youtube-dl

commit da634d0a8b409673ea095710c642bbd61ffec429
parent 86f2541695ba0280982e47e52c5cf26946d5d7c6
Author: Sergey M․ <dstftw@gmail.com>
Date:   Sat, 11 Jul 2015 04:43:55 +0600

Merge branch 'dufferzafar-webofstories'

Diffstat:
M
youtube_dl/extractor/__init__.py
 | 
5
++++-
M
youtube_dl/extractor/webofstories.py
 | 
41
+++++++++++++++++++++++++++++++++++++++++

2 files changed, 45 insertions(+), 1 deletion(-)
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
@@ -721,7 +721,10 @@ from .wdr import (
     WDRMobileIE,
     WDRMausIE,
 )
-from .webofstories import WebOfStoriesIE
+from .webofstories import (
+    WebOfStoriesIE,
+    WebOfStoriesPlaylistIE,
+)
 from .weibo import WeiboIE
 from .wimp import WimpIE
 from .wistia import WistiaIE
diff --git a/youtube_dl/extractor/webofstories.py b/youtube_dl/extractor/webofstories.py
@@ -1,6 +1,8 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import re
+
 from .common import InfoExtractor
 from ..utils import int_or_none
 
@@ -98,3 +100,42 @@ class WebOfStoriesIE(InfoExtractor):
             'description': description,
             'duration': duration,
         }
+
+
+class WebOfStoriesPlaylistIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?webofstories\.com/playAll/(?P<id>[^/]+)'
+    _TEST = {
+        'url': 'http://www.webofstories.com/playAll/donald.knuth',
+        'info_dict': {
+            'id': 'donald.knuth',
+            'title': 'Donald Knuth (Scientist)',
+        },
+        'playlist_mincount': 97,
+    }
+
+    def _real_extract(self, url):
+        playlist_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, playlist_id)
+
+        entries = [
+            self.url_result('http://www.webofstories.com/play/%s' % video_number, 'WebOfStories')
+            for video_number in set(re.findall('href="/playAll/%s\?sId=(\d+)"' % playlist_id, webpage))
+        ]
+
+        title = self._search_regex(
+            r'<div id="speakerName">\s*<span>([^<]+)</span>',
+            webpage, 'speaker', default=None)
+        if title:
+            field = self._search_regex(
+                r'<span id="primaryField">([^<]+)</span>',
+                webpage, 'field', default=None)
+            if field:
+                title += ' (%s)' % field
+
+        if not title:
+            title = self._search_regex(
+                r'<title>Play\s+all\s+stories\s*-\s*([^<]+)\s*-\s*Web\s+of\s+Stories</title>',
+                webpage, 'title')
+
+        return self.playlist_result(entries, playlist_id, title)