+ # _VALID_URL matches Vimeo URLs
+ _VALID_URL = r'(?:https?://)?(?:(?:www|player).)?vimeo\.com/(?:groups/[^/]+/)?(?:videos?/)?([0-9]+)'
+
+ def __init__(self, downloader=None):
+ InfoExtractor.__init__(self, downloader)
+
+ @staticmethod
+ def suitable(url):
+ return (re.match(VimeoIE._VALID_URL, url) is not None)
+
+ def report_download_webpage(self, video_id):
+ """Report webpage download."""
+ self._downloader.to_screen(u'[vimeo] %s: Downloading webpage' % video_id)
+
+ def report_extraction(self, video_id):
+ """Report information extraction."""
+ self._downloader.to_screen(u'[vimeo] %s: Extracting information' % video_id)
+
+ def _real_initialize(self):
+ return
+
+ def _real_extract(self, url, new_video=True):
+ # Extract ID from URL
+ mobj = re.match(self._VALID_URL, url)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
+ return
+
+ # At this point we have a new video
+ self._downloader.increment_downloads()
+ video_id = mobj.group(1)
+
+ # Retrieve video webpage to extract further information
+ request = urllib2.Request("http://vimeo.com/moogaloop/load/clip:%s" % video_id, None, std_headers)
+ try:
+ self.report_download_webpage(video_id)
+ webpage = urllib2.urlopen(request).read()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
+ return
+
+ # Now we begin extracting as much information as we can from what we
+ # retrieved. First we extract the information common to all extractors,
+ # and latter we extract those that are Vimeo specific.
+ self.report_extraction(video_id)
+
+ # Extract title
+ mobj = re.search(r'<caption>(.*?)</caption>', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract video title')
+ return
+ video_title = mobj.group(1).decode('utf-8')
+ simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
+
+ # Extract uploader
+ mobj = re.search(r'<uploader_url>http://vimeo.com/(.*?)</uploader_url>', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract video uploader')
+ return
+ video_uploader = mobj.group(1).decode('utf-8')
+
+ # Extract video thumbnail
+ mobj = re.search(r'<thumbnail>(.*?)</thumbnail>', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract video thumbnail')
+ return
+ video_thumbnail = mobj.group(1).decode('utf-8')
+
+ # # Extract video description
+ # mobj = re.search(r'<meta property="og:description" content="(.*)" />', webpage)
+ # if mobj is None:
+ # self._downloader.trouble(u'ERROR: unable to extract video description')
+ # return
+ # video_description = mobj.group(1).decode('utf-8')
+ # if not video_description: video_description = 'No description available.'
+ video_description = 'Foo.'
+
+ # Vimeo specific: extract request signature
+ mobj = re.search(r'<request_signature>(.*?)</request_signature>', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract request signature')
+ return
+ sig = mobj.group(1).decode('utf-8')
+
+ # Vimeo specific: Extract request signature expiration
+ mobj = re.search(r'<request_signature_expires>(.*?)</request_signature_expires>', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract request signature expiration')
+ return
+ sig_exp = mobj.group(1).decode('utf-8')
+
+ video_url = "http://vimeo.com/moogaloop/play/clip:%s/%s/%s" % (video_id, sig, sig_exp)
+
+ try:
+ # Process video information
+ self._downloader.process_info({
+ 'id': video_id.decode('utf-8'),
+ 'url': video_url,
+ 'uploader': video_uploader,
+ 'upload_date': u'NA',
+ 'title': video_title,
+ 'stitle': simple_title,
+ 'ext': u'mp4',
+ 'thumbnail': video_thumbnail.decode('utf-8'),
+ 'description': video_description,
+ 'thumbnail': video_thumbnail,
+ 'description': video_description,
+ 'player_url': None,
+ })
+ except UnavailableVideoError:
+ self._downloader.trouble(u'ERROR: unable to download video')
+
+
+class GenericIE(InfoExtractor):
+ """Generic last-resort information extractor."""
+
+ def __init__(self, downloader=None):
+ InfoExtractor.__init__(self, downloader)
+
+ @staticmethod
+ def suitable(url):
+ return True
+
+ def report_download_webpage(self, video_id):
+ """Report webpage download."""
+ self._downloader.to_screen(u'WARNING: Falling back on generic information extractor.')
+ self._downloader.to_screen(u'[generic] %s: Downloading webpage' % video_id)
+
+ def report_extraction(self, video_id):
+ """Report information extraction."""
