_ Git - youtube-dl/blob - 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     unified_strdate,
   8     str_to_int,
   9     urlencode_postdata,
  10 )
  11
  12
  13 class RadioJavanIE(InfoExtractor):
  14     _VALID_URL = r'https?://(?:www\.)?radiojavan\.com/videos/video/(?P<id>[^/]+)/?'
  15     _HOST_TRACKER_URL = 'https://www.radiojavan.com/videos/video_host'
  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         webpage = self._download_webpage(url, video_id)
  35
  36         download_host = self._download_json(
  37             self._HOST_TRACKER_URL,
  38             video_id,
  39             data=urlencode_postdata({'id': video_id}),
  40             headers={
  41                 'Content-Type': 'application/x-www-form-urlencoded',
  42                 'Referer': url,
  43             }
  44         )['host']
  45
  46         formats = [{
  47             'url': '%s/%s' % (download_host, video_path),
  48             'format_id': '%sp' % height,
  49             'height': int(height),
  50         } for height, video_path in re.findall(r"RJ\.video(\d+)p\s*=\s*'/?([^']+)'", webpage)]
  51         self._sort_formats(formats)
  52
  53         title = self._og_search_title(webpage)
  54         thumbnail = self._og_search_thumbnail(webpage)
  55
  56         upload_date = unified_strdate(self._search_regex(
  57             r'class="date_added">Date added: ([^<]+)<',
  58             webpage, 'upload date', fatal=False))
  59
  60         view_count = str_to_int(self._search_regex(
  61             r'class="views">Plays: ([\d,]+)',
  62             webpage, 'view count', fatal=False))
  63         like_count = str_to_int(self._search_regex(
  64             r'class="rating">([\d,]+) likes',
  65             webpage, 'like count', fatal=False))
  66         dislike_count = str_to_int(self._search_regex(
  67             r'class="rating">([\d,]+) dislikes',
  68             webpage, 'dislike count', fatal=False))
  69
  70         return {
  71             'id': video_id,
  72             'title': title,
  73             'thumbnail': thumbnail,
  74             'upload_date': upload_date,
  75             'view_count': view_count,
  76             'like_count': like_count,
  77             'dislike_count': dislike_count,
  78             'formats': formats,
  79         }