youtube-dl/youtube_dl/extractor/hornbunny.py

50 lines
1.5 KiB
Python
Raw Normal View History

2014-08-30 18:43:03 +00:00
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
2014-09-01 21:04:36 +00:00
from ..utils import (
int_or_none,
parse_duration,
)
2014-08-30 18:43:03 +00:00
class HornBunnyIE(InfoExtractor):
_VALID_URL = r'http?://(?:www\.)?hornbunny\.com/videos/(?P<title_dash>[a-z-]+)-(?P<id>\d+)\.html'
_TEST = {
'url': 'http://hornbunny.com/videos/panty-slut-jerk-off-instruction-5227.html',
2016-10-26 16:10:51 +00:00
'md5': 'e20fd862d1894b67564c96f180f43924',
2014-08-30 18:43:03 +00:00
'info_dict': {
'id': '5227',
2016-10-26 16:10:51 +00:00
'ext': 'mp4',
2014-08-30 18:43:03 +00:00
'title': 'panty slut jerk off instruction',
2014-09-01 21:04:36 +00:00
'duration': 550,
'age_limit': 18,
2016-10-26 16:10:51 +00:00
'view_count': int,
'thumbnail': r're:^https?://.*\.jpg$',
2014-08-30 18:43:03 +00:00
}
}
def _real_extract(self, url):
2016-10-26 16:10:51 +00:00
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
title = self._og_search_title(webpage)
info_dict = self._parse_html5_media_entries(url, webpage, video_id)[0]
2014-11-23 19:41:03 +00:00
2014-09-01 21:04:36 +00:00
duration = parse_duration(self._search_regex(
r'<strong>Runtime:</strong>\s*([0-9:]+)</div>',
webpage, 'duration', fatal=False))
view_count = int_or_none(self._search_regex(
r'<strong>Views:</strong>\s*(\d+)</div>',
webpage, 'view count', fatal=False))
2014-08-30 18:43:03 +00:00
2016-10-26 16:10:51 +00:00
info_dict.update({
2014-08-30 18:43:03 +00:00
'id': video_id,
'title': title,
'duration': duration,
2014-09-01 21:04:36 +00:00
'view_count': view_count,
'age_limit': 18,
2016-10-26 16:10:51 +00:00
})
return info_dict