yt_dlp/extractor/izlesene.py

   1 import urllib.parse
   2
   3 from .common import InfoExtractor
   4 from ..utils import (
   5     determine_ext,
   6     float_or_none,
   7     get_element_by_id,
   8     int_or_none,
   9     parse_iso8601,
  10     str_to_int,
  11 )
  12
  13
  14 class IzleseneIE(InfoExtractor):
  15     _VALID_URL = r'''(?x)
  16         https?://(?:(?:www|m)\.)?izlesene\.com/
  17         (?:video|embedplayer)/(?:[^/]+/)?(?P<id>[0-9]+)
  18         '''
  19     _TESTS = [
  20         {
  21             'url': 'http://www.izlesene.com/video/sevincten-cildirtan-dogum-gunu-hediyesi/7599694',
  22             'md5': '4384f9f0ea65086734b881085ee05ac2',
  23             'info_dict': {
  24                 'id': '7599694',
  25                 'ext': 'mp4',
  26                 'title': 'Sevinçten Çıldırtan Doğum Günü Hediyesi',
  27                 'description': 'md5:253753e2655dde93f59f74b572454f6d',
  28                 'thumbnail': r're:^https?://.*\.jpg',
  29                 'uploader_id': 'pelikzzle',
  30                 'timestamp': int,
  31                 'upload_date': '20140702',
  32                 'duration': 95.395,
  33                 'age_limit': 0,
  34             },
  35         },
  36         {
  37             'url': 'http://www.izlesene.com/video/tarkan-dortmund-2006-konseri/17997',
  38             'md5': '97f09b6872bffa284cb7fa4f6910cb72',
  39             'info_dict': {
  40                 'id': '17997',
  41                 'ext': 'mp4',
  42                 'title': 'Tarkan Dortmund 2006 Konseri',
  43                 'thumbnail': r're:^https://.*\.jpg',
  44                 'uploader_id': 'parlayankiz',
  45                 'timestamp': int,
  46                 'upload_date': '20061112',
  47                 'duration': 253.666,
  48                 'age_limit': 0,
  49             },
  50         },
  51     ]
  52
  53     def _real_extract(self, url):
  54         video_id = self._match_id(url)
  55
  56         webpage = self._download_webpage(f'http://www.izlesene.com/video/{video_id}', video_id)
  57
  58         video = self._parse_json(
  59             self._search_regex(
  60                 r'videoObj\s*=\s*({.+?})\s*;\s*\n', webpage, 'streams'),
  61             video_id)
  62
  63         title = video.get('videoTitle') or self._og_search_title(webpage)
  64
  65         formats = []
  66         for stream in video['media']['level']:
  67             source_url = stream.get('source')
  68             if not source_url or not isinstance(source_url, str):
  69                 continue
  70             ext = determine_ext(url, 'mp4')
  71             quality = stream.get('value')
  72             height = int_or_none(quality)
  73             formats.append({
  74                 'format_id': f'{quality}p' if quality else 'sd',
  75                 'url': urllib.parse.unquote(source_url),
  76                 'ext': ext,
  77                 'height': height,
  78             })
  79
  80         description = self._og_search_description(webpage, default=None)
  81         thumbnail = video.get('posterURL') or self._proto_relative_url(
  82             self._og_search_thumbnail(webpage), scheme='http:')
  83
  84         uploader = self._html_search_regex(
  85             r"adduserUsername\s*=\s*'([^']+)';",
  86             webpage, 'uploader', fatal=False)
  87         timestamp = parse_iso8601(self._html_search_meta(
  88             'uploadDate', webpage, 'upload date'))
  89
  90         duration = float_or_none(video.get('duration') or self._html_search_regex(
  91             r'videoduration["\']?\s*=\s*(["\'])(?P<value>(?:(?!\1).)+)\1',
  92             webpage, 'duration', fatal=False, group='value'), scale=1000)
  93
  94         view_count = str_to_int(get_element_by_id('videoViewCount', webpage))
  95         comment_count = self._html_search_regex(
  96             r'comment_count\s*=\s*\'([^\']+)\';',
  97             webpage, 'comment_count', fatal=False)
  98
  99         return {
 100             'id': video_id,
 101             'title': title,
 102             'description': description,
 103             'thumbnail': thumbnail,
 104             'uploader_id': uploader,
 105             'timestamp': timestamp,
 106             'duration': duration,
 107             'view_count': int_or_none(view_count),
 108             'comment_count': int_or_none(comment_count),
 109             'age_limit': self._family_friendly_search(webpage),
 110             'formats': formats,
 111         }