[extractor/ViMP] Add playlist extractor (#4147)

Authored by: FestplattenSchnitzel
This commit is contained in:
FestplattenSchnitzel 2022-06-29 02:06:25 +02:00 committed by GitHub
parent 5fb450a64c
commit 1db1461272
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 74 additions and 2 deletions

View File

@ -1934,7 +1934,10 @@
from .vidbit import VidbitIE
from .viddler import ViddlerIE
from .videa import VideaIE
from .videocampus_sachsen import VideocampusSachsenIE
from .videocampus_sachsen import (
VideocampusSachsenIE,
ViMPPlaylistIE,
)
from .videodetective import VideoDetectiveIE
from .videofyme import VideofyMeIE
from .videomore import (

View File

@ -1,8 +1,9 @@
import functools
import re
from .common import InfoExtractor
from ..compat import compat_HTTPError
from ..utils import ExtractorError
from ..utils import ExtractorError, OnDemandPagedList, urlencode_postdata
class VideocampusSachsenIE(InfoExtractor):
@ -183,3 +184,71 @@ def _real_extract(self, url):
'formats': formats,
'subtitles': subtitles,
}
class ViMPPlaylistIE(InfoExtractor):
IE_NAME = 'ViMP:Playlist'
_VALID_URL = r'''(?x)(?P<host>https?://(?:%s))/(?:
album/view/aid/(?P<album_id>[0-9]+)|
(?P<mode>category|channel)/(?P<name>[\w-]+)/(?P<id>[0-9]+)
)''' % '|'.join(map(re.escape, VideocampusSachsenIE._INSTANCES))
_TESTS = [{
'url': 'https://vimp.oth-regensburg.de/channel/Designtheorie-1-SoSe-2020/3',
'info_dict': {
'id': 'channel-3',
'title': 'Designtheorie 1 SoSe 2020 :: Channels :: ViMP OTH Regensburg',
},
'playlist_mincount': 9,
}, {
'url': 'https://www.fh-bielefeld.de/medienportal/album/view/aid/208',
'info_dict': {
'id': 'album-208',
'title': 'KG Praktikum ABT/MEC :: Playlists :: FH-Medienportal',
},
'playlist_mincount': 4,
}, {
'url': 'https://videocampus.sachsen.de/category/online-tutorials-onyx/91',
'info_dict': {
'id': 'category-91',
'title': 'Online-Seminare ONYX - BPS - Bildungseinrichtungen - VCS',
},
'playlist_mincount': 7,
}]
_PAGE_SIZE = 10
def _fetch_page(self, host, url_part, id, data, page):
webpage = self._download_webpage(
f'{host}/media/ajax/component/boxList/{url_part}', id,
query={'page': page, 'page_only': 1}, data=urlencode_postdata(data))
urls = re.findall(r'"([^"]+/video/[^"]+)"', webpage)
for url in urls:
yield self.url_result(host + url, VideocampusSachsenIE)
def _real_extract(self, url):
host, album_id, mode, name, id = self._match_valid_url(url).group(
'host', 'album_id', 'mode', 'name', 'id')
webpage = self._download_webpage(url, album_id or id, fatal=False) or ''
title = (self._html_search_meta('title', webpage, fatal=False)
or self._html_extract_title(webpage))
url_part = (f'aid/{album_id}' if album_id
else f'category/{name}/category_id/{id}' if mode == 'category'
else f'title/{name}/channel/{id}')
mode = mode or 'album'
data = {
'vars[mode]': mode,
f'vars[{mode}]': album_id or id,
'vars[context]': '4' if album_id else '1' if mode == 'category' else '3',
'vars[context_id]': album_id or id,
'vars[layout]': 'thumb',
'vars[per_page][thumb]': str(self._PAGE_SIZE),
}
return self.playlist_result(
OnDemandPagedList(functools.partial(
self._fetch_page, host, url_part, album_id or id, data), self._PAGE_SIZE),
playlist_title=title, id=f'{mode}-{album_id or id}')