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'https?://(?:(?:www|m)\.)?izlesene\.com/(?:video|embedplayer)/(?:[^/]+/)?(?P<id>[0-9]+)'
  18     _STREAM_URL = 'http://panel.izlesene.com/api/streamurl/{id:}/{format:}'
  19     _TEST = {
  20         'url': 'http://www.izlesene.com/video/sevincten-cildirtan-dogum-gunu-hediyesi/7599694',
  21         'md5': '4384f9f0ea65086734b881085ee05ac2',
  22         'info_dict': {
  23             'id': '7599694',
  24             'ext': 'mp4',
  25             'title': 'Sevinçten Çıldırtan Doğum Günü Hediyesi',
  26             'description': 'Annesi oğluna doğum günü hediyesi olarak minecraft cd si alıyor, ve çocuk hunharca seviniyor',
  27             'thumbnail': 're:^http://.*\.jpg',
  28             'uploader_id': 'pelikzzle',
  29             'timestamp': 1404298698,
  30             'upload_date': '20140702',
  31             'duration': 95.395,
  32             'age_limit': 0,
  33         }
  34     }
  35
  36     def _real_extract(self, url):
  37         mobj = re.match(self._VALID_URL, url)
  38         video_id = mobj.group('id')
  39         url = 'http://www.izlesene.com/video/%s' % video_id
  40
  41         webpage = self._download_webpage(url, video_id)
  42
  43         title = self._og_search_title(webpage)
  44         description = self._og_search_description(webpage)
  45         thumbnail = self._og_search_thumbnail(webpage)
  46
  47         uploader = self._html_search_regex(
  48             r"adduserUsername\s*=\s*'([^']+)';", webpage, 'uploader', fatal=False, default='')
  49         timestamp = parse_iso8601(self._html_search_meta(
  50             'uploadDate', webpage, 'upload date', fatal=False))
  51
  52         duration = int_or_none(self._html_search_regex(
  53             r'"videoduration"\s*:\s*"([^"]+)"', webpage, 'duration', fatal=False))
  54         if duration:
  55             duration /= 1000.0
  56
  57         view_count = str_to_int(get_element_by_id('videoViewCount', webpage))
  58         comment_count = self._html_search_regex(
  59             r'comment_count\s*=\s*\'([^\']+)\';', webpage, 'uploader', fatal=False)
  60
  61         family_friendly = self._html_search_meta(
  62             'isFamilyFriendly', webpage, 'age limit', fatal=False)
  63
  64         content_url = self._html_search_meta(
  65             'contentURL', webpage, 'content URL', fatal=False)
  66         ext = determine_ext(content_url, 'mp4')
  67
  68         # Might be empty for some videos.
  69         qualities = self._html_search_regex(
  70             r'"quality"\s*:\s*"([^"]+)"', webpage, 'qualities', fatal=False, default='')
  71
  72         formats = []
  73         for quality in qualities.split('|'):
  74             json = self._download_json(
  75                 self._STREAM_URL.format(id=video_id, format=quality), video_id,
  76                 note='Getting video URL for "%s" quality' % quality,
  77                 errnote='Failed to get video URL for "%s" quality' % quality
  78             )
  79             formats.append({
  80                 'url': json.get('streamurl'),
  81                 'ext': ext,
  82                 'format_id': '%sp' % quality if quality else 'sd',
  83             })
  84
  85         return {
  86             'id': video_id,
  87             'title': title,
  88             'description': description,
  89             'thumbnail': thumbnail,
  90             'uploader_id': uploader,
  91             'timestamp': timestamp,
  92             'duration': duration,
  93             'view_count': int_or_none(view_count),
  94             'comment_count': int_or_none(comment_count),
  95             'age_limit': 18 if family_friendly == 'False' else 0,
  96             'formats': formats,
  97         }