diff options
author | Ruirize <ruirize@live.co.uk> | 2013-09-18 15:54:45 +0100 |
---|---|---|
committer | Ruirize <ruirize@live.co.uk> | 2013-09-18 15:54:45 +0100 |
commit | eb03f4dad3ebb0f781e6742b6c1c590506d58e5b (patch) | |
tree | 0648d4c0721386785b132e445c344f2c7377286a /youtube_dl/extractor | |
parent | 830dd1944a3db8de373fe78ac805302915caf126 (diff) |
Added Newgrounds support
Diffstat (limited to 'youtube_dl/extractor')
-rw-r--r-- | youtube_dl/extractor/__init__.py | 1 | ||||
-rw-r--r-- | youtube_dl/extractor/newgrounds.py | 37 |
2 files changed, 38 insertions, 0 deletions
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 761575062..e1ec38cf2 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -68,6 +68,7 @@ from .myvideo import MyVideoIE from .naver import NaverIE from .nba import NBAIE from .nbc import NBCNewsIE +from .newgrounds import NewgroundsIE from .ooyala import OoyalaIE from .orf import ORFIE from .pbs import PBSIE diff --git a/youtube_dl/extractor/newgrounds.py b/youtube_dl/extractor/newgrounds.py new file mode 100644 index 000000000..d19145a72 --- /dev/null +++ b/youtube_dl/extractor/newgrounds.py @@ -0,0 +1,37 @@ +import json +import re + +from .common import InfoExtractor +from ..utils import determine_ext + +class NewgroundsIE(InfoExtractor): + _VALID_URL = r'(?:https?://)?(?:www\.)?newgrounds\.com/audio/listen/(?P<id>\d+)' + _TEST = { + u'url': u'http://www.newgrounds.com/audio/listen/549479', + u'file': u'549479_B7---BusMode.mp3', + u'md5': u'2924d938f60415cd7afbe7ae9042a99e', + u'info_dict': { + u"title": u"B7 - BusMode", + u"uploader" : u"Burn7", + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + music_id = mobj.group('id') + webpage = self._download_webpage(url, music_id) + + title = self._html_search_regex(r',"name":"([^"]+)",', webpage, 'music title', flags=re.DOTALL) + uploader = self._html_search_regex(r',"artist":"([^"]+)",', webpage, 'music uploader', flags=re.DOTALL) + + music_url_json_string = '{"url":"' + self._html_search_regex(r'{"url":"([^"]+)",', webpage, 'music url', flags=re.DOTALL) + '"}' + music_url_json = json.loads(music_url_json_string) + music_url = music_url_json['url'] + + return [{ + 'id': music_id, + 'title': title, + 'url': music_url, + 'uploader': uploader, + 'ext': determine_ext(music_url), + }] |