youtube_dl/extractor/allmyvideos.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     compat_urllib_parse,
  10     compat_urllib_request,
  11 )
  12
  13
  14 class AllmyvideosIE(InfoExtractor):
  15     IE_NAME = 'allmyvideos.net'
  16     _VALID_URL = r'https?://allmyvideos\.net/(?P<id>[a-zA-Z0-9_-]+)'
  17
  18     _TEST = {
  19         'url': 'http://allmyvideos.net/jih3nce3x6wn',
  20         'md5': '710883dee1bfc370ecf9fa6a89307c88',
  21         'info_dict': {
  22             'id': 'jih3nce3x6wn',
  23             'ext': 'mp4',
  24             'title': 'youtube-dl test video',
  25         },
  26     }
  27
  28     def _real_extract(self, url):
  29         mobj = re.match(self._VALID_URL, url)
  30         video_id = mobj.group('id')
  31
  32         orig_webpage = self._download_webpage(url, video_id)
  33         fields = re.findall(r'type="hidden" name="(.+?)"\s* value="?(.+?)">', orig_webpage)
  34         data = dict(fields)
  35
  36         post = compat_urllib_parse.urlencode(data)
  37         headers = {
  38             b'Content-Type': b'application/x-www-form-urlencoded',
  39         }
  40         req = compat_urllib_request.Request(url, post, headers)
  41         webpage = self._download_webpage(
  42             req, video_id, note='Downloading video page ...')
  43
  44         title = os.path.splitext(data['fname'])[0]
  45
  46         #Could be several links with different quality
  47         links = re.findall(r'"file" : "?(.+?)",', webpage)
  48         # Assume the links are ordered in quality
  49         formats = [{
  50             'url': l,
  51             'quality': i,
  52         } for i, l in enumerate(links)]
  53         self._sort_formats(formats)
  54
  55         return {
  56             'id': video_id,
  57             'title': title,
  58             'formats': formats,
  59         }