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