Dette script bør ikke installeres direkte. Det er et bibliotek, som andre scripts kan inkludere med metadirektivet // @require https://update.greasyfork.org/scripts/471264/1222840/MagicScraper.js
Define your rules object (either inline or external)
const rules = {
// Your rules object here
};
Define the options
const options = {
keepChildren: false, // Set to true if you want to retain children of scraped elements
};
Call the scraper function with the rules object or the external URL.
magicScraper(rules, [options]);
// OR
magicScraper('https://example.com/rules.json', [options]);
Rules definition
const rules = {
// Global rules for the entire example.com domain
'example.com': {
title: 'h1',
content: '.main-content',
pages: {
// Specific rules for the homepage of example.com
'/': {
subtitle: '.subtitle',
featuredImage: '.featured-image',
},
// Fallback rules for any other page under example.com
'*': {
defaultTitle: 'h2',
},
},
// Specific rules for any page under the blog subdomain
'blog.example.com/*': {
blogTitle: '.blog-title',
blogContent: '.blog-content',
},
// Wildcard rules for any subdomain under example.com
'*.example.com': {
subdomainTitle: '.subdomain-title',
},
// Wildcard rules for any page under the about subdomain
'about.example.com/*': {
aboutSection: '.about-section',
}
},
// Global rules for the entire test.com domain
'test.com': {
title: 'h1',
testContent: '.test-content',
},
// Fallback rules for any other domain not specified above
'*': {
defaultTitle: 'h1',
defaultContent: '.main-content',
},
};