youtube-dl

commit 46d9760f5ebd86ee5b34fd669f44b124f34fffc1
parent 90d71d3f088bbb787795aa6018eda21e2a821e7d
Author: Philipp Hagemeister <phihag@phihag.de>
Date:   Fri, 12 Dec 2014 20:17:26 +0100

Merge remote-tracking branch 'fstirlitz/master'

Diffstat:
M
youtube_dl/extractor/__init__.py
 | 
1
+
A
youtube_dl/extractor/ccc.py
 | 
46
++++++++++++++++++++++++++++++++++++++++++++++

2 files changed, 47 insertions(+), 0 deletions(-)
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
@@ -48,6 +48,7 @@ from .canalplus import CanalplusIE
 from .canalc2 import Canalc2IE
 from .cbs import CBSIE
 from .cbsnews import CBSNewsIE
+from .ccc import ComCarCoffIE
 from .ceskatelevize import CeskaTelevizeIE
 from .channel9 import Channel9IE
 from .chilloutzone import ChilloutzoneIE
diff --git a/youtube_dl/extractor/ccc.py b/youtube_dl/extractor/ccc.py
@@ -0,0 +1,46 @@
+# encoding: utf-8
+import re
+import json
+
+from .common import InfoExtractor
+from ..utils import (
+    unified_strdate,
+)
+
+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',
+            },
+        }
+    ]
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_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]
+
+        return {
+            'id': video_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),
+        }