1 # -*- coding: utf-8 -*-
2 from __future__ import unicode_literals
6 from .common import InfoExtractor
17 class GorillaVidIE(InfoExtractor):
18 IE_DESC = 'GorillaVid.in, daclips.in, movpod.in, fastvideo.in and realvid.net'
20 https?://(?P<host>(?:www\.)?
21 (?:daclips\.in|gorillavid\.in|movpod\.in|fastvideo\.in|realvid\.net))/
22 (?:embed-)?(?P<id>[0-9a-zA-Z]+)(?:-[0-9]+x[0-9]+\.html)?
25 _FILE_NOT_FOUND_REGEX = r'>(?:404 - )?File Not Found<'
28 'url': 'http://gorillavid.in/06y9juieqpmi',
29 'md5': '5ae4a3580620380619678ee4875893ba',
33 'title': 'Rebecca Black My Moment Official Music Video Reaction-6GK87Rc8bzQ',
34 'thumbnail': 're:http://.*\.jpg',
37 'url': 'http://gorillavid.in/embed-z08zf8le23c6-960x480.html',
38 'md5': 'c9e293ca74d46cad638e199c3f3fe604',
42 'title': 'Say something nice',
43 'thumbnail': 're:http://.*\.jpg',
46 'url': 'http://daclips.in/3rso4kdn6f9m',
47 'md5': '1ad8fd39bb976eeb66004d3a4895f106',
51 'title': 'Micro Pig piglets ready on 16th July 2009-bG0PdrCdxUc',
52 'thumbnail': 're:http://.*\.jpg',
55 # video with countdown timeout
56 'url': 'http://fastvideo.in/1qmdn1lmsmbw',
57 'md5': '8b87ec3f6564a3108a0e8e66594842ba',
61 'title': 'Man of Steel - Trailer',
62 'thumbnail': 're:http://.*\.jpg',
65 'url': 'http://realvid.net/ctn2y6p2eviw',
66 'md5': 'b2166d2cf192efd6b6d764c18fd3710e',
71 'thumbnail': 're:http://.*\.jpg',
74 'url': 'http://movpod.in/0wguyyxi1yca',
75 'only_matching': True,
78 def _real_extract(self, url):
79 mobj = re.match(self._VALID_URL, url)
80 video_id = mobj.group('id')
82 webpage = self._download_webpage('http://%s/%s' % (mobj.group('host'), video_id), video_id)
84 if re.search(self._FILE_NOT_FOUND_REGEX, webpage) is not None:
85 raise ExtractorError('Video %s does not exist' % video_id, expected=True)
87 fields = dict(re.findall(r'''(?x)<input\s+
94 if fields['op'] == 'download1':
95 countdown = int_or_none(self._search_regex(
96 r'<span id="countdown_str">(?:[Ww]ait)?\s*<span id="cxc">(\d+)</span>\s*(?:seconds?)?</span>',
97 webpage, 'countdown', default=None))
99 self._sleep(countdown, video_id)
101 post = compat_urllib_parse.urlencode(fields)
103 req = compat_urllib_request.Request(url, post)
104 req.add_header('Content-type', 'application/x-www-form-urlencoded')
106 webpage = self._download_webpage(req, video_id, 'Downloading video page')
108 title = self._search_regex(
109 [r'style="z-index: [0-9]+;">([^<]+)</span>', r'>Watch (.+) '],
110 webpage, 'title', default=None) or self._og_search_title(webpage)
111 video_url = self._search_regex(
112 r'file\s*:\s*["\'](http[^"\']+)["\'],', webpage, 'file url')
113 thumbnail = self._search_regex(
114 r'image\s*:\s*["\'](http[^"\']+)["\'],', webpage, 'thumbnail', fatal=False)
125 'thumbnail': thumbnail,