Scrapes and displays data from the web page based on rules.
Dieses Skript sollte nicht direkt installiert werden. Es handelt sich hier um eine Bibliothek für andere Skripte, welche über folgenden Befehl in den Metadaten eines Skriptes eingebunden wird // @require https://update.greasyfork.org/scripts/471264/1222840/MagicScraper.js
const rules = {
// Your rules object here
};
const options = {
keepChildren: false, // Set to true if you want to retain children of scraped elements
};
magicScraper(rules, [options]);
// OR
magicScraper('https://example.com/rules.json', [options]);
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',
},
};