+
+class NBAIE(InfoExtractor):
+ _VALID_URL = r'^(?:https?://)?(?:watch\.|www\.)?nba\.com/(?:nba/)?video(/[^?]*)(\?.*)?$'
+ IE_NAME = u'nba'
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
+ return
+
+ video_id = mobj.group(1)
+ if video_id.endswith('/index.html'):
+ video_id = video_id[:-len('/index.html')]
+
+ webpage = self._download_webpage(url, video_id)
+
+ video_url = u'http://ht-mobile.cdn.turner.com/nba/big' + video_id + '_nba_1280x720.mp4'
+ def _findProp(rexp, default=None):
+ m = re.search(rexp, webpage)
+ if m:
+ return unescapeHTML(m.group(1))
+ else:
+ return default
+
+ shortened_video_id = video_id.rpartition('/')[2]
+ title = _findProp(r'<meta property="og:title" content="(.*?)"', shortened_video_id).replace('NBA.com: ', '')
+ info = {
+ 'id': shortened_video_id,
+ 'url': video_url,
+ 'ext': 'mp4',
+ 'title': title,
+ 'uploader_date': _findProp(r'<b>Date:</b> (.*?)</div>'),
+ 'description': _findProp(r'<div class="description">(.*?)</h1>'),
+ }
+ return [info]
+
+class JustinTVIE(InfoExtractor):
+ """Information extractor for justin.tv and twitch.tv"""
+ # TODO: One broadcast may be split into multiple videos. The key
+ # 'broadcast_id' is the same for all parts, and 'broadcast_part'
+ # starts at 1 and increases. Can we treat all parts as one video?
+
+ _VALID_URL = r"""(?x)^(?:http://)?(?:www\.)?(?:twitch|justin)\.tv/
+ ([^/]+)(?:/b/([^/]+))?/?(?:\#.*)?$"""
+ _JUSTIN_PAGE_LIMIT = 100
+ IE_NAME = u'justin.tv'
+
+ def report_extraction(self, file_id):
+ """Report information extraction."""
+ self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, file_id))
+
+ def report_download_page(self, channel, offset):
+ """Report attempt to download a single page of videos."""
+ self._downloader.to_screen(u'[%s] %s: Downloading video information from %d to %d' %
+ (self.IE_NAME, channel, offset, offset + self._JUSTIN_PAGE_LIMIT))
+
+ # Return count of items, list of *valid* items
+ def _parse_page(self, url):
+ try:
+ urlh = compat_urllib_request.urlopen(url)
+ webpage_bytes = urlh.read()
+ webpage = webpage_bytes.decode('utf-8', 'ignore')
+ except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
+ self._downloader.trouble(u'ERROR: unable to download video info JSON: %s' % compat_str(err))
+ return
+
+ response = json.loads(webpage)
+ if type(response) != list:
+ error_text = response.get('error', 'unknown error')
+ self._downloader.trouble(u'ERROR: Justin.tv API: %s' % error_text)
+ return
+ info = []
+ for clip in response:
+ video_url = clip['video_file_url']
+ if video_url:
+ video_extension = os.path.splitext(video_url)[1][1:]
+ video_date = re.sub('-', '', clip['start_time'][:10])
+ video_uploader_id = clip.get('user_id', clip.get('channel_id'))
+ info.append({
+ 'id': clip['id'],
+ 'url': video_url,
+ 'title': clip['title'],
+ 'uploader': clip.get('channel_name', video_uploader_id),
+ 'uploader_id': video_uploader_id,
+ 'upload_date': video_date,
+ 'ext': video_extension,
+ })
+ return (len(response), info)
+
+ 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
+
+ api = 'http://api.justin.tv'
+ video_id = mobj.group(mobj.lastindex)
+ paged = False
+ if mobj.lastindex == 1:
+ paged = True
+ api += '/channel/archives/%s.json'
+ else:
+ api += '/broadcast/by_archive/%s.json'