+ self._downloader.to_screen(u'[generic] %s: Extracting information' % video_id)
+
+ def _real_initialize(self):
+ return
+
+ def _real_extract(self, url):
+ # At this point we have a new video
+ self._downloader.increment_downloads()
+
+ video_id = url.split('/')[-1]
+ request = urllib2.Request(url)
+ try:
+ self.report_download_webpage(video_id)
+ webpage = urllib2.urlopen(request).read()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
+ return
+ except ValueError, err:
+ # since this is the last-resort InfoExtractor, if
+ # this error is thrown, it'll be thrown here
+ self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
+ return
+
+ self.report_extraction(video_id)
+ # Start with something easy: JW Player in SWFObject
+ mobj = re.search(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage)
+ if mobj is None:
+ # Broaden the search a little bit
+ mobj = re.search(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
+ return
+
+ # It's possible that one of the regexes
+ # matched, but returned an empty group:
+ if mobj.group(1) is None:
+ self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
+ return
+
+ video_url = urllib.unquote(mobj.group(1))
+ video_id = os.path.basename(video_url)
+
+ # here's a fun little line of code for you:
+ video_extension = os.path.splitext(video_id)[1][1:]
+ video_id = os.path.splitext(video_id)[0]
+
+ # it's tempting to parse this further, but you would
+ # have to take into account all the variations like
+ # Video Title - Site Name
+ # Site Name | Video Title
+ # Video Title - Tagline | Site Name
+ # and so on and so forth; it's just not practical
+ mobj = re.search(r'<title>(.*)</title>', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract title')
+ return
+ video_title = mobj.group(1).decode('utf-8')
+ video_title = sanitize_title(video_title)
+ simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
+
+ # video uploader is domain name
+ mobj = re.match(r'(?:https?://)?([^/]*)/.*', url)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract title')
+ return
+ video_uploader = mobj.group(1).decode('utf-8')
+
+ try:
+ # Process video information
+ self._downloader.process_info({
+ 'id': video_id.decode('utf-8'),
+ 'url': video_url.decode('utf-8'),
+ 'uploader': video_uploader,
+ 'upload_date': u'NA',
+ 'title': video_title,
+ 'stitle': simple_title,
+ 'ext': video_extension.decode('utf-8'),
+ 'format': u'NA',
+ 'player_url': None,
+ })
+ except UnavailableVideoError, err:
+ self._downloader.trouble(u'\nERROR: unable to download video')
+
+
+class YoutubeSearchIE(InfoExtractor):
+ """Information Extractor for YouTube search queries."""
+ _VALID_QUERY = r'ytsearch(\d+|all)?:[\s\S]+'
+ _TEMPLATE_URL = 'http://www.youtube.com/results?search_query=%s&page=%s&gl=US&hl=en'
+ _VIDEO_INDICATOR = r'href="/watch\?v=.+?"'
+ _MORE_PAGES_INDICATOR = r'(?m)>\s*Next\s*</a>'
+ _youtube_ie = None
+ _max_youtube_results = 1000
+
+ def __init__(self, youtube_ie, downloader=None):
+ InfoExtractor.__init__(self, downloader)
+ self._youtube_ie = youtube_ie
+
+ @staticmethod
+ def suitable(url):
+ return (re.match(YoutubeSearchIE._VALID_QUERY, url) is not None)
+
+ def report_download_page(self, query, pagenum):
+ """Report attempt to download playlist page with given number."""
+ query = query.decode(preferredencoding())
+ self._downloader.to_screen(u'[youtube] query "%s": Downloading page %s' % (query, pagenum))
+
+ def _real_initialize(self):
+ self._youtube_ie.initialize()
+
+ def _real_extract(self, query):
+ mobj = re.match(self._VALID_QUERY, query)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: invalid search query "%s"' % query)
+ return
+
+ prefix, query = query.split(':')
+ prefix = prefix[8:]
+ query = query.encode('utf-8')
+ if prefix == '':
+ self._download_n_results(query, 1)
+ return
+ elif prefix == 'all':
+ self._download_n_results(query, self._max_youtube_results)
+ return
+ else:
+ try:
+ n = long(prefix)
+ if n <= 0:
+ self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query))
+ return
+ elif n > self._max_youtube_results:
+ self._downloader.to_stderr(u'WARNING: ytsearch returns max %i results (you requested %i)' % (self._max_youtube_results, n))
+ n = self._max_youtube_results
+ self._download_n_results(query, n)
+ return
+ except ValueError: # parsing prefix as integer fails
+ self._download_n_results(query, 1)
+ return
+
+ def _download_n_results(self, query, n):
+ """Downloads a specified number of results for a query"""
+
+ video_ids = []
+ already_seen = set()
+ pagenum = 1
+
+ while True:
+ self.report_download_page(query, pagenum)
+ result_url = self._TEMPLATE_URL % (urllib.quote_plus(query), pagenum)
+ request = urllib2.Request(result_url)
+ try:
+ page = urllib2.urlopen(request).read()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err))
+ return
+
+ # Extract video identifiers
+ for mobj in re.finditer(self._VIDEO_INDICATOR, page):
+ video_id = page[mobj.span()[0]:mobj.span()[1]].split('=')[2][:-1]
+ if video_id not in already_seen:
+ video_ids.append(video_id)
+ already_seen.add(video_id)
+ if len(video_ids) == n:
+ # Specified n videos reached
+ for id in video_ids:
+ self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id)
+ return
+
+ if re.search(self._MORE_PAGES_INDICATOR, page) is None:
+ for id in video_ids:
+ self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id)
+ return
+
+ pagenum = pagenum + 1
+
+
+class GoogleSearchIE(InfoExtractor):
+ """Information Extractor for Google Video search queries."""
+ _VALID_QUERY = r'gvsearch(\d+|all)?:[\s\S]+'
+ _TEMPLATE_URL = 'http://video.google.com/videosearch?q=%s+site:video.google.com&start=%s&hl=en'
+ _VIDEO_INDICATOR = r'videoplay\?docid=([^\&>]+)\&'
+ _MORE_PAGES_INDICATOR = r'<span>Next</span>'
+ _google_ie = None
+ _max_google_results = 1000
+
+ def __init__(self, google_ie, downloader=None):
+ InfoExtractor.__init__(self, downloader)
+ self._google_ie = google_ie
+
+ @staticmethod
+ def suitable(url):
+ return (re.match(GoogleSearchIE._VALID_QUERY, url) is not None)
+
+ def report_download_page(self, query, pagenum):
+ """Report attempt to download playlist page with given number."""
