Raphaël G. Git Repositories - youtubedl/blob - 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\.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': 'http://videa.hu/static/still/1.4.1.1007274.1204470.3',
  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
  48     @staticmethod
  49     def _extract_urls(webpage):
  50         return [url for _, url in re.findall(
  51             r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//videa\.hu/player\?.*?\bv=.+?)\1',
  52             webpage)]
  53
  54     def _real_extract(self, url):
  55         video_id = self._match_id(url)
  56
  57         info = self._download_xml(
  58             'http://videa.hu/videaplayer_get_xml.php', video_id,
  59             query={'v': video_id})
  60
  61         video = xpath_element(info, './/video', 'video', fatal=True)
  62         sources = xpath_element(info, './/video_sources', 'sources', fatal=True)
  63
  64         title = xpath_text(video, './title', fatal=True)
  65
  66         formats = []
  67         for source in sources.findall('./video_source'):
  68             source_url = source.text
  69             if not source_url:
  70                 continue
  71             f = parse_codecs(source.get('codecs'))
  72             f.update({
  73                 'url': source_url,
  74                 'ext': mimetype2ext(source.get('mimetype')) or 'mp4',
  75                 'format_id': source.get('name'),
  76                 'width': int_or_none(source.get('width')),
  77                 'height': int_or_none(source.get('height')),
  78             })
  79             formats.append(f)
  80         self._sort_formats(formats)
  81
  82         thumbnail = xpath_text(video, './poster_src')
  83         duration = int_or_none(xpath_text(video, './duration'))
  84
  85         age_limit = None
  86         is_adult = xpath_text(video, './is_adult_content', default=None)
  87         if is_adult:
  88             age_limit = 18 if is_adult == '1' else 0
  89
  90         return {
  91             'id': video_id,
  92             'title': title,
  93             'thumbnail': thumbnail,
  94             'duration': duration,
  95             'age_limit': age_limit,
  96             'formats': formats,
  97         }