Upstream/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-12-13 14:37:43 +01:00
Code Issues Packages Projects Releases Wiki Activity

[webofstories] Fix extraction

Browse Source
This commit is contained in:
Philipp Hagemeister 2015-02-19 02:12:08 +01:00
parent 71d53ace2f
commit 3d54788495
1 changed files with 10 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

22
youtube_dl/extractor/webofstories.py
View File

@ -45,19 +45,17 @@ def _real_extract(self, url):
description = self._html_search_meta('description', webpage) description = self._html_search_meta('description', webpage)
thumbnail = self._og_search_thumbnail(webpage) thumbnail = self._og_search_thumbnail(webpage)
story_filename = self._search_regex( embed_params = [s.strip(" \r\n\t'") for s in self._search_regex(
r'\.storyFileName\("([^"]+)"\)', webpage, 'story filename') r'(?s)\$\("#embedCode"\).html\(getEmbedCode\((.*?)\)',
speaker_id = self._search_regex( webpage, 'embed params').split(',')]
r'\.speakerId\("([^"]+)"\)', webpage, 'speaker ID')
story_id = self._search_regex( (
r'\.storyId\((\d+)\)', webpage, 'story ID') _, speaker_id, story_id, story_duration,
speaker_type = self._search_regex( speaker_type, great_life, _thumbnail, _has_subtitles,
r'\.speakerType\("([^"]+)"\)', webpage, 'speaker type') story_filename, _story_order) = embed_params
great_life = self._search_regex(
r'isGreatLifeStory\s*=\s*(true|false)', webpage, 'great life story')
is_great_life_series = great_life == 'true' is_great_life_series = great_life == 'true'
duration = int_or_none(self._search_regex( duration = int_or_none(story_duration)
r'\.duration\((\d+)\)', webpage, 'duration', fatal=False))
# URL building, see: http://www.webofstories.com/scripts/player.js # URL building, see: http://www.webofstories.com/scripts/player.js
ms_prefix = '' ms_prefix = ''