1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-12-05 08:27:43 +00:00
youtube-dl/youtube_dl/extractor/sunporno.py

80 lines
2.6 KiB
Python
Raw Normal View History

2014-08-31 10:48:34 +00:00
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
parse_duration,
int_or_none,
qualities,
determine_ext,
2014-08-31 10:48:34 +00:00
)
class SunPornoIE(InfoExtractor):
2016-08-13 07:13:49 +00:00
_VALID_URL = r'https?://(?:(?:www\.)?sunporno\.com/videos|embeds\.sunporno\.com/embed)/(?P<id>\d+)'
_TESTS = [{
2014-08-31 10:48:34 +00:00
'url': 'http://www.sunporno.com/videos/807778/',
'md5': '507887e29033502f29dba69affeebfc9',
2014-08-31 10:48:34 +00:00
'info_dict': {
'id': '807778',
'ext': 'mp4',
2014-08-31 10:48:34 +00:00
'title': 'md5:0a400058e8105d39e35c35e7c5184164',
'description': 'md5:a31241990e1bd3a64e72ae99afb325fb',
'thumbnail': r're:^https?://.*\.jpg$',
2014-08-31 10:48:34 +00:00
'duration': 302,
'age_limit': 18,
2014-08-31 10:48:34 +00:00
}
2016-08-13 07:13:49 +00:00
}, {
'url': 'http://embeds.sunporno.com/embed/807778',
'only_matching': True,
}]
2014-08-31 10:48:34 +00:00
def _real_extract(self, url):
2014-12-26 13:28:51 +00:00
video_id = self._match_id(url)
2014-08-31 10:48:34 +00:00
2016-08-13 07:13:49 +00:00
webpage = self._download_webpage(
'http://www.sunporno.com/videos/%s' % video_id, video_id)
2014-08-31 10:48:34 +00:00
2014-12-26 13:28:51 +00:00
title = self._html_search_regex(
r'<title>([^<]+)</title>', webpage, 'title')
description = self._html_search_meta(
'description', webpage, 'description')
2014-08-31 10:48:34 +00:00
thumbnail = self._html_search_regex(
r'poster="([^"]+)"', webpage, 'thumbnail', fatal=False)
2014-08-31 10:48:34 +00:00
duration = parse_duration(self._search_regex(
(r'itemprop="duration"[^>]*>\s*(\d+:\d+)\s*<',
r'>Duration:\s*<span[^>]+>\s*(\d+:\d+)\s*<'),
2014-12-26 13:28:51 +00:00
webpage, 'duration', fatal=False))
2014-08-31 10:48:34 +00:00
view_count = int_or_none(self._html_search_regex(
2015-06-06 10:58:20 +00:00
r'class="views">(?:<noscript>)?\s*(\d+)\s*<',
2014-12-26 13:28:51 +00:00
webpage, 'view count', fatal=False))
comment_count = int_or_none(self._html_search_regex(
2014-12-26 13:28:51 +00:00
r'(\d+)</b> Comments?',
webpage, 'comment count', fatal=False, default=None))
formats = []
quality = qualities(['mp4', 'flv'])
for video_url in re.findall(r'<(?:source|video) src="([^"]+)"', webpage):
video_ext = determine_ext(video_url)
formats.append({
'url': video_url,
'format_id': video_ext,
'quality': quality(video_ext),
})
self._sort_formats(formats)
2014-08-31 10:48:34 +00:00
return {
'id': video_id,
'title': title,
'description': description,
'thumbnail': thumbnail,
'duration': duration,
'view_count': view_count,
'comment_count': comment_count,
'formats': formats,
'age_limit': 18,
2014-08-31 10:48:34 +00:00
}