_info:
2162 self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
2164 video_uploader = video_info['owner']
2167 if 'title' not in video_info:
2168 self._downloader.trouble(u'ERROR: unable to extract video title')
2170 video_title = video_info['title']
2171 video_title = video_title.decode('utf-8')
2174 if 'thumbnail' not in video_info:
2175 self._downloader.trouble(u'WARNING: unable to extract video thumbnail')
2176 video_thumbnail = ''
2178 video_thumbnail = video_info['thumbnail']
2182 if 'upload_date' in video_info:
2183 upload_time = video_info['upload_date']
2184 timetuple = email.utils.parsedate_tz(upload_time)
2185 if timetuple is not None:
2187 upload_date = time.strftime('%Y%m%d', timetuple[0:9])
2192 video_description = video_info.get('description', 'No description available.')
2194 url_map = video_info['video_urls']
2195 if len(url_map.keys()) > 0:
2196 # Decide which formats to download
2197 req_format = self._downloader.params.get('format', None)
2198 format_limit = self._downloader.params.get('format_limit', None)
2200 if format_limit is not None and format_limit in self._available_formats:
2201 format_list = self._available_formats[self._available_formats.index(format_limit):]
2203 format_list = self._available_formats
2204 existing_formats = [x for x in format_list if x in url_map]
2205 if len(existing_formats) == 0:
2206 self._downloader.trouble(u'ERROR: no known formats available for video')
2208 if req_format is None:
2209 video_url_list = [(existing_formats[0], url_map[existing_formats[0]])] # Best quality
2210 elif req_format == 'worst':
2211 video_url_list = [(existing_formats[len(existing_formats)-1], url_map[existing_formats[len(existing_formats)-1]])] # worst quality
2212 elif req_format == '-1':
2213 video_url_list = [(f, url_map[f]) for f in existing_formats] # All formats
2216 if req_format not in url_map:
2217 self._downloader.trouble(u'ERROR: requested format not available')
2219 video_url_list = [(req_format, url_map[req_format])] # Specific format
2222 for format_param, video_real_url in video_url_list:
2224 video_extension = self._video_extensions.get(format_param, 'mp4')
2227 'id': video_id.decode('utf-8'),
2228 'url': video_real_url.decode('utf-8'),
2229 'uploader': video_uploader.decode('utf-8'),
2230 'upload_date': upload_date,
2231 'title': video_title,
2232 'ext': video_extension.decode('utf-8'),
2233 'format': (format_param is None and u'NA' or format_param.decode('utf-8')),
2234 'thumbnail': video_thumbnail.decode('utf-8'),
2235 'description': video_description.decode('utf-8'),
2239 class BlipTVIE(InfoExtractor):
2240 """Information extractor for blip.tv"""
2242 _VALID_URL = r'^(?:https?://)?(?:\w+\.)?blip\.tv(/.+)$'
2243 _URL_EXT = r'^.*\.([a-z0-9]+)$'
2244 IE_NAME = u'blip.tv'
2246 def report_extraction(self, file_id):
2247 """Report information extraction."""
2248 self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, file_id))
2250 def report_direct_download(self, title):
2251 """Report information extraction."""
2252 self._downloader.to_screen(u'[%s] %s: Direct download detected' % (self.IE_NAME, title))
2254 def _real_extract(self, url):
2255 mobj = re.match(self._VALID_URL, url)
2257 self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
2264 json_url = url + cchar + 'skin=json&version=2&no_wrap=1'
2265 request = compat_urllib_request.Request(json_url.encode('utf-8'))
2266 self.report_extraction(mobj.group(1))
2269 urlh = compat_urllib_request.urlopen(request)
2270 if urlh.headers.get('Content-Type', '').startswith('video/'): # Direct download
2271 basename = url.split('/')[-1]
2272 title,ext = os.path.splitext(basename)
2273 title = title.decode('UTF-8')
2274 ext = ext.replace('.', '')
2275 self.report_direct_download(title)
2280 'upload_date': None,
2285 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
2286 self._downloader.trouble(u'ERROR: unable to download video info webpage: %s' % compat_str(err))
2288 if info is None: # Regular URL
2290 json_code = urlh.read()
2291 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
2292 self._downloader.trouble(u'ERROR: unable to read video info webpage: %s' % compat_str(err))
2296 json_data = json.loads(json_code)
2297 if 'Post' in json_data:
2298 data = json_data['Post']
2302 upload_date = datetime.datetime.strptime(data['datestamp'], '%m-%d-%y %H:%M%p').strftime('%Y%m%d')
2303 video_url = data['media']['url']
2304 umobj = re.match(self._URL_EXT, video_url)
2306 raise ValueError('Can not determine filename extension')
2307 ext = umobj.group(1)
2310 'id': data['item_id'],
2312 'uploader': data['display_name'],
2313 'upload_date': upload_date,
2314 'title': data['title'],
2316 'format': data['media']['mimeType'],
2317 'thumbnail': data['thumbnailUrl'],
2318 'description': data['description'],
2319 'player_url': data['embedUrl']
2321 except (ValueError,KeyError) as err:
2322 self._downloader.trouble(u'ERROR: unable to parse video information: %s' % repr(err))
2325 std_headers['User-Agent'] = 'iTunes/10.6.1'
2329 class MyVideoIE(InfoExtractor):
2330 """Information Extractor for myvideo.de."""
2332 _VALID_URL = r'(?:http://)?(?:www\.)?myvideo\.de/watch/([0-9]+)/([^?/]+).*'
2333 IE_NAME = u'myvideo'
2335 def __init__(self, downloader=None):
2336 InfoExtractor.__init__(self, downloader)
2338 def report_download_webpage(self, video_id):
2339 """Report webpage download."""
