w/youtube-dl
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity

[archiveorg] improve format extraction(closes #10219)

Browse source
This commit is contained in:
Remita Amine 2016-08-05 16:40:21 +01:00
parent 0ca057b965
commit d50aca41f8
1 changed files with 38 additions and 40 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

78
youtube_dl/extractor/archiveorg.py
View file

@ -1,67 +1,65 @@
from __future__ import unicode_literals from __future__ import unicode_literals
from .common import InfoExtractor from .jwplatform import JWPlatformBaseIE
from ..utils import unified_strdate from ..utils import (
unified_strdate,
clean_html,
)
class ArchiveOrgIE(InfoExtractor): class ArchiveOrgIE(JWPlatformBaseIE):
IE_NAME = 'archive.org' IE_NAME = 'archive.org'
IE_DESC = 'archive.org videos' IE_DESC = 'archive.org videos'
_VALID_URL = r'https?://(?:www\.)?archive\.org/details/(?P<id>[^?/]+)(?:[?].*)?$' _VALID_URL = r'https?://(?:www\.)?archive\.org/(?:details|embed)/(?P<id>[^/?#]+)(?:[?].*)?$'
_TESTS = [{ _TESTS = [{
'url': 'http://archive.org/details/XD300-23_68HighlightsAResearchCntAugHumanIntellect', 'url': 'http://archive.org/details/XD300-23_68HighlightsAResearchCntAugHumanIntellect',
'md5': '8af1d4cf447933ed3c7f4871162602db', 'md5': '8af1d4cf447933ed3c7f4871162602db',
'info_dict': { 'info_dict': {
'id': 'XD300-23_68HighlightsAResearchCntAugHumanIntellect', 'id': 'XD300-23_68HighlightsAResearchCntAugHumanIntellect',
'ext': 'ogv', 'ext': 'ogg',
'title': '1968 Demo - FJCC Conference Presentation Reel #1', 'title': '1968 Demo - FJCC Conference Presentation Reel #1',
'description': 'md5:1780b464abaca9991d8968c877bb53ed', 'description': 'md5:da45c349df039f1cc8075268eb1b5c25',
'upload_date': '19681210', 'upload_date': '19681210',
'uploader': 'SRI International' 'uploader': 'SRI International'
} }
}, { }, {
'url': 'https://archive.org/details/Cops1922', 'url': 'https://archive.org/details/Cops1922',
'md5': '18f2a19e6d89af8425671da1cf3d4e04', 'md5': 'bc73c8ab3838b5a8fc6c6651fa7b58ba',
'info_dict': { 'info_dict': {
'id': 'Cops1922', 'id': 'Cops1922',
'ext': 'ogv', 'ext': 'mp4',
'title': 'Buster Keaton\'s "Cops" (1922)', 'title': 'Buster Keaton\'s "Cops" (1922)',
'description': 'md5:70f72ee70882f713d4578725461ffcc3', 'description': 'md5:b4544662605877edd99df22f9620d858',
} }
}, {
'url': 'http://archive.org/embed/XD300-23_68HighlightsAResearchCntAugHumanIntellect',
'only_matching': True,
}] }]
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) video_id = self._match_id(url)
webpage = self._download_webpage(
'http://archive.org/embed/' + video_id, video_id)
jwplayer_playlist = self._parse_json(self._search_regex(
r"(?s)Play\('[^']+'\s*,\s*(\[.+\])\s*,\s*{.*?}\);",
webpage, 'jwplayer playlist'), video_id)
info = self._parse_jwplayer_data(
{'playlist': jwplayer_playlist}, video_id, base_url=url)
json_url = url + ('&' if '?' in url else '?') + 'output=json' def get_optional(metadata, field):
data = self._download_json(json_url, video_id) return metadata.get(field, [None])[0]
def get_optional(data_dict, field): metadata = self._download_json(
return data_dict['metadata'].get(field, [None])[0] 'http://archive.org/details/' + video_id, video_id, query={
'output': 'json',
title = get_optional(data, 'title') })['metadata']
description = get_optional(data, 'description') info.update({
uploader = get_optional(data, 'creator') 'title': get_optional(metadata, 'title') or info.get('title'),
upload_date = unified_strdate(get_optional(data, 'date')) 'description': clean_html(get_optional(metadata, 'description')),
})
formats = [ if info.get('_type') != 'playlist':
{ info.update({
'format': fdata['format'], 'uploader': get_optional(metadata, 'creator'),
'url': 'http://' + data['server'] + data['dir'] + fn, 'upload_date': unified_strdate(get_optional(metadata, 'date')),
'file_size': int(fdata['size']), })
} return info
for fn, fdata in data['files'].items()
if 'Video' in fdata['format']]
self._sort_formats(formats)
return {
'_type': 'video',
'id': video_id,
'title': title,
'formats': formats,
'description': description,
'uploader': uploader,
'upload_date': upload_date,
'thumbnail': data.get('misc', {}).get('image'),
}