w/youtube-dl
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity

[hornbunny] Fix extraction (#10981)

Browse source
This commit is contained in:
Yen Chi Hsuan 2016-10-27 00:10:51 +08:00
parent 3d8d44c7b1
commit ec8705117a
No known key found for this signature in database
GPG key ID: 3FDDD575826C5C30
2 changed files with 18 additions and 19 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

6
ChangeLog
View file

@ -1,3 +1,9 @@
version <unreleased>
Extractors
* [hornbunny] Fix extraction (#10981)
version 2016.10.26 version 2016.10.26
Extractors Extractors

31
youtube_dl/extractor/hornbunny.py
View file

@ -1,8 +1,6 @@
# coding: utf-8 # coding: utf-8
from __future__ import unicode_literals from __future__ import unicode_literals
import re
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..utils import (
int_or_none, int_or_none,
@ -14,29 +12,24 @@ class HornBunnyIE(InfoExtractor):
_VALID_URL = r'http?://(?:www\.)?hornbunny\.com/videos/(?P<title_dash>[a-z-]+)-(?P<id>\d+)\.html' _VALID_URL = r'http?://(?:www\.)?hornbunny\.com/videos/(?P<title_dash>[a-z-]+)-(?P<id>\d+)\.html'
_TEST = { _TEST = {
'url': 'http://hornbunny.com/videos/panty-slut-jerk-off-instruction-5227.html', 'url': 'http://hornbunny.com/videos/panty-slut-jerk-off-instruction-5227.html',
'md5': '95e40865aedd08eff60272b704852ad7', 'md5': 'e20fd862d1894b67564c96f180f43924',
'info_dict': { 'info_dict': {
'id': '5227', 'id': '5227',
'ext': 'flv', 'ext': 'mp4',
'title': 'panty slut jerk off instruction', 'title': 'panty slut jerk off instruction',
'duration': 550, 'duration': 550,
'age_limit': 18, 'age_limit': 18,
'view_count': int,
'thumbnail': 're:^https?://.*\.jpg$',
} }
} }
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) video_id = self._match_id(url)
video_id = mobj.group('id')
webpage = self._download_webpage( webpage = self._download_webpage(url, video_id)
url, video_id, note='Downloading initial webpage') title = self._og_search_title(webpage)
title = self._html_search_regex( info_dict = self._parse_html5_media_entries(url, webpage, video_id)[0]
r'class="title">(.*?)</h2>', 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')
duration = parse_duration(self._search_regex( duration = parse_duration(self._search_regex(
r'<strong>Runtime:</strong>\s*([0-9:]+)</div>', r'<strong>Runtime:</strong>\s*([0-9:]+)</div>',
@ -45,12 +38,12 @@ class HornBunnyIE(InfoExtractor):
r'<strong>Views:</strong>\s*(\d+)</div>', r'<strong>Views:</strong>\s*(\d+)</div>',
webpage, 'view count', fatal=False)) webpage, 'view count', fatal=False))
return { info_dict.update({
'id': video_id, 'id': video_id,
'url': video_url,
'title': title, 'title': title,
'ext': 'flv',
'duration': duration, 'duration': duration,
'view_count': view_count, 'view_count': view_count,
'age_limit': 18, 'age_limit': 18,
} })
return info_dict