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 (
   8     get_element_by_id,
   9     parse_iso8601,
  10     determine_ext,
  11     int_or_none,
  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': 're:^http://.*\.jpg',
  31                 'uploader_id': 'pelikzzle',
  32                 'timestamp': 1404298698,
  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                 'description': 'Tarkan Dortmund 2006 Konseri',
  46                 'thumbnail': 're:^http://.*\.jpg',
  47                 'uploader_id': 'parlayankiz',
  48                 'timestamp': 1163318593,
  49                 'upload_date': '20061112',
  50                 'duration': 253.666,
  51                 'age_limit': 0,
  52             }
  53         },
  54     ]
  55
  56     def _real_extract(self, url):
  57         mobj = re.match(self._VALID_URL, url)
  58         video_id = mobj.group('id')
  59         url = 'http://www.izlesene.com/video/%s' % video_id
  60
  61         webpage = self._download_webpage(url, video_id)
  62
  63         title = self._og_search_title(webpage)
  64         description = self._og_search_description(webpage)
  65         thumbnail = self._og_search_thumbnail(webpage)
  66
  67         uploader = self._html_search_regex(
  68             r"adduserUsername\s*=\s*'([^']+)';",
  69             webpage, 'uploader', fatal=False, default='')
  70         timestamp = parse_iso8601(self._html_search_meta(
  71             'uploadDate', webpage, 'upload date', fatal=False))
  72
  73         duration = int_or_none(self._html_search_regex(
  74             r'"videoduration"\s*:\s*"([^"]+)"',
  75             webpage, 'duration', fatal=False))
  76         if duration:
  77             duration /= 1000.0
  78
  79         view_count = str_to_int(get_element_by_id('videoViewCount', webpage))
  80         comment_count = self._html_search_regex(
  81             r'comment_count\s*=\s*\'([^\']+)\';',
  82             webpage, 'comment_count', fatal=False)
  83
  84         family_friendly = self._html_search_meta(
  85             'isFamilyFriendly', webpage, 'age limit', fatal=False)
  86
  87         content_url = self._html_search_meta(
  88             'contentURL', webpage, 'content URL', fatal=False)
  89         ext = determine_ext(content_url, 'mp4')
  90
  91         # Might be empty for some videos.
  92         streams = self._html_search_regex(
  93             r'"qualitylevel"\s*:\s*"([^"]+)"',
  94             webpage, 'streams', fatal=False, default='')
  95
  96         formats = []
  97         if streams:
  98             for stream in streams.split('|'):
  99                 quality, url = re.search(r'\[(\w+)\](.+)', stream).groups()
 100                 formats.append({
 101                     'format_id': '%sp' % quality if quality else 'sd',
 102                     'url': url,
 103                     'ext': ext,
 104                 })
 105         else:
 106             stream_url = self._search_regex(
 107                 r'"streamurl"\s?:\s?"([^"]+)"', webpage, 'stream URL')
 108             formats.append({
 109                 'format_id': 'sd',
 110                 'url': stream_url,
 111                 'ext': ext,
 112             })
 113
 114         return {
 115             'id': video_id,
 116             'title': title,
 117             'description': description,
 118             'thumbnail': thumbnail,
 119             'uploader_id': uploader,
 120             'timestamp': timestamp,
 121             'duration': duration,
 122             'view_count': int_or_none(view_count),
 123             'comment_count': int_or_none(comment_count),
 124             'age_limit': 18 if family_friendly == 'False' else 0,
 125             'formats': formats,
 126         }