ytdl-org
/
youtube-dl
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

[slutload] Simplify (#2898)

master
Philipp Hagemeister 2014-05-13 10:04:29 +02:00
parent 948bcc60df
commit 5301304bf2
1 changed files with 27 additions and 26 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

53
youtube_dl/extractor/slutload.py
View File

@ -1,3 +1,5 @@
from __future__ import unicode_literals
import re import re
from .common import InfoExtractor from .common import InfoExtractor
@ -5,42 +7,41 @@ from ..utils import (
ExtractorError, ExtractorError,
) )
class SlutloadIE(InfoExtractor): class SlutloadIE(InfoExtractor):
_VALID_URL = r'^https?://(?:\w+\.)?slutload\.com/video/[^/]+/(?P<videoid>[^/]+)/?$' _VALID_URL = r'^https?://(?:\w+\.)?slutload\.com/video/[^/]+/(?P<id>[^/]+)/?$'
_TEST = { _TEST = {
u'url': u'http://www.slutload.com/video/virginie-baisee-en-cam/TD73btpBqSxc/', 'url': 'http://www.slutload.com/video/virginie-baisee-en-cam/TD73btpBqSxc/',
u'file': u'TD73btpBqSxc.mp4', 'md5': '0cf531ae8006b530bd9df947a6a0df77',
u'md5': u'0cf531ae8006b530bd9df947a6a0df77', 'info_dict': {
u'info_dict': { 'id': 'TD73btpBqSxc',
u"title": u"virginie baisee en cam", 'ext': 'mp4',
u"age_limit": 18, "title": "virginie baisee en cam",
"age_limit": 18,
'thumbnail': 're:https?://.*?\.jpg'
} }
} }
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
video_id = mobj.group('videoid')
# Get webpage content
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
# Get the video title
video_title = self._html_search_regex(r'<h1><strong>([^<]+)</strong>', video_title = self._html_search_regex(r'<h1><strong>([^<]+)</strong>',
webpage, u'title').strip() webpage, 'title').strip()
# Get the video url video_url = self._html_search_regex(
result = re.compile(r'<div id="vidPlayer"\s+data-url="([^"]+)"\s+previewer-file="([^"]+)"', re.S).search(webpage) r'(?s)<div id="vidPlayer"\s+data-url="([^"]+)"',
if result is None: webpage, 'video URL')
raise ExtractorError(u'ERROR: unable to extract video_url') thumbnail = self._html_search_regex(
r'(?s)<div id="vidPlayer"\s+.*?previewer-file="([^"]+)"',
webpage, 'thumbnail', fatal=False)
video_url, video_thumb = result.group(1,2) return {
'id': video_id,
info = {'id': video_id, 'url': video_url,
'url': video_url, 'title': video_title,
'title': video_title, 'thumbnail': thumbnail,
'thumbnail': video_thumb, 'age_limit': 18
'ext': 'mp4', }
'age_limit': 18}
return [info]