2340 self._downloader.to_screen(u'[myvideo] %s: Downloading webpage' % video_id)
2342 def report_extraction(self, video_id):
2343 """Report information extraction."""
2344 self._downloader.to_screen(u'[myvideo] %s: Extracting information' % video_id)
2346 def _real_extract(self,url):
2347 mobj = re.match(self._VALID_URL, url)
2349 self._download.trouble(u'ERROR: invalid URL: %s' % url)
2352 video_id = mobj.group(1)
2355 request = compat_urllib_request.Request('http://www.myvideo.de/watch/%s' % video_id)
2357 self.report_download_webpage(video_id)
2358 webpage = compat_urllib_request.urlopen(request).read()
2359 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
2360 self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err))
2363 self.report_extraction(video_id)
2364 mobj = re.search(r'<link rel=\'image_src\' href=\'(http://is[0-9].myvideo\.de/de/movie[0-9]+/[a-f0-9]+)/thumbs/[^.]+\.jpg\' />',
2367 self._downloader.trouble(u'ERROR: unable to extract media URL')
2369 video_url = mobj.group(1) + ('/%s.flv' % video_id)
2371 mobj = re.search('<title>([^<]+)</title>', webpage)
2373 self._downloader.trouble(u'ERROR: unable to extract title')
2376 video_title = mobj.group(1)
2382 'upload_date': None,
2383 'title': video_title,
2387 class ComedyCentralIE(InfoExtractor):
2388 """Information extractor for The Daily Show and Colbert Report """
2390 _VALID_URL = r'^(:(?P<shortname>tds|thedailyshow|cr|colbert|colbertnation|colbertreport))|(https?://)?(www\.)?(?P<showname>thedailyshow|colbertnation)\.com/full-episodes/(?P<episode>.*)$'
2391 IE_NAME = u'comedycentral'
2393 _available_formats = ['3500', '2200', '1700', '1200', '750', '400']
2395 _video_extensions = {
2403 _video_dimensions = {
2412 def report_extraction(self, episode_id):
2413 self._downloader.to_screen(u'[comedycentral] %s: Extracting information' % episode_id)
2415 def report_config_download(self, episode_id):
2416 self._downloader.to_screen(u'[comedycentral] %s: Downloading configuration' % episode_id)
2418 def report_index_download(self, episode_id):
2419 self._downloader.to_screen(u'[comedycentral] %s: Downloading show index' % episode_id)
2421 def report_player_url(self, episode_id):
2422 self._downloader.to_screen(u'[comedycentral] %s: Determining player URL' % episode_id)
2425 def _print_formats(self, formats):
2426 print('Available formats:')
2428 print('%s\t:\t%s\t[%s]' %(x, self._video_extensions.get(x, 'mp4'), self._video_dimensions.get(x, '???')))
2431 def _real_extract(self, url):
2432 mobj = re.match(self._VALID_URL, url)
2434 self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
2437 if mobj.group('shortname'):
2438 if mobj.group('shortname') in ('tds', 'thedailyshow'):
2439 url = u'http://www.thedailyshow.com/full-episodes/'
2441 url = u'http://www.colbertnation.com/full-episodes/'
2442 mobj = re.match(self._VALID_URL, url)
2443 assert mobj is not None
2445 dlNewest = not mobj.group('episode')
2447 epTitle = mobj.group('showname')
2449 epTitle = mobj.group('episode')
2451 req = compat_urllib_request.Request(url)
2452 self.report_extraction(epTitle)
2454 htmlHandle = compat_urllib_request.urlopen(req)
2455 html = htmlHandle.read()
2456 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
2457 self._downloader.trouble(u'ERROR: unable to download webpage: %s' % compat_str(err))
2460 url = htmlHandle.geturl()
2461 mobj = re.match(self._VALID_URL, url)
2463 self._downloader.trouble(u'ERROR: Invalid redirected URL: ' + url)
2465 if mobj.group('episode') == '':
2466 self._downloader.trouble(u'ERROR: Redirected URL is still not specific: ' + url)
2468 epTitle = mobj.group('episode')
2470 mMovieParams = re.findall('(?:<param name="movie" value="|var url = ")(http://media.mtvnservices.com/([^"]*episode.*?:.*?))"', html)
2472 if len(mMovieParams) == 0:
2473 # The Colbert Report embeds the information in a without
2474 # a URL prefix; so extract the alternate reference
2475 # and then add the URL prefix manually.
