[ie/Bild.de] Extract HLS formats (#8032)

Closes #7951
Authored by: barsnick
pull/8128/head
barsnick 1 year ago committed by GitHub
parent 23d829a342
commit b4c1c408c6
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23

@ -1,6 +1,7 @@
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..utils import (
int_or_none, int_or_none,
traverse_obj,
unescapeHTML, unescapeHTML,
) )
@ -8,7 +9,8 @@ from ..utils import (
class BildIE(InfoExtractor): class BildIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?bild\.de/(?:[^/]+/)+(?P<display_id>[^/]+)-(?P<id>\d+)(?:,auto=true)?\.bild\.html' _VALID_URL = r'https?://(?:www\.)?bild\.de/(?:[^/]+/)+(?P<display_id>[^/]+)-(?P<id>\d+)(?:,auto=true)?\.bild\.html'
IE_DESC = 'Bild.de' IE_DESC = 'Bild.de'
_TEST = { _TESTS = [{
'note': 'static MP4 only',
'url': 'http://www.bild.de/video/clip/apple-ipad-air/das-koennen-die-neuen-ipads-38184146.bild.html', 'url': 'http://www.bild.de/video/clip/apple-ipad-air/das-koennen-die-neuen-ipads-38184146.bild.html',
'md5': 'dd495cbd99f2413502a1713a1156ac8a', 'md5': 'dd495cbd99f2413502a1713a1156ac8a',
'info_dict': { 'info_dict': {
@ -19,7 +21,19 @@ class BildIE(InfoExtractor):
'thumbnail': r're:^https?://.*\.jpg$', 'thumbnail': r're:^https?://.*\.jpg$',
'duration': 196, 'duration': 196,
} }
} }, {
'note': 'static MP4 and HLS',
'url': 'https://www.bild.de/video/clip/news-ausland/deftiger-abgang-vom-10m-turm-bademeister-sorgt-fuer-skandal-85158620.bild.html',
'md5': 'fb0ed4f09c495d4ba7ce2eee0bb90de1',
'info_dict': {
'id': '85158620',
'ext': 'mp4',
'title': 'Der Sprungturm-Skandal',
'description': 'md5:709b543c24dc31bbbffee73bccda34ad',
'thumbnail': r're:^https?://.*\.jpg$',
'duration': 69,
}
}]
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) video_id = self._match_id(url)
@ -27,11 +41,23 @@ class BildIE(InfoExtractor):
video_data = self._download_json( video_data = self._download_json(
url.split('.bild.html')[0] + ',view=json.bild.html', video_id) url.split('.bild.html')[0] + ',view=json.bild.html', video_id)
formats = []
for src in traverse_obj(video_data, ('clipList', 0, 'srces', lambda _, v: v['src'])):
src_type = src.get('type')
if src_type == 'application/x-mpegURL':
formats.extend(
self._extract_m3u8_formats(
src['src'], video_id, 'mp4', m3u8_id='hls', fatal=False))
elif src_type == 'video/mp4':
formats.append({'url': src['src'], 'format_id': 'http-mp4'})
else:
self.report_warning(f'Skipping unsupported format type: "{src_type}"')
return { return {
'id': video_id, 'id': video_id,
'title': unescapeHTML(video_data['title']).strip(), 'title': unescapeHTML(video_data['title']).strip(),
'description': unescapeHTML(video_data.get('description')), 'description': unescapeHTML(video_data.get('description')),
'url': video_data['clipList'][0]['srces'][0]['src'], 'formats': formats,
'thumbnail': video_data.get('poster'), 'thumbnail': video_data.get('poster'),
'duration': int_or_none(video_data.get('durationSec')), 'duration': int_or_none(video_data.get('durationSec')),
} }

Loading…
Cancel
Save