+ query = query.decode(preferredencoding())
+ self._downloader.to_screen(u'[video.google] query "%s": Downloading page %s' % (query, pagenum))
+
+ def _real_initialize(self):
+ self._google_ie.initialize()
+
+ def _real_extract(self, query):
+ mobj = re.match(self._VALID_QUERY, query)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: invalid search query "%s"' % query)
+ return
+
+ prefix, query = query.split(':')
+ prefix = prefix[8:]
+ query = query.encode('utf-8')
+ if prefix == '':
+ self._download_n_results(query, 1)
+ return
+ elif prefix == 'all':
+ self._download_n_results(query, self._max_google_results)
+ return
+ else:
+ try:
+ n = long(prefix)
+ if n <= 0:
+ self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query))
+ return
+ elif n > self._max_google_results:
+ self._downloader.to_stderr(u'WARNING: gvsearch returns max %i results (you requested %i)' % (self._max_google_results, n))
+ n = self._max_google_results
+ self._download_n_results(query, n)
+ return
+ except ValueError: # parsing prefix as integer fails
+ self._download_n_results(query, 1)
+ return
+
+ def _download_n_results(self, query, n):
+ """Downloads a specified number of results for a query"""
+
+ video_ids = []
+ already_seen = set()
+ pagenum = 1
+
+ while True:
+ self.report_download_page(query, pagenum)
+ result_url = self._TEMPLATE_URL % (urllib.quote_plus(query), pagenum)
+ request = urllib2.Request(result_url)
+ try:
+ page = urllib2.urlopen(request).read()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err))
+ return
+
+ # Extract video identifiers
+ for mobj in re.finditer(self._VIDEO_INDICATOR, page):
+ video_id = mobj.group(1)
+ if video_id not in already_seen:
+ video_ids.append(video_id)
+ already_seen.add(video_id)
+ if len(video_ids) == n:
+ # Specified n videos reached
+ for id in video_ids:
+ self._google_ie.extract('http://video.google.com/videoplay?docid=%s' % id)
+ return
+
+ if re.search(self._MORE_PAGES_INDICATOR, page) is None:
+ for id in video_ids:
+ self._google_ie.extract('http://video.google.com/videoplay?docid=%s' % id)
+ return
+
+ pagenum = pagenum + 1
+
+
+class YahooSearchIE(InfoExtractor):
+ """Information Extractor for Yahoo! Video search queries."""
+ _VALID_QUERY = r'yvsearch(\d+|all)?:[\s\S]+'
+ _TEMPLATE_URL = 'http://video.yahoo.com/search/?p=%s&o=%s'
+ _VIDEO_INDICATOR = r'href="http://video\.yahoo\.com/watch/([0-9]+/[0-9]+)"'
+ _MORE_PAGES_INDICATOR = r'\s*Next'
+ _yahoo_ie = None
+ _max_yahoo_results = 1000
+
+ def __init__(self, yahoo_ie, downloader=None):
+ InfoExtractor.__init__(self, downloader)
+ self._yahoo_ie = yahoo_ie
+
+ @staticmethod
+ def suitable(url):
+ return (re.match(YahooSearchIE._VALID_QUERY, url) is not None)
+
+ def report_download_page(self, query, pagenum):
+ """Report attempt to download playlist page with given number."""
+ query = query.decode(preferredencoding())
+ self._downloader.to_screen(u'[video.yahoo] query "%s": Downloading page %s' % (query, pagenum))
+
+ def _real_initialize(self):
+ self._yahoo_ie.initialize()
+
+ def _real_extract(self, query):
+ mobj = re.match(self._VALID_QUERY, query)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: invalid search query "%s"' % query)
+ return
+
+ prefix, query = query.split(':')
+ prefix = prefix[8:]
+ query = query.encode('utf-8')
+ if prefix == '':
+ self._download_n_results(query, 1)
+ return
+ elif prefix == 'all':
+ self._download_n_results(query, self._max_yahoo_results)
+ return
+ else:
+ try:
+ n = long(prefix)
+ if n <= 0:
+ self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query))
+ return
+ elif n > self._max_yahoo_results:
+ self._downloader.to_stderr(u'WARNING: yvsearch returns max %i results (you requested %i)' % (self._max_yahoo_results, n))
+ n = self._max_yahoo_results
+ self._download_n_results(query, n)
+ return
+ except ValueError: # parsing prefix as integer fails
+ self._download_n_results(query, 1)
+ return
+
+ def _download_n_results(self, query, n):
+ """Downloads a specified number of results for a query"""
+
+ video_ids = []
+ already_seen = set()
+ pagenum = 1
+
+ while True:
+ self.report_download_page(query, pagenum)
+ result_url = self._TEMPLATE_URL % (urllib.quote_plus(query), pagenum)
+ request = urllib2.Request(result_url)
+ try:
+ page = urllib2.urlopen(request).read()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err))
+ return
+
+ # Extract video identifiers
+ for mobj in re.finditer(self._VIDEO_INDICATOR, page):
+ video_id = mobj.group(1)
+ if video_id not in already_seen:
+ video_ids.append(video_id)
+ already_seen.add(video_id)
+ if len(video_ids) == n:
+ # Specified n videos reached
+ for id in video_ids:
+ self._yahoo_ie.extract('http://video.yahoo.com/watch/%s' % id)
+ return
+
+ if re.search(self._MORE_PAGES_INDICATOR, page) is None:
+ for id in video_ids:
+ self._yahoo_ie.extract('http://video.yahoo.com/watch/%s' % id)
+ return
+
+ pagenum = pagenum + 1
+
+
+class YoutubePlaylistIE(InfoExtractor):
+ """Information Extractor for YouTube playlists."""
