Madeorsk/youtube-dl
1
0
Fork 0
mirror of https://codeberg.org/polarisfm/youtube-dl synced 2024-11-26 18:34:32 +01:00
Code Issues Releases Wiki Activity

[playerglobewien] - add extraction from seehas, add extraction of all thumbnails

Browse Source
This commit is contained in:
Oneboy1979 2020-04-17 15:13:21 +02:00
parent 59bf7a1f26
commit 06a9eb6764
1 changed files with 37 additions and 30 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

61
youtube_dl/extractor/playerglobewien.py
View File

@ -6,7 +6,7 @@ from .common import InfoExtractor
class PlayerGlobeWienIE(InfoExtractor): class PlayerGlobeWienIE(InfoExtractor):
_VALID_URL = r'https?://player.(?:globe.wien|hader.at)/(?:globe-wien|hader)/(?P<id>.*)' _VALID_URL = r'https?://player\.(hader\.at|globe\.wien)/[^/]+/(?P<id>[^/?#]+)'
_TESTS = [ _TESTS = [
{ {
'url': 'https://player.globe.wien/globe-wien/corona-podcast-teil-4', 'url': 'https://player.globe.wien/globe-wien/corona-podcast-teil-4',
@ -55,39 +55,46 @@ class PlayerGlobeWienIE(InfoExtractor):
] ]
def _real_extract(self, url): def _real_extract(self, url):
format_id = self._match_id(url) video_id = self._match_id(url)
webpage = self._download_webpage(url, format_id) webpage = self._download_webpage(url, video_id)
thumbnail = self._html_search_regex( next_data = self._parse_json(
r'<img class="(?:.+?)" src="(?P<thumbnail>.+?)"', self._search_regex(
webpage, 'thumbnail', group='thumbnail') or self._og_search_thumbnail(webpage) r'<script[^>]+id="__NEXT_DATA__"[^>]+type="application/json"[^>]*>([^<]+)</script>',
description = self._og_search_description(webpage) webpage, 'next data'),
video_id)
vod = next_data.get('props').get('initialState').get('vod')
formats = [] formats = []
title = self._og_search_title(webpage) for key in vod.get('streamUrl'):
title = re.sub(r'^(Globe Wien VOD -|Hader VOD -)\s*', '', title) src_url = vod.get('streamUrl').get(key)
if key == 'hls':
streamurl = self._download_json("https://player.globe.wien/api/playout?vodId=" + format_id,
format_id).get('streamUrl')
if streamurl.get('hls'):
formats.extend(self._extract_m3u8_formats( formats.extend(self._extract_m3u8_formats(
streamurl.get('hls'), format_id, 'mp4', entry_protocol='m3u8_native', m3u8_id='hls')) src_url, video_id, ext='mp4', m3u8_id=key, fatal=False))
elif key == 'dash':
if streamurl.get('dash'):
formats.extend(self._extract_mpd_formats( formats.extend(self._extract_mpd_formats(
streamurl.get('dash'), format_id, mpd_id='dash', fatal=False)) src_url, video_id, mpd_id=key, fatal=False))
else:
if streamurl.get('audio'):
formats.append({ formats.append({
'url': streamurl.get('audio'), 'format_id': key,
'format_id': format_id, 'url': src_url
'vcodec': 'none',
}) })
thumbnails = []
for key in vod.get('images'):
thumbnails.append({
'id': key,
'url': vod.get('images').get(key),
})
self._check_formats(formats, video_id)
self._sort_formats(formats) self._sort_formats(formats)
return { return {
'id': format_id, 'id': vod.get('id'),
'title': title, 'title': vod.get('title'),
'thumbnail': thumbnail, 'description': vod.get('teaserDescription'),
'description': description, 'release_year': vod.get('year'),
'duration': (vod.get('durationMinutes') or 0) * 60,
'formats': formats, 'formats': formats,
'thumbnails': thumbnails,
} }