Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/cloudy.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..utils import (
   6     str_to_int,
   7     unified_strdate,
   8 )
   9
  10
  11 class CloudyIE(InfoExtractor):
  12     _IE_DESC = 'cloudy.ec'
  13     _VALID_URL = r'https?://(?:www\.)?cloudy\.ec/(?:v/|embed\.php\?.*?\bid=)(?P<id>[A-Za-z0-9]+)'
  14     _TESTS = [{
  15         'url': 'https://www.cloudy.ec/v/af511e2527aac',
  16         'md5': '29832b05028ead1b58be86bf319397ca',
  17         'info_dict': {
  18             'id': 'af511e2527aac',
  19             'ext': 'mp4',
  20             'title': 'Funny Cats and Animals Compilation june 2013',
  21             'upload_date': '20130913',
  22             'view_count': int,
  23         }
  24     }, {
  25         'url': 'http://www.cloudy.ec/embed.php?autoplay=1&id=af511e2527aac',
  26         'only_matching': True,
  27     }]
  28
  29     def _real_extract(self, url):
  30         video_id = self._match_id(url)
  31
  32         webpage = self._download_webpage(
  33             'https://www.cloudy.ec/embed.php', video_id, query={
  34                 'id': video_id,
  35                 'playerPage': 1,
  36                 'autoplay': 1,
  37             })
  38
  39         info = self._parse_html5_media_entries(url, webpage, video_id)[0]
  40
  41         webpage = self._download_webpage(
  42             'https://www.cloudy.ec/v/%s' % video_id, video_id, fatal=False)
  43
  44         if webpage:
  45             info.update({
  46                 'title': self._search_regex(
  47                     r'<h\d[^>]*>([^<]+)<', webpage, 'title'),
  48                 'upload_date': unified_strdate(self._search_regex(
  49                     r'>Published at (\d{4}-\d{1,2}-\d{1,2})', webpage,
  50                     'upload date', fatal=False)),
  51                 'view_count': str_to_int(self._search_regex(
  52                     r'([\d,.]+) views<', webpage, 'view count', fatal=False)),
  53             })
  54
  55         if not info.get('title'):
  56             info['title'] = video_id
  57
  58         info['id'] = video_id
  59
  60         return info