diff options
Diffstat (limited to 'youtube_dl')
| -rwxr-xr-x | youtube_dl/InfoExtractors.py | 39 | ||||
| -rw-r--r-- | youtube_dl/extractor/teamcoco.py | 46 |
2 files changed, 47 insertions, 38 deletions
diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py index d9cb3260d..300bd7a72 100755 --- a/youtube_dl/InfoExtractors.py +++ b/youtube_dl/InfoExtractors.py @@ -57,6 +57,7 @@ from .extractor.soundcloud import SoundcloudIE, SoundcloudSetIE from .extractor.spiegel import SpiegelIE from .extractor.stanfordoc import StanfordOpenClassroomIE from .extractor.steam import SteamIE +from .extractor.teamcoco import TeamcocoIE from .extractor.ted import TEDIE from .extractor.tumblr import TumblrIE from .extractor.ustream import UstreamIE @@ -111,44 +112,6 @@ from .extractor.zdf import ZDFIE -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, - }] class XHamsterIE(InfoExtractor): """Information Extractor for xHamster""" diff --git a/youtube_dl/extractor/teamcoco.py b/youtube_dl/extractor/teamcoco.py new file mode 100644 index 000000000..092ac74d8 --- /dev/null +++ b/youtube_dl/extractor/teamcoco.py @@ -0,0 +1,46 @@ +import re + +from .common import InfoExtractor +from ..utils import ( + ExtractorError, +) + + +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, + }] |