Merge remote-tracking branch 'peugeot/drtuber'

This commit is contained in:
Philipp Hagemeister 2014-09-01 23:17:27 +02:00
commit 94388f50b3
2 changed files with 49 additions and 0 deletions

View File

@ -70,6 +70,7 @@
from .dfb import DFBIE
from .dotsub import DotsubIE
from .dreisat import DreiSatIE
from .drtuber import DrTuberIE
from .drtv import DRTVIE
from .dump import DumpIE
from .defense import DefenseGouvFrIE

View File

@ -0,0 +1,48 @@
from __future__ import unicode_literals
import re
from .common import InfoExtractor
class DrTuberIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?drtuber\.com/video/(?P<id>\d+)/(?P<title_dash>[\w-]+)'
_TEST = {
'url': 'http://www.drtuber.com/video/1740434/hot-perky-blonde-naked-golf',
'md5': '93e680cf2536ad0dfb7e74d94a89facd',
'info_dict': {
'id': '1740434',
'ext': 'mp4',
'title': 'Hot Perky Blonde Naked Golf',
'categories': list, # NSFW
'thumbnail': 're:https?://.*\.jpg$',
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
webpage = self._download_webpage(url, video_id)
video_url = self._html_search_regex(
r'<source src="([^"]+)"', webpage, 'video URL')
title = self._html_search_regex(
r'<title>([^<]+)\s*-\s*Free', webpage, 'title')
thumbnail = self._html_search_regex(
r'poster="([^"]+)"',
webpage, 'thumbnail', fatal=False)
categories_str = self._html_search_regex(
r'<meta name="keywords" content="([^"]+)"', webpage, 'categories', fatal=False)
categories = categories_str.split(' ')
return {
'id': video_id,
'url': video_url,
'title': title,
'thumbnail': thumbnail,
'categories': categories,
}