Browse Source

[webofstories:playlist] Improve and add test

totalwebcasting
Sergey M․ 10 years ago
parent
commit
fac54cb426
1 changed files with 24 additions and 8 deletions
  1. +24
    -8
      youtube_dl/extractor/webofstories.py

+ 24
- 8
youtube_dl/extractor/webofstories.py View File

@ -104,7 +104,14 @@ class WebOfStoriesIE(InfoExtractor):
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 @@ class WebOfStoriesPlaylistIE(InfoExtractor):
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(
r'<title>([^<]+)\s*-\s*Web\sof\sStories</title>', webpage, 'title')
description = self._html_search_meta(
'description', webpage, 'description')
return self.playlist_result(entries, playlist_id, title, description)
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)

Loading…
Cancel
Save