debian/control: Add recommends on aria2 | wget | curl to use external downloaders.

[youtubedl] / youtube_dl / extractor / teamcoco.py

diff --git a/youtube_dl/extractor/teamcoco.py b/youtube_dl/extractor/teamcoco.py
index 092ac74d8ea4969ecfc047b88ffd6e5d099f8ca3..18a8237197ca4f017252fa181b08bfacf67c44b2 100644 (file)
--- a/youtube_dl/extractor/teamcoco.py
+++ b/youtube_dl/extractor/teamcoco.py
@@ -1,46 +1,86 @@
+from __future__ import unicode_literals
+
 import re
 
 from .common import InfoExtractor
-from ..utils import (
-    ExtractorError,
-)
 
 
 class TeamcocoIE(InfoExtractor):
-    _VALID_URL = r'http://teamcoco\.com/video/(?P<url_title>.*)'
+    _VALID_URL = r'http://teamcoco\.com/video/(?P<video_id>[0-9]+)?/?(?P<display_id>.*)'
+    _TESTS = [
+        {
+            'url': 'http://teamcoco.com/video/80187/conan-becomes-a-mary-kay-beauty-consultant',
+            'md5': '3f7746aa0dc86de18df7539903d399ea',
+            'info_dict': {
+                'id': '80187',
+                'ext': 'mp4',
+                'title': 'Conan Becomes A Mary Kay Beauty Consultant',
+                'description': 'Mary Kay is perhaps the most trusted name in female beauty, so of course Conan is a natural choice to sell their products.'
+            }
+        }, {
+            'url': 'http://teamcoco.com/video/louis-ck-interview-george-w-bush',
+            'md5': 'cde9ba0fa3506f5f017ce11ead928f9a',
+            'info_dict': {
+                'id': '19705',
+                'ext': 'mp4',
+                "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:
-            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')
+        display_id = mobj.group('display_id')
+        webpage = self._download_webpage(url, display_id)
+
+        video_id = mobj.group("video_id")
+        if not video_id:
+            video_id = self._html_search_regex(
+                r'<div\s+class="player".*?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, display_id, 'Downloading data webpage')
 
-        video_title = self._html_search_regex(r'<meta property="og:title" content="(.+?)"',
-            webpage, u'title')
+        qualities = ['500k', '480p', '1000k', '720p', '1080p']
+        formats = []
+        for filed in data.findall('files/file'):
+            if filed.attrib.get('playmode') == 'all':
+                # it just duplicates one of the entries
+                break
+            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:
+                format_id = filed.attrib['bitrate']
+            tbr = (
+                int(filed.attrib['bitrate'])
+                if filed.attrib['bitrate'].isdigit()
+                else None)
 
-        thumbnail = self._html_search_regex(r'<meta property="og:image" content="(.+?)"',
-            webpage, u'thumbnail', fatal=False)
+            try:
+                quality = qualities.index(format_id)
+            except ValueError:
+                quality = -1
+            formats.append({
+                'url': file_url,
+                'ext': 'mp4',
+                'tbr': tbr,
+                'format_id': format_id,
+                'quality': quality,
+            })
 
-        video_description = self._html_search_regex(r'<meta property="og:description" content="(.*?)"',
-            webpage, u'description', fatal=False)
+        self._sort_formats(formats)
 
-        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,
-        }]
+        return {
+            'id': video_id,
+            'display_id': display_id,
+            'formats': formats,
+            'title': self._og_search_title(webpage),
+            'thumbnail': self._og_search_thumbnail(webpage),
+            'description': self._og_search_description(webpage),
+        }