+
+ _VALID_URL = r'(?:http://)?(?:\w+\.)?youtube.com/(?:(?:view_play_list|my_playlists|artist|playlist)\?.*?(p|a|list)=|user/.*?/user/|p/|user/.*?#[pg]/c/)([0-9A-Za-z]+)(?:/.*?/([0-9A-Za-z_-]+))?.*'
+ _TEMPLATE_URL = 'http://www.youtube.com/%s?%s=%s&page=%s&gl=US&hl=en'
+ _VIDEO_INDICATOR = r'/watch\?v=(.+?)&'
+ _MORE_PAGES_INDICATOR = r'(?m)>\s*Next\s*</a>'
+ _youtube_ie = None
+
+ def __init__(self, youtube_ie, downloader=None):
+ InfoExtractor.__init__(self, downloader)
+ self._youtube_ie = youtube_ie
+
+ @staticmethod
+ def suitable(url):
+ return (re.match(YoutubePlaylistIE._VALID_URL, url) is not None)
+
+ def report_download_page(self, playlist_id, pagenum):
+ """Report attempt to download playlist page with given number."""
+ self._downloader.to_screen(u'[youtube] PL %s: Downloading page #%s' % (playlist_id, pagenum))
+
+ def _real_initialize(self):
+ self._youtube_ie.initialize()
+
+ def _real_extract(self, url):
+ # Extract playlist id
+ mobj = re.match(self._VALID_URL, url)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: invalid url: %s' % url)
+ return
+
+ # Single video case
+ if mobj.group(3) is not None:
+ self._youtube_ie.extract(mobj.group(3))
+ return
+
+ # Download playlist pages
+ # prefix is 'p' as default for playlists but there are other types that need extra care
+ playlist_prefix = mobj.group(1)
+ if playlist_prefix == 'a':
+ playlist_access = 'artist'
+ else:
+ playlist_prefix = 'p'
+ playlist_access = 'view_play_list'
+ playlist_id = mobj.group(2)
+ video_ids = []
+ pagenum = 1
+
+ while True:
+ self.report_download_page(playlist_id, pagenum)
+ request = urllib2.Request(self._TEMPLATE_URL % (playlist_access, playlist_prefix, playlist_id, pagenum))
+ try:
+ page = urllib2.urlopen(request).read()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err))
+ return
+
+ # Extract video identifiers
+ ids_in_page = []
+ for mobj in re.finditer(self._VIDEO_INDICATOR, page):
+ if mobj.group(1) not in ids_in_page:
+ ids_in_page.append(mobj.group(1))
+ video_ids.extend(ids_in_page)
+
+ if re.search(self._MORE_PAGES_INDICATOR, page) is None:
+ break
+ pagenum = pagenum + 1
+
+ playliststart = self._downloader.params.get('playliststart', 1) - 1
+ playlistend = self._downloader.params.get('playlistend', -1)
+ video_ids = video_ids[playliststart:playlistend]
+
+ for id in video_ids:
+ self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id)
+ return
+
+
+class YoutubeUserIE(InfoExtractor):
+ """Information Extractor for YouTube users."""
+
+ _VALID_URL = r'(?:(?:(?:http://)?(?:\w+\.)?youtube.com/user/)|ytuser:)([A-Za-z0-9_-]+)'
+ _TEMPLATE_URL = 'http://gdata.youtube.com/feeds/api/users/%s'
+ _GDATA_PAGE_SIZE = 50
+ _GDATA_URL = 'http://gdata.youtube.com/feeds/api/users/%s/uploads?max-results=%d&start-index=%d'
+ _VIDEO_INDICATOR = r'/watch\?v=(.+?)&'
+ _youtube_ie = None
+
+ def __init__(self, youtube_ie, downloader=None):
+ InfoExtractor.__init__(self, downloader)
+ self._youtube_ie = youtube_ie
+
+ @staticmethod
+ def suitable(url):
+ return (re.match(YoutubeUserIE._VALID_URL, url) is not None)
+
+ def report_download_page(self, username, start_index):
+ """Report attempt to download user page."""
+ self._downloader.to_screen(u'[youtube] user %s: Downloading video ids from %d to %d' %
+ (username, start_index, start_index + self._GDATA_PAGE_SIZE))
+
+ def _real_initialize(self):
+ self._youtube_ie.initialize()
+
+ def _real_extract(self, url):
+ # Extract username
+ mobj = re.match(self._VALID_URL, url)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: invalid url: %s' % url)
+ return
+
+ username = mobj.group(1)
+
+ # Download video ids using YouTube Data API. Result size per
+ # query is limited (currently to 50 videos) so we need to query
+ # page by page until there are no video ids - it means we got
+ # all of them.
+
+ video_ids = []
+ pagenum = 0
+
+ while True:
+ start_index = pagenum * self._GDATA_PAGE_SIZE + 1
+ self.report_download_page(username, start_index)
+
+ request = urllib2.Request(self._GDATA_URL % (username, self._GDATA_PAGE_SIZE, start_index))
+
+ try:
+ page = urllib2.urlopen(request).read()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err))
+ return
+
+ # Extract video identifiers
+ ids_in_page = []
+
+ for mobj in re.finditer(self._VIDEO_INDICATOR, page):
+ if mobj.group(1) not in ids_in_page:
+ ids_in_page.append(mobj.group(1))
+
+ video_ids.extend(ids_in_page)
+
+ # A little optimization - if current page is not
+ # "full", ie. does not contain PAGE_SIZE video ids then
+ # we can assume that this page is the last one - there
+ # are no more ids on further pages - no need to query
+ # again.
