feat: add www.itmedia.co.jp custom parser (#366)
* feat: add www.itmedia.co.jp custom parser * feat: add nlab.itmedia.co.jp support * fix: title selectorspull/365/head^2
parent
9218f80da6
commit
d7dbea8a95
File diff suppressed because it is too large
Load Diff
@ -0,0 +1,39 @@
|
||||
export const WwwItmediaCoJpExtractor = {
|
||||
domain: 'www.itmedia.co.jp',
|
||||
|
||||
supportedDomains: [
|
||||
'www.atmarkit.co.jp',
|
||||
'techtarget.itmedia.co.jp',
|
||||
'nlab.itmedia.co.jp',
|
||||
],
|
||||
|
||||
title: {
|
||||
selectors: ['#cmsTitle h1'],
|
||||
},
|
||||
|
||||
author: {
|
||||
selectors: ['#byline'],
|
||||
},
|
||||
|
||||
date_published: {
|
||||
selectors: [['meta[name="article:modified_time"]', 'value']],
|
||||
},
|
||||
|
||||
dek: {
|
||||
selectors: ['#cmsAbstract h2'],
|
||||
},
|
||||
|
||||
lead_image_url: {
|
||||
selectors: [['meta[name="og:image"]', 'value']],
|
||||
},
|
||||
|
||||
content: {
|
||||
selectors: ['#cmsBody'],
|
||||
|
||||
defaultCleaner: false,
|
||||
|
||||
transforms: {},
|
||||
|
||||
clean: ['#snsSharebox'],
|
||||
},
|
||||
};
|
Loading…
Reference in New Issue