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 )
  10
  11
  12 class RadioJavanIE(InfoExtractor):
  13     _VALID_URL = r'https?://(?:www\.)?radiojavan\.com/videos/video/(?P<id>[^/]+)/?'
  14     _TEST = {
  15         'url': 'http://www.radiojavan.com/videos/video/chaartaar-ashoobam',
  16         'md5': 'e85208ffa3ca8b83534fca9fe19af95b',
  17         'info_dict': {
  18             'id': 'chaartaar-ashoobam',
  19             'ext': 'mp4',
  20             'title': 'Chaartaar - Ashoobam',
  21             'thumbnail': r're:^https?://.*\.jpe?g$',
  22             'upload_date': '20150215',
  23             'view_count': int,
  24             'like_count': int,
  25             'dislike_count': int,
  26         }
  27     }
  28
  29     def _real_extract(self, url):
  30         video_id = self._match_id(url)
  31
  32         webpage = self._download_webpage(url, video_id)
  33
  34         formats = [{
  35             'url': 'https://media.rdjavan.com/media/music_video/%s' % video_path,
  36             'format_id': '%sp' % height,
  37             'height': int(height),
  38         } for height, video_path in re.findall(r"RJ\.video(\d+)p\s*=\s*'/?([^']+)'", webpage)]
  39         self._sort_formats(formats)
  40
  41         title = self._og_search_title(webpage)
  42         thumbnail = self._og_search_thumbnail(webpage)
  43
  44         upload_date = unified_strdate(self._search_regex(
  45             r'class="date_added">Date added: ([^<]+)<',
  46             webpage, 'upload date', fatal=False))
  47
  48         view_count = str_to_int(self._search_regex(
  49             r'class="views">Plays: ([\d,]+)',
  50             webpage, 'view count', fatal=False))
  51         like_count = str_to_int(self._search_regex(
  52             r'class="rating">([\d,]+) likes',
  53             webpage, 'like count', fatal=False))
  54         dislike_count = str_to_int(self._search_regex(
  55             r'class="rating">([\d,]+) dislikes',
  56             webpage, 'dislike count', fatal=False))
  57
  58         return {
  59             'id': video_id,
  60             'title': title,
  61             'thumbnail': thumbnail,
  62             'upload_date': upload_date,
  63             'view_count': view_count,
  64             'like_count': like_count,
  65             'dislike_count': dislike_count,
  66             'formats': formats,
  67         }