+
+ if len(ids_in_page) < self._GDATA_PAGE_SIZE:
+ break
+
+ pagenum += 1
+
+ all_ids_count = len(video_ids)
+ playliststart = self._downloader.params.get('playliststart', 1) - 1
+ playlistend = self._downloader.params.get('playlistend', -1)
+
+ if playlistend == -1:
+ video_ids = video_ids[playliststart:]
+ else:
+ video_ids = video_ids[playliststart:playlistend]
+
+ self._downloader.to_screen("[youtube] user %s: Collected %d video ids (downloading %d of them)" %
+ (username, all_ids_count, len(video_ids)))
+
+ for video_id in video_ids:
+ self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % video_id)
+
+
+class DepositFilesIE(InfoExtractor):
+ """Information extractor for depositfiles.com"""
+
+ _VALID_URL = r'(?:http://)?(?:\w+\.)?depositfiles.com/(?:../(?#locale))?files/(.+)'
+
+ def __init__(self, downloader=None):
+ InfoExtractor.__init__(self, downloader)
+
+ @staticmethod
+ def suitable(url):
+ return (re.match(DepositFilesIE._VALID_URL, url) is not None)
+
+ def report_download_webpage(self, file_id):
+ """Report webpage download."""
+ self._downloader.to_screen(u'[DepositFiles] %s: Downloading webpage' % file_id)
+
+ def report_extraction(self, file_id):
+ """Report information extraction."""
+ self._downloader.to_screen(u'[DepositFiles] %s: Extracting information' % file_id)
+
+ def _real_initialize(self):
+ return
+
+ def _real_extract(self, url):
+ # At this point we have a new file
+ self._downloader.increment_downloads()
+
+ file_id = url.split('/')[-1]
+ # Rebuild url in english locale
+ url = 'http://depositfiles.com/en/files/' + file_id
+
+ # Retrieve file webpage with 'Free download' button pressed
+ free_download_indication = { 'gateway_result' : '1' }
+ request = urllib2.Request(url, urllib.urlencode(free_download_indication))
+ try:
+ self.report_download_webpage(file_id)
+ webpage = urllib2.urlopen(request).read()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.trouble(u'ERROR: Unable to retrieve file webpage: %s' % str(err))
+ return
+
+ # Search for the real file URL
+ mobj = re.search(r'<form action="(http://fileshare.+?)"', webpage)
+ if (mobj is None) or (mobj.group(1) is None):
+ # Try to figure out reason of the error.
+ mobj = re.search(r'<strong>(Attention.*?)</strong>', webpage, re.DOTALL)
+ if (mobj is not None) and (mobj.group(1) is not None):
+ restriction_message = re.sub('\s+', ' ', mobj.group(1)).strip()
+ self._downloader.trouble(u'ERROR: %s' % restriction_message)
+ else:
+ self._downloader.trouble(u'ERROR: unable to extract download URL from: %s' % url)
+ return
+
+ file_url = mobj.group(1)
+ file_extension = os.path.splitext(file_url)[1][1:]
+
+ # Search for file title
+ mobj = re.search(r'<b title="(.*?)">', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract title')
+ return
+ file_title = mobj.group(1).decode('utf-8')
+
+ try:
+ # Process file information
+ self._downloader.process_info({
+ 'id': file_id.decode('utf-8'),
+ 'url': file_url.decode('utf-8'),
+ 'uploader': u'NA',
+ 'upload_date': u'NA',
+ 'title': file_title,
+ 'stitle': file_title,
+ 'ext': file_extension.decode('utf-8'),
+ 'format': u'NA',
+ 'player_url': None,
+ })
+ except UnavailableVideoError, err:
+ self._downloader.trouble(u'ERROR: unable to download file')
+
+
+class FacebookIE(InfoExtractor):
+ """Information Extractor for Facebook"""
+
+ _VALID_URL = r'^(?:https?://)?(?:\w+\.)?facebook.com/video/video.php\?(?:.*?)v=(?P<ID>\d+)(?:.*)'
+ _LOGIN_URL = 'https://login.facebook.com/login.php?m&next=http%3A%2F%2Fm.facebook.com%2Fhome.php&'
+ _NETRC_MACHINE = 'facebook'
+ _available_formats = ['highqual', 'lowqual']
+ _video_extensions = {
+ 'highqual': 'mp4',
+ 'lowqual': 'mp4',
+ }
+
+ def __init__(self, downloader=None):
+ InfoExtractor.__init__(self, downloader)
+
+ @staticmethod
+ def suitable(url):
+ return (re.match(FacebookIE._VALID_URL, url) is not None)
+
+ def _reporter(self, message):
+ """Add header and report message."""
+ self._downloader.to_screen(u'[facebook] %s' % message)
+
+ def report_login(self):
+ """Report attempt to log in."""
+ self._reporter(u'Logging in')
+
+ def report_video_webpage_download(self, video_id):
+ """Report attempt to download video webpage."""
+ self._reporter(u'%s: Downloading video webpage' % video_id)
+
+ def report_information_extraction(self, video_id):
+ """Report attempt to extract video information."""
