yt_dlp/extractor/radiojavan.py

   1 import re
   2
   3 from .common import InfoExtractor
   4 from ..utils import (
   5     parse_resolution,
   6     str_to_int,
   7     unified_strdate,
   8     urlencode_postdata,
   9     urljoin,
  10 )
  11
  12
  13 class RadioJavanIE(InfoExtractor):
  14     _WORKING = False
  15     _VALID_URL = r'https?://(?:www\.)?radiojavan\.com/videos/video/(?P<id>[^/]+)/?'
  16     _TEST = {
  17         'url': 'http://www.radiojavan.com/videos/video/chaartaar-ashoobam',
  18         'md5': 'e85208ffa3ca8b83534fca9fe19af95b',
  19         'info_dict': {
  20             'id': 'chaartaar-ashoobam',
  21             'ext': 'mp4',
  22             'title': 'Chaartaar - Ashoobam',
  23             'thumbnail': r're:^https?://.*\.jpe?g$',
  24             'upload_date': '20150215',
  25             'view_count': int,
  26             'like_count': int,
  27             'dislike_count': int,
  28         }
  29     }
  30
  31     def _real_extract(self, url):
  32         video_id = self._match_id(url)
  33
  34         download_host = self._download_json(
  35             'https://www.radiojavan.com/videos/video_host', video_id,
  36             data=urlencode_postdata({'id': video_id}),
  37             headers={
  38                 'Content-Type': 'application/x-www-form-urlencoded',
  39                 'Referer': url,
  40             }).get('host', 'https://host1.rjmusicmedia.com')
  41
  42         webpage = self._download_webpage(url, video_id)
  43
  44         formats = []
  45         for format_id, _, video_path in re.findall(
  46                 r'RJ\.video(?P<format_id>\d+[pPkK])\s*=\s*(["\'])(?P<url>(?:(?!\2).)+)\2',
  47                 webpage):
  48             f = parse_resolution(format_id)
  49             f.update({
  50                 'url': urljoin(download_host, video_path),
  51                 'format_id': format_id,
  52             })
  53             formats.append(f)
  54
  55         title = self._og_search_title(webpage)
  56         thumbnail = self._og_search_thumbnail(webpage)
  57
  58         upload_date = unified_strdate(self._search_regex(
  59             r'class="date_added">Date added: ([^<]+)<',
  60             webpage, 'upload date', fatal=False))
  61
  62         view_count = str_to_int(self._search_regex(
  63             r'class="views">Plays: ([\d,]+)',
  64             webpage, 'view count', fatal=False))
  65         like_count = str_to_int(self._search_regex(
  66             r'class="rating">([\d,]+) likes',
  67             webpage, 'like count', fatal=False))
  68         dislike_count = str_to_int(self._search_regex(
  69             r'class="rating">([\d,]+) dislikes',
  70             webpage, 'dislike count', fatal=False))
  71
  72         return {
  73             'id': video_id,
  74             'title': title,
  75             'thumbnail': thumbnail,
  76             'upload_date': upload_date,
  77             'view_count': view_count,
  78             'like_count': like_count,
  79             'dislike_count': dislike_count,
  80             'formats': formats,
  81         }