youtube_dl/extractor/radiojavan.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..utils import (
   7     parse_resolution,
   8     str_to_int,
   9     unified_strdate,
  10     urlencode_postdata,
  11     urljoin,
  12 )
  13
  14
  15 class RadioJavanIE(InfoExtractor):
  16     _VALID_URL = r'https?://(?:www\.)?radiojavan\.com/videos/video/(?P<id>[^/]+)/?'
  17     _TEST = {
  18         'url': 'http://www.radiojavan.com/videos/video/chaartaar-ashoobam',
  19         'md5': 'e85208ffa3ca8b83534fca9fe19af95b',
  20         'info_dict': {
  21             'id': 'chaartaar-ashoobam',
  22             'ext': 'mp4',
  23             'title': 'Chaartaar - Ashoobam',
  24             'thumbnail': r're:^https?://.*\.jpe?g$',
  25             'upload_date': '20150215',
  26             'view_count': int,
  27             'like_count': int,
  28             'dislike_count': int,
  29         }
  30     }
  31
  32     def _real_extract(self, url):
  33         video_id = self._match_id(url)
  34
  35         download_host = self._download_json(
  36             'https://www.radiojavan.com/videos/video_host', video_id,
  37             data=urlencode_postdata({'id': video_id}),
  38             headers={
  39                 'Content-Type': 'application/x-www-form-urlencoded',
  40                 'Referer': url,
  41             }).get('host', 'https://host1.rjmusicmedia.com')
  42
  43         webpage = self._download_webpage(url, video_id)
  44
  45         formats = []
  46         for format_id, _, video_path in re.findall(
  47                 r'RJ\.video(?P<format_id>\d+[pPkK])\s*=\s*(["\'])(?P<url>(?:(?!\2).)+)\2',
  48                 webpage):
  49             f = parse_resolution(format_id)
  50             f.update({
  51                 'url': urljoin(download_host, video_path),
  52                 'format_id': format_id,
  53             })
  54             formats.append(f)
  55         self._sort_formats(formats)
  56
  57         title = self._og_search_title(webpage)
  58         thumbnail = self._og_search_thumbnail(webpage)
  59
  60         upload_date = unified_strdate(self._search_regex(
  61             r'class="date_added">Date added: ([^<]+)<',
  62             webpage, 'upload date', fatal=False))
  63
  64         view_count = str_to_int(self._search_regex(
  65             r'class="views">Plays: ([\d,]+)',
  66             webpage, 'view count', fatal=False))
  67         like_count = str_to_int(self._search_regex(
  68             r'class="rating">([\d,]+) likes',
  69             webpage, 'like count', fatal=False))
  70         dislike_count = str_to_int(self._search_regex(
  71             r'class="rating">([\d,]+) dislikes',
  72             webpage, 'dislike count', fatal=False))
  73
  74         return {
  75             'id': video_id,
  76             'title': title,
  77             'thumbnail': thumbnail,
  78             'upload_date': upload_date,
  79             'view_count': view_count,
  80             'like_count': like_count,
  81             'dislike_count': dislike_count,
  82             'formats': formats,
  83         }