+ self._reporter(u'%s: Extracting video information' % video_id)
+
+ def _parse_page(self, video_webpage):
+ """Extract video information from page"""
+ # General data
+ data = {'title': r'class="video_title datawrap">(.*?)</',
+ 'description': r'<div class="datawrap">(.*?)</div>',
+ 'owner': r'\("video_owner_name", "(.*?)"\)',
+ 'upload_date': r'data-date="(.*?)"',
+ 'thumbnail': r'\("thumb_url", "(?P<THUMB>.*?)"\)',
+ }
+ video_info = {}
+ for piece in data.keys():
+ mobj = re.search(data[piece], video_webpage)
+ if mobj is not None:
+ video_info[piece] = urllib.unquote_plus(mobj.group(1).decode("unicode_escape"))
+
+ # Video urls
+ video_urls = {}
+ for fmt in self._available_formats:
+ mobj = re.search(r'\("%s_src\", "(.+?)"\)' % fmt, video_webpage)
+ if mobj is not None:
+ # URL is in a Javascript segment inside an escaped Unicode format within
+ # the generally utf-8 page
+ video_urls[fmt] = urllib.unquote_plus(mobj.group(1).decode("unicode_escape"))
+ video_info['video_urls'] = video_urls
+
+ return video_info
+
+ def _real_initialize(self):
+ if self._downloader is None:
+ return
+
+ useremail = None
+ password = None
+ downloader_params = self._downloader.params
+
+ # Attempt to use provided username and password or .netrc data
+ if downloader_params.get('username', None) is not None:
+ useremail = downloader_params['username']
+ password = downloader_params['password']
+ elif downloader_params.get('usenetrc', False):
+ try:
+ info = netrc.netrc().authenticators(self._NETRC_MACHINE)
+ if info is not None:
+ useremail = info[0]
+ password = info[2]
+ else:
+ raise netrc.NetrcParseError('No authenticators for %s' % self._NETRC_MACHINE)
+ except (IOError, netrc.NetrcParseError), err:
+ self._downloader.to_stderr(u'WARNING: parsing .netrc: %s' % str(err))
+ return
+
+ if useremail is None:
+ return
+
+ # Log in
+ login_form = {
+ 'email': useremail,
+ 'pass': password,
+ 'login': 'Log+In'
+ }
+ request = urllib2.Request(self._LOGIN_URL, urllib.urlencode(login_form))
+ try:
+ self.report_login()
+ login_results = urllib2.urlopen(request).read()
+ if re.search(r'<form(.*)name="login"(.*)</form>', login_results) is not None:
+ self._downloader.to_stderr(u'WARNING: unable to log in: bad username/password, or exceded login rate limit (~3/min). Check credentials or wait.')
+ return
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.to_stderr(u'WARNING: unable to log in: %s' % str(err))
+ return
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
+ return
+ video_id = mobj.group('ID')
+
+ # Get video webpage
+ self.report_video_webpage_download(video_id)
+ request = urllib2.Request('https://www.facebook.com/video/video.php?v=%s' % video_id)
+ try:
+ page = urllib2.urlopen(request)
+ video_webpage = page.read()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % str(err))
+ return
+
+ # Start extracting information
+ self.report_information_extraction(video_id)
+
+ # Extract information
+ video_info = self._parse_page(video_webpage)
+
+ # uploader
+ if 'owner' not in video_info:
+ self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
+ return
+ video_uploader = video_info['owner']
+
+ # title
+ if 'title' not in video_info:
+ self._downloader.trouble(u'ERROR: unable to extract video title')
+ return
+ video_title = video_info['title']
+ video_title = video_title.decode('utf-8')
+ video_title = sanitize_title(video_title)
+
+ # simplified title
+ simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
+ simple_title = simple_title.strip(ur'_')
+
+ # thumbnail image
+ if 'thumbnail' not in video_info:
+ self._downloader.trouble(u'WARNING: unable to extract video thumbnail')
+ video_thumbnail = ''
+ else:
+ video_thumbnail = video_info['thumbnail']
+
+ # upload date
+ upload_date = u'NA'
+ if 'upload_date' in video_info:
+ upload_time = video_info['upload_date']
+ timetuple = email.utils.parsedate_tz(upload_time)
+ if timetuple is not None:
+ try:
+ upload_date = time.strftime('%Y%m%d', timetuple[0:9])
+ except:
+ pass
+
+ # description
+ video_description = video_info.get('description', 'No description available.')
+
+ url_map = video_info['video_urls']
+ if len(url_map.keys()) > 0:
+ # Decide which formats to download
+ req_format = self._downloader.params.get('format', None)
+ format_limit = self._downloader.params.get('format_limit', None)
+
+ if format_limit is not None and format_limit in self._available_formats:
+ format_list = self._available_formats[self._available_formats.index(format_limit):]
+ else:
+ format_list = self._available_formats
+ existing_formats = [x for x in format_list if x in url_map]
+ if len(existing_formats) == 0:
+ self._downloader.trouble(u'ERROR: no known formats available for video')
+ return
+ if req_format is None:
+ video_url_list = [(existing_formats[0], url_map[existing_formats[0]])] # Best quality
+ elif req_format == '-1':
+ video_url_list = [(f, url_map[f]) for f in existing_formats] # All formats
+ else:
+ # Specific format
+ if req_format not in url_map:
+ self._downloader.trouble(u'ERROR: requested format not available')
+ return
+ video_url_list = [(req_format, url_map[req_format])] # Specific format
+
+ for format_param, video_real_url in video_url_list:
+
+ # At this point we have a new video
+ self._downloader.increment_downloads()
+
+ # Extension
+ video_extension = self._video_extensions.get(format_param, 'mp4')
+
+ try:
+ # Process video information
+ self._downloader.process_info({
+ 'id': video_id.decode('utf-8'),
+ 'url': video_real_url.decode('utf-8'),
+ 'uploader': video_uploader.decode('utf-8'),
+ 'upload_date': upload_date,
+ 'title': video_title,
+ 'stitle': simple_title,
+ 'ext': video_extension.decode('utf-8'),
+ 'format': (format_param is None and u'NA' or format_param.decode('utf-8')),
+ 'thumbnail': video_thumbnail.decode('utf-8'),
+ 'description': video_description.decode('utf-8'),
+ 'player_url': None,
+ })
+ except UnavailableVideoError, err:
+ self._downloader.trouble(u'\nERROR: unable to download video')
+
+class BlipTVIE(InfoExtractor):
+ """Information extractor for blip.tv"""
+
+ _VALID_URL = r'^(?:https?://)?(?:\w+\.)?blip\.tv(/.+)$'
+ _URL_EXT = r'^.*\.([a-z0-9]+)$'
+
+ @staticmethod
+ def suitable(url):
+ return (re.match(BlipTVIE._VALID_URL, url) is not None)
+
+ def report_extraction(self, file_id):
+ """Report information extraction."""
