From 3d54788495aae464a4ce63b5f093d4409f600dd8 Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Thu, 19 Feb 2015 02:12:08 +0100 Subject: [PATCH] [webofstories] Fix extraction --- youtube_dl/extractor/webofstories.py | 22 ++++++++++------------ 1 file changed, 10 insertions(+), 12 deletions(-) diff --git a/youtube_dl/extractor/webofstories.py b/youtube_dl/extractor/webofstories.py index 396cf4e83..73077a312 100644 --- a/youtube_dl/extractor/webofstories.py +++ b/youtube_dl/extractor/webofstories.py @@ -45,19 +45,17 @@ def _real_extract(self, url): 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 = ''