The Daily Show Podcast support

diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
index 1bb3e1a1ce5042bd420a4f3fae1fb89ce2369ef5..e94779d40455f9069f679afb6e7dd7753147afa2 100644 (file)
--- a/youtube_dl/extractor/__init__.py
+++ b/youtube_dl/extractor/__init__.py
@@ -84,7 +84,7 @@ from .cnn import (
 )
 from .collegehumor import CollegeHumorIE
 from .collegerama import CollegeRamaIE
 )
 from .collegehumor import CollegeHumorIE
 from .collegerama import CollegeRamaIE

-from .comedycentral import ComedyCentralIE, ComedyCentralShowsIE
+from .comedycentral import ComedyCentralIE, ComedyCentralShowsIE, TheDailyShowPodcastIE

 from .comcarcoff import ComCarCoffIE
 from .commonmistakes import CommonMistakesIE, UnicodeBOMIE
 from .condenast import CondeNastIE
 from .comcarcoff import ComCarCoffIE
 from .commonmistakes import CommonMistakesIE, UnicodeBOMIE
 from .condenast import CondeNastIE


@@ -250,6 +250,7 @@ from .letv import (
     LetvPlaylistIE
 )
 from .lifenews import LifeNewsIE
     LetvPlaylistIE
 )
 from .lifenews import LifeNewsIE

+from .libsyn import LibsynIE

 from .liveleak import LiveLeakIE
 from .livestream import (
     LivestreamIE,
 from .liveleak import LiveLeakIE
 from .livestream import (
     LivestreamIE,

diff --git a/youtube_dl/extractor/comedycentral.py b/youtube_dl/extractor/comedycentral.py
index e5edcc84b69ef7bdffdbb7ed158c901c560a7575..e427b9821cfe8b7aab793e7c814474efbac4477e 100644 (file)
--- a/youtube_dl/extractor/comedycentral.py
+++ b/youtube_dl/extractor/comedycentral.py
@@ -2,6 +2,7 @@ from __future__ import unicode_literals
 
 import re
 
 
 import re
 

+from .common import InfoExtractor

 from .mtv import MTVServicesInfoExtractor
 from ..compat import (
     compat_str,
 from .mtv import MTVServicesInfoExtractor
 from ..compat import (
     compat_str,


@@ -272,3 +273,23 @@ class ComedyCentralShowsIE(MTVServicesInfoExtractor):
             'title': show_name + ' ' + title,
             'description': description,
         }
             'title': show_name + ' ' + title,
             'description': description,
         }

+
+class TheDailyShowPodcastIE(InfoExtractor):
+    _VALID_URL = r'(?P<scheme>https?:)?//thedailyshow\.cc\.com/podcast/(?P<id>[a-z\-]+)'
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+
+        player_url = self._search_regex(r'<iframe(?:\s+[^>]+)?\s*src="((?:https?:)?//html5-player\.libsyn\.com/embed/episode/id/[0-9]+)', webpage, 'player URL')
+        if player_url.startswith('//'):
+            mobj = re.match(self._VALID_URL, url)
+            scheme = mobj.group('scheme')
+            if not scheme:
+                scheme = 'https:'
+            player_url = scheme + player_url
+
+        return {
+            '_type': 'url_transparent',
+            'url': player_url,
+        }

diff --git a/youtube_dl/extractor/libsyn.py b/youtube_dl/extractor/libsyn.py
new file mode 100644 (file)
index 0000000..4b5029f
--- /dev/null
+++ b/youtube_dl/extractor/libsyn.py
@@ -0,0 +1,41 @@
+# encoding: utf-8
+from .common import InfoExtractor
+from ..utils import (
+    unified_strdate,
+)
+
+class LibsynIE(InfoExtractor):
+    _VALID_URL = r'(?:https?:)?//html5-player\.libsyn\.com/embed/episode/id/(?P<id>[0-9]+)(?:/.*)?'
+
+    def _real_extract(self, url):
+        if url.startswith('//'):
+            url = 'https:' + url
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+
+        podcast_title         = self._search_regex(r'<h2>(.*?)</h2>', webpage, 'show title')
+        podcast_episode_title = self._search_regex(r'<h3>(.*?)</h3>', webpage, 'episode title')
+        podcast_date          = unified_strdate(self._search_regex(r'<div class="release_date">Released: (.*?)</div>', webpage, 'release date'))
+        podcast_description   = self._search_regex(r'<div id="info_text_body">(.*?)</div>', webpage, 'description')
+
+        url0 = self._search_regex(r'var mediaURLLibsyn = "(?P<url0>https?://.*)";', webpage, 'first media URL')
+        url1 = self._search_regex(r'var mediaURL = "(?P<url1>https?://.*)";', webpage, 'second media URL')
+
+        if url0 != url1:
+            formats = [{
+                'url': url0
+            }, {
+                'url': url1
+            }]
+        else:
+            formats = [{
+                'url': url0
+            }]
+
+        return {
+            'id': display_id,
+            'title': podcast_episode_title,
+            'description': podcast_description,
+            'upload_date': podcast_date,
+            'formats': formats,
+        }