+ self._downloader.to_screen(u'[blip.tv] %s: Extracting information' % file_id)
+
+ def _simplify_title(self, title):
+ res = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', title)
+ res = res.strip(ur'_')
+ return res
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
+ return
+
+ if '?' in url:
+ cchar = '&'
+ else:
+ cchar = '?'
+ json_url = url + cchar + 'skin=json&version=2&no_wrap=1'
+ request = urllib2.Request(json_url)
+ self.report_extraction(mobj.group(1))
+ try:
+ json_code = urllib2.urlopen(request).read()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.trouble(u'ERROR: unable to download video info webpage: %s' % str(err))
+ return
+ try:
+ json_data = json.loads(json_code)
+ if 'Post' in json_data:
+ data = json_data['Post']
+ else:
+ data = json_data
+
+ upload_date = datetime.datetime.strptime(data['datestamp'], '%m-%d-%y %H:%M%p').strftime('%Y%m%d')
+ video_url = data['media']['url']
+ umobj = re.match(self._URL_EXT, video_url)
+ if umobj is None:
+ raise ValueError('Can not determine filename extension')
+ ext = umobj.group(1)
+
+ self._downloader.increment_downloads()
+
+ info = {
+ 'id': data['item_id'],
+ 'url': video_url,
+ 'uploader': data['display_name'],
+ 'upload_date': upload_date,
+ 'title': data['title'],
+ 'stitle': self._simplify_title(data['title']),
+ 'ext': ext,
+ 'format': data['media']['mimeType'],
+ 'thumbnail': data['thumbnailUrl'],
+ 'description': data['description'],
+ 'player_url': data['embedUrl']
+ }
+ except (ValueError,KeyError), err:
+ self._downloader.trouble(u'ERROR: unable to parse video information: %s' % repr(err))
+ return
+
+ try:
+ self._downloader.process_info(info)
+ except UnavailableVideoError, err:
+ self._downloader.trouble(u'\nERROR: unable to download video')
+
+
+class MyVideoIE(InfoExtractor):
+ """Information Extractor for myvideo.de."""
+
+ _VALID_URL = r'(?:http://)?(?:www\.)?myvideo\.de/watch/([0-9]+)/([^?/]+).*'
+
+ def __init__(self, downloader=None):
+ InfoExtractor.__init__(self, downloader)
+
+ @staticmethod
+ def suitable(url):
+ return (re.match(MyVideoIE._VALID_URL, url) is not None)
+
+ def report_download_webpage(self, video_id):
+ """Report webpage download."""
+ self._downloader.to_screen(u'[myvideo] %s: Downloading webpage' % video_id)
+
+ def report_extraction(self, video_id):
+ """Report information extraction."""
+ self._downloader.to_screen(u'[myvideo] %s: Extracting information' % video_id)
+
+ def _real_initialize(self):
+ return
+
+ def _real_extract(self,url):
+ mobj = re.match(self._VALID_URL, url)
+ if mobj is None:
+ self._download.trouble(u'ERROR: invalid URL: %s' % url)
+ return
+
+ video_id = mobj.group(1)
+ simple_title = mobj.group(2).decode('utf-8')
+ # should actually not be necessary
+ simple_title = sanitize_title(simple_title)
+ simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', simple_title)
+
+ # Get video webpage
+ request = urllib2.Request('http://www.myvideo.de/watch/%s' % video_id)
+ try:
+ self.report_download_webpage(video_id)
+ webpage = urllib2.urlopen(request).read()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
+ return
+
+ self.report_extraction(video_id)
+ mobj = re.search(r'<link rel=\'image_src\' href=\'(http://is[0-9].myvideo\.de/de/movie[0-9]+/[a-f0-9]+)/thumbs/[^.]+\.jpg\' />',
+ webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract media URL')
+ return
+ video_url = mobj.group(1) + ('/%s.flv' % video_id)
+
+ mobj = re.search('<title>([^<]+)</title>', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract title')
+ return
+
+ video_title = mobj.group(1)
+ video_title = sanitize_title(video_title)
+
+ try:
+ print(video_url)
+ self._downloader.process_info({
+ 'id': video_id,
+ 'url': video_url,
+ 'uploader': u'NA',
+ 'upload_date': u'NA',
+ 'title': video_title,
+ 'stitle': simple_title,
+ 'ext': u'flv',
+ 'format': u'NA',
+ 'player_url': None,
+ })
+ except UnavailableVideoError:
+ self._downloader.trouble(u'\nERROR: Unable to download video')
+
+class ComedyCentralIE(InfoExtractor):
+ """Information extractor for The Daily Show and Colbert Report """
+
+ _VALID_URL = r'^(:(?P<shortname>tds|thedailyshow|cr|colbert|colbertnation|colbertreport))|(https?://)?(www\.)(?P<showname>thedailyshow|colbertnation)\.com/full-episodes/(?P<episode>.*)$'
+
+ @staticmethod
+ def suitable(url):
+ return (re.match(ComedyCentralIE._VALID_URL, url) is not None)