2477 altMovieParams = re.findall('data-mgid="([^"]*episode.*?:.*?)"', html)
2478 if len(altMovieParams) == 0:
2479 self._downloader.trouble(u'ERROR: unable to find Flash URL in webpage ' + url)
2482 mMovieParams = [("http://media.mtvnservices.com/" + altMovieParams[0], altMovieParams[0])]
2484 playerUrl_raw = mMovieParams[0][0]
2485 self.report_player_url(epTitle)
2487 urlHandle = compat_urllib_request.urlopen(playerUrl_raw)
2488 playerUrl = urlHandle.geturl()
2489 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
2490 self._downloader.trouble(u'ERROR: unable to find out player URL: ' + compat_str(err))
2493 uri = mMovieParams[0][1]
2494 indexUrl = 'http://shadow.comedycentral.com/feeds/video_player/mrss/?' + compat_urllib_parse.urlencode({'uri': uri})
2495 self.report_index_download(epTitle)
2497 indexXml = compat_urllib_request.urlopen(indexUrl).read()
2498 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
2499 self._downloader.trouble(u'ERROR: unable to download episode index: ' + compat_str(err))
2504 idoc = xml.etree.ElementTree.fromstring(indexXml)
2505 itemEls = idoc.findall('.//item')
2506 for itemEl in itemEls:
2507 mediaId = itemEl.findall('./guid')[0].text
2508 shortMediaId = mediaId.split(':')[-1]
2509 showId = mediaId.split(':')[-2].replace('.com', '')
2510 officialTitle = itemEl.findall('./title')[0].text
2511 officialDate = itemEl.findall('./pubDate')[0].text
2513 configUrl = ('http://www.comedycentral.com/global/feeds/entertainment/media/mediaGenEntertainment.jhtml?' +
2514 compat_urllib_parse.urlencode({'uri': mediaId}))
2515 configReq = compat_urllib_request.Request(configUrl)
2516 self.report_config_download(epTitle)
2518 configXml = compat_urllib_request.urlopen(configReq).read()
2519 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
2520 self._downloader.trouble(u'ERROR: unable to download webpage: %s' % compat_str(err))
2523 cdoc = xml.etree.ElementTree.fromstring(configXml)
2525 for rendition in cdoc.findall('.//rendition'):
2526 finfo = (rendition.attrib['bitrate'], rendition.findall('./src')[0].text)
2530 self._downloader.trouble(u'\nERROR: unable to download ' + mediaId + ': No videos found')
2533 if self._downloader.params.get('listformats', None):
2534 self._print_formats([i[0] for i in turls])
2537 # For now, just pick the highest bitrate
2538 format,video_url = turls[-1]
2540 # Get the format arg from the arg stream
2541 req_format = self._downloader.params.get('format', None)
2543 # Select format if we can find one
2546 format, video_url = f, v
2549 # Patch to download from alternative CDN, which does not
2550 # break on current RTMPDump builds
2551 broken_cdn = "rtmpe://viacomccstrmfs.fplive.net/viacomccstrm/gsp.comedystor/"
2552 better_cdn = "rtmpe://cp10740.edgefcs.net/ondemand/mtvnorigin/gsp.comedystor/"
2554 if video_url.startswith(broken_cdn):
2555 video_url = video_url.replace(broken_cdn, better_cdn)
2557 effTitle = showId + u'-' + epTitle
2562 'upload_date': officialDate,
2567 'description': officialTitle,
2568 'player_url': None #playerUrl
2571 results.append(info)
2576 class EscapistIE(InfoExtractor):
2577 """Information extractor for The Escapist """
2579 _VALID_URL = r'^(https?://)?(www\.)?escapistmagazine\.com/videos/view/(?P<showname>[^/]+)/(?P<episode>[^/?]+)[/?]?.*$'
2580 IE_NAME = u'escapist'
2582 def report_extraction(self, showName):
2583 self._downloader.to_screen(u'[escapist] %s: Extracting information' % showName)
2585 def report_config_download(self, showName):
2586 self._downloader.to_screen(u'[escapist] %s: Downloading configuration' % showName)
2588 def _real_extract(self, url):
2589 mobj = re.match(self._VALID_URL, url)
2591 self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
2593 showName = mobj.group('showname')
2594 videoId = mobj.group('episode')
2596 self.report_extraction(showName)
2598 webPage = compat_urllib_request.urlopen(url)
2599 webPageBytes = webPage.read()
2600 m = re.match(r'text/html; charset="?([^"]+)"?', webPage.headers['Content-Type'])
2601 webPage = webPageBytes.decode(m.group(1) if m else 'utf-8')
2602 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
2603 self._downloader.trouble(u'ERROR: unable to download webpage: ' + compat_str(err))
2606 descMatch = re.search('<meta name="description" content="([^"]*)"', webPage)
2607 description = unescapeHTML(descMatch.group(1))
2608 imgMatch = re.search('<meta property="og:image" content="([^"]*)"', webPage)
2609 imgUrl = unescapeHTML(imgMatch.group(1))
2610 playerUrlMatch = re.search('<meta property="og:video" content="([^"]*)"', webPage)
2611 playerUrl = unescapeHTML(playerUrlMatch.group(1))
2612 configUrlMatch = re.search('config=(.*)$', playerUrl)
2613 configUrl = compat_urllib_parse.unquote(configUrlMatch.group(1))
2615 self.report_config_download(showName)
2617 configJSON = compat_urllib_request.urlopen(configUrl).read()
2618 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
2619 self._downloader.trouble(u'ERROR: unable to download configuration: ' + compat_str(err))
2622 # Technically, it's JavaScript, not JSON
2623 configJSON = configJSON.replace("'", '"')
2626 config = json.loads(configJSON)
2627 except (ValueError,) as err:
2628 self._downloader.trouble(u'ERROR: Invalid JSON in configuration file: ' + compat_str(err))
2631 playlist = config['playlist']
2632 videoUrl = playlist[1]['url']
2637 'uploader': showName,
2638 'upload_date': None,
2641 'thumbnail': imgUrl,
2642 'description': description,
2643 'player_url': playerUrl,
2649 class CollegeHumorIE(InfoExtractor):
2650 """Information extractor for collegehumor.com"""
2652 _VALID_URL = r'^(?:https?://)?(?:www\.)?collegehumor\.com/video/(?P<videoid>[0-9]+)/(?P<shorttitle>.*)$'
2653 IE_NAME = u'collegehumor'
2655 def report_manifest(self, video_id):
2656 """Report information extraction."""
2657 self._downloader.to_screen(u'[%s] %s: Downloading XML manifest' % (self.IE_NAME, video_id))
2659 def report_extraction(self, video_id):
2660 """Report information extraction."""
