0
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-16 01:25:06 +00:00

[anysex] Fix extraction

This commit is contained in:
Sergey M․ 2014-09-27 22:29:27 +07:00
parent 8e6f8051f0
commit 497339fa0e

View file

@ -35,7 +35,7 @@ def _real_extract(self, url):
title = self._html_search_regex(r'<title>(.*?)</title>', webpage, 'title') title = self._html_search_regex(r'<title>(.*?)</title>', webpage, 'title')
description = self._html_search_regex( description = self._html_search_regex(
r'<div class="description">([^<]+)</div>', webpage, 'description', fatal=False) r'<div class="description"[^>]*>([^<]+)</div>', webpage, 'description', fatal=False)
thumbnail = self._html_search_regex( thumbnail = self._html_search_regex(
r'preview_url\s*:\s*\'(.*?)\'', webpage, 'thumbnail', fatal=False) r'preview_url\s*:\s*\'(.*?)\'', webpage, 'thumbnail', fatal=False)
@ -43,7 +43,7 @@ def _real_extract(self, url):
r'<a href="http://anysex\.com/categories/[^"]+" title="[^"]*">([^<]+)</a>', webpage) r'<a href="http://anysex\.com/categories/[^"]+" title="[^"]*">([^<]+)</a>', webpage)
duration = parse_duration(self._search_regex( duration = parse_duration(self._search_regex(
r'<b>Duration:</b> (\d+:\d+)', webpage, 'duration', fatal=False)) r'<b>Duration:</b> (?:<q itemprop="duration">)?(\d+:\d+)', webpage, 'duration', fatal=False))
view_count = int_or_none(self._html_search_regex( view_count = int_or_none(self._html_search_regex(
r'<b>Views:</b> (\d+)', webpage, 'view count', fatal=False)) r'<b>Views:</b> (\d+)', webpage, 'view count', fatal=False))