]>
jfr.im git - yt-dlp.git/blob - yt_dlp/extractor/apa.py
2 from __future__
import unicode_literals
6 from .common
import InfoExtractor
14 class APAIE(InfoExtractor
):
15 _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})'
17 'url': 'http://uvp.apa.at/embed/293f6d17-692a-44e3-9fd5-7b178f3a1029',
18 'md5': '2b12292faeb0a7d930c778c7a5b4759b',
20 'id': '293f6d17-692a-44e3-9fd5-7b178f3a1029',
22 'title': '293f6d17-692a-44e3-9fd5-7b178f3a1029',
23 'thumbnail': r
're:^https?://.*\.jpg$',
26 'url': 'https://uvp-apapublisher.sf.apa.at/embed/2f94e9e6-d945-4db2-9548-f9a41ebf7b78',
27 'only_matching': True,
29 'url': 'http://uvp-rma.sf.apa.at/embed/70404cca-2f47-4855-bbb8-20b1fae58f76',
30 'only_matching': True,
32 'url': 'http://uvp-kleinezeitung.sf.apa.at/embed/f1c44979-dba2-4ebf-b021-e4cf2cac3c81',
33 'only_matching': True,
37 def _extract_urls(webpage
):
40 for mobj
in re
.finditer(
41 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',
44 def _real_extract(self, url):
45 mobj = re.match(self._VALID_URL, url)
46 video_id, base_url = mobj.group('id', 'base_url
')
48 webpage = self._download_webpage(
49 '%s/player
/%s' % (base_url, video_id), video_id)
51 jwplatform_id = self._search_regex(
52 r'media
[iI
]d\s
*:\s
*["\'](?P<id>[a-zA-Z0-9]{8})', webpage,
53 'jwplatform id', default=None)
56 return self.url_result(
57 'jwplatform:' + jwplatform_id, ie='JWPlatform',
60 def extract(field, name=None):
61 return self._search_regex(
62 r'\b%s["\']\s
*:\s
*(["\'])(?P<value>(?:(?!\1).)+)\1' % field,
63 webpage, name or field, default=None, group='value')
65 title = extract('title') or video_id
66 description = extract('description')
67 thumbnail = extract('poster', 'thumbnail')
70 for format_id in ('hls', 'progressive'):
71 source_url = url_or_none(extract(format_id))
74 ext = determine_ext(source_url)
76 formats.extend(self._extract_m3u8_formats(
77 source_url, video_id, 'mp4', entry_protocol='m3u8_native',
78 m3u8_id='hls', fatal=False))
80 height = int_or_none(self._search_regex(
81 r'(\d+)\.mp4', source_url, 'height', default=None))
84 'format_id': format_id,
87 self._sort_formats(formats)
92 'description': description,
93 'thumbnail': thumbnail,