2661 self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id))
2663 def _real_extract(self, url):
2664 mobj = re.match(self._VALID_URL, url)
2666 self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
2668 video_id = mobj.group('videoid')
2673 'upload_date': None,
2676 self.report_extraction(video_id)
2677 xmlUrl = 'http://www.collegehumor.com/moogaloop/video/' + video_id
2679 metaXml = compat_urllib_request.urlopen(xmlUrl).read()
2680 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
2681 self._downloader.trouble(u'ERROR: unable to download video info XML: %s' % compat_str(err))
2684 mdoc = xml.etree.ElementTree.fromstring(metaXml)
2686 videoNode = mdoc.findall('./video')[0]
2687 info['description'] = videoNode.findall('./description')[0].text
2688 info['title'] = videoNode.findall('./caption')[0].text
2689 info['thumbnail'] = videoNode.findall('./thumbnail')[0].text
2690 manifest_url = videoNode.findall('./file')[0].text
2692 self._downloader.trouble(u'\nERROR: Invalid metadata XML file')
2695 manifest_url += '?hdcore=2.10.3'
2696 self.report_manifest(video_id)
2698 manifestXml = compat_urllib_request.urlopen(manifest_url).read()
2699 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
2700 self._downloader.trouble(u'ERROR: unable to download video info XML: %s' % compat_str(err))
2703 adoc = xml.etree.ElementTree.fromstring(manifestXml)
2705 media_node = adoc.findall('./{http://ns.adobe.com/f4m/1.0}media')[0]
2706 node_id = media_node.attrib['url']
2707 video_id = adoc.findall('./{http://ns.adobe.com/f4m/1.0}id')[0].text
2708 except IndexError as err:
2709 self._downloader.trouble(u'\nERROR: Invalid manifest file')
2712 url_pr = compat_urllib_parse_urlparse(manifest_url)
2713 url = url_pr.scheme + '://' + url_pr.netloc + '/z' + video_id[:-2] + '/' + node_id + 'Seg1-Frag1'
2720 class XVideosIE(InfoExtractor):
2721 """Information extractor for xvideos.com"""
2723 _VALID_URL = r'^(?:https?://)?(?:www\.)?xvideos\.com/video([0-9]+)(?:.*)'
2724 IE_NAME = u'xvideos'
2726 def report_webpage(self, video_id):
2727 """Report information extraction."""
2728 self._downloader.to_screen(u'[%s] %s: Downloading webpage' % (self.IE_NAME, video_id))
2730 def report_extraction(self, video_id):
2731 """Report information extraction."""
2732 self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id))
2734 def _real_extract(self, url):
2735 mobj = re.match(self._VALID_URL, url)
2737 self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
2739 video_id = mobj.group(1).decode('utf-8')
2741 self.report_webpage(video_id)
2743 request = compat_urllib_request.Request(r'http://www.xvideos.com/video' + video_id)
2745 webpage = compat_urllib_request.urlopen(request).read()
2746 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
2747 self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % compat_str(err))
2750 self.report_extraction(video_id)
2754 mobj = re.search(r'flv_url=(.+?)&', webpage)
2756 self._downloader.trouble(u'ERROR: unable to extract video url')
2758 video_url = compat_urllib_parse.unquote(mobj.group(1).decode('utf-8'))
2762 mobj = re.search(r'<title>(.*?)\s+-\s+XVID', webpage)
2764 self._downloader.trouble(u'ERROR: unable to extract video title')
2766 video_title = mobj.group(1).decode('utf-8')
2769 # Extract video thumbnail
2770 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)
2772 self._downloader.trouble(u'ERROR: unable to extract video thumbnail')
2774 video_thumbnail = mobj.group(0).decode('utf-8')
2780 'upload_date': None,
2781 'title': video_title,
2783 'thumbnail': video_thumbnail,
2784 'description': None,
2790 class SoundcloudIE(InfoExtractor):
2791 """Information extractor for soundcloud.com
2792 To access the media, the uid of the song and a stream token
2793 must be extracted from the page source and the script must make
2794 a request to media.soundcloud.com/crossdomain.xml. Then
2795 the media can be grabbed by requesting from an url composed
2796 of the stream token and uid
2799 _VALID_URL = r'^(?:https?://)?(?:www\.)?soundcloud\.com/([\w\d-]+)/([\w\d-]+)'
2800 IE_NAME = u'soundcloud'
2802 def __init__(self, downloader=None):
2803 InfoExtractor.__init__(self, downloader)
2805 def report_webpage(self, video_id):
2806 """Report information extraction."""
2807 self._downloader.to_screen(u'[%s] %s: Downloading webpage' % (self.IE_NAME, video_id))
2809 def report_extraction(self, video_id):
2810 """Report information extraction."""
2811 self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id))
2813 def _real_extract(self, url):
2814 mobj = re.match(self._VALID_URL, url)
2816 self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
2819 # extract uploader (which is in the url)
2820 uploader = mobj.group(1).decode('utf-8')
2821 # extract simple title (uploader + slug of song title)
2822 slug_title = mobj.group(2).decode('utf-8')
2823 simple_title = uploader + u'-' + slug_title
2825 self.report_webpage('%s/%s' % (uploader, slug_title))
2827 request = compat_urllib_request.Request('http://soundcloud.com/%s/%s' % (uploader, slug_title))
2829 webpage = compat_urllib_request.urlopen(request).read()
2830 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
2831 self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % compat_str(err))
2834 self.report_extraction('%s/%s' % (uploader, slug_title))
2836 # extract uid and stream token that soundcloud hands out for access
2837 mobj = re.search('"uid":"([\w\d]+?)".*?stream_token=([\w\d]+)', webpage)
2839 video_id = mobj.group(1)
2840 stream_token = mobj.group(2)
2842 # extract unsimplified title
2843 mobj = re.search('"title":"(.*?)",', webpage)
2845 title = mobj.group(1).decode('utf-8')
2847 title = simple_title
2849 # construct media url (with uid/token)
2850 mediaURL = "http://media.soundcloud.com/stream/%s?stream_token=%s"
2851 mediaURL = mediaURL % (video_id, stream_token)
2854 description = u'No description available'
2855 mobj = re.search('track-description-value"><p>(.*?)</p>', webpage)
2857 description = mobj.group(1)
2861 mobj = re.search("pretty-date'>on ([\w]+ [\d]+, [\d]+ \d+:\d+)</abbr></h2>", webpage)
2864 upload_date = datetime.datetime.strptime(mobj.group(1), '%B %d, %Y %H:%M').strftime('%Y%m%d')
2865 except Exception as err:
2866 self._downloader.to_stderr(compat_str(err))
2868 # for soundcloud, a request to a cross domain is required for cookies
2869 request = compat_urllib_request.Request('http://media.soundcloud.com/crossdomain.xml', std_headers)
2872 'id': video_id.decode('utf-8'),
2874 'uploader': uploader.decode('utf-8'),
2875 'upload_date': upload_date,
2878 'description': description.decode('utf-8')
2882 class InfoQIE(InfoExtractor):
2883 """Information extractor for infoq.com"""
2885 _VALID_URL = r'^(?:https?://)?(?:www\.)?infoq\.com/[^/]+/[^/]+$'
2888 def report_webpage(self, video_id):
2889 """Report information extraction."""
