Merge pull request #7691 from ryandesign/use-PYTHON-env-var

[youtube-dl] / youtube_dl / extractor / webofstories.py

diff --git a/youtube_dl/extractor/webofstories.py b/youtube_dl/extractor/webofstories.py
index 396cf4e8312ca73f90f45b3e24f3fb3561f54fa8..2037d9b3d57cd5876d85e9552ffcc9f387fcc975 100644 (file)
--- 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
 
@@ -45,19 +47,17 @@ class WebOfStoriesIE(InfoExtractor):
         description = self._html_search_meta('description', webpage)
         thumbnail = self._og_search_thumbnail(webpage)
 
-        story_filename = self._search_regex(
-            r'\.storyFileName\("([^"]+)"\)', webpage, 'story filename')
-        speaker_id = self._search_regex(
-            r'\.speakerId\("([^"]+)"\)', webpage, 'speaker ID')
-        story_id = self._search_regex(
-            r'\.storyId\((\d+)\)', webpage, 'story ID')
-        speaker_type = self._search_regex(
-            r'\.speakerType\("([^"]+)"\)', webpage, 'speaker type')
-        great_life = self._search_regex(
-            r'isGreatLifeStory\s*=\s*(true|false)', webpage, 'great life story')
+        embed_params = [s.strip(" \r\n\t'") for s in self._search_regex(
+            r'(?s)\$\("#embedCode"\).html\(getEmbedCode\((.*?)\)',
+            webpage, 'embed params').split(',')]
+
+        (
+            _, speaker_id, story_id, story_duration,
+            speaker_type, great_life, _thumbnail, _has_subtitles,
+            story_filename, _story_order) = embed_params
+
         is_great_life_series = great_life == 'true'
-        duration = int_or_none(self._search_regex(
-            r'\.duration\((\d+)\)', webpage, 'duration', fatal=False))
+        duration = int_or_none(story_duration)
 
         # URL building, see: http://www.webofstories.com/scripts/player.js
         ms_prefix = ''
@@ -100,3 +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)