+
+ def report_extraction(self, episode_id):
+ self._downloader.to_screen(u'[comedycentral] %s: Extracting information' % episode_id)
+
+ def report_config_download(self, episode_id):
+ self._downloader.to_screen(u'[comedycentral] %s: Downloading configuration' % episode_id)
+
+ def report_player_url(self, episode_id):
+ self._downloader.to_screen(u'[comedycentral] %s: Determining player URL' % episode_id)
+
+ def _simplify_title(self, title):
+ res = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', title)
+ res = res.strip(ur'_')
+ return res
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
+ return
+
+ if mobj.group('shortname'):
+ if mobj.group('shortname') in ('tds', 'thedailyshow'):
+ url = 'http://www.thedailyshow.com/full-episodes/'
+ else:
+ url = 'http://www.colbertnation.com/full-episodes/'
+ mobj = re.match(self._VALID_URL, url)
+ assert mobj is not None
+
+ dlNewest = not mobj.group('episode')
+ if dlNewest:
+ epTitle = mobj.group('showname')
+ else:
+ epTitle = mobj.group('episode')
+
+ req = urllib2.Request(url)
+ self.report_extraction(epTitle)
+ try:
+ htmlHandle = urllib2.urlopen(req)
+ html = htmlHandle.read()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.trouble(u'ERROR: unable to download webpage: %s' % unicode(err))
+ return
+ if dlNewest:
+ url = htmlHandle.geturl()
+ mobj = re.match(self._VALID_URL, url)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: Invalid redirected URL: ' + url)
+ return
+ if mobj.group('episode') == '':
+ self._downloader.trouble(u'ERROR: Redirected URL is still not specific: ' + url)
+ return
+ epTitle = mobj.group('episode')
+
+ mMovieParams = re.findall('<param name="movie" value="(http://media.mtvnservices.com/(.*?:episode:([^:]*):)(.*?))"/>', html)
+ if len(mMovieParams) == 0:
+ self._downloader.trouble(u'ERROR: unable to find Flash URL in webpage ' + url)
+ return
+ show_id = mMovieParams[0][2]
+ ACT_COUNT = { # TODO: Detect this dynamically
+ 'thedailyshow.com': 4,
+ 'colbertnation.com': 3,
+ }.get(show_id, 4)
+ OFFSET = {
+ 'thedailyshow.com': 1,
+ 'colbertnation.com': 1,
+ }.get(show_id, 1)
+
+ first_player_url = mMovieParams[0][0]
+ startMediaNum = int(mMovieParams[0][3]) + OFFSET
+ movieId = mMovieParams[0][1]
+
+ playerReq = urllib2.Request(first_player_url)
+ self.report_player_url(epTitle)
+ try:
+ playerResponse = urllib2.urlopen(playerReq)
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.trouble(u'ERROR: unable to download player: %s' % unicode(err))
+ return
+ player_url = playerResponse.geturl()
+
+ for actNum in range(ACT_COUNT):
+ mediaNum = startMediaNum + actNum
+ mediaId = movieId + str(mediaNum)
+ configUrl = ('http://www.comedycentral.com/global/feeds/entertainment/media/mediaGenEntertainment.jhtml?' +
+ urllib.urlencode({'uri': mediaId}))
+ configReq = urllib2.Request(configUrl)
+ self.report_config_download(epTitle)
+ try:
+ configXml = urllib2.urlopen(configReq).read()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.trouble(u'ERROR: unable to download webpage: %s' % unicode(err))
+ return
+
+ cdoc = xml.etree.ElementTree.fromstring(configXml)
+ turls = []
+ for rendition in cdoc.findall('.//rendition'):
+ finfo = (rendition.attrib['bitrate'], rendition.findall('./src')[0].text)
+ turls.append(finfo)
+
+ if len(turls) == 0:
+ self._downloader.trouble(u'\nERROR: unable to download ' + str(mediaNum) + ': No videos found')
+ continue
+
+ # For now, just pick the highest bitrate
+ format,video_url = turls[-1]
+
+ self._downloader.increment_downloads()
+
+ effTitle = show_id.replace('.com', '') + '-' + epTitle
+ info = {
+ 'id': str(mediaNum),
+ 'url': video_url,
+ 'uploader': show_id,
+ 'upload_date': 'NA',
+ 'title': effTitle,
+ 'stitle': self._simplify_title(effTitle),
+ 'ext': 'mp4',
+ 'format': format,
+ 'thumbnail': None,
+ 'description': 'TODO: Not yet supported',
+ 'player_url': player_url
+ }
+
+ try:
+ self._downloader.process_info(info)
+ except UnavailableVideoError, err:
+ self._downloader.trouble(u'\nERROR: unable to download ' + str(mediaNum))
+ continue
+
+
+class PostProcessor(object):
+ """Post Processor class.
+
+ PostProcessor objects can be added to downloaders with their
+ add_post_processor() method. When the downloader has finished a
+ successful download, it will take its internal chain of PostProcessors
Rapsys Git / youtubedl / blobdiff