diff options
Diffstat (limited to 'youtube_dl/extractor/gorillavid.py')
-rw-r--r-- | youtube_dl/extractor/gorillavid.py | 87 |
1 files changed, 87 insertions, 0 deletions
diff --git a/youtube_dl/extractor/gorillavid.py b/youtube_dl/extractor/gorillavid.py new file mode 100644 index 000000000..50ef54cce --- /dev/null +++ b/youtube_dl/extractor/gorillavid.py @@ -0,0 +1,87 @@ +# -*- coding: utf-8 -*- +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + determine_ext, + compat_urllib_parse, + compat_urllib_request, +) + + +class GorillaVidIE(InfoExtractor): + IE_DESC = 'GorillaVid.in and daclips.in' + _VALID_URL = r'''(?x) + https?://(?:www\.)? + (?:daclips\.in|gorillavid\.in)/ + (?:embed-)?(?P<id>[0-9a-zA-Z]+)(?:-[0-9]+x[0-9]+\.html)? + ''' + + _TESTS = [{ + 'url': 'http://gorillavid.in/06y9juieqpmi', + 'md5': '5ae4a3580620380619678ee4875893ba', + 'info_dict': { + 'id': '06y9juieqpmi', + 'ext': 'flv', + 'title': 'Rebecca Black My Moment Official Music Video Reaction', + 'thumbnail': 're:http://.*\.jpg', + }, + }, { + 'url': 'http://gorillavid.in/embed-z08zf8le23c6-960x480.html', + 'md5': 'c9e293ca74d46cad638e199c3f3fe604', + 'info_dict': { + 'id': 'z08zf8le23c6', + 'ext': 'mp4', + 'title': 'Say something nice', + 'thumbnail': 're:http://.*\.jpg', + }, + }, { + 'url': 'http://daclips.in/3rso4kdn6f9m', + 'info_dict': { + 'id': '3rso4kdn6f9m', + 'ext': 'mp4', + 'title': 'Micro Pig piglets ready on 16th July 2009', + 'thumbnail': 're:http://.*\.jpg', + }, + }] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + webpage = self._download_webpage(url, video_id) + + fields = dict(re.findall(r'''(?x)<input\s+ + type="hidden"\s+ + name="([^"]+)"\s+ + (?:id="[^"]+"\s+)? + value="([^"]*)" + ''', webpage)) + + if fields['op'] == 'download1': + post = compat_urllib_parse.urlencode(fields) + + req = compat_urllib_request.Request(url, post) + req.add_header('Content-type', 'application/x-www-form-urlencoded') + + webpage = self._download_webpage(req, video_id, 'Downloading video page') + + title = self._search_regex(r'style="z-index: [0-9]+;">([0-9a-zA-Z ]+)(?:-.+)?</span>', webpage, 'title') + thumbnail = self._search_regex(r'image:\'(http[^\']+)\',', webpage, 'thumbnail') + url = self._search_regex(r'file: \'(http[^\']+)\',', webpage, 'file url') + + formats = [{ + 'format_id': 'sd', + 'url': url, + 'ext': determine_ext(url), + 'quality': 1, + }] + + return { + 'id': video_id, + 'title': title, + 'thumbnail': thumbnail, + 'formats': formats, + } |