1
0
Fork 0
mirror of https://gitlab.com/dstftw/youtube-dl.git synced 2020-11-16 09:42:26 +00:00

[cracked] Add new extractor

This commit is contained in:
hassaanaliw 2014-07-16 18:45:42 +05:00
parent bd1f325b42
commit 43f0537c06
2 changed files with 48 additions and 0 deletions

View file

@ -52,6 +52,7 @@ from .cnn import (
from .collegehumor import CollegeHumorIE
from .comedycentral import ComedyCentralIE, ComedyCentralShowsIE
from .condenast import CondeNastIE
from .cracked import CrackedIE
from .criterion import CriterionIE
from .crunchyroll import CrunchyrollIE
from .cspan import CSpanIE
@ -396,6 +397,7 @@ from .youtube import (
YoutubeUserIE,
YoutubeWatchLaterIE,
)
from .zdf import ZDFIE

View file

@ -0,0 +1,46 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
class CrackedIE(InfoExtractor):
_VALID_URL = r'http?://.*?\.cracked\.com/video_+(?P<id>.*)_.*'
_TEST = {
'url': 'http://www.cracked.com/video_18803_4-social-criticisms-hidden-in-sonic-hedgehog-games.html',
'info_dict': {
'id': '18803',
'ext': 'mp4',
'title': "4 Social Criticisms Hidden in 'Sonic the Hedgehog' Games | Cracked.com",
'height': 375,
'width': 666,
}
}
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._search_regex(r'<title>(.*?)</title>',webpage,'title')
video_url = self._search_regex(r'var CK_vidSrc = "+(.*)"',webpage,'url')
width = self._search_regex(r'width="(.*?)"',webpage,'width')
height = re.findall(r'height="(.*?)"',webpage)[1]
return {
'url':video_url,
'id': video_id,
'ext':'mp4',
'title':title,
'height':int(height),
'width':int(width)
}