2890 self._downloader.to_screen(u'[%s] %s: Downloading webpage' % (self.IE_NAME, video_id))
2892 def report_extraction(self, video_id):
2893 """Report information extraction."""
2894 self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id))
2896 def _real_extract(self, url):
2897 mobj = re.match(self._VALID_URL, url)
2899 self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
2902 self.report_webpage(url)
2904 request = compat_urllib_request.Request(url)
2906 webpage = compat_urllib_request.urlopen(request).read()
2907 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
2908 self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % compat_str(err))
2911 self.report_extraction(url)
2915 mobj = re.search(r"jsclassref='([^']*)'", webpage)
2917 self._downloader.trouble(u'ERROR: unable to extract video url')
2919 video_url = 'rtmpe://video.infoq.com/cfx/st/' + compat_urllib_parse.unquote(mobj.group(1).decode('base64'))
2923 mobj = re.search(r'contentTitle = "(.*?)";', webpage)
2925 self._downloader.trouble(u'ERROR: unable to extract video title')
2927 video_title = mobj.group(1).decode('utf-8')
2929 # Extract description
2930 video_description = u'No description available.'
2931 mobj = re.search(r'<meta name="description" content="(.*)"(?:\s*/)?>', webpage)
2932 if mobj is not None:
2933 video_description = mobj.group(1).decode('utf-8')
2935 video_filename = video_url.split('/')[-1]
2936 video_id, extension = video_filename.split('.')
2942 'upload_date': None,
2943 'title': video_title,
2944 'ext': extension, # Extension is always(?) mp4, but seems to be flv
2946 'description': video_description,
2951 class MixcloudIE(InfoExtractor):
2952 """Information extractor for www.mixcloud.com"""
2953 _VALID_URL = r'^(?:https?://)?(?:www\.)?mixcloud\.com/([\w\d-]+)/([\w\d-]+)'
2954 IE_NAME = u'mixcloud'
2956 def __init__(self, downloader=None):
2957 InfoExtractor.__init__(self, downloader)
2959 def report_download_json(self, file_id):
2960 """Report JSON download."""
2961 self._downloader.to_screen(u'[%s] Downloading json' % self.IE_NAME)
2963 def report_extraction(self, file_id):
2964 """Report information extraction."""
2965 self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, file_id))
2967 def get_urls(self, jsonData, fmt, bitrate='best'):
2968 """Get urls from 'audio_formats' section in json"""
2971 bitrate_list = jsonData[fmt]
2972 if bitrate is None or bitrate == 'best' or bitrate not in bitrate_list:
2973 bitrate = max(bitrate_list) # select highest
2975 url_list = jsonData[fmt][bitrate]
2976 except TypeError: # we have no bitrate info.
2977 url_list = jsonData[fmt]
2980 def check_urls(self, url_list):
2981 """Returns 1st active url from list"""
2982 for url in url_list:
2984 compat_urllib_request.urlopen(url)
2986 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
2991 def _print_formats(self, formats):
2992 print('Available formats:')
2993 for fmt in formats.keys():
2994 for b in formats[fmt]:
2996 ext = formats[fmt][b][0]
2997 print('%s\t%s\t[%s]' % (fmt, b, ext.split('.')[-1]))
2998 except TypeError: # we have no bitrate info
2999 ext = formats[fmt][0]
3000 print('%s\t%s\t[%s]' % (fmt, '??', ext.split('.')[-1]))
3003 def _real_extract(self, url):
3004 mobj = re.match(self._VALID_URL, url)
3006 self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
3008 # extract uploader & filename from url
3009 uploader = mobj.group(1).decode('utf-8')
3010 file_id = uploader + "-" + mobj.group(2).decode('utf-8')
3012 # construct API request
3013 file_url = 'http://www.mixcloud.com/api/1/cloudcast/' + '/'.join(url.split('/')[-3:-1]) + '.json'
3014 # retrieve .json file with links to files
3015 request = compat_urllib_request.Request(file_url)
3017 self.report_download_json(file_url)
3018 jsonData = compat_urllib_request.urlopen(request).read()
3019 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
3020 self._downloader.trouble(u'ERROR: Unable to retrieve file: %s' % compat_str(err))
3024 json_data = json.loads(jsonData)
3025 player_url = json_data['player_swf_url']
3026 formats = dict(json_data['audio_formats'])
3028 req_format = self._downloader.params.get('format', None)
3031 if self._downloader.params.get('listformats', None):
3032 self._print_formats(formats)
3035 if req_format is None or req_format == 'best':
3036 for format_param in formats.keys():
3037 url_list = self.get_urls(formats, format_param)
3039 file_url = self.check_urls(url_list)
3040 if file_url is not None:
3043 if req_format not in formats.keys():
3044 self._downloader.trouble(u'ERROR: format is not available')
3047 url_list = self.get_urls(formats, req_format)
3048 file_url = self.check_urls(url_list)
3049 format_param = req_format
3052 'id': file_id.decode('utf-8'),
3053 'url': file_url.decode('utf-8'),
3054 'uploader': uploader.decode('utf-8'),
3055 'upload_date': None,
3056 'title': json_data['name'],
3057 'ext': file_url.split('.')[-1].decode('utf-8'),
3058 'format': (format_param is None and u'NA' or format_param.decode('utf-8')),
3059 'thumbnail': json_data['thumbnail_url'],
3060 'description': json_data['description'],
3061 'player_url': player_url.decode('utf-8'),
3064 class StanfordOpenClassroomIE(InfoExtractor):
3065 """Information extractor for Stanford's Open ClassRoom"""
3067 _VALID_URL = r'^(?:https?://)?openclassroom.stanford.edu(?P<path>/?|(/MainFolder/(?:HomePage|CoursePage|VideoPage)\.php([?]course=(?P<course>[^&]+)(&video=(?P<video>[^&]+))?(&.*)?)?))$'
3068 IE_NAME = u'stanfordoc'
3070 def report_download_webpage(self, objid):
3071 """Report information extraction."""
