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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import os.path
   5 import re
   6
   7 from .common import InfoExtractor
   8 from ..compat import (
   9     compat_urllib_parse,
  10     compat_urllib_request,
  11 )
  12 from ..utils import (
  13     ExtractorError,
  14     remove_start,
  15 )
  16
  17
  18 class MonikerIE(InfoExtractor):
  19     IE_DESC = 'allmyvideos.net and vidspot.net'
  20     _VALID_URL = r'https?://(?:www\.)?(?:allmyvideos|vidspot)\.net/(?:(?:2|v)/v-)?(?P<id>[a-zA-Z0-9_-]+)'
  21
  22     _TESTS = [{
  23         'url': 'http://allmyvideos.net/jih3nce3x6wn',
  24         'md5': '710883dee1bfc370ecf9fa6a89307c88',
  25         'info_dict': {
  26             'id': 'jih3nce3x6wn',
  27             'ext': 'mp4',
  28             'title': 'youtube-dl test video',
  29         },
  30     }, {
  31         'url': 'http://allmyvideos.net/embed-jih3nce3x6wn',
  32         'md5': '710883dee1bfc370ecf9fa6a89307c88',
  33         'info_dict': {
  34             'id': 'jih3nce3x6wn',
  35             'ext': 'mp4',
  36             'title': 'youtube-dl test video',
  37         },
  38     }, {
  39         'url': 'http://vidspot.net/l2ngsmhs8ci5',
  40         'md5': '710883dee1bfc370ecf9fa6a89307c88',
  41         'info_dict': {
  42             'id': 'l2ngsmhs8ci5',
  43             'ext': 'mp4',
  44             'title': 'youtube-dl test video',
  45         },
  46     }, {
  47         'url': 'https://www.vidspot.net/l2ngsmhs8ci5',
  48         'only_matching': True,
  49     }, {
  50         'url': 'http://vidspot.net/2/v-ywDf99',
  51         'md5': '5f8254ce12df30479428b0152fb8e7ba',
  52         'info_dict': {
  53             'id': 'ywDf99',
  54             'ext': 'mp4',
  55             'title': 'IL FAIT LE MALIN EN PORSHE CAYENNE ( mais pas pour longtemps)',
  56             'description': 'IL FAIT LE MALIN EN PORSHE CAYENNE.',
  57         },
  58     }, {
  59         'url': 'http://allmyvideos.net/v/v-HXZm5t',
  60         'only_matching': True,
  61     }]
  62
  63     def _real_extract(self, url):
  64         orig_video_id = self._match_id(url)
  65         video_id = remove_start(orig_video_id, 'embed-')
  66         url = url.replace(orig_video_id, video_id)
  67         assert re.match(self._VALID_URL, url) is not None
  68         orig_webpage = self._download_webpage(url, video_id)
  69
  70         if '>File Not Found<' in orig_webpage:
  71             raise ExtractorError('Video %s does not exist' % video_id, expected=True)
  72
  73         error = self._search_regex(
  74             r'class="err">([^<]+)<', orig_webpage, 'error', default=None)
  75         if error:
  76             raise ExtractorError(
  77                 '%s returned error: %s' % (self.IE_NAME, error), expected=True)
  78
  79         builtin_url = self._search_regex(
  80             r'<iframe[^>]+src=(["\'])(?P<url>.+?/builtin-.+?)\1',
  81             orig_webpage, 'builtin URL', default=None, group='url')
  82
  83         if builtin_url:
  84             req = compat_urllib_request.Request(builtin_url)
  85             req.add_header('Referer', url)
  86             webpage = self._download_webpage(req, video_id, 'Downloading builtin page')
  87             title = self._og_search_title(orig_webpage).strip()
  88             description = self._og_search_description(orig_webpage).strip()
  89         else:
  90             fields = re.findall(r'type="hidden" name="(.+?)"\s* value="?(.+?)">', orig_webpage)
  91             data = dict(fields)
  92
  93             post = compat_urllib_parse.urlencode(data)
  94             headers = {
  95                 b'Content-Type': b'application/x-www-form-urlencoded',
  96             }
  97             req = compat_urllib_request.Request(url, post, headers)
  98             webpage = self._download_webpage(
  99                 req, video_id, note='Downloading video page ...')
 100
 101             title = os.path.splitext(data['fname'])[0]
 102             description = None
 103
 104         # Could be several links with different quality
 105         links = re.findall(r'"file" : "?(.+?)",', webpage)
 106         # Assume the links are ordered in quality
 107         formats = [{
 108             'url': l,
 109             'quality': i,
 110         } for i, l in enumerate(links)]
 111         self._sort_formats(formats)
 112
 113         return {
 114             'id': video_id,
 115             'title': title,
 116             'description': description,
 117             'formats': formats,
 118         }