- def _real_extract(self, url):
- m_url = re.match(self._VALID_URL, url)
- video_id = m_url.group('id')
- blog = m_url.group('blog_name')
-
- url = 'http://%s.tumblr.com/post/%s/' % (blog, video_id)
- webpage = self._download_webpage(url, video_id)
-
- re_video = r'src=\\x22(?P<video_url>http://%s\.tumblr\.com/video_file/%s/(.*?))\\x22 type=\\x22video/(?P<ext>.*?)\\x22' % (blog, video_id)
- video = re.search(re_video, webpage)
- if video is None:
- raise ExtractorError(u'Unable to extract video')
- video_url = video.group('video_url')
- ext = video.group('ext')
-
- video_thumbnail = self._search_regex(r'posters(.*?)\[\\x22(?P<thumb>.*?)\\x22',
- webpage, u'thumbnail', fatal=False) # We pick the first poster
- if video_thumbnail: video_thumbnail = video_thumbnail.replace('\\', '')
-
- # The only place where you can get a title, it's not complete,
- # but searching in other places doesn't work for all videos
- video_title = self._html_search_regex(r'<title>(?P<title>.*?)</title>',
- webpage, u'title', flags=re.DOTALL)
-
- return [{'id': video_id,
- 'url': video_url,
- 'title': video_title,
- 'thumbnail': video_thumbnail,
- 'ext': ext
- }]
-
-class BandcampIE(InfoExtractor):
- _VALID_URL = r'http://.*?\.bandcamp\.com/track/(?P<title>.*)'
-
- def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- title = mobj.group('title')
- webpage = self._download_webpage(url, title)
- # We get the link to the free download page
- m_download = re.search(r'freeDownloadPage: "(.*?)"', webpage)
- if m_download is None:
- raise ExtractorError(u'No free songs found')
-
- download_link = m_download.group(1)
- id = re.search(r'var TralbumData = {(.*?)id: (?P<id>\d*?)$',
- webpage, re.MULTILINE|re.DOTALL).group('id')
-
- download_webpage = self._download_webpage(download_link, id,
- 'Downloading free downloads page')
- # We get the dictionary of the track from some javascrip code
- info = re.search(r'items: (.*?),$',
- download_webpage, re.MULTILINE).group(1)
- info = json.loads(info)[0]
- # We pick mp3-320 for now, until format selection can be easily implemented.
- mp3_info = info[u'downloads'][u'mp3-320']
- # If we try to use this url it says the link has expired
- initial_url = mp3_info[u'url']
- re_url = r'(?P<server>http://(.*?)\.bandcamp\.com)/download/track\?enc=mp3-320&fsig=(?P<fsig>.*?)&id=(?P<id>.*?)&ts=(?P<ts>.*)$'
- m_url = re.match(re_url, initial_url)
- #We build the url we will use to get the final track url
- # This url is build in Bandcamp in the script download_bunde_*.js
- request_url = '%s/statdownload/track?enc=mp3-320&fsig=%s&id=%s&ts=%s&.rand=665028774616&.vrs=1' % (m_url.group('server'), m_url.group('fsig'), id, m_url.group('ts'))
- final_url_webpage = self._download_webpage(request_url, id, 'Requesting download url')
- # If we could correctly generate the .rand field the url would be
- #in the "download_url" key
- final_url = re.search(r'"retry_url":"(.*?)"', final_url_webpage).group(1)
-
- track_info = {'id':id,
- 'title' : info[u'title'],
- 'ext' : 'mp3',
- 'url' : final_url,
- 'thumbnail' : info[u'thumb_url'],
- 'uploader' : info[u'artist']
- }
-
- return [track_info]
-
-class RedTubeIE(InfoExtractor):
- """Information Extractor for redtube"""
- _VALID_URL = r'(?:http://)?(?:www\.)?redtube\.com/(?P<id>[0-9]+)'
-
- def _real_extract(self,url):
- mobj = re.match(self._VALID_URL, url)