3072 self._downloader.to_screen(u'[%s] %s: Downloading webpage' % (self.IE_NAME, objid))
3074 def report_extraction(self, video_id):
3075 """Report information extraction."""
3076 self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id))
3078 def _real_extract(self, url):
3079 mobj = re.match(self._VALID_URL, url)
3081 self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
3084 if mobj.group('course') and mobj.group('video'): # A specific video
3085 course = mobj.group('course')
3086 video = mobj.group('video')
3088 'id': course + '_' + video,
3090 'upload_date': None,
3093 self.report_extraction(info['id'])
3094 baseUrl = 'http://openclassroom.stanford.edu/MainFolder/courses/' + course + '/videos/'
3095 xmlUrl = baseUrl + video + '.xml'
3097 metaXml = compat_urllib_request.urlopen(xmlUrl).read()
3098 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
3099 self._downloader.trouble(u'ERROR: unable to download video info XML: %s' % compat_str(err))
3101 mdoc = xml.etree.ElementTree.fromstring(metaXml)
3103 info['title'] = mdoc.findall('./title')[0].text
3104 info['url'] = baseUrl + mdoc.findall('./videoFile')[0].text
3106 self._downloader.trouble(u'\nERROR: Invalid metadata XML file')
3108 info['ext'] = info['url'].rpartition('.')[2]
3110 elif mobj.group('course'): # A course page
3111 course = mobj.group('course')
3116 'upload_date': None,
3119 self.report_download_webpage(info['id'])
3121 coursepage = compat_urllib_request.urlopen(url).read()
3122 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
3123 self._downloader.trouble(u'ERROR: unable to download course info page: ' + compat_str(err))
3126 m = re.search('<h1>([^<]+)</h1>', coursepage)
3128 info['title'] = unescapeHTML(m.group(1))
3130 info['title'] = info['id']
3132 m = re.search('<description>([^<]+)</description>', coursepage)
3134 info['description'] = unescapeHTML(m.group(1))
3136 links = orderedSet(re.findall('<a href="(VideoPage.php\?[^"]+)">', coursepage))
3139 'type': 'reference',
3140 'url': 'http://openclassroom.stanford.edu/MainFolder/' + unescapeHTML(vpage),
3144 for entry in info['list']:
3145 assert entry['type'] == 'reference'
3146 results += self.extract(entry['url'])
3151 'id': 'Stanford OpenClassroom',
3154 'upload_date': None,
3157 self.report_download_webpage(info['id'])
3158 rootURL = 'http://openclassroom.stanford.edu/MainFolder/HomePage.php'
3160 rootpage = compat_urllib_request.urlopen(rootURL).read()
3161 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
3162 self._downloader.trouble(u'ERROR: unable to download course info page: ' + compat_str(err))
3165 info['title'] = info['id']
3167 links = orderedSet(re.findall('<a href="(CoursePage.php\?[^"]+)">', rootpage))
3170 'type': 'reference',
3171 'url': 'http://openclassroom.stanford.edu/MainFolder/' + unescapeHTML(cpage),
3176 for entry in info['list']:
3177 assert entry['type'] == 'reference'
3178 results += self.extract(entry['url'])
3181 class MTVIE(InfoExtractor):
3182 """Information extractor for MTV.com"""
3184 _VALID_URL = r'^(?P<proto>https?://)?(?:www\.)?mtv\.com/videos/[^/]+/(?P<videoid>[0-9]+)/[^/]+$'
3187 def report_webpage(self, video_id):
3188 """Report information extraction."""
3189 self._downloader.to_screen(u'[%s] %s: Downloading webpage' % (self.IE_NAME, video_id))
3191 def report_extraction(self, video_id):
3192 """Report information extraction."""
