mirrors/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2025-10-31 06:35:12 +00:00
Code Issues Projects Releases Wiki Activity

[newgrounds] Improve formats and uploader extraction (closes #13346)

Browse Source
This commit is contained in:
Sergey M․
2017-06-11 19:44:44 +07:00
parent 7409af9eb3
commit 6e999fbc12
1 changed files with 43 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

48
youtube_dl/extractor/newgrounds.py
View File

@@ -1,6 +1,7 @@
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import int_or_none
class NewgroundsIE(InfoExtractor):
@@ -23,24 +24,61 @@ class NewgroundsIE(InfoExtractor):
'title': 'Dancin',
'uploader': 'Squirrelman82',
},
}, {
# source format unavailable, additional mp4 formats
'url': 'http://www.newgrounds.com/portal/view/689400',
'info_dict': {
'id': '689400',
'ext': 'mp4',
'title': 'ZTV News Episode 8',
'uploader': 'BennettTheSage',
},
'params': {
'skip_download': True,
},
}]
def _real_extract(self, url):
media_id = self._match_id(url)
webpage = self._download_webpage(url, media_id)
title = self._html_search_regex(
r'<title>([^>]+)</title>', webpage, 'title')
uploader = self._html_search_regex(
r'Author\s*<a[^>]+>([^<]+)', webpage, 'uploader', fatal=False)
video_url = self._parse_json(self._search_regex(
r'"url"\s*:\s*("[^"]+"),', webpage, ''), media_id)
music_url = self._parse_json(self._search_regex(
r'"url":("[^"]+"),', webpage, ''), media_id)
formats = [{
'url': video_url,
'format_id': 'source',
'quality': 1,
}]
max_resolution = int_or_none(self._search_regex(
r'max_resolution["\']\s*:\s*(\d+)', webpage, 'max resolution',
default=None))
if max_resolution:
url_base = video_url.rpartition('.')[0]
for resolution in (360, 720, 1080):
if resolution > max_resolution:
break
formats.append({
'url': '%s.%dp.mp4' % (url_base, resolution),
'format_id': '%dp' % resolution,
'height': resolution,
})
self._check_formats(formats, media_id)
self._sort_formats(formats)
uploader = self._html_search_regex(
r'(?:Author|Writer)\s*<a[^>]+>([^<]+)', webpage, 'uploader',
fatal=False)
return {
'id': media_id,
'title': title,
'url': music_url,
'uploader': uploader,
'formats': formats,
}