github/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-21 20:46:36 -05:00
Code Issues Projects Releases Packages Wiki Activity

[vier:videos] Fix extraction with old approach (Closes #6806)

Browse source
This commit is contained in:
Sergey M․ 2015-09-09 23:59:17 +06:00
parent 73f536439e
commit cc1ac11017
1 changed files with 5 additions and 8 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

13
youtube_dl/extractor/vier.py
View file

@ -2,6 +2,7 @@
from __future__ import unicode_literals from __future__ import unicode_literals
import re import re
import itertools
from .common import InfoExtractor from .common import InfoExtractor
@ -91,31 +92,27 @@ def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
program = mobj.group('program') program = mobj.group('program')
webpage = self._download_webpage(url, program)
page_id = mobj.group('page') page_id = mobj.group('page')
if page_id: if page_id:
page_id = int(page_id) page_id = int(page_id)
start_page = page_id start_page = page_id
last_page = start_page + 1
playlist_id = '%s-page%d' % (program, page_id) playlist_id = '%s-page%d' % (program, page_id)
else: else:
start_page = 0 start_page = 0
last_page = int(self._search_regex(
r'videos\?page=(\d+)">laatste</a>',
webpage, 'last page', default=0)) + 1
playlist_id = program playlist_id = program
entries = [] entries = []
for current_page_id in range(start_page, last_page): for current_page_id in itertools.count(start_page):
current_page = self._download_webpage( current_page = self._download_webpage(
'http://www.vier.be/%s/videos?page=%d' % (program, current_page_id), 'http://www.vier.be/%s/videos?page=%d' % (program, current_page_id),
program, program,
'Downloading page %d' % (current_page_id + 1)) if current_page_id != page_id else webpage 'Downloading page %d' % (current_page_id + 1))
page_entries = [ page_entries = [
self.url_result('http://www.vier.be' + video_url, 'Vier') self.url_result('http://www.vier.be' + video_url, 'Vier')
for video_url in re.findall( for video_url in re.findall(
r'<h3><a href="(/[^/]+/videos/[^/]+(?:/\d+)?)">', current_page)] r'<h3><a href="(/[^/]+/videos/[^/]+(?:/\d+)?)">', current_page)]
entries.extend(page_entries) entries.extend(page_entries)
if page_id or '>Meer<' not in current_page:
break
return self.playlist_result(entries, playlist_id) return self.playlist_result(entries, playlist_id)