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 ..compat import compat_urllib_parse
   9 from ..utils import (
  10     ExtractorError,
  11     sanitized_Request,
  12 )
  13
  14
  15 class PlayedIE(InfoExtractor):
  16     IE_NAME = 'played.to'
  17     _VALID_URL = r'https?://(?:www\.)?played\.to/(?P<id>[a-zA-Z0-9_-]+)'
  18
  19     _TEST = {
  20         'url': 'http://played.to/j2f2sfiiukgt',
  21         'md5': 'c2bd75a368e82980e7257bf500c00637',
  22         'info_dict': {
  23             'id': 'j2f2sfiiukgt',
  24             'ext': 'flv',
  25             'title': 'youtube-dl_test_video.mp4',
  26         },
  27         'skip': 'Removed for copyright infringement.',  # oh wow
  28     }
  29
  30     def _real_extract(self, url):
  31         video_id = self._match_id(url)
  32         orig_webpage = self._download_webpage(url, video_id)
  33
  34         m_error = re.search(
  35             r'(?s)Reason for deletion:.*?<b class="err"[^>]*>(?P<msg>[^<]+)</b>', orig_webpage)
  36         if m_error:
  37             raise ExtractorError(m_error.group('msg'), expected=True)
  38
  39         data = self._hidden_inputs(orig_webpage)
  40
  41         self._sleep(2, video_id)
  42
  43         post = compat_urllib_parse.urlencode(data)
  44         headers = {
  45             b'Content-Type': b'application/x-www-form-urlencoded',
  46         }
  47         req = sanitized_Request(url, post, headers)
  48         webpage = self._download_webpage(
  49             req, video_id, note='Downloading video page ...')
  50
  51         title = os.path.splitext(data['fname'])[0]
  52
  53         video_url = self._search_regex(
  54             r'file: "?(.+?)",', webpage, 'video URL')
  55
  56         return {
  57             'id': video_id,
  58             'title': title,
  59             'url': video_url,
  60         }