diff options
| author | Sergey M․ <dstftw@gmail.com> | 2014-07-18 20:29:35 +0700 | 
|---|---|---|
| committer | Sergey M․ <dstftw@gmail.com> | 2014-07-18 20:29:35 +0700 | 
| commit | 61bbddbaa6ac8e0e61a763d0b1500d952f3e027f (patch) | |
| tree | a5f6c0b49491ea2c392a62de3e8652cc5fc8251e | |
| parent | 0382ecb78d763abf579e686c56085877eef7897c (diff) | |
| parent | 43f0537c06384b9b97235a93ea39649ee3de4d45 (diff) | |
Merge branch 'cracked' of https://github.com/hassaanaliw/youtube-dl
| -rw-r--r-- | youtube_dl/extractor/__init__.py | 2 | ||||
| -rw-r--r-- | youtube_dl/extractor/cracked.py | 46 | 
2 files changed, 48 insertions, 0 deletions
| diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 03d2e446d..f78aa066f 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -53,6 +53,7 @@ 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 @@ -399,6 +400,7 @@ from .youtube import (      YoutubeUserIE,      YoutubeWatchLaterIE,  ) +  from .zdf import ZDFIE diff --git a/youtube_dl/extractor/cracked.py b/youtube_dl/extractor/cracked.py new file mode 100644 index 000000000..37c0f7ffb --- /dev/null +++ b/youtube_dl/extractor/cracked.py @@ -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) + + +        }
\ No newline at end of file | 
