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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5 import os.path
   6
   7 from .common import InfoExtractor
   8 from ..utils import (
   9     compat_urllib_parse,
  10     compat_urllib_request,
  11 )
  12
  13
  14 class PlayedIE(InfoExtractor):
  15     IE_NAME = 'played.to'
  16     _VALID_URL = r'https?://(?:www\.)?played\.to/(?P<id>[a-zA-Z0-9_-]+)'
  17
  18     _TEST = {
  19         'url': 'http://played.to/j2f2sfiiukgt',
  20         'md5': 'c2bd75a368e82980e7257bf500c00637',
  21         'info_dict': {
  22             'id': 'j2f2sfiiukgt',
  23             'ext': 'flv',
  24             'title': 'youtube-dl_test_video.mp4',
  25         },
  26     }
  27
  28     def _real_extract(self, url):
  29         video_id = self._match_id(url)
  30
  31         orig_webpage = self._download_webpage(url, video_id)
  32         fields = re.findall(
  33             r'type="hidden" name="([^"]+)"\s+value="([^"]+)">', orig_webpage)
  34         data = dict(fields)
  35
  36         self._sleep(2, video_id)
  37
  38         post = compat_urllib_parse.urlencode(data)
  39         headers = {
  40             b'Content-Type': b'application/x-www-form-urlencoded',
  41         }
  42         req = compat_urllib_request.Request(url, post, headers)
  43         webpage = self._download_webpage(
  44             req, video_id, note='Downloading video page ...')
  45
  46         title = os.path.splitext(data['fname'])[0]
  47
  48         video_url = self._search_regex(
  49             r'file: "?(.+?)",', webpage, 'video URL')
  50
  51         return {
  52             'id': video_id,
  53             'title': title,
  54             'url': video_url,
  55         }