youtube-dl

commit 7866c9e17362c21002d3bf7d3972c8139f220414
parent a09141548aa31db7c7d9457b10f5c84e6e32beba
Author: Sergey M․ <dstftw@gmail.com>
Date:   Sun, 22 Mar 2015 08:24:26 +0600

Merge branch 'fstirlitz-the-daily-show-podcast'

Diffstat:
M
youtube_dl/extractor/__init__.py
 | 
1
+
M
youtube_dl/extractor/generic.py
 | 
17
+++++++++++++++++
A
youtube_dl/extractor/libsyn.py
 | 
59
+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++

3 files changed, 77 insertions(+), 0 deletions(-)
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
@@ -250,6 +250,7 @@ from .letv import (
     LetvTvIE,
     LetvPlaylistIE
 )
+from .libsyn import LibsynIE
 from .lifenews import LifeNewsIE
 from .liveleak import LiveLeakIE
 from .livestream import (
diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py
@@ -527,6 +527,17 @@ class GenericIE(InfoExtractor):
             },
             'add_ie': ['Viddler'],
         },
+        # Libsyn embed
+        {
+            'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
+            'info_dict': {
+                'id': '3377616',
+                'ext': 'mp3',
+                'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
+                'description': 'md5:601cb790edd05908957dae8aaa866465',
+                'upload_date': '20150220',
+            },
+        },
         # jwplayer YouTube
         {
             'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
@@ -1013,6 +1024,12 @@ class GenericIE(InfoExtractor):
         if mobj is not None:
             return self.url_result(mobj.group('url'))
 
+        # Look for Libsyn player
+        mobj = re.search(
+            r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
+        if mobj is not None:
+            return self.url_result(mobj.group('url'))
+
         # Look for Ooyala videos
         mobj = (re.search(r'player\.ooyala\.com/[^"?]+\?[^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
                 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
diff --git a/youtube_dl/extractor/libsyn.py b/youtube_dl/extractor/libsyn.py
@@ -0,0 +1,59 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+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]+)'
+
+    _TEST = {
+        'url': 'http://html5-player.libsyn.com/embed/episode/id/3377616/',
+        'md5': '443360ee1b58007bc3dcf09b41d093bb',
+        'info_dict': {
+            'id': '3377616',
+            'ext': 'mp3',
+            'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
+            'description': 'md5:601cb790edd05908957dae8aaa866465',
+            'upload_date': '20150220',
+        },
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+
+        formats = [{
+            'url': media_url,
+        } for media_url in set(re.findall('var\s+mediaURL(?:Libsyn)?\s*=\s*"([^"]+)"', webpage))]
+
+        podcast_title = self._search_regex(
+            r'<h2>([^<]+)</h2>', webpage, 'title')
+        episode_title = self._search_regex(
+            r'<h3>([^<]+)</h3>', webpage, 'title', default=None)
+
+        title = '%s - %s' %(podcast_title, episode_title) if podcast_title else episode_title
+
+        description = self._html_search_regex(
+            r'<div id="info_text_body">(.+?)</div>', webpage,
+            'description', fatal=False)
+
+        thumbnail = self._search_regex(
+            r'<img[^>]+class="info-show-icon"[^>]+src="([^"]+)"',
+            webpage, 'thumbnail', fatal=False)
+
+        release_date = unified_strdate(self._search_regex(
+            r'<div class="release_date">Released: ([^<]+)<', webpage, 'release date', fatal=False))
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'upload_date': release_date,
+            'formats': formats,
+        }