etc/yt-dlp
0
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-12-03 03:57:26 +00:00
Code Issues Projects Releases Wiki Activity

[archiveorg] Add test, simplify and modernize

Browse source
This commit is contained in:
Sergey M․ 2014-12-29 02:08:46 +06:00
parent 0fa629d05b
commit e8e28989eb
1 changed files with 29 additions and 31 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

58
youtube_dl/extractor/archiveorg.py
View file

@ -1,50 +1,48 @@
from __future__ import unicode_literals
import json
import re
from .common import InfoExtractor
from ..utils import (
unified_strdate,
)
from ..utils import unified_strdate
class ArchiveOrgIE(InfoExtractor):
IE_NAME = 'archive.org'
IE_DESC = 'archive.org videos'
_VALID_URL = r'(?:https?://)?(?:www\.)?archive\.org/details/(?P<id>[^?/]+)(?:[?].*)?$'
_TEST = {
"url": "http://archive.org/details/XD300-23_68HighlightsAResearchCntAugHumanIntellect",
'file': 'XD300-23_68HighlightsAResearchCntAugHumanIntellect.ogv',
_VALID_URL = r'https?://(?:www\.)?archive\.org/details/(?P<id>[^?/]+)(?:[?].*)?$'
_TESTS = [{
'url': 'http://archive.org/details/XD300-23_68HighlightsAResearchCntAugHumanIntellect',
'md5': '8af1d4cf447933ed3c7f4871162602db',
'info_dict': {
"title": "1968 Demo - FJCC Conference Presentation Reel #1",
"description": "Reel 1 of 3: Also known as the \"Mother of All Demos\", Doug Engelbart's presentation at the Fall Joint Computer Conference in San Francisco, December 9, 1968 titled \"A Research Center for Augmenting Human Intellect.\" For this presentation, Doug and his team astonished the audience by not only relating their research, but demonstrating it live. This was the debut of the mouse, interactive computing, hypermedia, computer supported software engineering, video teleconferencing, etc. See also <a href=\"http://dougengelbart.org/firsts/dougs-1968-demo.html\" rel=\"nofollow\">Doug's 1968 Demo page</a> for more background, highlights, links, and the detailed paper published in this conference proceedings. Filmed on 3 reels: Reel 1 | <a href=\"http://www.archive.org/details/XD300-24_68HighlightsAResearchCntAugHumanIntellect\" rel=\"nofollow\">Reel 2</a> | <a href=\"http://www.archive.org/details/XD300-25_68HighlightsAResearchCntAugHumanIntellect\" rel=\"nofollow\">Reel 3</a>",
"upload_date": "19681210",
"uploader": "SRI International"
'id': 'XD300-23_68HighlightsAResearchCntAugHumanIntellect',
'ext': 'ogv',
'title': '1968 Demo - FJCC Conference Presentation Reel #1',
'description': 'md5:1780b464abaca9991d8968c877bb53ed',
'upload_date': '19681210',
'uploader': 'SRI International'
}
}, {
'url': 'https://archive.org/details/Cops1922',
'md5': '18f2a19e6d89af8425671da1cf3d4e04',
'info_dict': {
'id': 'Cops1922',
'ext': 'ogv',
'title': 'Buster Keaton\'s "Cops" (1922)',
'description': 'md5:70f72ee70882f713d4578725461ffcc3',
}
def get_optional_metadata(self, data, field):
try:
return data['metadata'][field][0]
except KeyError:
return None
}]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
video_id = self._match_id(url)
json_url = url + ('?' if '?' in url else '&') + 'output=json'
json_data = self._download_webpage(json_url, video_id)
data = json.loads(json_data)
data = self._download_json(json_url, video_id)
title = self.get_optional_metadata(data, 'title')
description = self.get_optional_metadata(data, 'description')
uploader = self.get_optional_metadata(data, 'creator')
upload_date = self.get_optional_metadata(data, 'date')
if upload_date:
upload_date = unified_strdate(upload_date)
def get_optional(data_dict, field):
return data_dict['metadata'].get(field, [None])[0]
title = get_optional(data, 'title')
description = get_optional(data, 'description')
uploader = get_optional(data, 'creator')
upload_date = unified_strdate(get_optional(data, 'date'))
formats = [
{