[newgrounds] Extract more metadata (closes #13232)

This commit is contained in:
Sergey M․ 2017-06-11 21:27:32 +07:00
parent 2ae2ffda5e
commit 28a4d6cce8
No known key found for this signature in database
GPG key ID: 2C393E0F18A9236D

View file

@ -6,6 +6,9 @@
from ..utils import ( from ..utils import (
extract_attributes, extract_attributes,
int_or_none, int_or_none,
parse_duration,
parse_filesize,
unified_timestamp,
) )
@ -19,7 +22,10 @@ class NewgroundsIE(InfoExtractor):
'ext': 'mp3', 'ext': 'mp3',
'title': 'B7 - BusMode', 'title': 'B7 - BusMode',
'uploader': 'Burn7', 'uploader': 'Burn7',
} 'timestamp': 1378878540,
'upload_date': '20130911',
'duration': 143,
},
}, { }, {
'url': 'https://www.newgrounds.com/portal/view/673111', 'url': 'https://www.newgrounds.com/portal/view/673111',
'md5': '3394735822aab2478c31b1004fe5e5bc', 'md5': '3394735822aab2478c31b1004fe5e5bc',
@ -28,6 +34,8 @@ class NewgroundsIE(InfoExtractor):
'ext': 'mp4', 'ext': 'mp4',
'title': 'Dancin', 'title': 'Dancin',
'uploader': 'Squirrelman82', 'uploader': 'Squirrelman82',
'timestamp': 1460256780,
'upload_date': '20160410',
}, },
}, { }, {
# source format unavailable, additional mp4 formats # source format unavailable, additional mp4 formats
@ -37,6 +45,8 @@ class NewgroundsIE(InfoExtractor):
'ext': 'mp4', 'ext': 'mp4',
'title': 'ZTV News Episode 8', 'title': 'ZTV News Episode 8',
'uploader': 'BennettTheSage', 'uploader': 'BennettTheSage',
'timestamp': 1487965140,
'upload_date': '20170224',
}, },
'params': { 'params': {
'skip_download': True, 'skip_download': True,
@ -51,11 +61,11 @@ def _real_extract(self, url):
title = self._html_search_regex( title = self._html_search_regex(
r'<title>([^>]+)</title>', webpage, 'title') r'<title>([^>]+)</title>', webpage, 'title')
video_url = self._parse_json(self._search_regex( media_url = self._parse_json(self._search_regex(
r'"url"\s*:\s*("[^"]+"),', webpage, ''), media_id) r'"url"\s*:\s*("[^"]+"),', webpage, ''), media_id)
formats = [{ formats = [{
'url': video_url, 'url': media_url,
'format_id': 'source', 'format_id': 'source',
'quality': 1, 'quality': 1,
}] }]
@ -64,7 +74,7 @@ def _real_extract(self, url):
r'max_resolution["\']\s*:\s*(\d+)', webpage, 'max resolution', r'max_resolution["\']\s*:\s*(\d+)', webpage, 'max resolution',
default=None)) default=None))
if max_resolution: if max_resolution:
url_base = video_url.rpartition('.')[0] url_base = media_url.rpartition('.')[0]
for resolution in (360, 720, 1080): for resolution in (360, 720, 1080):
if resolution > max_resolution: if resolution > max_resolution:
break break
@ -77,14 +87,32 @@ def _real_extract(self, url):
self._check_formats(formats, media_id) self._check_formats(formats, media_id)
self._sort_formats(formats) self._sort_formats(formats)
uploader = self._html_search_regex( uploader = self._search_regex(
r'(?:Author|Writer)\s*<a[^>]+>([^<]+)', webpage, 'uploader', r'(?:Author|Writer)\s*<a[^>]+>([^<]+)', webpage, 'uploader',
fatal=False) fatal=False)
timestamp = unified_timestamp(self._search_regex(
r'<dt>Uploaded</dt>\s*<dd>([^<]+)', webpage, 'timestamp',
default=None))
duration = parse_duration(self._search_regex(
r'<dd>Song\s*</dd><dd>.+?</dd><dd>([^<]+)', webpage, 'duration',
default=None))
filesize_approx = parse_filesize(self._html_search_regex(
r'<dd>Song\s*</dd><dd>(.+?)</dd>', webpage, 'filesize',
default=None))
if len(formats) == 1:
formats[0]['filesize_approx'] = filesize_approx
if '<dd>Song' in webpage:
formats[0]['vcodec'] = 'none'
return { return {
'id': media_id, 'id': media_id,
'title': title, 'title': title,
'uploader': uploader, 'uploader': uploader,
'timestamp': timestamp,
'duration': duration,
'formats': formats, 'formats': formats,
} }