Add TeamcocoIE (closes #212)

diff --git a/test/tests.json b/test/tests.json
index eed0628138e22ceb4ff0483ec744f13c183f8bb2..f57ebf1c9a8d3f9149786b9caeabf93585d9a4ee 100644 (file)
--- a/test/tests.json
+++ b/test/tests.json
@@ -472,5 +472,15 @@
       "uploader_id": "forestwander-nature-pictures",
       "description": "Waterfalls in the Springtime at Dark Hollow Waterfalls. These are located just off of Skyline Drive in Virginia. They are only about 6/10 of a mile hike but it is a pretty steep hill and a good climb back up."
     }
+  },
+  {
+    "name": "Teamcoco",
+    "url": "http://teamcoco.com/video/louis-ck-interview-george-w-bush",
+    "file": "19705.mp4",
+    "md5": "27b6f7527da5acf534b15f21b032656e",
+    "info_dict":{
+      "title": "Louis C.K. Interview Pt. 1 11/3/11",
+      "description": "Louis C.K. got starstruck by George W. Bush, so what? Part one."
+    }
   }
 ]

diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py
index fe47e5254c5755ac9a800edfada209754bb27946..6b644e15f5ec6921aea3ce4c9616e1bf5a4ff67d 100755 (executable)
--- a/youtube_dl/InfoExtractors.py
+++ b/youtube_dl/InfoExtractors.py
@@ -4341,6 +4341,51 @@ class FlickrIE(InfoExtractor):
             '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)
+
+        mobj = re.search(r'<article class="video" data-id="(\d+?)"', webpage)
+        video_id = mobj.group(1)
+
+        self.report_extraction(video_id)
+
+        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'<meta property="og:description" content="(.*?)"', webpage)
+        if mobj is None:
+            raise ExtractorError(u'Unable to extract description')
+        description = mobj.group(1)
+
+        data_url = 'http://teamcoco.com/cvp/2.0/%s.xml' % video_id
+        data = self._download_webpage(data_url, video_id, 'Downloading data webpage')
+        mobj = re.search(r'<file type="high".*?>(.*?)</file>', data)
+        if mobj is None:
+            raise ExtractorError(u'Unable to extract video url')
+        video_url = mobj.group(1)
+
+        return [{
+            'id':          video_id,
+            'url':         video_url,
+            'ext':         'mp4',
+            'title':       video_title,
+            'thumbnail':   thumbnail,
+            'description': description,
+        }]
 
 def gen_extractors():
     """ Return a list of an instance of every supported extractor.
@@ -4402,6 +4447,7 @@ def gen_extractors():
         HowcastIE(),
         VineIE(),
         FlickrIE(),
+        TeamcocoIE(),
         GenericIE()
     ]