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 ..compat import compat_urllib_parse_unquote
   8 from ..utils import (
   9     determine_ext,
  10     float_or_none,
  11     get_element_by_id,
  12     int_or_none,
  13     parse_iso8601,
  14     str_to_int,
  15 )
  16
  17
  18 class IzleseneIE(InfoExtractor):
  19     _VALID_URL = r'''(?x)
  20         https?://(?:(?:www|m)\.)?izlesene\.com/
  21         (?:video|embedplayer)/(?:[^/]+/)?(?P<id>[0-9]+)
  22         '''
  23     _TESTS = [
  24         {
  25             'url': 'http://www.izlesene.com/video/sevincten-cildirtan-dogum-gunu-hediyesi/7599694',
  26             'md5': '4384f9f0ea65086734b881085ee05ac2',
  27             'info_dict': {
  28                 'id': '7599694',
  29                 'ext': 'mp4',
  30                 'title': 'Sevinçten Çıldırtan Doğum Günü Hediyesi',
  31                 'description': 'md5:253753e2655dde93f59f74b572454f6d',
  32                 'thumbnail': 're:^https?://.*\.jpg',
  33                 'uploader_id': 'pelikzzle',
  34                 'timestamp': int,
  35                 'upload_date': '20140702',
  36                 'duration': 95.395,
  37                 'age_limit': 0,
  38             }
  39         },
  40         {
  41             'url': 'http://www.izlesene.com/video/tarkan-dortmund-2006-konseri/17997',
  42             'md5': '97f09b6872bffa284cb7fa4f6910cb72',
  43             'info_dict': {
  44                 'id': '17997',
  45                 'ext': 'mp4',
  46                 'title': 'Tarkan Dortmund 2006 Konseri',
  47                 'thumbnail': 're:^https://.*\.jpg',
  48                 'uploader_id': 'parlayankiz',
  49                 'timestamp': int,
  50                 'upload_date': '20061112',
  51                 'duration': 253.666,
  52                 'age_limit': 0,
  53             }
  54         },
  55     ]
  56
  57     def _real_extract(self, url):
  58         video_id = self._match_id(url)
  59
  60         url = 'http://www.izlesene.com/video/%s' % video_id
  61         webpage = self._download_webpage(url, video_id)
  62
  63         title = self._og_search_title(webpage)
  64         description = self._og_search_description(webpage, default=None)
  65         thumbnail = self._proto_relative_url(
  66             self._og_search_thumbnail(webpage), scheme='http:')
  67
  68         uploader = self._html_search_regex(
  69             r"adduserUsername\s*=\s*'([^']+)';",
  70             webpage, 'uploader', fatal=False)
  71         timestamp = parse_iso8601(self._html_search_meta(
  72             'uploadDate', webpage, 'upload date'))
  73
  74         duration = float_or_none(self._html_search_regex(
  75             r'"videoduration"\s*:\s*"([^"]+)"',
  76             webpage, 'duration', fatal=False), scale=1000)
  77
  78         view_count = str_to_int(get_element_by_id('videoViewCount', webpage))
  79         comment_count = self._html_search_regex(
  80             r'comment_count\s*=\s*\'([^\']+)\';',
  81             webpage, 'comment_count', fatal=False)
  82
  83         content_url = self._html_search_meta(
  84             'contentURL', webpage, 'content URL', fatal=False)
  85         ext = determine_ext(content_url, 'mp4')
  86
  87         # Might be empty for some videos.
  88         streams = self._html_search_regex(
  89             r'"qualitylevel"\s*:\s*"([^"]+)"', webpage, 'streams', default='')
  90
  91         formats = []
  92         if streams:
  93             for stream in streams.split('|'):
  94                 quality, url = re.search(r'\[(\w+)\](.+)', stream).groups()
  95                 formats.append({
  96                     'format_id': '%sp' % quality if quality else 'sd',
  97                     'url': compat_urllib_parse_unquote(url),
  98                     'ext': ext,
  99                 })
 100         else:
 101             stream_url = self._search_regex(
 102                 r'"streamurl"\s*:\s*"([^"]+)"', webpage, 'stream URL')
 103             formats.append({
 104                 'format_id': 'sd',
 105                 'url': compat_urllib_parse_unquote(stream_url),
 106                 'ext': ext,
 107             })
 108
 109         return {
 110             'id': video_id,
 111             'title': title,
 112             'description': description,
 113             'thumbnail': thumbnail,
 114             'uploader_id': uploader,
 115             'timestamp': timestamp,
 116             'duration': duration,
 117             'view_count': int_or_none(view_count),
 118             'comment_count': int_or_none(comment_count),
 119             'age_limit': self._family_friendly_search(webpage),
 120             'formats': formats,
 121         }