youtube_dl/extractor/videa.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     int_or_none,
   9     mimetype2ext,
  10     parse_codecs,
  11     xpath_element,
  12     xpath_text,
  13 )
  14
  15
  16 class VideaIE(InfoExtractor):
  17     _VALID_URL = r'''(?x)
  18                     https?://
  19                         videa(?:kid)?\.hu/
  20                         (?:
  21                             videok/(?:[^/]+/)*[^?#&]+-|
  22                             player\?.*?\bv=|
  23                             player/v/
  24                         )
  25                         (?P<id>[^?#&]+)
  26                     '''
  27     _TESTS = [{
  28         'url': 'http://videa.hu/videok/allatok/az-orult-kigyasz-285-kigyot-kigyo-8YfIAjxwWGwT8HVQ',
  29         'md5': '97a7af41faeaffd9f1fc864a7c7e7603',
  30         'info_dict': {
  31             'id': '8YfIAjxwWGwT8HVQ',
  32             'ext': 'mp4',
  33             'title': 'Az őrült kígyász 285 kígyót enged szabadon',
  34             'thumbnail': r're:^https?://.*',
  35             'duration': 21,
  36         },
  37     }, {
  38         'url': 'http://videa.hu/videok/origo/jarmuvek/supercars-elozes-jAHDWfWSJH5XuFhH',
  39         'only_matching': True,
  40     }, {
  41         'url': 'http://videa.hu/player?v=8YfIAjxwWGwT8HVQ',
  42         'only_matching': True,
  43     }, {
  44         'url': 'http://videa.hu/player/v/8YfIAjxwWGwT8HVQ?autoplay=1',
  45         'only_matching': True,
  46     }, {
  47         'url': 'https://videakid.hu/videok/origo/jarmuvek/supercars-elozes-jAHDWfWSJH5XuFhH',
  48         'only_matching': True,
  49     }, {
  50         'url': 'https://videakid.hu/player?v=8YfIAjxwWGwT8HVQ',
  51         'only_matching': True,
  52     }, {
  53         'url': 'https://videakid.hu/player/v/8YfIAjxwWGwT8HVQ?autoplay=1',
  54         'only_matching': True,
  55     }]
  56
  57     @staticmethod
  58     def _extract_urls(webpage):
  59         return [url for _, url in re.findall(
  60             r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//videa\.hu/player\?.*?\bv=.+?)\1',
  61             webpage)]
  62
  63     def _real_extract(self, url):
  64         video_id = self._match_id(url)
  65
  66         info = self._download_xml(
  67             'http://videa.hu/videaplayer_get_xml.php', video_id,
  68             query={'v': video_id})
  69
  70         video = xpath_element(info, './/video', 'video', fatal=True)
  71         sources = xpath_element(info, './/video_sources', 'sources', fatal=True)
  72
  73         title = xpath_text(video, './title', fatal=True)
  74
  75         formats = []
  76         for source in sources.findall('./video_source'):
  77             source_url = source.text
  78             if not source_url:
  79                 continue
  80             f = parse_codecs(source.get('codecs'))
  81             f.update({
  82                 'url': source_url,
  83                 'ext': mimetype2ext(source.get('mimetype')) or 'mp4',
  84                 'format_id': source.get('name'),
  85                 'width': int_or_none(source.get('width')),
  86                 'height': int_or_none(source.get('height')),
  87             })
  88             formats.append(f)
  89         self._sort_formats(formats)
  90
  91         thumbnail = xpath_text(video, './poster_src')
  92         duration = int_or_none(xpath_text(video, './duration'))
  93
  94         age_limit = None
  95         is_adult = xpath_text(video, './is_adult_content', default=None)
  96         if is_adult:
  97             age_limit = 18 if is_adult == '1' else 0
  98
  99         return {
 100             'id': video_id,
 101             'title': title,
 102             'thumbnail': thumbnail,
 103             'duration': duration,
 104             'age_limit': age_limit,
 105             'formats': formats,
 106         }