mirror of
https://codeberg.org/polarisfm/youtube-dl
synced 2024-11-22 16:44:32 +01:00
Merge branch 'dufferzafar-webofstories'
This commit is contained in:
commit
da634d0a8b
@ -721,7 +721,10 @@ from .wdr import (
|
||||
WDRMobileIE,
|
||||
WDRMausIE,
|
||||
)
|
||||
from .webofstories import WebOfStoriesIE
|
||||
from .webofstories import (
|
||||
WebOfStoriesIE,
|
||||
WebOfStoriesPlaylistIE,
|
||||
)
|
||||
from .weibo import WeiboIE
|
||||
from .wimp import WimpIE
|
||||
from .wistia import WistiaIE
|
||||
|
@ -1,6 +1,8 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import int_or_none
|
||||
|
||||
@ -98,3 +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)
|
||||
|
Loading…
Reference in New Issue
Block a user