Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/gorillavid.py

   1 # -*- coding: utf-8 -*-
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..utils import (
   8     ExtractorError,
   9     determine_ext,
  10     compat_urllib_parse,
  11     compat_urllib_request,
  12 )
  13
  14
  15 class GorillaVidIE(InfoExtractor):
  16     IE_DESC = 'GorillaVid.in, daclips.in and movpod.in'
  17     _VALID_URL = r'''(?x)
  18         https?://(?P<host>(?:www\.)?
  19             (?:daclips\.in|gorillavid\.in|movpod\.in))/
  20         (?:embed-)?(?P<id>[0-9a-zA-Z]+)(?:-[0-9]+x[0-9]+\.html)?
  21     '''
  22
  23     _FILE_NOT_FOUND_REGEX = r'>(?:404 - )?File Not Found<'
  24
  25     _TESTS = [{
  26         'url': 'http://gorillavid.in/06y9juieqpmi',
  27         'md5': '5ae4a3580620380619678ee4875893ba',
  28         'info_dict': {
  29             'id': '06y9juieqpmi',
  30             'ext': 'flv',
  31             'title': 'Rebecca Black My Moment Official Music Video Reaction-6GK87Rc8bzQ',
  32             'thumbnail': 're:http://.*\.jpg',
  33         },
  34     }, {
  35         'url': 'http://gorillavid.in/embed-z08zf8le23c6-960x480.html',
  36         'md5': 'c9e293ca74d46cad638e199c3f3fe604',
  37         'info_dict': {
  38             'id': 'z08zf8le23c6',
  39             'ext': 'mp4',
  40             'title': 'Say something nice',
  41             'thumbnail': 're:http://.*\.jpg',
  42         },
  43     }, {
  44         'url': 'http://daclips.in/3rso4kdn6f9m',
  45         'md5': '1ad8fd39bb976eeb66004d3a4895f106',
  46         'info_dict': {
  47             'id': '3rso4kdn6f9m',
  48             'ext': 'mp4',
  49             'title': 'Micro Pig piglets ready on 16th July 2009-bG0PdrCdxUc',
  50             'thumbnail': 're:http://.*\.jpg',
  51         }
  52     }, {
  53         'url': 'http://movpod.in/0wguyyxi1yca',
  54         'only_matching': True,
  55     }]
  56
  57     def _real_extract(self, url):
  58         mobj = re.match(self._VALID_URL, url)
  59         video_id = mobj.group('id')
  60
  61         webpage = self._download_webpage('http://%s/%s' % (mobj.group('host'), video_id), video_id)
  62
  63         if re.search(self._FILE_NOT_FOUND_REGEX, webpage) is not None:
  64             raise ExtractorError('Video %s does not exist' % video_id, expected=True)
  65
  66         fields = dict(re.findall(r'''(?x)<input\s+
  67             type="hidden"\s+
  68             name="([^"]+)"\s+
  69             (?:id="[^"]+"\s+)?
  70             value="([^"]*)"
  71             ''', webpage))
  72
  73         if fields['op'] == 'download1':
  74             post = compat_urllib_parse.urlencode(fields)
  75
  76             req = compat_urllib_request.Request(url, post)
  77             req.add_header('Content-type', 'application/x-www-form-urlencoded')
  78
  79             webpage = self._download_webpage(req, video_id, 'Downloading video page')
  80
  81         title = self._search_regex(r'style="z-index: [0-9]+;">([^<]+)</span>', webpage, 'title')
  82         video_url = self._search_regex(r'file\s*:\s*\'(http[^\']+)\',', webpage, 'file url')
  83         thumbnail = self._search_regex(r'image\s*:\s*\'(http[^\']+)\',', webpage, 'thumbnail', fatal=False)
  84
  85         formats = [{
  86             'format_id': 'sd',
  87             'url': video_url,
  88             'ext': determine_ext(video_url),
  89             'quality': 1,
  90         }]
  91
  92         return {
  93             'id': video_id,
  94             'title': title,
  95             'thumbnail': thumbnail,
  96             'formats': formats,
  97         }