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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..utils import get_element_by_id, parse_iso8601, determine_ext, int_or_none
   8
   9
  10 class IzleseneIE(InfoExtractor):
  11     _VALID_URL = r'https?://(?:www\.|m\.)?izlesene\.com/(?:video|embedplayer)/(?:[^/]+/)?(?P<id>[0-9]+)'
  12     _STREAM_URL = 'http://panel.izlesene.com/api/streamurl/{id:}/{format:}'
  13     _TEST = {
  14         'url': 'http://www.izlesene.com/video/sevincten-cildirtan-dogum-gunu-hediyesi/7599694',
  15         'md5': '4384f9f0ea65086734b881085ee05ac2',
  16         'info_dict': {
  17             'id': '7599694',
  18             'title': u'Sevinçten Çıldırtan Doğum Günü Hediyesi',
  19             'upload_date': '20140702',
  20             'uploader_id': 'pelikzzle',
  21             'description': u'Annesi oğluna doğum günü hediyesi olarak minecraft cd si alıyor, ve çocuk hunharca seviniyor',
  22             'timestamp': 1404298698,
  23             'duration': 95,
  24             'ext': 'mp4',
  25             'thumbnail': 're:^http://.*\.jpg',
  26             'age_limit': 0,
  27         }
  28     }
  29
  30     def _real_extract(self, url):
  31         mobj = re.match(self._VALID_URL, url)
  32         video_id = mobj.group('id')
  33         url = 'http://www.izlesene.com/video/%s' % video_id
  34
  35         webpage = self._download_webpage(url, video_id)
  36
  37         title = self._og_search_title(webpage)
  38         description = self._og_search_description(webpage)
  39         thumbnail = self._og_search_thumbnail(webpage)
  40         duration = int(
  41             self._html_search_regex(
  42                 r'"videoduration"\s?:\s?"([^"]+)"', webpage, 'duration',
  43                 fatal=False, default='0')
  44             ) / 1000
  45         view_count = get_element_by_id('videoViewCount',
  46                                        webpage).replace('.', '')
  47         timestamp = parse_iso8601(self._html_search_meta('uploadDate', webpage,
  48                                   'upload date', fatal=False))
  49         family_friendly = self._html_search_meta('isFamilyFriendly', webpage,
  50                                                  'age limit', fatal=False)
  51         uploader = self._html_search_regex(r"adduserUsername\s?=\s?'([^']+)';",
  52                                            webpage, 'uploader', fatal=False,
  53                                            default='')
  54         comment_count = self._html_search_regex(
  55             r'comment_count\s?=\s?\'([^\']+)\';',
  56             webpage, 'uploader', fatal=False)
  57
  58         content_url = self._html_search_meta('contentURL', webpage,
  59                                              'content URL', fatal=False)
  60         ext = determine_ext(content_url)
  61
  62         # Might be empty for some videos.
  63         qualities = self._html_search_regex(r'"quality"\s?:\s?"([^"]+)"',
  64                                             webpage, 'qualities', fatal=False,
  65                                             default='')
  66
  67         formats = []
  68         for quality in qualities.split('|'):
  69             json = self._download_json(
  70                 self._STREAM_URL.format(id=video_id, format=quality), video_id,
  71                 note=u'Getting video URL for "%s" quality' % quality,
  72                 errnote=u'Failed to get video URL for "%s" quality' % quality
  73             )
  74             video_format = '%sp' % quality if quality else 'sd'
  75             formats.append({
  76                 'url': json.get('streamurl'),
  77                 'ext': ext,
  78                 'format': video_format,
  79                 'format_id': video_format,
  80             })
  81
  82         return {
  83             'id': video_id,
  84             'title': title,
  85             'formats': formats,
  86             'description': description,
  87             'thumbnail': thumbnail,
  88             'duration': duration,
  89             'view_count': int_or_none(view_count),
  90             'timestamp': timestamp,
  91             'age_limit': 18 if family_friendly == 'False' else 0,
  92             'uploader_id': uploader,
  93             'comment_count': int_or_none(comment_count),
  94         }