2014-08-31 06:48:34 -04:00
|
|
|
import re
|
|
|
|
|
|
|
|
from .common import InfoExtractor
|
|
|
|
from ..utils import (
|
2024-05-26 15:27:21 -04:00
|
|
|
determine_ext,
|
2014-08-31 06:48:34 -04:00
|
|
|
int_or_none,
|
2024-05-26 15:27:21 -04:00
|
|
|
parse_duration,
|
2014-08-31 14:08:19 -04:00
|
|
|
qualities,
|
2014-08-31 06:48:34 -04:00
|
|
|
)
|
|
|
|
|
|
|
|
|
|
|
|
class SunPornoIE(InfoExtractor):
|
2016-08-13 03:13:49 -04:00
|
|
|
_VALID_URL = r'https?://(?:(?:www\.)?sunporno\.com/videos|embeds\.sunporno\.com/embed)/(?P<id>\d+)'
|
|
|
|
_TESTS = [{
|
2014-08-31 06:48:34 -04:00
|
|
|
'url': 'http://www.sunporno.com/videos/807778/',
|
2016-08-13 03:09:35 -04:00
|
|
|
'md5': '507887e29033502f29dba69affeebfc9',
|
2014-08-31 06:48:34 -04:00
|
|
|
'info_dict': {
|
|
|
|
'id': '807778',
|
2016-08-13 03:09:35 -04:00
|
|
|
'ext': 'mp4',
|
2014-08-31 06:48:34 -04:00
|
|
|
'title': 'md5:0a400058e8105d39e35c35e7c5184164',
|
|
|
|
'description': 'md5:a31241990e1bd3a64e72ae99afb325fb',
|
2017-01-02 07:08:07 -05:00
|
|
|
'thumbnail': r're:^https?://.*\.jpg$',
|
2014-08-31 06:48:34 -04:00
|
|
|
'duration': 302,
|
2014-09-01 16:38:40 -04:00
|
|
|
'age_limit': 18,
|
2014-08-31 06:48:34 -04:00
|
|
|
}
|
2016-08-13 03:13:49 -04:00
|
|
|
}, {
|
|
|
|
'url': 'http://embeds.sunporno.com/embed/807778',
|
|
|
|
'only_matching': True,
|
|
|
|
}]
|
2014-08-31 06:48:34 -04:00
|
|
|
|
|
|
|
def _real_extract(self, url):
|
2014-12-26 08:28:51 -05:00
|
|
|
video_id = self._match_id(url)
|
2014-08-31 06:48:34 -04:00
|
|
|
|
2016-08-13 03:13:49 -04:00
|
|
|
webpage = self._download_webpage(
|
|
|
|
'http://www.sunporno.com/videos/%s' % video_id, video_id)
|
2014-08-31 06:48:34 -04:00
|
|
|
|
2022-04-04 04:27:35 -04:00
|
|
|
title = self._html_extract_title(webpage)
|
2014-12-26 08:28:51 -05:00
|
|
|
description = self._html_search_meta(
|
|
|
|
'description', webpage, 'description')
|
2014-08-31 06:48:34 -04:00
|
|
|
thumbnail = self._html_search_regex(
|
2014-08-31 14:08:19 -04:00
|
|
|
r'poster="([^"]+)"', webpage, 'thumbnail', fatal=False)
|
2014-08-31 06:48:34 -04:00
|
|
|
|
|
|
|
duration = parse_duration(self._search_regex(
|
2016-08-13 03:09:35 -04:00
|
|
|
(r'itemprop="duration"[^>]*>\s*(\d+:\d+)\s*<',
|
|
|
|
r'>Duration:\s*<span[^>]+>\s*(\d+:\d+)\s*<'),
|
2014-12-26 08:28:51 -05:00
|
|
|
webpage, 'duration', fatal=False))
|
2014-08-31 06:48:34 -04:00
|
|
|
|
|
|
|
view_count = int_or_none(self._html_search_regex(
|
2015-06-06 06:58:20 -04:00
|
|
|
r'class="views">(?:<noscript>)?\s*(\d+)\s*<',
|
2014-12-26 08:28:51 -05:00
|
|
|
webpage, 'view count', fatal=False))
|
2014-08-31 14:08:19 -04:00
|
|
|
comment_count = int_or_none(self._html_search_regex(
|
2014-12-26 08:28:51 -05:00
|
|
|
r'(\d+)</b> Comments?',
|
2016-08-13 03:09:35 -04:00
|
|
|
webpage, 'comment count', fatal=False, default=None))
|
2014-08-31 14:08:19 -04:00
|
|
|
|
|
|
|
formats = []
|
|
|
|
quality = qualities(['mp4', 'flv'])
|
2015-02-14 07:33:52 -05:00
|
|
|
for video_url in re.findall(r'<(?:source|video) src="([^"]+)"', webpage):
|
2014-08-31 14:08:19 -04:00
|
|
|
video_ext = determine_ext(video_url)
|
|
|
|
formats.append({
|
|
|
|
'url': video_url,
|
|
|
|
'format_id': video_ext,
|
|
|
|
'quality': quality(video_ext),
|
|
|
|
})
|
2014-08-31 06:48:34 -04:00
|
|
|
|
|
|
|
return {
|
|
|
|
'id': video_id,
|
|
|
|
'title': title,
|
|
|
|
'description': description,
|
|
|
|
'thumbnail': thumbnail,
|
|
|
|
'duration': duration,
|
|
|
|
'view_count': view_count,
|
2014-08-31 14:08:19 -04:00
|
|
|
'comment_count': comment_count,
|
|
|
|
'formats': formats,
|
2014-09-01 16:38:40 -04:00
|
|
|
'age_limit': 18,
|
2014-08-31 06:48:34 -04:00
|
|
|
}
|