diff options
Diffstat (limited to 'youtube_dl/InfoExtractors.py')
| -rwxr-xr-x | youtube_dl/InfoExtractors.py | 111 |
1 files changed, 104 insertions, 7 deletions
diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py index cd7923c52..2dd1c49f6 100755 --- a/youtube_dl/InfoExtractors.py +++ b/youtube_dl/InfoExtractors.py @@ -3427,18 +3427,26 @@ class UstreamIE(InfoExtractor): 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') + self.report_extraction(video_id) + try: + m = re.search(r'data-title="(?P<title>.+)"',webpage) + title = m.group('title') + m = re.search(r'data-content-type="channel".*?>(?P<uploader>.*?)</a>', + webpage, re.DOTALL) + uploader = unescapeHTML(m.group('uploader').strip()) + m = re.search(r'<link rel="image_src" href="(?P<thumb>.*?)"', webpage) + thumb = m.group('thumb') + except AttributeError: + raise ExtractorError(u'Unable to extract info') info = { 'id':video_id, 'url':video_url, 'ext': 'flv', 'title': title, - 'uploader': uploader + 'uploader': uploader, + 'thumbnail': thumb, } - return [info] + return info class WorldStarHipHopIE(InfoExtractor): _VALID_URL = r'https?://(?:www|m)\.worldstar(?:candy|hiphop)\.com/videos/video\.php\?v=(?P<id>.*)' @@ -4159,7 +4167,7 @@ class RedTubeIE(InfoExtractor): class InaIE(InfoExtractor): """Information Extractor for Ina.fr""" - _VALID_URL = r'(?:http://)?(?:www.)?ina\.fr/video/(?P<id>I[0-9]+)/.*' + _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) @@ -4186,6 +4194,93 @@ class InaIE(InfoExtractor): '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) + + mobj = re.search(r'\'file\': "(http://mobile-media\.howcast\.com/\d+\.mp4)"', webpage) + if mobj is None: + raise ExtractorError(u'Unable to extract video URL') + video_url = mobj.group(1) + + mobj = re.search(r'<meta content=(?:"([^"]+)"|\'([^\']+)\') property=\'og:title\'', webpage) + if mobj is None: + raise ExtractorError(u'Unable to extract title') + video_title = mobj.group(1) or mobj.group(2) + + mobj = re.search(r'<meta content=(?:"([^"]+)"|\'([^\']+)\') name=\'description\'', webpage) + if mobj is None: + self._downloader.report_warning(u'unable to extract description') + video_description = None + else: + video_description = mobj.group(1) or mobj.group(2) + + mobj = re.search(r'<meta content=\'(.+?)\' property=\'og:image\'', webpage) + if mobj is None: + raise ExtractorError(u'Unable to extract thumbnail') + thumbnail = mobj.group(1) + + 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) + + mobj = re.search(r'<meta property="twitter:player:stream" content="(.+?)"', webpage) + if mobj is None: + raise ExtractorError(u'Unable to extract video URL') + video_url = mobj.group(1) + + mobj = re.search(r'<meta property="og:title" content="(.+?)"', webpage) + if mobj is None: + raise ExtractorError(u'Unable to extract title') + video_title = mobj.group(1) + + mobj = re.search(r'<meta property="og:image" content="(.+?)(\?.*?)?"', webpage) + if mobj is None: + raise ExtractorError(u'Unable to extract thumbnail') + thumbnail = mobj.group(1) + + mobj = re.search(r'<div class="user">.*?<h2>(.+?)</h2>', webpage, re.DOTALL) + if mobj is None: + raise ExtractorError(u'Unable to extract uploader') + uploader = mobj.group(1) + + return [{ + 'id': video_id, + 'url': video_url, + 'ext': 'mp4', + 'title': video_title, + 'thumbnail': thumbnail, + 'uploader': uploader, + }] + 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. @@ -4243,6 +4338,8 @@ def gen_extractors(): BandcampIE(), RedTubeIE(), InaIE(), + HowcastIE(), + VineIE(), GenericIE() ] |