+ api = api % (video_id,)
+
+ self.report_extraction(video_id)
+
+ info = []
+ offset = 0
+ limit = self._JUSTIN_PAGE_LIMIT
+ while True:
+ if paged:
+ self.report_download_page(video_id, offset)
+ page_url = api + ('?offset=%d&limit=%d' % (offset, limit))
+ page_count, page_info = self._parse_page(page_url)
+ info.extend(page_info)
+ if not paged or page_count != limit:
+ break
+ offset += limit
+ return info
+
+class FunnyOrDieIE(InfoExtractor):
+ _VALID_URL = r'^(?:https?://)?(?:www\.)?funnyordie\.com/videos/(?P<id>[0-9a-f]+)/.*$'
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
+ return
+
+ video_id = mobj.group('id')
+ webpage = self._download_webpage(url, video_id)
+
+ m = re.search(r'<video[^>]*>\s*<source[^>]*>\s*<source src="(?P<url>[^"]+)"', webpage, re.DOTALL)
+ if not m:
+ self._downloader.trouble(u'ERROR: unable to find video information')
+ video_url = unescapeHTML(m.group('url'))
+
+ m = re.search(r"class='player_page_h1'>\s+<a.*?>(?P<title>.*?)</a>", webpage)
+ if not m:
+ self._downloader.trouble(u'Cannot find video title')
+ title = unescapeHTML(m.group('title'))
+
+ m = re.search(r'<meta property="og:description" content="(?P<desc>.*?)"', webpage)
+ if m:
+ desc = unescapeHTML(m.group('desc'))
+ else:
+ desc = None
+
+ info = {
+ 'id': video_id,
+ 'url': video_url,
+ 'ext': 'mp4',
+ 'title': title,
+ 'description': desc,
+ }
+ return [info]
+
+class TweetReelIE(InfoExtractor):
+ _VALID_URL = r'^(?:https?://)?(?:www\.)?tweetreel\.com/[?](?P<id>[0-9a-z]+)$'
+
+ 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')
+ webpage = self._download_webpage(url, video_id)
+
+ m = re.search(r'<div id="left" status_id="([0-9]+)">', webpage)
+ if not m:
+ self._downloader.trouble(u'ERROR: Cannot find status ID')
+ status_id = m.group(1)
+
+ m = re.search(r'<div class="tweet_text">(.*?)</div>', webpage, flags=re.DOTALL)
+ if not m:
+ self._downloader.trouble(u'WARNING: Cannot find description')
+ desc = unescapeHTML(re.sub('<a.*?</a>', '', m.group(1))).strip()
+
+ m = re.search(r'<div class="tweet_info">.*?from <a target="_blank" href="https?://twitter.com/(?P<uploader_id>.+?)">(?P<uploader>.+?)</a>', webpage, flags=re.DOTALL)
+ if not m:
+ self._downloader.trouble(u'ERROR: Cannot find uploader')
+ uploader = unescapeHTML(m.group('uploader'))
+ uploader_id = unescapeHTML(m.group('uploader_id'))
+
+ m = re.search(r'<span unixtime="([0-9]+)"', webpage)
+ if not m:
+ self._downloader.trouble(u'ERROR: Cannot find upload date')
+ upload_date = datetime.datetime.fromtimestamp(int(m.group(1))).strftime('%Y%m%d')
+
+ title = desc
+ video_url = 'http://files.tweetreel.com/video/' + status_id + '.mov'
+
+ info = {
+ 'id': video_id,
+ 'url': video_url,
+ 'ext': 'mov',
+ 'title': title,
+ 'description': desc,
+ 'uploader': uploader,
+ 'uploader_id': uploader_id,
+ 'internal_id': status_id,
+ 'upload_date': upload_date
+ }
+ return [info]
+
+class SteamIE(InfoExtractor):
+ _VALID_URL = r"""http://store.steampowered.com/
+ (?P<urltype>video|app)/ #If the page is only for videos or for a game
+ (?P<gameID>\d+)/?
+ (?P<videoID>\d*)(?P<extra>\??) #For urltype == video we sometimes get the videoID
+ """
+
+ def suitable(self, url):
+ """Receives a URL and returns True if suitable for this IE."""
