X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fccc.py;h=73470214412b542adad72f1227e66fd341742e82;hb=77d95677b7ab4a9840ef142b14627b07a9a31120;hp=809725f1251ddffddca399dd3c36f6d873779ba1;hpb=dc65a213fd73a385470fe1d8f7ad48a174d11bd4;p=youtube-dl

diff --git a/youtube_dl/extractor/ccc.py b/youtube_dl/extractor/ccc.py
index 809725f12..734702144 100644
--- a/youtube_dl/extractor/ccc.py
+++ b/youtube_dl/extractor/ccc.py
@@ -1,46 +1,77 @@
-# encoding: utf-8
-import re
-import json
+from __future__ import unicode_literals
 
 from .common import InfoExtractor
 from ..utils import (
-    unified_strdate,
+    int_or_none,
+    parse_iso8601,
 )
 
-class ComCarCoffIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?comediansincarsgettingcoffee\.com/(?P<id>[a-z0-9\-]+)/?'
-    _TESTS = [
-        {
-            'url': 'http://comediansincarsgettingcoffee.com/miranda-sings-happy-thanksgiving-miranda/',
-            'info_dict': {
-                'id': 'miranda-sings-happy-thanksgiving-miranda',
-                'upload_date': '20141127',
-                'title': 'Happy Thanksgiving Miranda',
-                'description': 'Jerry Seinfeld and his special guest Miranda Sings cruise around town in search of coffee, complaining and apologizing along the way.',
-                'thumbnail': 'http://ccc.crackle.com/images/s5e4_thumb.jpg',
-            },
+
+class CCCIE(InfoExtractor):
+    IE_NAME = 'media.ccc.de'
+    _VALID_URL = r'https?://(?:www\.)?media\.ccc\.de/v/(?P<id>[^/?#&]+)'
+
+    _TESTS = [{
+        'url': 'https://media.ccc.de/v/30C3_-_5443_-_en_-_saal_g_-_201312281830_-_introduction_to_processor_design_-_byterazor#video',
+        'md5': '3a1eda8f3a29515d27f5adb967d7e740',
+        'info_dict': {
+            'id': '1839',
+            'ext': 'mp4',
+            'title': 'Introduction to Processor Design',
+            'description': 'md5:df55f6d073d4ceae55aae6f2fd98a0ac',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            'upload_date': '20131228',
+            'timestamp': 1388188800,
+            'duration': 3710,
         }
-    ]
+    }, {
+        'url': 'https://media.ccc.de/v/32c3-7368-shopshifting#download',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
         display_id = self._match_id(url)
         webpage = self._download_webpage(url, display_id)
+        event_id = self._search_regex(r"data-id='(\d+)'", webpage, 'event id')
+        event_data = self._download_json('https://media.ccc.de/public/events/%s' % event_id, event_id)
 
-        full_data = json.loads(self._search_regex(
-            r'<script type="application/json" id="videoData">(?P<json>.+?)</script>',
-            webpage, 'json'))
-
-        video_id = full_data['activeVideo']['video']
-        video_data = full_data['videos'][video_id]
+        formats = []
+        for recording in event_data.get('recordings', []):
+            recording_url = recording.get('recording_url')
+            if not recording_url:
+                continue
+            language = recording.get('language')
+            folder = recording.get('folder')
+            format_id = None
+            if language:
+                format_id = language
+            if folder:
+                if language:
+                    format_id += '-' + folder
+                else:
+                    format_id = folder
+            vcodec = 'h264' if 'h264' in folder else (
+                'none' if folder in ('mp3', 'opus') else None
+            )
+            formats.append({
+                'format_id': format_id,
+                'url': recording_url,
+                'width': int_or_none(recording.get('width')),
+                'height': int_or_none(recording.get('height')),
+                'filesize': int_or_none(recording.get('size'), invscale=1024 * 1024),
+                'language': language,
+                'vcodec': vcodec,
+            })
+        self._sort_formats(formats)
 
         return {
-            'id': video_id,
+            'id': event_id,
             'display_id': display_id,
-            'title': video_data['title'],
-            'description': video_data['description'],
-            # XXX: the original datum is a full ISO timestamp... why convert it to a worse format?
-            'upload_date': unified_strdate(video_data['pubDate']),
-            'thumbnail': video_data['images']['thumb'],
-            # XXX: what do we do with video_data['images']['poster']?
-            'formats': self._extract_m3u8_formats(video_data['mediaUrl'], video_id),
+            'title': event_data['title'],
+            'description': event_data.get('description'),
+            'thumbnail': event_data.get('thumb_url'),
+            'timestamp': parse_iso8601(event_data.get('date')),
+            'duration': int_or_none(event_data.get('length')),
+            'tags': event_data.get('tags'),
+            'formats': formats,
         }