- if mobj is None:
- raise ExtractorError(u'Invalid URL: %s' % url)
-
- video_id = mobj.group('id')
- video_extension = 'mp4'
- webpage = self._download_webpage(url, video_id)
-
- self.report_extraction(video_id)
-
- video_url = self._html_search_regex(r'<source src="(.+?)" type="video/mp4">',
- webpage, u'video URL')
-
- video_title = self._html_search_regex('<h1 class="videoTitle slidePanelMovable">(.+?)</h1>',
- webpage, u'title')
-
- return [{
- 'id': video_id,
- 'url': video_url,
- 'ext': video_extension,
- 'title': video_title,
- }]
-
-class InaIE(InfoExtractor):
- """Information Extractor for Ina.fr"""
- _VALID_URL = r'(?:http://)?(?:www\.)?ina\.fr/video/(?P<id>I[0-9]+)/.*'
-
- def _real_extract(self,url):
- mobj = re.match(self._VALID_URL, url)
-
- video_id = mobj.group('id')
- mrss_url='http://player.ina.fr/notices/%s.mrss' % video_id
- video_extension = 'mp4'
- webpage = self._download_webpage(mrss_url, video_id)
-
- self.report_extraction(video_id)
-
- video_url = self._html_search_regex(r'<media:player url="(?P<mp4url>http://mp4.ina.fr/[^"]+\.mp4)',
- webpage, u'video URL')
-
- video_title = self._search_regex(r'<title><!\[CDATA\[(?P<titre>.*?)]]></title>',
- webpage, u'title')
-
- return [{
- 'id': video_id,
- 'url': video_url,
- 'ext': video_extension,
- 'title': video_title,
- }]
-
-class HowcastIE(InfoExtractor):
- """Information Extractor for Howcast.com"""
- _VALID_URL = r'(?:https?://)?(?:www\.)?howcast\.com/videos/(?P<id>\d+)'
-
- def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
-
- video_id = mobj.group('id')
- webpage_url = 'http://www.howcast.com/videos/' + video_id
- webpage = self._download_webpage(webpage_url, video_id)
-
- self.report_extraction(video_id)
-
- video_url = self._search_regex(r'\'?file\'?: "(http://mobile-media\.howcast\.com/[0-9]+\.mp4)',
- webpage, u'video URL')
-
- video_title = self._html_search_regex(r'<meta content=(?:"([^"]+)"|\'([^\']+)\') property=\'og:title\'',
- webpage, u'title')
-
- video_description = self._html_search_regex(r'<meta content=(?:"([^"]+)"|\'([^\']+)\') name=\'description\'',
- webpage, u'description', fatal=False)
-
- thumbnail = self._html_search_regex(r'<meta content=\'(.+?)\' property=\'og:image\'',
- webpage, u'thumbnail', fatal=False)
-
- return [{
- 'id': video_id,
- 'url': video_url,
- 'ext': 'mp4',
- 'title': video_title,
- 'description': video_description,
- 'thumbnail': thumbnail,
- }]
-
-class VineIE(InfoExtractor):
- """Information Extractor for Vine.co"""
- _VALID_URL = r'(?:https?://)?(?:www\.)?vine\.co/v/(?P<id>\w+)'
-
- def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
-
- video_id = mobj.group('id')
- webpage_url = 'https://vine.co/v/' + video_id
- webpage = self._download_webpage(webpage_url, video_id)
-
- self.report_extraction(video_id)
-
- video_url = self._html_search_regex(r'<meta property="twitter:player:stream" content="(.+?)"',
- webpage, u'video URL')
-
- video_title = self._html_search_regex(r'<meta property="og:title" content="(.+?)"',
- webpage, u'title')
-
- thumbnail = self._html_search_regex(r'<meta property="og:image" content="(.+?)(\?.*?)?"',
- webpage, u'thumbnail', fatal=False)
-
- uploader = self._html_search_regex(r'<div class="user">.*?<h2>(.+?)</h2>',
- webpage, u'uploader', fatal=False, flags=re.DOTALL)
-
- return [{
- 'id': video_id,
- 'url': video_url,
- 'ext': 'mp4',
