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 ..compat import (
   9     compat_urllib_parse,
  10     compat_urllib_request,
  11 )
  12 from ..utils import (
  13     ExtractorError,
  14 )
  15
  16
  17 class PlayedIE(InfoExtractor):
  18     IE_NAME = 'played.to'
  19     _VALID_URL = r'https?://(?:www\.)?played\.to/(?P<id>[a-zA-Z0-9_-]+)'
  20
  21     _TEST = {
  22         'url': 'http://played.to/j2f2sfiiukgt',
  23         'md5': 'c2bd75a368e82980e7257bf500c00637',
  24         'info_dict': {
  25             'id': 'j2f2sfiiukgt',
  26             'ext': 'flv',
  27             'title': 'youtube-dl_test_video.mp4',
  28         },
  29         'skip': 'Removed for copyright infringement.',  # oh wow
  30     }
  31
  32     def _real_extract(self, url):
  33         video_id = self._match_id(url)
  34         orig_webpage = self._download_webpage(url, video_id)
  35
  36         m_error = re.search(
  37             r'(?s)Reason for deletion:.*?<b class="err"[^>]*>(?P<msg>[^<]+)</b>', orig_webpage)
  38         if m_error:
  39             raise ExtractorError(m_error.group('msg'), expected=True)
  40
  41         fields = re.findall(
  42             r'type="hidden" name="([^"]+)"\s+value="([^"]+)">', orig_webpage)
  43         data = dict(fields)
  44
  45         self._sleep(2, video_id)
  46
  47         post = compat_urllib_parse.urlencode(data)
  48         headers = {
  49             b'Content-Type': b'application/x-www-form-urlencoded',
  50         }
  51         req = compat_urllib_request.Request(url, post, headers)
  52         webpage = self._download_webpage(
  53             req, video_id, note='Downloading video page ...')
  54
  55         title = os.path.splitext(data['fname'])[0]
  56
  57         video_url = self._search_regex(
  58             r'file: "?(.+?)",', webpage, 'video URL')
  59
  60         return {
  61             'id': video_id,
  62             'title': title,
  63             'url': video_url,
  64         }