[JizzBunker] Add new extractor

This commit is contained in:
Pip Longrun 2019-12-26 16:32:31 +01:00
parent 18ff573e50
commit 6990899c55
2 changed files with 44 additions and 0 deletions

View File

@ -494,6 +494,7 @@ from .jamendo import (
JamendoAlbumIE,
)
from .jeuxvideo import JeuxVideoIE
from .jizzbunker import JizzBunkerIE
from .jove import JoveIE
from .joj import JojIE
from .jwplatform import JWPlatformIE

View File

@ -0,0 +1,43 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
int_or_none,
)
class JizzBunkerIE(InfoExtractor):
_VALID_URL = r'https://(?:www\.)?jizzbunker\.com/(?P<id>\d+)/(?P<display_id>.+)\.html'
_TEST = {
'url': 'https://jizzbunker.com/22295/blonde-girl-strips-at-home.html',
'info_dict': {
'id': '22295',
'display_id': 'blonde-girl-strips-at-home',
'ext': '480',
'title': 'Blonde girl strips at home',
'thumbnail': r're:^https?://.*\.jpg$',
}
}
def _real_extract(self, url):
video_id = self._match_id(url)
display_id = re.match(self._VALID_URL, url).group('display_id')
webpage = self._download_webpage(url, video_id)
title = self._html_search_regex(r'<h1[^>]*>\n?(.+?)</h1>', webpage, 'title')
thumbnail = self._og_search_thumbnail(webpage, default=None)
duration = int_or_none(self._search_regex(r'dur: (\d+)', webpage, 'duration', default=None))
video_url = self._search_regex(r"type:'video/mp4',src:'(https://[^']+)", webpage, 'video url')
return {
'id': video_id,
'display_id': display_id,
'title': title,
'thumbnail': thumbnail,
'duration': duration,
'url': video_url,
}