Merge branch 'the-daily-show-podcast' of https://github.com/fstirlitz/youtube-dl into fstirlitz-the-daily-show-podcast

youtube_dl/extractor/__init__.py

@@ -84,7 +84,7 @@ from .cnn import (
 )
 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
@@ -251,6 +251,7 @@ from .letv import (
     LetvPlaylistIE
 )
 from .lifenews import LifeNewsIE
+from .libsyn import LibsynIE
 from .liveleak import LiveLeakIE
 from .livestream import (
     LivestreamIE,

youtube_dl/extractor/comedycentral.py

@@ -2,6 +2,7 @@ from __future__ import unicode_literals
 
 import re
 
+from .common import InfoExtractor
 from .mtv import MTVServicesInfoExtractor
 from ..compat import (
     compat_str,
@@ -272,3 +273,27 @@ class ComedyCentralShowsIE(MTVServicesInfoExtractor):
             'title': show_name + ' ' + title,
             'description': description,
         }
+
+class TheDailyShowPodcastIE(InfoExtractor):
+    _VALID_URL = r'(?P<scheme>https?:)?//thedailyshow\.cc\.com/podcast/(?P<id>[a-z\-]+)'
+    _TESTS = [{
+        "url": "http://thedailyshow.cc.com/podcast/episodetwelve",
+        'only_matching': True,
+    }]
+
+    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,
+        }

youtube_dl/extractor/libsyn.py

@@ -0,0 +1,50 @@
+# 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]+)(?:/.*)?'
+    _TESTS = [{
+        'url': "http://html5-player.libsyn.com/embed/episode/id/3377616/",
+        'info_dict': {
+            'id': "3377616",
+            'ext': "mp3",
+            'title': "Episode 12: Bassem Youssef: Egypt's Jon Stewart",
+            'description': "<p>Bassem Youssef joins executive producer Steve Bodow and senior producer Sara Taksler for a conversation about how&nbsp;<em style=\"font-family: Tahoma, Geneva, sans-serif; font-size: 12.8000001907349px;\">The Daily Show</em>&nbsp;inspired Bassem to create&nbsp;<em style=\"font-family: Tahoma, Geneva, sans-serif; font-size: 12.8000001907349px;\">Al-Bernameg</em>, his massively popular (and now banned) Egyptian news satire program. Sara discusses her soon-to-be-released documentary,&nbsp;<em style=\"font-family: Tahoma, Geneva, sans-serif; font-size: 12.8000001907349px;\">Tickling Giants</em>, which chronicles how Bassem and his staff risked their safety every day to tell jokes.</p>",
+        },
+    }]
+
+    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,
+        }