X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fhornbunny.py;h=c458a959d9767c47eeaaf7a05f5c853637b6ab34;hb=HEAD;hp=a42fba0cbaf548247d9fbb77365a211fc4a1ca30;hpb=04b4aa4a7b5f3257923640fbba4f90efb2a195fc;p=youtube-dl diff --git a/youtube_dl/extractor/hornbunny.py b/youtube_dl/extractor/hornbunny.py index a42fba0cb..c458a959d 100644 --- a/youtube_dl/extractor/hornbunny.py +++ b/youtube_dl/extractor/hornbunny.py @@ -1,44 +1,49 @@ # coding: utf-8 from __future__ import unicode_literals -import re - from .common import InfoExtractor -from ..utils import int_or_none +from ..utils import ( + int_or_none, + parse_duration, +) + class HornBunnyIE(InfoExtractor): _VALID_URL = r'http?://(?:www\.)?hornbunny\.com/videos/(?P[a-z-]+)-(?P\d+)\.html' _TEST = { 'url': 'http://hornbunny.com/videos/panty-slut-jerk-off-instruction-5227.html', - 'md5': '95e40865aedd08eff60272b704852ad7', + 'md5': 'e20fd862d1894b67564c96f180f43924', 'info_dict': { 'id': '5227', - 'ext': 'flv', + 'ext': 'mp4', 'title': 'panty slut jerk off instruction', - 'duration': 550 + 'duration': 550, + 'age_limit': 18, + 'view_count': int, + 'thumbnail': r're:^https?://.*\.jpg$', } } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) - title = self._html_search_regex(r'class="title">(.*?)', 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'Runtime: (?P\d+):(?P\d+)', webpage) - duration = int(mobj.group('minutes')) * 60 + int(mobj.group('seconds')) if mobj else None + title = self._og_search_title(webpage) + info_dict = self._parse_html5_media_entries(url, webpage, video_id)[0] - view_count = self._html_search_regex(r'Views: (\d+)', webpage, 'view count', fatal=False) + duration = parse_duration(self._search_regex( + r'Runtime:\s*([0-9:]+)', + webpage, 'duration', fatal=False)) + view_count = int_or_none(self._search_regex( + r'Views:\s*(\d+)', + webpage, 'view count', fatal=False)) - return { + info_dict.update({ 'id': video_id, - 'url': video_url, 'title': title, - 'ext': 'flv', 'duration': duration, - 'view_count': int_or_none(view_count), - } + 'view_count': view_count, + 'age_limit': 18, + }) + + return info_dict