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

   1 # -*- coding: utf-8 -*-
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..compat import compat_urllib_parse
   6 from ..utils import (
   7     ExtractorError,
   8     NO_DEFAULT,
   9     sanitized_Request,
  10 )
  11
  12
  13 class VodlockerIE(InfoExtractor):
  14     _VALID_URL = r'https?://(?:www\.)?vodlocker\.(?:com|city)/(?:embed-)?(?P<id>[0-9a-zA-Z]+)(?:\..*?)?'
  15
  16     _TESTS = [{
  17         'url': 'http://vodlocker.com/e8wvyzz4sl42',
  18         'md5': 'ce0c2d18fa0735f1bd91b69b0e54aacf',
  19         'info_dict': {
  20             'id': 'e8wvyzz4sl42',
  21             'ext': 'mp4',
  22             'title': 'Germany vs Brazil',
  23             'thumbnail': 're:http://.*\.jpg',
  24         },
  25     }]
  26
  27     def _real_extract(self, url):
  28         video_id = self._match_id(url)
  29         webpage = self._download_webpage(url, video_id)
  30
  31         if any(p in webpage for p in (
  32                 '>THIS FILE WAS DELETED<',
  33                 '>File Not Found<',
  34                 'The file you were looking for could not be found, sorry for any inconvenience.<')):
  35             raise ExtractorError('Video %s does not exist' % video_id, expected=True)
  36
  37         fields = self._hidden_inputs(webpage)
  38
  39         if fields['op'] == 'download1':
  40             self._sleep(3, video_id)  # they do detect when requests happen too fast!
  41             post = compat_urllib_parse.urlencode(fields)
  42             req = sanitized_Request(url, post)
  43             req.add_header('Content-type', 'application/x-www-form-urlencoded')
  44             webpage = self._download_webpage(
  45                 req, video_id, 'Downloading video page')
  46
  47         def extract_file_url(html, default=NO_DEFAULT):
  48             return self._search_regex(
  49                 r'file:\s*"(http[^\"]+)",', html, 'file url', default=default)
  50
  51         video_url = extract_file_url(webpage, default=None)
  52
  53         if not video_url:
  54             embed_url = self._search_regex(
  55                 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?://)?vodlocker\.(?:com|city)/embed-.+?)\1',
  56                 webpage, 'embed url', group='url')
  57             embed_webpage = self._download_webpage(
  58                 embed_url, video_id, 'Downloading embed webpage')
  59             video_url = extract_file_url(embed_webpage)
  60             thumbnail_webpage = embed_webpage
  61         else:
  62             thumbnail_webpage = webpage
  63
  64         title = self._search_regex(
  65             r'id="file_title".*?>\s*(.*?)\s*<(?:br|span)', webpage, 'title')
  66         thumbnail = self._search_regex(
  67             r'image:\s*"(http[^\"]+)",', thumbnail_webpage, 'thumbnail', fatal=False)
  68
  69         formats = [{
  70             'format_id': 'sd',
  71             'url': video_url,
  72         }]
  73
  74         return {
  75             'id': video_id,
  76             'title': title,
  77             'thumbnail': thumbnail,
  78             'formats': formats,
  79         }