+ return re.match(self._VALID_URL, url, re.VERBOSE) is not None
+
+ def _real_extract(self, url):
+ m = re.match(self._VALID_URL, url, re.VERBOSE)
+ urlRE = r"'movie_(?P<videoID>\d+)': \{\s*FILENAME: \"(?P<videoURL>[\w:/\.\?=]+)\"(,\s*MOVIE_NAME: \"(?P<videoName>[\w:/\.\?=\+-]+)\")?\s*\},"
+ gameID = m.group('gameID')
+ videourl = 'http://store.steampowered.com/video/%s/' % gameID
+ webpage = self._download_webpage(videourl, gameID)
+ mweb = re.finditer(urlRE, webpage)
+ namesRE = r'<span class="title">(?P<videoName>.+?)</span>'
+ titles = re.finditer(namesRE, webpage)
+ videos = []
+ for vid,vtitle in zip(mweb,titles):
+ video_id = vid.group('videoID')
+ title = vtitle.group('videoName')
+ video_url = vid.group('videoURL')
+ if not video_url:
+ self._downloader.trouble(u'ERROR: Cannot find video url for %s' % video_id)
+ info = {
+ 'id':video_id,
+ 'url':video_url,
+ 'ext': 'flv',
+ 'title': unescapeHTML(title)
+ }
+ videos.append(info)
+ return videos
+
+class UstreamIE(InfoExtractor):
+ _VALID_URL = r'https?://www\.ustream\.tv/recorded/(?P<videoID>\d+)'
+ IE_NAME = u'ustream'
+
+ def _real_extract(self, url):
+ m = re.match(self._VALID_URL, url)
+ video_id = m.group('videoID')
+ video_url = u'http://tcdn.ustream.tv/video/%s' % video_id
+ webpage = self._download_webpage(url, video_id)
+ m = re.search(r'data-title="(?P<title>.+)"',webpage)
+ title = m.group('title')
+ m = re.search(r'<a class="state" data-content-type="channel" data-content-id="(?P<uploader>\d+)"',webpage)
+ uploader = m.group('uploader')
+ info = {
+ 'id':video_id,
+ 'url':video_url,
+ 'ext': 'flv',
+ 'title': title,
+ 'uploader': uploader
+ }
+ return [info]
+
+
+
+class YouPornIE(InfoExtractor):
+ """Information extractor for youporn.com."""
+
+ _VALID_URL = r'^(?:https?://)?(?:\w+\.)?youporn\.com/watch/(?P<videoid>[0-9]+)/(?P<title>[^/]+)'
+
+ def __init__(self, downloader=None):
+ InfoExtractor.__init__(self, downloader)
+
+ # def report_id(self, video_id):
+ # """Report finding video ID"""
+ # self._downloader.to_screen(u'[youporn] Video ID: %s' % video_id)
+
+ # def report_webpage(self, url):
+ # """Report downloading page"""
+ # self._downloader.to_screen(u'[youporn] Downloaded page: %s' % url)
+
+ # def report_title(self, video_title):
+ # """Report dfinding title"""
+ # self._downloader.to_screen(u'[youporn] Title: %s' % video_title)
+
+ # def report_uploader(self, uploader):
+ # """Report dfinding title"""
+ # self._downloader.to_screen(u'[youporn] Uploader: %s' % uploader)
+
+ # def report_upload_date(self, video_date):
+ # """Report finding date"""
+ # self._downloader.to_screen(u'[youporn] Date: %s' % video_date)
+
+ def _print_formats(self, formats):
+ """Print all available formats"""
+ print('Available formats:')
+ print(u'ext\t\tformat')
+ print(u'---------------------------------')
+ for format in formats:
+ print(u'%s\t\t%s' % (format['ext'], format['format']))
+
+ def _specific(self, req_format, formats):
+ for x in formats:
+ if(x["format"]==req_format):
+ return x
+ return None
+
+ 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('videoid')
+ #self.report_id(video_id)
+
+ webpage = self._download_webpage(url, video_id)
+ #self.report_webpage(url)
+
+ # Get the video title
+ VIDEO_TITLE_RE = r'videoTitleArea">(?P<title>.*)</h1>'
+ result = re.search(VIDEO_TITLE_RE, webpage)
+ if result is None:
+ self._downloader.trouble(u'ERROR: unable to extract video title')
+ return
+ video_title = result.group('title').strip()
+ #self.report_title(video_title)
+
+ # Get the video date
+ VIDEO_DATE_RE = r'Date:</b>(?P<date>.*)</li>'
+ result = re.search(VIDEO_DATE_RE, webpage)
+ if result is None:
+ self._downloader.trouble(u'ERROR: unable to extract video date')
+ return
+ upload_date = result.group('date').strip()
+ #self.report_upload_date(upload_date)
+
+ # Get the video uploader
+ VIDEO_UPLOADER_RE = r'Submitted:</b>(?P<uploader>.*)</li>'
+ result = re.search(VIDEO_UPLOADER_RE, webpage)
+ if result is None:
+ self._downloader.trouble(u'ERROR: unable to extract uploader')
+ return
+ video_uploader = result.group('uploader').strip()
+ video_uploader = clean_html( video_uploader )
+ #self.report_uploader(video_uploader)
+
+ # Get all of the formats available
+ DOWNLOAD_LIST_RE = r'(?s)<ul class="downloadList">(?P<download_list>.*?)</ul>'
