diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index c05a436417..0f7d44616d 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -388,6 +388,7 @@ from .pornhub import ( PornHubPlaylistIE, ) from .pornotube import PornotubeIE +from .pornovoisines import PornoVoisinesIE from .pornoxo import PornoXOIE from .primesharetv import PrimeShareTVIE from .promptfile import PromptFileIE diff --git a/youtube_dl/extractor/pornovoisines.py b/youtube_dl/extractor/pornovoisines.py new file mode 100644 index 0000000000..efbb6a8187 --- /dev/null +++ b/youtube_dl/extractor/pornovoisines.py @@ -0,0 +1,101 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re +import datetime +import random + +from ..compat import compat_urllib_parse +from .common import InfoExtractor + +class PornoVoisinesIE(InfoExtractor): + _VALID_URL = r'^((?:http://)?(?:www\.)?pornovoisines.com)/showvideo/(\d+)/([^/]+)' + + VIDEO_URL_TEMPLATE = 'http://stream%d.pornovoisines.com' \ + '/static/media/video/transcoded/%s-640x360-1000-trscded.mp4' + + SERVER_NUMBERS = (1, 2) + + _TEST = { + 'url': 'http://www.pornovoisines.com/showvideo/1285/recherche-appartement/', + 'md5': '5ac670803bc12e9e7f9f662ce64cf1d1', + 'info_dict': { + 'id': '1285', + 'display_id': 'recherche-appartement', + 'ext': 'mp4', + 'title': "Recherche appartement", + 'upload_date': '20140925', + 'view_count': int, + 'duration': 120, + 'categories': ["Débutante", "Scénario", "Sodomie"], + 'description': 're:^Pour la .+ original...$', + 'thumbnail': 're:^http://', + 'uploader': "JMTV", + 'average_rating': float, + 'comment_count': int, + 'age_limit': 18, + } + } + + @classmethod + def build_video_url(cls, id): + server_nr = random.choice(cls.SERVER_NUMBERS) + return cls.VIDEO_URL_TEMPLATE % (server_nr, id) + + @staticmethod + def parse_upload_date(str): + return datetime.datetime.strptime(str, "%d-%m-%Y").strftime("%Y%m%d") + + @staticmethod + def parse_categories(str): + return map(lambda s: s.strip(), str.split(',')) + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + url_prefix = mobj.group(1) + id = mobj.group(2) + display_id = mobj.group(3) + + webpage = self._download_webpage(url, id) + + title = self._html_search_regex(r'