feat: add www.infoq.com custom parser (#368)
* feat: add www.infoq.com custom parser * fix: date_published selectorpull/367/head^2
parent
ce5cd2dd0d
commit
4eb73dffb0
File diff suppressed because it is too large
Load Diff
@ -0,0 +1,35 @@
|
|||||||
|
export const WwwInfoqComExtractor = {
|
||||||
|
domain: 'www.infoq.com',
|
||||||
|
|
||||||
|
title: {
|
||||||
|
selectors: ['h1.heading'],
|
||||||
|
},
|
||||||
|
|
||||||
|
author: {
|
||||||
|
selectors: ['div.widget.article__authors'],
|
||||||
|
},
|
||||||
|
|
||||||
|
date_published: {
|
||||||
|
selectors: ['.article__readTime.date'],
|
||||||
|
format: 'YYYY年MM月DD日',
|
||||||
|
timezone: 'Asia/Tokyo',
|
||||||
|
},
|
||||||
|
|
||||||
|
dek: {
|
||||||
|
selectors: [['meta[name="og:description"]', 'value']],
|
||||||
|
},
|
||||||
|
|
||||||
|
lead_image_url: {
|
||||||
|
selectors: [['meta[name="og:image"]', 'value']],
|
||||||
|
},
|
||||||
|
|
||||||
|
content: {
|
||||||
|
selectors: ['div.article__data'],
|
||||||
|
|
||||||
|
defaultCleaner: false,
|
||||||
|
|
||||||
|
transforms: {},
|
||||||
|
|
||||||
|
clean: [],
|
||||||
|
},
|
||||||
|
};
|
Loading…
Reference in New Issue