[newgrounds:playlist] Add extractor (closes #10611)

This commit is contained in:
Sergey M․ 2017-06-11 20:50:33 +07:00
parent 6e999fbc12
commit 70e7967202
No known key found for this signature in database
GPG key ID: 2C393E0F18A9236D
2 changed files with 59 additions and 2 deletions

View file

@ -636,7 +636,10 @@ from .neteasemusic import (
NetEaseMusicProgramIE, NetEaseMusicProgramIE,
NetEaseMusicDjRadioIE, NetEaseMusicDjRadioIE,
) )
from .newgrounds import NewgroundsIE from .newgrounds import (
NewgroundsIE,
NewgroundsPlaylistIE,
)
from .newstube import NewstubeIE from .newstube import NewstubeIE
from .nextmedia import ( from .nextmedia import (
NextMediaIE, NextMediaIE,

View file

@ -1,7 +1,12 @@
from __future__ import unicode_literals from __future__ import unicode_literals
import re
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import int_or_none from ..utils import (
extract_attributes,
int_or_none,
)
class NewgroundsIE(InfoExtractor): class NewgroundsIE(InfoExtractor):
@ -82,3 +87,52 @@ class NewgroundsIE(InfoExtractor):
'uploader': uploader, 'uploader': uploader,
'formats': formats, 'formats': formats,
} }
class NewgroundsPlaylistIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?newgrounds\.com/(?:collection|[^/]+/search/[^/]+)/(?P<id>[^/?#&]+)'
_TESTS = [{
'url': 'https://www.newgrounds.com/collection/cats',
'info_dict': {
'id': 'cats',
'title': 'Cats',
},
'playlist_mincount': 46,
}, {
'url': 'http://www.newgrounds.com/portal/search/author/ZONE-SAMA',
'info_dict': {
'id': 'ZONE-SAMA',
'title': 'Portal Search: ZONE-SAMA',
},
'playlist_mincount': 47,
}, {
'url': 'http://www.newgrounds.com/audio/search/title/cats',
'only_matching': True,
}]
def _real_extract(self, url):
playlist_id = self._match_id(url)
webpage = self._download_webpage(url, playlist_id)
title = self._search_regex(
r'<title>([^>]+)</title>', webpage, 'title', default=None)
# cut left menu
webpage = self._search_regex(
r'(?s)<div[^>]+\bclass=["\']column wide(.+)',
webpage, 'wide column', default=webpage)
entries = []
for a, path, media_id in re.findall(
r'(<a[^>]+\bhref=["\']/?((?:portal/view|audio/listen)/(\d+))[^>]+>)',
webpage):
a_class = extract_attributes(a).get('class')
if a_class not in ('item-portalsubmission', 'item-audiosubmission'):
continue
entries.append(
self.url_result(
'https://www.newgrounds.com/%s' % path,
ie=NewgroundsIE.ie_key(), video_id=media_id))
return self.playlist_result(entries, playlist_id, title)