+ result = re.search(DOWNLOAD_LIST_RE, webpage)
+ if result is None:
+ self._downloader.trouble(u'ERROR: unable to extract download list')
+ return
+ download_list_html = result.group('download_list').strip()
+
+ # Get all of the links from the page
+ LINK_RE = r'(?s)<a href="(?P<url>[^"]+)">'
+ links = re.findall(LINK_RE, download_list_html)
+ if(len(links) == 0):
+ self._downloader.trouble(u'ERROR: no known formats available for video')
+ return
+
+ self._downloader.to_screen(u'[youporn] Links found: %d' % len(links))
+
+ formats = []
+ for link in links:
+
+ # A link looks like this:
+ # http://cdn1.download.youporn.phncdn.com/201210/31/8004515/480p_370k_8004515/YouPorn%20-%20Nubile%20Films%20The%20Pillow%20Fight.mp4?nvb=20121113051249&nva=20121114051249&ir=1200&sr=1200&hash=014b882080310e95fb6a0
+ # A path looks like this:
+ # /201210/31/8004515/480p_370k_8004515/YouPorn%20-%20Nubile%20Films%20The%20Pillow%20Fight.mp4
+ video_url = unescapeHTML( link )
+ path = compat_urllib_parse_urlparse( video_url ).path
+ extension = os.path.splitext( path )[1][1:]
+ format = path.split('/')[4].split('_')[:2]
+ size = format[0]
+ bitrate = format[1]
+ format = "-".join( format )
+ title = u'%s-%s-%s' % (video_title, size, bitrate)
+
+ formats.append({
+ 'id': video_id,
+ 'url': video_url,
+ 'uploader': video_uploader,
+ 'upload_date': upload_date,
+ 'title': title,
+ 'ext': extension,
+ 'format': format,
+ 'thumbnail': None,
+ 'description': None,
+ 'player_url': None
+ })
+
+ if self._downloader.params.get('listformats', None):
+ self._print_formats(formats)
+ return
+
+ req_format = self._downloader.params.get('format', None)
+ #format_limit = self._downloader.params.get('format_limit', None)
+ self._downloader.to_screen(u'[youporn] Format: %s' % req_format)
+
+
+ if req_format is None or req_format == 'best':
+ return [formats[0]]
+ elif req_format == 'worst':
+ return [formats[-1]]
+ elif req_format in ('-1', 'all'):
+ return formats
+ else:
+ format = self._specific( req_format, formats )
+ if result is None:
+ self._downloader.trouble(u'ERROR: requested format not available')
+ return
+ return [format]
+
+
+
+class PornotubeIE(InfoExtractor):
+ """Information extractor for pornotube.com."""
+
+ _VALID_URL = r'^(?:https?://)?(?:\w+\.)?pornotube\.com(/c/(?P<channel>[0-9]+))?(/m/(?P<videoid>[0-9]+))(/(?P<title>.+))$'
+
+ # def __init__(self, downloader=None):
+ # InfoExtractor.__init__(self, downloader)
+
+ # def report_extract_entry(self, url):
+ # """Report downloading extry"""
+ # self._downloader.to_screen(u'[pornotube] Downloading entry: %s' % url.decode('utf-8'))
+
+ # def report_date(self, upload_date):
+ # """Report finding uploaded date"""
+ # self._downloader.to_screen(u'[pornotube] Entry date: %s' % upload_date)
+
+ # def report_webpage(self, url):
+ # """Report downloading page"""
+ # self._downloader.to_screen(u'[pornotube] Downloaded page: %s' % url)
+
+ # def report_title(self, video_title):
+ # """Report downloading extry"""
+ # self._downloader.to_screen(u'[pornotube] Title: %s' % video_title.decode('utf-8'))
+
+ 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('videoid')
+ video_title = mobj.group('title')
+ #self.report_title(video_title);
+
+ # Get webpage content
+ webpage = self._download_webpage(url, video_id)
+ #self.report_webpage(url)
+
+ # Get the video URL
+ VIDEO_URL_RE = r'url: "(?P<url>http://video[0-9].pornotube.com/.+\.flv)",'
+ result = re.search(VIDEO_URL_RE, webpage)
+ if result is None:
+ self._downloader.trouble(u'ERROR: unable to extract video url')
+ return
+ video_url = compat_urllib_parse.unquote(result.group('url'))
+ #self.report_extract_entry(video_url)
+
+ #Get the uploaded date
+ VIDEO_UPLOADED_RE = r'<div class="video_added_by">Added (?P<date>[0-9\/]+) by'
+ result = re.search(VIDEO_UPLOADED_RE, webpage)
+ if result is None:
+ self._downloader.trouble(u'ERROR: unable to extract video title')
+ return
+ upload_date = result.group('date')
+ #self.report_date(upload_date);
+
+ info = {'id': video_id,
+ 'url': video_url,
+ 'uploader': None,
+ 'upload_date': upload_date,
+ 'title': video_title,
+ 'ext': 'flv',
+ 'format': 'flv',
+ 'thumbnail': None,
+ 'description': None,
+ 'player_url': None}
+
+ return [info]
+
+
+
+class YouJizzIE(InfoExtractor):
+ """Information extractor for youjizz.com."""
