Mirrors/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-02 17:22:31 +01:00
Code Issues Releases Activity

[webofstories:playlist] Improve and add test

Browse Source
This commit is contained in:
Sergey M․ 2015-07-11 04:43:29 +06:00
parent 3f19b9b7c1
commit fac54cb426
1 changed files with 22 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

28
youtube_dl/extractor/webofstories.py
View File

@ -104,7 +104,14 @@ def _real_extract(self, url):
class WebOfStoriesPlaylistIE(InfoExtractor): class WebOfStoriesPlaylistIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?webofstories\.com/playAll/(?P<id>[^/]+)' _VALID_URL = r'https?://(?:www\.)?webofstories\.com/playAll/(?P<id>[^/]+)'
_TESTS = [] _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): def _real_extract(self, url):
playlist_id = self._match_id(url) playlist_id = self._match_id(url)
@ -116,10 +123,19 @@ def _real_extract(self, url):
for video_number in set(re.findall('href="/playAll/%s\?sId=(\d+)"' % playlist_id, webpage)) for video_number in set(re.findall('href="/playAll/%s\?sId=(\d+)"' % playlist_id, webpage))
] ]
title = self._html_search_regex( title = self._search_regex(
r'<title>([^<]+)\s*-\s*Web\sof\sStories</title>', webpage, 'title') 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
description = self._html_search_meta( if not title:
'description', webpage, 'description') 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, description) return self.playlist_result(entries, playlist_id, title)