yt_dlp/extractor/apa.py

   1 from .common import InfoExtractor
   2 from ..utils import (
   3     determine_ext,
   4     int_or_none,
   5     url_or_none,
   6 )
   7
   8
   9 class APAIE(InfoExtractor):
  10     _VALID_URL = r'(?P<base_url>https?://[^/]+\.apa\.at)/embed/(?P<id>[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})'
  11     _EMBED_REGEX = [r'<iframe[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//[^/]+\.apa\.at/embed/[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12}.*?)\1']
  12     _TESTS = [{
  13         'url': 'http://uvp.apa.at/embed/293f6d17-692a-44e3-9fd5-7b178f3a1029',
  14         'md5': '2b12292faeb0a7d930c778c7a5b4759b',
  15         'info_dict': {
  16             'id': '293f6d17-692a-44e3-9fd5-7b178f3a1029',
  17             'ext': 'mp4',
  18             'title': '293f6d17-692a-44e3-9fd5-7b178f3a1029',
  19             'thumbnail': r're:^https?://.*\.jpg$',
  20         },
  21     }, {
  22         'url': 'https://uvp-apapublisher.sf.apa.at/embed/2f94e9e6-d945-4db2-9548-f9a41ebf7b78',
  23         'only_matching': True,
  24     }, {
  25         'url': 'http://uvp-rma.sf.apa.at/embed/70404cca-2f47-4855-bbb8-20b1fae58f76',
  26         'only_matching': True,
  27     }, {
  28         'url': 'http://uvp-kleinezeitung.sf.apa.at/embed/f1c44979-dba2-4ebf-b021-e4cf2cac3c81',
  29         'only_matching': True,
  30     }]
  31
  32     def _real_extract(self, url):
  33         mobj = self._match_valid_url(url)
  34         video_id, base_url = mobj.group('id', 'base_url')
  35
  36         webpage = self._download_webpage(
  37             '%s/player/%s' % (base_url, video_id), video_id)
  38
  39         jwplatform_id = self._search_regex(
  40             r'media[iI]d\s*:\s*["\'](?P<id>[a-zA-Z0-9]{8})', webpage,
  41             'jwplatform id', default=None)
  42
  43         if jwplatform_id:
  44             return self.url_result(
  45                 'jwplatform:' + jwplatform_id, ie='JWPlatform',
  46                 video_id=video_id)
  47
  48         def extract(field, name=None):
  49             return self._search_regex(
  50                 r'\b%s["\']\s*:\s*(["\'])(?P<value>(?:(?!\1).)+)\1' % field,
  51                 webpage, name or field, default=None, group='value')
  52
  53         title = extract('title') or video_id
  54         description = extract('description')
  55         thumbnail = extract('poster', 'thumbnail')
  56
  57         formats = []
  58         for format_id in ('hls', 'progressive'):
  59             source_url = url_or_none(extract(format_id))
  60             if not source_url:
  61                 continue
  62             ext = determine_ext(source_url)
  63             if ext == 'm3u8':
  64                 formats.extend(self._extract_m3u8_formats(
  65                     source_url, video_id, 'mp4', entry_protocol='m3u8_native',
  66                     m3u8_id='hls', fatal=False))
  67             else:
  68                 height = int_or_none(self._search_regex(
  69                     r'(\d+)\.mp4', source_url, 'height', default=None))
  70                 formats.append({
  71                     'url': source_url,
  72                     'format_id': format_id,
  73                     'height': height,
  74                 })
  75
  76         return {
  77             'id': video_id,
  78             'title': title,
  79             'description': description,
  80             'thumbnail': thumbnail,
  81             'formats': formats,
  82         }