_ Git - youtube-dl/blob - youtube_dl/extractor/radiojavan.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..utils import(
   6     parse_duration,
   7     str_to_int
   8 )
   9
  10 class RadioJavanIE(InfoExtractor):
  11     _VALID_URL = r'https?://(?:www\.)?radiojavan\.com/videos/video/(?P<id>[^/]+)/?'
  12     _TEST = {
  13         'url': 'http://www.radiojavan.com/videos/video/chaartaar-ashoobam',
  14         'md5': 'e85208ffa3ca8b83534fca9fe19af95b',
  15         'info_dict': {
  16             'id': 'chaartaar-ashoobam',
  17             'ext': 'mp4',
  18             'title': 'Chaartaar - Ashoobam',
  19             'description': 'Chaartaar - Ashoobam',
  20             'thumbnail': 're:^https?://.*\.jpe?g$',
  21         }
  22     }
  23
  24     def _real_extract(self, url):
  25         display_id = self._match_id(url)
  26         webpage = self._download_webpage(url, display_id)
  27         urls = list()
  28         prefix = 'https://media.rdjavan.com/media/music_video/'
  29
  30         video_url_480 = self._search_regex(
  31             r'RJ\.video480p = \'([^\']+)\'', webpage, '480 video url', fatal= False)
  32         video_url_720 = self._search_regex(
  33             r'RJ\.video720p = \'([^\']+)\'', webpage, '720 video url', fatal= False)
  34         video_url_1080 = self._search_regex(
  35             r'RJ\.video1080p = \'([^\']+)\'', webpage, '1080 video url', fatal= False)
  36
  37         if video_url_480:
  38             urls.append({'url': prefix + video_url_480, 'format': '480p'})
  39         if video_url_720:
  40             urls.append({'url': prefix + video_url_720, 'format': '720p'})
  41         if video_url_1080:
  42             urls.append({'url': prefix + video_url_1080, 'format': '1080p'})
  43
  44         title = self._og_search_title(webpage)
  45         thumbnail = self._og_search_thumbnail(webpage)
  46         formats = [{
  47             'url': url['url'],
  48             'format': url['format']
  49         } for url in urls]
  50
  51         likes = self._search_regex(
  52             r'<span class="rating">([\d,]+)\s*likes</span>', webpage, 'Likes Count', fatal=False )
  53         likes = likes.replace(',', '')
  54         dislikes = self._search_regex(
  55             r'<span class="rating">([\d,]+)\s*dislikes</span>', webpage, 'Dislikes Count', fatal=False )
  56         dislikes = dislikes.replace(',', '')
  57
  58         plays = self._search_regex(
  59             r'views_publish[">\s]*<span[^>]+class="views">Plays: ([\d,]+)</span>', webpage, 'Play Count', fatal=False )
  60         plays = plays.replace(',', '')
  61
  62         return {
  63             'formats': formats,
  64             'id': display_id,
  65             'title': title,
  66             'description': title, # no description provided in RadioJavan
  67             'thumbnail': thumbnail,
  68             'like_count': str_to_int(likes),
  69             'dislike_count': str_to_int(dislikes),
  70             'viewCount': str_to_int(plays)
  71         }