From bbc9dc56f663ba8a61ce2d5c8aa3fdde7992fb78 Mon Sep 17 00:00:00 2001 From: peugeot Date: Sat, 30 Aug 2014 20:43:03 +0200 Subject: [PATCH] Add support for HornBunny --- youtube_dl/extractor/__init__.py | 1 + youtube_dl/extractor/hornbunny.py | 44 +++++++++++++++++++++++++++++++ 2 files changed, 45 insertions(+) create mode 100644 youtube_dl/extractor/hornbunny.py diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 1479d998a..17891fb80 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -134,6 +134,7 @@ from .grooveshark import GroovesharkIE from .hark import HarkIE from .helsinki import HelsinkiIE from .hentaistigma import HentaiStigmaIE +from .hornbunny import HornBunnyIE from .hotnewhiphop import HotNewHipHopIE from .howcast import HowcastIE from .howstuffworks import HowStuffWorksIE diff --git a/youtube_dl/extractor/hornbunny.py b/youtube_dl/extractor/hornbunny.py new file mode 100644 index 000000000..a42fba0cb --- /dev/null +++ b/youtube_dl/extractor/hornbunny.py @@ -0,0 +1,44 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import int_or_none + +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', + 'info_dict': { + 'id': '5227', + 'ext': 'flv', + 'title': 'panty slut jerk off instruction', + 'duration': 550 + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + 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 + + view_count = self._html_search_regex(r'Views: (\d+)', webpage, 'view count', fatal=False) + + return { + 'id': video_id, + 'url': video_url, + 'title': title, + 'ext': 'flv', + 'duration': duration, + 'view_count': int_or_none(view_count), + }