Browse Source

Add support for HornBunny

totalwebcasting
peugeot 10 years ago
parent
commit
bbc9dc56f6
2 changed files with 45 additions and 0 deletions
  1. +1
    -0
      youtube_dl/extractor/__init__.py
  2. +44
    -0
      youtube_dl/extractor/hornbunny.py

+ 1
- 0
youtube_dl/extractor/__init__.py View File

@ -134,6 +134,7 @@ from .grooveshark import GroovesharkIE
from .hark import HarkIE from .hark import HarkIE
from .helsinki import HelsinkiIE from .helsinki import HelsinkiIE
from .hentaistigma import HentaiStigmaIE from .hentaistigma import HentaiStigmaIE
from .hornbunny import HornBunnyIE
from .hotnewhiphop import HotNewHipHopIE from .hotnewhiphop import HotNewHipHopIE
from .howcast import HowcastIE from .howcast import HowcastIE
from .howstuffworks import HowStuffWorksIE from .howstuffworks import HowStuffWorksIE


+ 44
- 0
youtube_dl/extractor/hornbunny.py View File

@ -0,0 +1,44 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import int_or_none
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',
'duration': 550
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
webpage = self._download_webpage(url, video_id)
title = self._html_search_regex(r'class="title">(.*?)</h2>', webpage, 'title')
redirect_url = self._html_search_regex(r'pg&settings=(.*?)\|0"\);', webpage, 'title')
webpage2 = self._download_webpage(redirect_url, video_id)
video_url = self._html_search_regex(r'flvMask:(.*?);', webpage2, 'video_url')
mobj = re.search(r'<strong>Runtime:</strong> (?P<minutes>\d+):(?P<seconds>\d+)</div>', webpage)
duration = int(mobj.group('minutes')) * 60 + int(mobj.group('seconds')) if mobj else None
view_count = self._html_search_regex(r'<strong>Views:</strong> (\d+)</div>', webpage, 'view count', fatal=False)
return {
'id': video_id,
'url': video_url,
'title': title,
'ext': 'flv',
'duration': duration,
'view_count': int_or_none(view_count),
}

Loading…
Cancel
Save