X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/ca4d08063804fb264eb0ae9cc57894198f66e1fb..415fdb62500dca2e22067a05008dfbf87c75b662:/youtube_dl/extractor/pornhd.py diff --git a/youtube_dl/extractor/pornhd.py b/youtube_dl/extractor/pornhd.py index 71abd50..718fe9a 100644 --- a/youtube_dl/extractor/pornhd.py +++ b/youtube_dl/extractor/pornhd.py @@ -1,38 +1,81 @@ +from __future__ import unicode_literals + import re +import json from .common import InfoExtractor -from ..utils import compat_urllib_parse +from ..utils import int_or_none class PornHdIE(InfoExtractor): - _VALID_URL = r'(?:http://)?(?:www\.)?pornhd\.com/videos/(?P[0-9]+)/(?P.+)' + _VALID_URL = r'http://(?:www\.)?pornhd\.com/(?:[a-z]{2,4}/)?videos/(?P\d+)' _TEST = { - u'url': u'http://www.pornhd.com/videos/1962/sierra-day-gets-his-cum-all-over-herself-hd-porn-video', - u'file': u'1962.flv', - u'md5': u'35272469887dca97abd30abecc6cdf75', - u'info_dict': { - u"title": u"sierra-day-gets-his-cum-all-over-herself-hd-porn-video", - u"age_limit": 18, + 'url': 'http://www.pornhd.com/videos/1962/sierra-day-gets-his-cum-all-over-herself-hd-porn-video', + 'md5': '956b8ca569f7f4d8ec563e2c41598441', + 'info_dict': { + 'id': '1962', + 'ext': 'mp4', + 'title': 'Sierra loves doing laundry', + 'description': 'md5:8ff0523848ac2b8f9b065ba781ccf294', + 'age_limit': 18, } } def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) - - video_id = mobj.group('video_id') - video_title = mobj.group('video_title') + video_id = mobj.group('id') webpage = self._download_webpage(url, video_id) - video_url = self._html_search_regex( - r'&hd=(http.+?)&', webpage, u'video URL') - video_url = compat_urllib_parse.unquote(video_url) - age_limit = 18 + title = self._og_search_title(webpage) + TITLE_SUFFIX = ' porn HD Video | PornHD.com ' + if title.endswith(TITLE_SUFFIX): + title = title[:-len(TITLE_SUFFIX)] + + description = self._html_search_regex( + r'
([^<]+)
', webpage, 'description', fatal=False) + view_count = int_or_none(self._html_search_regex( + r'(\d+) views ', webpage, 'view count', fatal=False)) + + formats = [ + { + 'url': format_url, + 'ext': format.lower(), + 'format_id': '%s-%s' % (format.lower(), quality.lower()), + 'quality': 1 if quality.lower() == 'high' else 0, + } for format, quality, format_url in re.findall( + r'var __video([\da-zA-Z]+?)(Low|High)StreamUrl = \'(http://.+?)\?noProxy=1\'', webpage) + ] + + mobj = re.search(r'flashVars = (?P{.+?});', webpage) + if mobj: + flashvars = json.loads(mobj.group('flashvars')) + formats.extend([ + { + 'url': flashvars['hashlink'].replace('?noProxy=1', ''), + 'ext': 'flv', + 'format_id': 'flv-low', + 'quality': 0, + }, + { + 'url': flashvars['hd'].replace('?noProxy=1', ''), + 'ext': 'flv', + 'format_id': 'flv-high', + 'quality': 1, + } + ]) + thumbnail = flashvars['urlWallpaper'] + else: + thumbnail = self._og_search_thumbnail(webpage) + + self._sort_formats(formats) return { 'id': video_id, - 'url': video_url, - 'ext': 'flv', - 'title': video_title, - 'age_limit': age_limit, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'view_count': view_count, + 'formats': formats, + 'age_limit': 18, }