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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..utils import (
   6     int_or_none,
   7     mimetype2ext,
   8     parse_codecs,
   9     xpath_element,
  10     xpath_text,
  11 )
  12
  13
  14 class VideaIE(InfoExtractor):
  15     _VALID_URL = r'''(?x)
  16                     https?://
  17                         videa\.hu/
  18                         (?:
  19                             videok/(?:[^/]+/)*[^?#&]+-|
  20                             player\?.*?\bv=|
  21                             player/v/
  22                         )
  23                         (?P<id>[^?#&]+)
  24                     '''
  25     _TESTS = [{
  26         'url': 'http://videa.hu/videok/allatok/az-orult-kigyasz-285-kigyot-kigyo-8YfIAjxwWGwT8HVQ',
  27         'md5': '97a7af41faeaffd9f1fc864a7c7e7603',
  28         'info_dict': {
  29             'id': '8YfIAjxwWGwT8HVQ',
  30             'ext': 'mp4',
  31             'title': 'Az őrült kígyász 285 kígyót enged szabadon',
  32             'thumbnail': 'http://videa.hu/static/still/1.4.1.1007274.1204470.3',
  33             'duration': 21,
  34         },
  35     }, {
  36         'url': 'http://videa.hu/videok/origo/jarmuvek/supercars-elozes-jAHDWfWSJH5XuFhH',
  37         'only_matching': True,
  38     }, {
  39         'url': 'http://videa.hu/player?v=8YfIAjxwWGwT8HVQ',
  40         'only_matching': True,
  41     }, {
  42         'url': 'http://videa.hu/player/v/8YfIAjxwWGwT8HVQ?autoplay=1',
  43         'only_matching': True,
  44     }]
  45
  46     def _real_extract(self, url):
  47         video_id = self._match_id(url)
  48
  49         info = self._download_xml(
  50             'http://videa.hu/videaplayer_get_xml.php', video_id,
  51             query={'v': video_id})
  52
  53         video = xpath_element(info, './/video', 'video', fatal=True)
  54         sources = xpath_element(info, './/video_sources', 'sources', fatal=True)
  55
  56         title = xpath_text(video, './title', fatal=True)
  57
  58         formats = []
  59         for source in sources.findall('./video_source'):
  60             source_url = source.text
  61             if not source_url:
  62                 continue
  63             f = parse_codecs(source.get('codecs'))
  64             f.update({
  65                 'url': source_url,
  66                 'ext': mimetype2ext(source.get('mimetype')) or 'mp4',
  67                 'format_id': source.get('name'),
  68                 'width': int_or_none(source.get('width')),
  69                 'height': int_or_none(source.get('height')),
  70             })
  71             formats.append(f)
  72         self._sort_formats(formats)
  73
  74         thumbnail = xpath_text(video, './poster_src')
  75         duration = int_or_none(xpath_text(video, './duration'))
  76
  77         age_limit = None
  78         is_adult = xpath_text(video, './is_adult_content', default=None)
  79         if is_adult:
  80             age_limit = 18 if is_adult == '1' else 0
  81
  82         return {
  83             'id': video_id,
  84             'title': title,
  85             'thumbnail': thumbnail,
  86             'duration': duration,
  87             'age_limit': age_limit,
  88             'formats': formats,
  89         }