debian/NEWS: Add link to my webpage to give more details.

[youtubedl] / youtube_dl / extractor / teamcoco.py

diff --git a/youtube_dl/extractor/teamcoco.py b/youtube_dl/extractor/teamcoco.py
index 2bf26d05682e8e2535d412c2718d78bec6077622..9dcffead04d5466c14c6f2ff60995ecfb5435e6d 100644 (file)
--- a/youtube_dl/extractor/teamcoco.py
+++ b/youtube_dl/extractor/teamcoco.py
@@ -1,3 +1,5 @@
+from __future__ import unicode_literals
+

 import re
 
 from .common import InfoExtractor
 import re
 
 from .common import InfoExtractor


@@ -9,61 +11,66 @@ from ..utils import (
 class TeamcocoIE(InfoExtractor):
     _VALID_URL = r'http://teamcoco\.com/video/(?P<url_title>.*)'
     _TEST = {
 class TeamcocoIE(InfoExtractor):
     _VALID_URL = r'http://teamcoco\.com/video/(?P<url_title>.*)'
     _TEST = {

-        u'url': u'http://teamcoco.com/video/louis-ck-interview-george-w-bush',
-        u'file': u'19705.mp4',
-        u'md5': u'cde9ba0fa3506f5f017ce11ead928f9a',
-        u'info_dict': {
-            u"description": u"Louis C.K. got starstruck by George W. Bush, so what? Part one.", 
-            u"title": u"Louis C.K. Interview Pt. 1 11/3/11"
+        'url': 'http://teamcoco.com/video/louis-ck-interview-george-w-bush',
+        'file': '19705.mp4',
+        'md5': 'cde9ba0fa3506f5f017ce11ead928f9a',
+        'info_dict': {
+            "description": "Louis C.K. got starstruck by George W. Bush, so what? Part one.",
+            "title": "Louis C.K. Interview Pt. 1 11/3/11"

         }
     }
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         if mobj is None:
         }
     }
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         if mobj is None:

-            raise ExtractorError(u'Invalid URL: %s' % url)
+            raise ExtractorError('Invalid URL: %s' % url)

         url_title = mobj.group('url_title')
         webpage = self._download_webpage(url, url_title)
 
         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')
+        video_id = self._html_search_regex(
+            r'<article class="video" data-id="(\d+?)"',
+            webpage, 'video id')

 
         self.report_extraction(video_id)
 
         data_url = 'http://teamcoco.com/cvp/2.0/%s.xml' % video_id
         data = self._download_xml(data_url, video_id, 'Downloading data webpage')
 
 
         self.report_extraction(video_id)
 
         data_url = 'http://teamcoco.com/cvp/2.0/%s.xml' % video_id
         data = self._download_xml(data_url, video_id, 'Downloading data webpage')
 

-

         qualities = ['500k', '480p', '1000k', '720p', '1080p']
         formats = []
         qualities = ['500k', '480p', '1000k', '720p', '1080p']
         formats = []

-        for file in data.findall('files/file'):
-            if file.attrib.get('playmode') == 'all':
+        for filed in data.findall('files/file'):
+            if filed.attrib.get('playmode') == 'all':

                 # it just duplicates one of the entries
                 break
                 # it just duplicates one of the entries
                 break

-            file_url = file.text
+            file_url = filed.text

             m_format = re.search(r'(\d+(k|p))\.mp4', file_url)
             if m_format is not None:
                 format_id = m_format.group(1)
             else:
             m_format = re.search(r'(\d+(k|p))\.mp4', file_url)
             if m_format is not None:
                 format_id = m_format.group(1)
             else:

-                format_id = file.attrib['bitrate']
+                format_id = filed.attrib['bitrate']
+            tbr = (
+                int(filed.attrib['bitrate'])
+                if filed.attrib['bitrate'].isdigit()
+                else None)
+
+            try:
+                quality = qualities.index(format_id)
+            except ValueError:
+                quality = -1

             formats.append({
                 'url': file_url,
                 'ext': 'mp4',
             formats.append({
                 'url': file_url,
                 'ext': 'mp4',

+                'tbr': tbr,

                 'format_id': format_id,
                 'format_id': format_id,

+                'quality': quality,

             })
             })

-        def sort_key(f):
-            try:
-                return qualities.index(f['format_id'])
-            except ValueError:
-                return -1
-        formats.sort(key=sort_key)
-        if not formats:
-            raise ExtractorError(u'Unable to extract video URL')
+
+        self._sort_formats(formats)

 
         return {
 
         return {

-            'id':          video_id,
+            'id': video_id,

             'formats': formats,
             'formats': formats,

-            'title':       self._og_search_title(webpage),
-            'thumbnail':   self._og_search_thumbnail(webpage),
+            'title': self._og_search_title(webpage),
+            'thumbnail': self._og_search_thumbnail(webpage),

             'description': self._og_search_description(webpage),
         }
             'description': self._og_search_description(webpage),
         }