1
0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-12-15 14:47:44 +01:00
yt-dlp/yt_dlp/extractor/hellporno.py

73 lines
2.5 KiB
Python
Raw Normal View History

2014-12-26 15:49:12 +01:00
from .common import InfoExtractor
from ..utils import (
int_or_none,
merge_dicts,
remove_end,
unified_timestamp,
)
2014-12-26 15:49:12 +01:00
2014-12-29 10:38:07 +01:00
2014-12-26 15:49:12 +01:00
class HellPornoIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?hellporno\.(?:com/videos|net/v)/(?P<id>[^/]+)'
_TESTS = [{
2014-12-26 15:49:12 +01:00
'url': 'http://hellporno.com/videos/dixie-is-posing-with-naked-ass-very-erotic/',
'md5': 'f0a46ebc0bed0c72ae8fe4629f7de5f3',
2014-12-26 15:49:12 +01:00
'info_dict': {
'id': '149116',
2014-12-29 10:38:07 +01:00
'display_id': 'dixie-is-posing-with-naked-ass-very-erotic',
2014-12-26 15:49:12 +01:00
'ext': 'mp4',
'title': 'Dixie is posing with naked ass very erotic',
'description': 'md5:9a72922749354edb1c4b6e540ad3d215',
'categories': list,
'thumbnail': r're:https?://.*\.jpg$',
'duration': 240,
'timestamp': 1398762720,
'upload_date': '20140429',
'view_count': int,
2014-12-26 15:49:12 +01:00
'age_limit': 18,
},
}, {
'url': 'http://hellporno.net/v/186271/',
'only_matching': True,
}]
2014-12-26 15:49:12 +01:00
def _real_extract(self, url):
2014-12-29 10:38:07 +01:00
display_id = self._match_id(url)
2014-12-26 15:49:12 +01:00
webpage = self._download_webpage(url, display_id)
2014-12-26 15:49:12 +01:00
2022-04-04 10:27:35 +02:00
title = remove_end(self._html_extract_title(webpage), ' - Hell Porno')
2014-12-26 15:49:12 +01:00
info = self._parse_html5_media_entries(url, webpage, display_id)[0]
2014-12-26 15:49:12 +01:00
video_id = self._search_regex(
(r'chs_object\s*=\s*["\'](\d+)',
r'params\[["\']video_id["\']\]\s*=\s*(\d+)'), webpage, 'video id',
default=display_id)
description = self._search_regex(
r'class=["\']desc_video_view_v2[^>]+>([^<]+)', webpage,
'description', fatal=False)
categories = [
c.strip()
for c in self._html_search_meta(
'keywords', webpage, 'categories', default='').split(',')
if c.strip()]
duration = int_or_none(self._og_search_property(
'video:duration', webpage, fatal=False))
timestamp = unified_timestamp(self._og_search_property(
'video:release_date', webpage, fatal=False))
view_count = int_or_none(self._search_regex(
r'>Views\s+(\d+)', webpage, 'view count', fatal=False))
2014-12-26 15:49:12 +01:00
return merge_dicts(info, {
2014-12-26 15:49:12 +01:00
'id': video_id,
2014-12-29 10:38:07 +01:00
'display_id': display_id,
2014-12-26 15:49:12 +01:00
'title': title,
'description': description,
2014-12-26 15:49:12 +01:00
'categories': categories,
'duration': duration,
'timestamp': timestamp,
'view_count': view_count,
2014-12-26 15:49:12 +01:00
'age_limit': 18,
})