- 'title': video_title,
- 'thumbnail': thumbnail,
- 'uploader': uploader,
- }]
-
-class FlickrIE(InfoExtractor):
- """Information Extractor for Flickr videos"""
- _VALID_URL = r'(?:https?://)?(?:www\.)?flickr\.com/photos/(?P<uploader_id>[\w\-_@]+)/(?P<id>\d+).*'
-
- def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
-
- video_id = mobj.group('id')
- video_uploader_id = mobj.group('uploader_id')
- webpage_url = 'http://www.flickr.com/photos/' + video_uploader_id + '/' + video_id
- webpage = self._download_webpage(webpage_url, video_id)
-
- secret = self._search_regex(r"photo_secret: '(\w+)'", webpage, u'secret')
-
- first_url = 'https://secure.flickr.com/apps/video/video_mtl_xml.gne?v=x&photo_id=' + video_id + '&secret=' + secret + '&bitrate=700&target=_self'
- first_xml = self._download_webpage(first_url, video_id, 'Downloading first data webpage')
-
- node_id = self._html_search_regex(r'<Item id="id">(\d+-\d+)</Item>',
- first_xml, u'node_id')
-
- second_url = 'https://secure.flickr.com/video_playlist.gne?node_id=' + node_id + '&tech=flash&mode=playlist&bitrate=700&secret=' + secret + '&rd=video.yahoo.com&noad=1'
- second_xml = self._download_webpage(second_url, video_id, 'Downloading second data webpage')
-
- self.report_extraction(video_id)
-
- mobj = re.search(r'<STREAM APP="(.+?)" FULLPATH="(.+?)"', second_xml)
- if mobj is None:
- raise ExtractorError(u'Unable to extract video url')
- video_url = mobj.group(1) + unescapeHTML(mobj.group(2))
-
- video_title = self._html_search_regex(r'<meta property="og:title" content=(?:"([^"]+)"|\'([^\']+)\')',
- webpage, u'video title')
-
- video_description = self._html_search_regex(r'<meta property="og:description" content=(?:"([^"]+)"|\'([^\']+)\')',
- webpage, u'description', fatal=False)
-
- thumbnail = self._html_search_regex(r'<meta property="og:image" content=(?:"([^"]+)"|\'([^\']+)\')',
- webpage, u'thumbnail', fatal=False)
-
- return [{
- 'id': video_id,
- 'url': video_url,
- 'ext': 'mp4',
- 'title': video_title,
- 'description': video_description,
- 'thumbnail': thumbnail,
- 'uploader_id': video_uploader_id,
- }]
-
-class TeamcocoIE(InfoExtractor):
- _VALID_URL = r'http://teamcoco\.com/video/(?P<url_title>.*)'
-
- def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- if mobj is None:
- raise ExtractorError(u'Invalid URL: %s' % url)
- url_title = mobj.group('url_title')
- webpage = self._download_webpage(url, url_title)
-
- video_id = self._html_search_regex(r'<article class="video" data-id="(\d+?)"',
- webpage, u'video id')
-
- self.report_extraction(video_id)
-
- video_title = self._html_search_regex(r'<meta property="og:title" content="(.+?)"',
- webpage, u'title')
-
- thumbnail = self._html_search_regex(r'<meta property="og:image" content="(.+?)"',
- webpage, u'thumbnail', fatal=False)
-
- video_description = self._html_search_regex(r'<meta property="og:description" content="(.*?)"',
- webpage, u'description', fatal=False)
-
- data_url = 'http://teamcoco.com/cvp/2.0/%s.xml' % video_id
- data = self._download_webpage(data_url, video_id, 'Downloading data webpage')
-
- video_url = self._html_search_regex(r'<file type="high".*?>(.*?)</file>',
- data, u'video URL')
-
- return [{
- 'id': video_id,
- 'url': video_url,
- 'ext': 'mp4',
- 'title': video_title,
- 'thumbnail': thumbnail,
- 'description': video_description,
- }]