youtube_dl/extractor/fourtube.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..utils import (
   7     compat_urllib_request,
   8     unified_strdate,
   9     str_to_int,
  10     parse_duration,
  11     clean_html,
  12 )
  13
  14
  15 class FourTubeIE(InfoExtractor):
  16     IE_NAME = '4tube'
  17     _VALID_URL = r'https?://(?:www\.)?4tube\.com/videos/(?P<id>\d+)'
  18
  19     _TEST = {
  20         'url': 'http://www.4tube.com/videos/209733/hot-babe-holly-michaels-gets-her-ass-stuffed-by-black',
  21         'md5': '6516c8ac63b03de06bc8eac14362db4f',
  22         'info_dict': {
  23             'id': '209733',
  24             'ext': 'mp4',
  25             'title': 'Hot Babe Holly Michaels gets her ass stuffed by black',
  26             'uploader': 'WCP Club',
  27             'uploader_id': 'wcp-club',
  28             'upload_date': '20131031',
  29             'duration': 583,
  30         }
  31     }
  32
  33     def _real_extract(self, url):
  34         mobj = re.match(self._VALID_URL, url)
  35
  36         video_id = mobj.group('id')
  37         webpage_url = 'http://www.4tube.com/videos/' + video_id
  38         webpage = self._download_webpage(webpage_url, video_id)
  39
  40         self.report_extraction(video_id)
  41
  42         playlist_json = self._html_search_regex(r'var playerConfigPlaylist\s+=\s+([^;]+)', webpage, 'Playlist')
  43         media_id = self._search_regex(r'idMedia:\s*(\d+)', playlist_json, 'Media Id')
  44         sources = self._search_regex(r'sources:\s*\[([^\]]*)\]', playlist_json, 'Sources').split(',')
  45         title = self._search_regex(r'title:\s*"([^"]*)', playlist_json, 'Title')
  46         thumbnail_url = self._search_regex(r'image:\s*"([^"]*)', playlist_json, 'Thumbnail', fatal=False)
  47
  48         uploader_str = self._search_regex(r'<span>Uploaded by</span>(.*?)<span>', webpage, 'uploader', fatal=False)
  49         mobj = re.search(r'<a href="/sites/(?P<id>[^"]+)"><strong>(?P<name>[^<]+)</strong></a>', uploader_str)
  50         (uploader, uploader_id) = (mobj.group('name'), mobj.group('id')) if mobj else (clean_html(uploader_str), None)
  51
  52         upload_date = None
  53         view_count = None
  54         duration = None
  55         description = self._html_search_meta('description', webpage, 'description')
  56         if description:
  57             upload_date = self._search_regex(r'Published Date: (\d{2} [a-zA-Z]{3} \d{4})', description, 'upload date',
  58                 fatal=False)
  59             if upload_date:
  60                 upload_date = unified_strdate(upload_date)
  61             view_count = self._search_regex(r'Views: ([\d,\.]+)', description, 'view count', fatal=False)
  62             if view_count:
  63                 view_count = str_to_int(view_count)
  64             duration = parse_duration(self._search_regex(r'Length: (\d+m\d+s)', description, 'duration', fatal=False))
  65
  66         token_url = "http://tkn.4tube.com/{0}/desktop/{1}".format(media_id, "+".join(sources))
  67         headers = {
  68                 b'Content-Type': b'application/x-www-form-urlencoded',
  69                 b'Origin': b'http://www.4tube.com',
  70                 }
  71         token_req = compat_urllib_request.Request(token_url, b'{}', headers)
  72         tokens = self._download_json(token_req, video_id)
  73
  74         formats = [{
  75             'url': tokens[format]['token'],
  76             'format_id': format + 'p',
  77             'resolution': format + 'p',
  78             'quality': int(format),
  79             } for format in sources]
  80
  81         self._sort_formats(formats)
  82
  83         return {
  84             'id': video_id,
  85             'title': title,
  86             'formats': formats,
  87             'thumbnail': thumbnail_url,
  88             'uploader': uploader,
  89             'uploader_id': uploader_id,
  90             'upload_date': upload_date,
  91             'view_count': view_count,
  92             'duration': duration,
  93             'age_limit': 18,
  94             'webpage_url': webpage_url,
  95         }