import re
from .common import InfoExtractor
-from ..compat import compat_str
from ..utils import (
int_or_none,
sanitized_Request,
str_to_int,
unescapeHTML,
unified_strdate,
+ url_or_none,
)
from ..aes import aes_decrypt_text
'description': 'Love & Sex Answers: http://bit.ly/DanAndJenn -- Is It Unhealthy To Masturbate Daily?',
'thumbnail': r're:^https?://.*\.jpg$',
'uploader': 'Ask Dan And Jennifer',
- 'upload_date': '20101221',
+ 'upload_date': '20101217',
'average_rating': int,
'view_count': int,
'comment_count': int,
'description': 'http://sweetlivegirls.com Big Tits Awesome Brunette On amazing webcam show.mp4',
'thumbnail': r're:^https?://.*\.jpg$',
'uploader': 'Unknown',
- 'upload_date': '20111125',
+ 'upload_date': '20110418',
'average_rating': int,
'view_count': int,
'comment_count': int,
request.add_header('Cookie', 'age_verified=1')
webpage = self._download_webpage(request, display_id)
- title = self._search_regex(
- [r'(?:video_titles|videoTitle)\s*[:=]\s*(["\'])(?P<title>(?:(?!\1).)+)\1',
- r'<h1[^>]+class=["\']heading\d?["\'][^>]*>(?P<title>[^<]+)<'],
- webpage, 'title', group='title',
- default=None) or self._og_search_title(
+ title = self._html_search_regex(
+ r'(?s)<div[^>]+class=["\']watchVideoTitle[^>]+>(.+?)</div>',
+ webpage, 'title', default=None) or self._og_search_title(
webpage, default=None) or self._html_search_meta(
'title', webpage, fatal=True)
for definition in definitions:
if not isinstance(definition, dict):
continue
- video_url = definition.get('videoUrl')
- if isinstance(video_url, compat_str) and video_url:
+ video_url = url_or_none(definition.get('videoUrl'))
+ if video_url:
links.append(video_url)
# Fallback #1, this also contains extra low quality 180p format
formats.append(f)
self._sort_formats(formats)
- description = self._og_search_description(webpage, default=None)
+ description = self._html_search_regex(
+ r'(?s)<div[^>]+\bid=["\']description["\'][^>]*>(.+?)</div>',
+ webpage, 'description',
+ default=None) or self._og_search_description(
+ webpage, default=None)
thumbnail = self._search_regex(
r'(?:imageurl\s*=|poster\s*:)\s*(["\'])(?P<thumbnail>.+?)\1',
webpage, 'thumbnail', fatal=False, group='thumbnail')
r'(?s)<div[^>]+class=["\']submitByLink["\'][^>]*>(.+?)</div>',
webpage, 'uploader', fatal=False)
upload_date = unified_strdate(self._html_search_regex(
- r'(?s)<div[^>]+class=["\']videoInfo(?:Date|Time)["\'][^>]*>(.+?)</div>',
+ [r'Date\s+[Aa]dded:\s*<span>([^<]+)',
+ r'(?s)<div[^>]+class=["\']videoInfo(?:Date|Time)["\'][^>]*>(.+?)</div>'],
webpage, 'upload date', fatal=False))
age_limit = self._rta_search(webpage)