3193 self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id))
3195 def _real_extract(self, url):
3196 mobj = re.match(self._VALID_URL, url)
3198 self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
3200 if not mobj.group('proto'):
3201 url = 'http://' + url
3202 video_id = mobj.group('videoid')
3203 self.report_webpage(video_id)
3205 request = compat_urllib_request.Request(url)
3207 webpage = compat_urllib_request.urlopen(request).read()
3208 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
3209 self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % compat_str(err))
3212 mobj = re.search(r'<meta name="mtv_vt" content="([^"]+)"/>', webpage)
3214 self._downloader.trouble(u'ERROR: unable to extract song name')
3216 song_name = unescapeHTML(mobj.group(1).decode('iso-8859-1'))
3217 mobj = re.search(r'<meta name="mtv_an" content="([^"]+)"/>', webpage)
3219 self._downloader.trouble(u'ERROR: unable to extract performer')
3221 performer = unescapeHTML(mobj.group(1).decode('iso-8859-1'))
3222 video_title = performer + ' - ' + song_name
3224 mobj = re.search(r'<meta name="mtvn_uri" content="([^"]+)"/>', webpage)
3226 self._downloader.trouble(u'ERROR: unable to mtvn_uri')
3228 mtvn_uri = mobj.group(1)
3230 mobj = re.search(r'MTVN.Player.defaultPlaylistId = ([0-9]+);', webpage)
3232 self._downloader.trouble(u'ERROR: unable to extract content id')
3234 content_id = mobj.group(1)
3236 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
3237 self.report_extraction(video_id)
3238 request = compat_urllib_request.Request(videogen_url)
3240 metadataXml = compat_urllib_request.urlopen(request).read()
3241 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
3242 self._downloader.trouble(u'ERROR: unable to download video metadata: %s' % compat_str(err))
3245 mdoc = xml.etree.ElementTree.fromstring(metadataXml)
3246 renditions = mdoc.findall('.//rendition')
3248 # For now, always pick the highest quality.
3249 rendition = renditions[-1]
3252 _,_,ext = rendition.attrib['type'].partition('/')
3253 format = ext + '-' + rendition.attrib['width'] + 'x' + rendition.attrib['height'] + '_' + rendition.attrib['bitrate']
3254 video_url = rendition.find('./src').text
3256 self._downloader.trouble('Invalid rendition field.')
3262 'uploader': performer,
3263 'upload_date': None,
3264 'title': video_title,
3272 class YoukuIE(InfoExtractor):
3274 _VALID_URL = r'(?:http://)?v\.youku\.com/v_show/id_(?P<ID>[A-Za-z0-9]+)\.html'
3277 def __init__(self, downloader=None):
3278 InfoExtractor.__init__(self, downloader)
3280 def report_download_webpage(self, file_id):
3281 """Report webpage download."""
3282 self._downloader.to_screen(u'[Youku] %s: Downloading webpage' % file_id)
3284 def report_extraction(self, file_id):
3285 """Report information extraction."""
3286 self._downloader.to_screen(u'[Youku] %s: Extracting information' % file_id)
3289 nowTime = int(time.time() * 1000)
3290 random1 = random.randint(1000,1998)
3291 random2 = random.randint(1000,9999)
3293 return "%d%d%d" %(nowTime,random1,random2)
3295 def _get_file_ID_mix_string(self, seed):
3297 source = list("abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ/\:._-1234567890")
3299 for i in range(len(source)):
3300 seed = (seed * 211 + 30031 ) % 65536
3301 index = math.floor(seed / 65536 * len(source) )
3302 mixed.append(source[int(index)])
3303 source.remove(source[int(index)])
3304 #return ''.join(mixed)
3307 def _get_file_id(self, fileId, seed):
3308 mixed = self._get_file_ID_mix_string(seed)
3309 ids = fileId.split('*')
3313 realId.append(mixed[int(ch)])
3314 return ''.join(realId)
3316 def _real_extract(self, url):
3317 mobj = re.match(self._VALID_URL, url)
3319 self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
3321 video_id = mobj.group('ID')
3323 info_url = 'http://v.youku.com/player/getPlayList/VideoIDS/' + video_id
3325 request = compat_urllib_request.Request(info_url, None, std_headers)
3327 self.report_download_webpage(video_id)
3328 jsondata = compat_urllib_request.urlopen(request).read()
3329 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
3330 self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err))
3333 self.report_extraction(video_id)
3335 config = json.loads(jsondata)
3337 video_title = config['data'][0]['title']
3338 seed = config['data'][0]['seed']
3340 format = self._downloader.params.get('format', None)
3341 supported_format = config['data'][0]['streamfileids'].keys()
3343 if format is None or format == 'best':
3344 if 'hd2' in supported_format:
3349 elif format == 'worst':
3357 fileid = config['data'][0]['streamfileids'][format]
3358 seg_number = len(config['data'][0]['segs'][format])
3361 for i in xrange(seg_number):
3362 keys.append(config['data'][0]['segs'][format][i]['k'])
3365 #youku only could be viewed from mainland china
3367 self._downloader.trouble(u'ERROR: unable to extract info section')
3371 sid = self._gen_sid()
3372 fileid = self._get_file_id(fileid, seed)
3374 #column 8,9 of fileid represent the segment number
3375 #fileid[7:9] should be changed
3376 for index, key in enumerate(keys):
3378 temp_fileid = '%s%02X%s' % (fileid[0:8], index, fileid[10:])
3379 download_url = 'http://f.youku.com/player/getFlvPath/sid/%s_%02X/st/flv/fileid/%s?k=%s' % (sid, index, temp_fileid, key)
3382 'id': '%s_part%02d' % (video_id, index),
3383 'url': download_url,
3385 'upload_date': None,
3386 'title': video_title,
3389 files_info.append(info)
3394 class XNXXIE(InfoExtractor):
3395 """Information extractor for xnxx.com"""
3397 _VALID_URL = r'^http://video\.xnxx\.com/video([0-9]+)/(.*)'
3399 VIDEO_URL_RE = r'flv_url=(.*?)&'
3400 VIDEO_TITLE_RE = r'<title>(.*?)\s+-\s+XNXX.COM'
3401 VIDEO_THUMB_RE = r'url_bigthumb=(.*?)&'
3403 def report_webpage(self, video_id):
3404 """Report information extraction"""
3405 self._downloader.to_screen(u'[%s] %s: Downloading webpage' % (self.IE_NAME, video_id))
3407 def report_extraction(self, video_id):
3408 """Report information extraction"""
3409 self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id))
3411 def _real_extract(self, url):
3412 mobj = re.match(self._VALID_URL, url)
3414 self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
3416 video_id = mobj.group(1).decode('utf-8')
3418 self.report_webpage(video_id)
3420 # Get webpage content
3422 webpage = compat_urllib_request.urlopen(url).read()
3423 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
3424 self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % err)
3427 result = re.search(self.VIDEO_URL_RE, webpage)
3429 self._downloader.trouble(u'ERROR: unable to extract video url')
3431 video_url = compat_urllib_parse.unquote(result.group(1).decode('utf-8'))
3433 result = re.search(self.VIDEO_TITLE_RE, webpage)
3435 self._downloader.trouble(u'ERROR: unable to extract video title')
3437 video_title = result.group(1).decode('utf-8')
3439 result = re.search(self.VIDEO_THUMB_RE, webpage)
3441 self._downloader.trouble(u'ERROR: unable to extract video thumbnail')
3443 video_thumbnail = result.group(1).decode('utf-8')
3449 'upload_date': None,
3450 'title': video_title,
3452 'thumbnail': video_thumbnail,
3453 'description': None,
3457 class GooglePlusIE(InfoExtractor):
3458 """Information extractor for plus.google.com."""
