youtube-dl

commit cc61fc3934bb3d130e814e2d2345fe6cda2ad9c3
parent c2530d3319fd32adfc43cc349b9491040ee631d5
Author: Philipp Hagemeister <phihag@phihag.de>
Date:   Tue, 29 Nov 2016 10:11:08 +0100

[comedycentral] Add new extractor for full-episodes

CC seems to have added yet another indirection for full episodes - the mgid is now only in a linked feed.
This may be a little brittle, but it's better than failing outright.
Plus, the current The Daily Show episode now works :)

Diffstat:
M
youtube_dl/extractor/comedycentral.py
 | 
33
++++++++++++++++++++++++++++++++-
M
youtube_dl/extractor/extractors.py
 | 
1
+

2 files changed, 33 insertions(+), 1 deletion(-)
diff --git a/youtube_dl/extractor/comedycentral.py b/youtube_dl/extractor/comedycentral.py
@@ -6,7 +6,7 @@ from .common import InfoExtractor
 
 class ComedyCentralIE(MTVServicesInfoExtractor):
     _VALID_URL = r'''(?x)https?://(?:www\.)?cc\.com/
-        (video-clips|episodes|cc-studios|video-collections|full-episodes|shows)
+        (video-clips|episodes|cc-studios|video-collections|shows)
         /(?P<title>.*)'''
     _FEED_URL = 'http://comedycentral.com/feeds/mrss/'
 
@@ -27,6 +27,37 @@ class ComedyCentralIE(MTVServicesInfoExtractor):
     }]
 
 
+class ComedyCentralFullEpisodesIE(MTVServicesInfoExtractor):
+    _VALID_URL = r'''(?x)https?://(?:www\.)?cc\.com/
+        (?:full-episodes)
+        /(?P<id>[^?]+)'''
+    _FEED_URL = 'http://comedycentral.com/feeds/mrss/'
+
+    _TESTS = [{
+        'url': 'http://www.cc.com/full-episodes/pv391a/the-daily-show-with-trevor-noah-november-28--2016---ryan-speedo-green-season-22-ep-22028',
+        'info_dict': {
+            'description': 'Donald Trump is accused of exploiting his president-elect status for personal gain, Cuban leader Fidel Castro dies, and Ryan Speedo Green discusses "Sing for Your Life."',
+            'title': 'November 28, 2016 - Ryan Speedo Green',
+        },
+        'playlist_count': 4,
+    }]
+
+    def _real_extract(self, url):
+        playlist_id = self._match_id(url)
+        webpage = self._download_webpage(url, playlist_id)
+
+        feed_json = self._search_regex(r'var triforceManifestFeed\s*=\s*(\{.+?\});\n', webpage, 'triforce feeed')
+        feed = self._parse_json(feed_json, playlist_id)
+        zones = feed['manifest']['zones']
+
+        video_zone = zones['t2_lc_promo1']
+        feed = self._download_json(video_zone['feed'], playlist_id)
+        mgid = feed['result']['data']['id']
+
+        videos_info = self._get_videos_info(mgid)
+        return videos_info
+
+
 class ToshIE(MTVServicesInfoExtractor):
     IE_DESC = 'Tosh.0'
     _VALID_URL = r'^https?://tosh\.cc\.com/video-(?:clips|collections)/[^/]+/(?P<videotitle>[^/?#]+)'
diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py
@@ -180,6 +180,7 @@ from .cnn import (
 from .coub import CoubIE
 from .collegerama import CollegeRamaIE
 from .comedycentral import (
+    ComedyCentralFullEpisodesIE,
     ComedyCentralIE,
     ComedyCentralShortnameIE,
     ComedyCentralTVIE,