yt_dlp/extractor/apa.py

   1 import re
   2
   3 from .common import InfoExtractor
   4 from ..utils import (
   5     determine_ext,
   6     int_or_none,
   7     url_or_none,
   8 )
   9
  10
  11 class APAIE(InfoExtractor):
  12     _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})'
  13     _TESTS = [{
  14         'url': 'http://uvp.apa.at/embed/293f6d17-692a-44e3-9fd5-7b178f3a1029',
  15         'md5': '2b12292faeb0a7d930c778c7a5b4759b',
  16         'info_dict': {
  17             'id': '293f6d17-692a-44e3-9fd5-7b178f3a1029',
  18             'ext': 'mp4',
  19             'title': '293f6d17-692a-44e3-9fd5-7b178f3a1029',
  20             'thumbnail': r're:^https?://.*\.jpg$',
  21         },
  22     }, {
  23         'url': 'https://uvp-apapublisher.sf.apa.at/embed/2f94e9e6-d945-4db2-9548-f9a41ebf7b78',
  24         'only_matching': True,
  25     }, {
  26         'url': 'http://uvp-rma.sf.apa.at/embed/70404cca-2f47-4855-bbb8-20b1fae58f76',
  27         'only_matching': True,
  28     }, {
  29         'url': 'http://uvp-kleinezeitung.sf.apa.at/embed/f1c44979-dba2-4ebf-b021-e4cf2cac3c81',
  30         'only_matching': True,
  31     }]
  32
  33     @staticmethod
  34     def _extract_urls(webpage):
  35         return [
  36             mobj.group('url')
  37             for mobj in re.finditer(
  38                 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',
  39                 webpage)]
  40
  41     def _real_extract(self, url):
  42         mobj = self._match_valid_url(url)
  43         video_id, base_url = mobj.group('id', 'base_url')
  44
  45         webpage = self._download_webpage(
  46             '%s/player/%s' % (base_url, video_id), video_id)
  47
  48         jwplatform_id = self._search_regex(
  49             r'media[iI]d\s*:\s*["\'](?P<id>[a-zA-Z0-9]{8})', webpage,
  50             'jwplatform id', default=None)
  51
  52         if jwplatform_id:
  53             return self.url_result(
  54                 'jwplatform:' + jwplatform_id, ie='JWPlatform',
  55                 video_id=video_id)
  56
  57         def extract(field, name=None):
  58             return self._search_regex(
  59                 r'\b%s["\']\s*:\s*(["\'])(?P<value>(?:(?!\1).)+)\1' % field,
  60                 webpage, name or field, default=None, group='value')
  61
  62         title = extract('title') or video_id
  63         description = extract('description')
  64         thumbnail = extract('poster', 'thumbnail')
  65
  66         formats = []
  67         for format_id in ('hls', 'progressive'):
  68             source_url = url_or_none(extract(format_id))
  69             if not source_url:
  70                 continue
  71             ext = determine_ext(source_url)
  72             if ext == 'm3u8':
  73                 formats.extend(self._extract_m3u8_formats(
  74                     source_url, video_id, 'mp4', entry_protocol='m3u8_native',
  75                     m3u8_id='hls', fatal=False))
  76             else:
  77                 height = int_or_none(self._search_regex(
  78                     r'(\d+)\.mp4', source_url, 'height', default=None))
  79                 formats.append({
  80                     'url': source_url,
  81                     'format_id': format_id,
  82                     'height': height,
  83                 })
  84         self._sort_formats(formats)
  85
  86         return {
  87             'id': video_id,
  88             'title': title,
  89             'description': description,
  90             'thumbnail': thumbnail,
  91             'formats': formats,
  92         }