3460 _VALID_URL = r'(?:https://)?plus\.google\.com/(?:\w+/)*?(\d+)/posts/(\w+)'
3461 IE_NAME = u'plus.google'
3463 def __init__(self, downloader=None):
3464 InfoExtractor.__init__(self, downloader)
3466 def report_extract_entry(self, url):
3467 """Report downloading extry"""
3468 self._downloader.to_screen(u'[plus.google] Downloading entry: %s' % url.decode('utf-8'))
3470 def report_date(self, upload_date):
3471 """Report downloading extry"""
3472 self._downloader.to_screen(u'[plus.google] Entry date: %s' % upload_date)
3474 def report_uploader(self, uploader):
3475 """Report downloading extry"""
3476 self._downloader.to_screen(u'[plus.google] Uploader: %s' % uploader.decode('utf-8'))
3478 def report_title(self, video_title):
3479 """Report downloading extry"""
3480 self._downloader.to_screen(u'[plus.google] Title: %s' % video_title.decode('utf-8'))
3482 def report_extract_vid_page(self, video_page):
3483 """Report information extraction."""
3484 self._downloader.to_screen(u'[plus.google] Extracting video page: %s' % video_page.decode('utf-8'))
3486 def _real_extract(self, url):
3487 # Extract id from URL
3488 mobj = re.match(self._VALID_URL, url)
3490 self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
3493 post_url = mobj.group(0)
3494 video_id = mobj.group(2)
3496 video_extension = 'flv'
3498 # Step 1, Retrieve post webpage to extract further information
3499 self.report_extract_entry(post_url)
3500 request = compat_urllib_request.Request(post_url)
3502 webpage = compat_urllib_request.urlopen(request).read()
3503 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
3504 self._downloader.trouble(u'ERROR: Unable to retrieve entry webpage: %s' % compat_str(err))
3507 # Extract update date
3509 pattern = 'title="Timestamp">(.*?)</a>'
3510 mobj = re.search(pattern, webpage)
3512 upload_date = mobj.group(1)
3513 # Convert timestring to a format suitable for filename
3514 upload_date = datetime.datetime.strptime(upload_date, "%Y-%m-%d")
3515 upload_date = upload_date.strftime('%Y%m%d')
3516 self.report_date(upload_date)
3520 pattern = r'rel\="author".*?>(.*?)</a>'
3521 mobj = re.search(pattern, webpage)
3523 uploader = mobj.group(1)
3524 self.report_uploader(uploader)
3527 # Get the first line for title
3529 pattern = r'<meta name\=\"Description\" content\=\"(.*?)[\n<"]'
3530 mobj = re.search(pattern, webpage)
3532 video_title = mobj.group(1)
3533 self.report_title(video_title)
3535 # Step 2, Stimulate clicking the image box to launch video
3536 pattern = '"(https\://plus\.google\.com/photos/.*?)",,"image/jpeg","video"\]'
3537 mobj = re.search(pattern, webpage)
3539 self._downloader.trouble(u'ERROR: unable to extract video page URL')
3541 video_page = mobj.group(1)
3542 request = compat_urllib_request.Request(video_page)
3544 webpage = compat_urllib_request.urlopen(request).read()
3545 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
3546 self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err))
3548 self.report_extract_vid_page(video_page)
3551 # Extract video links on video page
3552 """Extract video links of all sizes"""
3553 pattern = '\d+,\d+,(\d+),"(http\://redirector\.googlevideo\.com.*?)"'
3554 mobj = re.findall(pattern, webpage)
3556 self._downloader.trouble(u'ERROR: unable to extract video links')
3558 # Sort in resolution
3559 links = sorted(mobj)
3561 # Choose the lowest of the sort, i.e. highest resolution
3562 video_url = links[-1]
3563 # Only get the url. The resolution part in the tuple has no use anymore
3564 video_url = video_url[-1]
3565 # Treat escaped \u0026 style hex
3566 video_url = unicode(video_url, "unicode_escape")
3570 'id': video_id.decode('utf-8'),
3572 'uploader': uploader.decode('utf-8'),
3573 'upload_date': upload_date.decode('utf-8'),
3574 'title': video_title.decode('utf-8'),
3575 'ext': video_extension.decode('utf-8'),