[teamcoco] Extract m3u8 URLs

[youtube-dl] / youtube_dl / extractor / teamcoco.py

diff --git a/youtube_dl/extractor/teamcoco.py b/youtube_dl/extractor/teamcoco.py
index 5793dbc1085a86fdf573a432805be129dc62de94..41677503c7a3f5d1530d4a4d8b8e2fc8631e28a2 100644 (file)
--- a/youtube_dl/extractor/teamcoco.py
+++ b/youtube_dl/extractor/teamcoco.py
@@ -4,7 +4,10 @@ import base64
 import re
 
 from .common import InfoExtractor
-from ..utils import qualities
+from ..utils import (
+    ExtractorError,
+    qualities,
+)
 
 
 class TeamcocoIE(InfoExtractor):
@@ -49,35 +52,37 @@ class TeamcocoIE(InfoExtractor):
             video_id = self._html_search_regex(
                 self._VIDEO_ID_REGEXES, webpage, 'video id')
 
-        embed_url = 'http://teamcoco.com/embed/v/%s' % video_id
-        embed = self._download_webpage(
-            embed_url, video_id, 'Downloading embed page')
-
-        encoded_data = self._search_regex(
-            r'"preload"\s*:\s*"([^"]+)"', embed, 'encoded data')
+        preloads = re.findall(r'"preload":\s*"([^"]+)"', webpage)
+        if not preloads:
+            raise ExtractorError('Preload information could not be extracted')
+        preload = max([(len(p), p) for p in preloads])[1]
         data = self._parse_json(
-            base64.b64decode(encoded_data.encode('ascii')).decode('utf-8'), video_id)
+            base64.b64decode(preload.encode('ascii')).decode('utf-8'), video_id)
 
         formats = []
         get_quality = qualities(['500k', '480p', '1000k', '720p', '1080p'])
         for filed in data['files']:
-            m_format = re.search(r'(\d+(k|p))\.mp4', filed['url'])
-            if m_format is not None:
-                format_id = m_format.group(1)
+            if filed['type'] == 'hls':
+                formats.extend(self._extract_m3u8_formats(
+                    filed['url'], video_id, ext='mp4'))
             else:
-                format_id = filed['bitrate']
-            tbr = (
-                int(filed['bitrate'])
-                if filed['bitrate'].isdigit()
-                else None)
+                m_format = re.search(r'(\d+(k|p))\.mp4', filed['url'])
+                if m_format is not None:
+                    format_id = m_format.group(1)
+                else:
+                    format_id = filed['bitrate']
+                tbr = (
+                    int(filed['bitrate'])
+                    if filed['bitrate'].isdigit()
+                    else None)
 
-            formats.append({
-                'url': filed['url'],
-                'ext': 'mp4',
-                'tbr': tbr,
-                'format_id': format_id,
-                'quality': get_quality(format_id),
-            })
+                formats.append({
+                    'url': filed['url'],
+                    'ext': 'mp4',
+                    'tbr': tbr,
+                    'format_id': format_id,
+                    'quality': get_quality(format_id),
+                })
 
         self._sort_formats(formats)