yt-dlp/yt_dlp/extractor/goshgay.py

48 lines
1.4 KiB
Python
Raw Normal View History

import urllib.parse
2014-07-09 06:14:53 -04:00
from .common import InfoExtractor
from ..utils import (
2014-12-12 06:55:13 -05:00
parse_duration,
2014-07-09 06:14:53 -04:00
)
class GoshgayIE(InfoExtractor):
2016-09-08 07:29:05 -04:00
_VALID_URL = r'https?://(?:www\.)?goshgay\.com/video(?P<id>\d+?)($|/)'
2014-07-09 06:14:53 -04:00
_TEST = {
2014-12-12 06:55:13 -05:00
'url': 'http://www.goshgay.com/video299069/diesel_sfw_xxx_video',
'md5': '4b6db9a0a333142eb9f15913142b0ed1',
2014-07-09 06:14:53 -04:00
'info_dict': {
2014-12-12 06:55:13 -05:00
'id': '299069',
2014-07-09 06:14:53 -04:00
'ext': 'flv',
2014-12-12 06:55:13 -05:00
'title': 'DIESEL SFW XXX Video',
'thumbnail': r're:^http://.*\.jpg$',
'duration': 80,
'age_limit': 18,
},
2014-07-09 06:14:53 -04:00
}
def _real_extract(self, url):
video_id = self._match_id(url)
2014-07-09 06:14:53 -04:00
webpage = self._download_webpage(url, video_id)
2014-12-12 06:44:32 -05:00
2014-12-12 06:55:13 -05:00
title = self._html_search_regex(
r'<h2>(.*?)<', webpage, 'title')
duration = parse_duration(self._html_search_regex(
r'<span class="duration">\s*-?\s*(.*?)</span>',
webpage, 'duration', fatal=False))
2014-07-09 06:14:53 -04:00
flashvars = urllib.parse.parse_qs(self._html_search_regex(
2014-12-12 06:55:13 -05:00
r'<embed.+?id="flash-player-embed".+?flashvars="([^"]+)"',
webpage, 'flashvars'))
thumbnail = flashvars.get('url_bigthumb', [None])[0]
video_url = flashvars['flv_url'][0]
2014-07-09 06:14:53 -04:00
return {
'id': video_id,
'url': video_url,
'title': title,
'thumbnail': thumbnail,
2014-12-12 06:55:13 -05:00
'duration': duration,
'age_limit': 18,
2014-07-09 06:14:53 -04:00
}