youtube-dl/youtube_dl/extractor/hornbunny.py

57 lines
1.8 KiB
Python
Raw Normal View History

2014-08-31 03:43:03 +09:00
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
2014-09-02 06:04:36 +09:00
from ..utils import (
int_or_none,
parse_duration,
)
2014-08-31 03:43:03 +09:00
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',
'md5': '95e40865aedd08eff60272b704852ad7',
'info_dict': {
'id': '5227',
'ext': 'flv',
'title': 'panty slut jerk off instruction',
2014-09-02 06:04:36 +09:00
'duration': 550,
'age_limit': 18,
2014-08-31 03:43:03 +09:00
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
2014-09-02 06:04:36 +09:00
webpage = self._download_webpage(
url, video_id, note='Downloading initial webpage')
title = self._html_search_regex(
r'class="title">(.*?)</h2>', webpage, 'title')
redirect_url = self._html_search_regex(
r'pg&settings=(.*?)\|0"\);', webpage, 'title')
2014-08-31 03:43:03 +09:00
webpage2 = self._download_webpage(redirect_url, video_id)
2014-09-02 06:04:36 +09:00
video_url = self._html_search_regex(
r'flvMask:(.*?);', webpage2, 'video_url')
2014-11-24 04:41:03 +09:00
2014-09-02 06:04:36 +09:00
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))
2014-08-31 03:43:03 +09:00
return {
'id': video_id,
'url': video_url,
'title': title,
'ext': 'flv',
'duration': duration,
2014-09-02 06:04:36 +09:00
'view_count': view_count,
'age_limit': 18,
2014-08-31 03:43:03 +09:00
}