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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..compat import compat_urllib_parse_unquote
   6 from ..utils import (
   7     determine_ext,
   8     float_or_none,
   9     get_element_by_id,
  10     int_or_none,
  11     parse_iso8601,
  12     str_to_int,
  13 )
  14
  15
  16 class IzleseneIE(InfoExtractor):
  17     _VALID_URL = r'''(?x)
  18         https?://(?:(?:www|m)\.)?izlesene\.com/
  19         (?:video|embedplayer)/(?:[^/]+/)?(?P<id>[0-9]+)
  20         '''
  21     _TESTS = [
  22         {
  23             'url': 'http://www.izlesene.com/video/sevincten-cildirtan-dogum-gunu-hediyesi/7599694',
  24             'md5': '4384f9f0ea65086734b881085ee05ac2',
  25             'info_dict': {
  26                 'id': '7599694',
  27                 'ext': 'mp4',
  28                 'title': 'Sevinçten Çıldırtan Doğum Günü Hediyesi',
  29                 'description': 'md5:253753e2655dde93f59f74b572454f6d',
  30                 'thumbnail': r're:^https?://.*\.jpg',
  31                 'uploader_id': 'pelikzzle',
  32                 'timestamp': int,
  33                 'upload_date': '20140702',
  34                 'duration': 95.395,
  35                 'age_limit': 0,
  36             }
  37         },
  38         {
  39             'url': 'http://www.izlesene.com/video/tarkan-dortmund-2006-konseri/17997',
  40             'md5': '97f09b6872bffa284cb7fa4f6910cb72',
  41             'info_dict': {
  42                 'id': '17997',
  43                 'ext': 'mp4',
  44                 'title': 'Tarkan Dortmund 2006 Konseri',
  45                 'thumbnail': r're:^https://.*\.jpg',
  46                 'uploader_id': 'parlayankiz',
  47                 'timestamp': int,
  48                 'upload_date': '20061112',
  49                 'duration': 253.666,
  50                 'age_limit': 0,
  51             }
  52         },
  53     ]
  54
  55     def _real_extract(self, url):
  56         video_id = self._match_id(url)
  57
  58         url = 'http://www.izlesene.com/video/%s' % video_id
  59         webpage = self._download_webpage(url, video_id)
  60
  61         title = self._og_search_title(webpage)
  62         description = self._og_search_description(webpage, default=None)
  63         thumbnail = self._proto_relative_url(
  64             self._og_search_thumbnail(webpage), scheme='http:')
  65
  66         uploader = self._html_search_regex(
  67             r"adduserUsername\s*=\s*'([^']+)';",
  68             webpage, 'uploader', fatal=False)
  69         timestamp = parse_iso8601(self._html_search_meta(
  70             'uploadDate', webpage, 'upload date'))
  71
  72         duration = float_or_none(self._html_search_regex(
  73             r'videoduration\s*=\s*\'([^\']+)\'',
  74             webpage, 'duration', fatal=False), scale=1000)
  75
  76         view_count = str_to_int(get_element_by_id('videoViewCount', webpage))
  77         comment_count = self._html_search_regex(
  78             r'comment_count\s*=\s*\'([^\']+)\';',
  79             webpage, 'comment_count', fatal=False)
  80
  81         streams_json = self._html_search_regex(
  82             r'_videoObj\s*=\s*(.+);', webpage, 'streams')
  83         streams = self._parse_json(streams_json, video_id)
  84
  85         formats = []
  86         for stream in streams.get('media').get('level'):
  87             url = stream.get('source')
  88             ext = determine_ext(url, 'mp4')
  89             quality = stream.get('value')
  90             formats.append({
  91                 'format_id': '%sp' % quality,
  92                 'url': compat_urllib_parse_unquote(url),
  93                 'ext': ext,
  94             })
  95
  96         return {
  97             'id': video_id,
  98             'title': title,
  99             'description': description,
 100             'thumbnail': thumbnail,
 101             'uploader_id': uploader,
 102             'timestamp': timestamp,
 103             'duration': duration,
 104             'view_count': int_or_none(view_count),
 105             'comment_count': int_or_none(comment_count),
 106             'age_limit': self._family_friendly_search(webpage),
 107             'formats': formats,
 108         }