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/(?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
  51     def _real_extract(self, url):
  52         orig_video_id = self._match_id(url)
  53         video_id = remove_start(orig_video_id, 'embed-')
  54         url = url.replace(orig_video_id, video_id)
  55         assert re.match(self._VALID_URL, url) is not None
  56         orig_webpage = self._download_webpage(url, video_id)
  57
  58         if '>File Not Found<' in orig_webpage:
  59             raise ExtractorError('Video %s does not exist' % video_id, expected=True)
  60
  61         error = self._search_regex(
  62             r'class="err">([^<]+)<', orig_webpage, 'error', default=None)
  63         if error:
  64             raise ExtractorError(
  65                 '%s returned error: %s' % (self.IE_NAME, error), expected=True)
  66
  67         fields = re.findall(r'type="hidden" name="(.+?)"\s* value="?(.+?)">', orig_webpage)
  68         data = dict(fields)
  69
  70         post = compat_urllib_parse.urlencode(data)
  71         headers = {
  72             b'Content-Type': b'application/x-www-form-urlencoded',
  73         }
  74         req = compat_urllib_request.Request(url, post, headers)
  75         webpage = self._download_webpage(
  76             req, video_id, note='Downloading video page ...')
  77
  78         title = os.path.splitext(data['fname'])[0]
  79
  80         # Could be several links with different quality
  81         links = re.findall(r'"file" : "?(.+?)",', webpage)
  82         # Assume the links are ordered in quality
  83         formats = [{
  84             'url': l,
  85             'quality': i,
  86         } for i, l in enumerate(links)]
  87         self._sort_formats(formats)
  88
  89         return {
  90             'id': video_id,
  91             'title': title,
  92             'formats': formats,
  93         }