+
+ _VALID_URL = r'^(?:https?://)?(?:\w+\.)?youjizz\.com/videos/(?P<videoid>[^.]+).html$'
+
+ def __init__(self, downloader=None):
+ InfoExtractor.__init__(self, downloader)
+
+ # def report_extract_entry(self, url):
+ # """Report downloading extry"""
+ # self._downloader.to_screen(u'[youjizz] Downloading entry: %s' % url.decode('utf-8'))
+
+ # def report_webpage(self, url):
+ # """Report downloading page"""
+ # self._downloader.to_screen(u'[youjizz] Downloaded page: %s' % url)
+
+ # def report_title(self, video_title):
+ # """Report downloading extry"""
+ # self._downloader.to_screen(u'[youjizz] Title: %s' % video_title.decode('utf-8'))
+
+ # def report_embed_page(self, embed_page):
+ # """Report downloading extry"""
+ # self._downloader.to_screen(u'[youjizz] Embed Page: %s' % embed_page.decode('utf-8'))
+
+ 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('videoid')
+
+ # Get webpage content
+ webpage = self._download_webpage(url, video_id)
+ #self.report_webpage(url)
+
+ # Get the video title
+ VIDEO_TITLE_RE = r'<title>(?P<title>.*)</title>'
+ result = re.search(VIDEO_TITLE_RE, webpage)
+ if result is None:
+ self._downloader.trouble(u'ERROR: unable to extract video title')
+ return
+ video_title = result.group('title').strip()
+ #self.report_title(video_title)
+
+ # Get the embed page
+ EMBED_PAGE_RE = r'http://www.youjizz.com/videos/embed/(?P<videoid>[0-9]+)'
+ result = re.search(EMBED_PAGE_RE, webpage)
+ if result is None:
+ self._downloader.trouble(u'ERROR: unable to extract embed page')
+ return
+
+ embed_page_url = result.group(0).strip()
+ video_id = result.group('videoid')
+ #self.report_embed_page(embed_page_url)
+
+ webpage = self._download_webpage(embed_page_url, video_id)
+
+ # Get the video URL
+ SOURCE_RE = r'so.addVariable\("file",encodeURIComponent\("(?P<source>[^"]+)"\)\);'
+ result = re.search(SOURCE_RE, webpage)
+ if result is None:
+ self._downloader.trouble(u'ERROR: unable to extract video url')
+ return
+ video_url = result.group('source')
+ #self.report_extract_entry(video_url)
+
+ info = {'id': video_id,
+ 'url': video_url,
+ 'uploader': None,
+ 'upload_date': None,
+ 'title': video_title,
+ 'ext': 'flv',
+ 'format': 'flv',
+ 'thumbnail': None,
+ 'description': None,
+ 'player_url': embed_page_url}
+
+ return [info]
+
+
+def gen_extractors():
+ """ Return a list of an instance of every supported extractor.
+ The order does matter; the first extractor matched is the one handling the URL.
+ """
+ return [
+ YoutubePlaylistIE(),
+ YoutubeChannelIE(),
+ YoutubeUserIE(),
+ YoutubeSearchIE(),
+ YoutubeIE(),
+ MetacafeIE(),
+ DailymotionIE(),
+ GoogleSearchIE(),
+ PhotobucketIE(),
+ YahooIE(),
+ YahooSearchIE(),
+ DepositFilesIE(),
+ FacebookIE(),
+ BlipTVUserIE(),
+ BlipTVIE(),
+ VimeoIE(),
+ MyVideoIE(),
+ ComedyCentralIE(),
+ EscapistIE(),
+ CollegeHumorIE(),
+ XVideosIE(),
+ SoundcloudIE(),
+ InfoQIE(),
+ MixcloudIE(),
+ StanfordOpenClassroomIE(),
+ MTVIE(),
+ YoukuIE(),
+ XNXXIE(),
+ YouJizzIE(),
+ PornotubeIE(),
+ YouPornIE(),
+ GooglePlusIE(),
+ ArteTvIE(),
+ NBAIE(),
+ JustinTVIE(),
+ FunnyOrDieIE(),
+ TweetReelIE(),
+ SteamIE(),
+ UstreamIE(),
+ GenericIE()
+ ]
+
+
projects / youtube-dl / blobdiff