aboutsummaryrefslogtreecommitdiffhomepage
path: root/youtube_dl/extractor/teamcoco.py
diff options
context:
space:
mode:
authorPhilipp Hagemeister <[email protected]>2013-06-23 22:31:50 +0200
committerPhilipp Hagemeister <[email protected]>2013-06-23 22:31:50 +0200
commitcd8b83029287fa9ad1385be4ecb32d52b5f545aa (patch)
tree61a195dc5b7ddf25bcae937da06fbba76dc660df /youtube_dl/extractor/teamcoco.py
parent1ac4004f3ad0d4ea528c9883a16617abf5429448 (diff)
downloadyoutube-dl-cd8b83029287fa9ad1385be4ecb32d52b5f545aa.tar.gz
youtube-dl-cd8b83029287fa9ad1385be4ecb32d52b5f545aa.zip
[Teamcoco] Move into own file
Diffstat (limited to 'youtube_dl/extractor/teamcoco.py')
-rw-r--r--youtube_dl/extractor/teamcoco.py46
1 files changed, 46 insertions, 0 deletions
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,
+ }]