Overview
The new JavaScript API v2 is designed to simplify work by moving away from generators in favor of async/await. This API also eliminates some limitations of the previous version, adds TypeScript support, and improves performance. We recommend using this JavaScript API for creating all new scrapers.
To use JavaScript API v2, simply inherit your scraper class from the base BaseParser. Let's examine the scraper class structure with an example:
- TypeScript
- JavaScript
files/parsers/v2-example/v2-example.ts
import { BaseParser } from 'a-parser-types';
export class JS_v2_example extends BaseParser {
static defaultConf: typeof BaseParser.defaultConf = {
version: '0.0.1',
results: {
flat: [
['title', 'Title'],
['h1', 'H1 Header']
],
arrays: {
h2: ['H2 Headers List', [
['header', 'Header'],
]],
}
},
max_size: 2 * 1024 * 1024,
parsecodes: {
200: 1,
},
results_format: "Title: $title\nH1: $h1\nH2 headers:\n$h2.format('$header\\n')\n",
limitH2Tags: 3,
};
static editableConf: typeof BaseParser.editableConf = [
['limitH2Tags', ['textfield', 'Limit H2 tags']],
];
async parse(set, results) {
const { success, data, headers } = await this.request('GET', set.query);
if (success && typeof data == 'string') {
let matches;
if (matches = data.match(/<title[^>]*>(.*?)<\/title>/))
results.title = matches[1];
if (matches = data.match(/<h1[^>]*>(.*?)<\/h1>/))
results.h1 = matches[1];
if (results.h2) {
let count = 0;
const re = /<h2[^>]*>(.*?)<\/h2>/g;
while(matches = re.exec(data)) {
results.h2.push(matches[1]);
if (++count == this.conf.limitH2Tags)
break;
}
}
}
return results;
}
}
files/parsers/v2-example-js/v2-example-js.js
const { BaseParser } = require("a-parser-types");
class JS_v2_example_js extends BaseParser {
static defaultConf = {
version: '0.0.1',
results: {
flat: [
['title', 'Title'],
['h1', 'H1 Header']
],
arrays: {
h2: ['H2 Headers List', [
['header', 'Header'],
]],
}
},
max_size: 2 * 1024 * 1024,
parsecodes: {
200: 1,
},
results_format: "Title: $title\nH1: $h1\nH2 headers:\n$h2.format('$header\\n')\n",
limitH2Tags: 3,
};
static editableConf = [
['limitH2Tags', ['textfield', 'Limit H2 tags']],
];
async parse(set, results) {
const { success, data, headers } = await this.request('GET', set.query);
if (success && typeof data == 'string') {
let matches;
if (matches = data.match(/<title[^>]*>(.*?)<\/title>/))
results.title = matches[1];
if (matches = data.match(/<h1[^>]*>(.*?)<\/h1>/))
results.h1 = matches[1];
if (results.h2) {
let count = 0;
const re = /<h2[^>]*>(.*?)<\/h2>/g;
while(matches = re.exec(data)) {
results.h2.push(matches[1]);
if (++count == this.conf.limitH2Tags)
break;
}
}
}
return results;
}
}
Useful links
🔗 Example of saving a file to disk
An example demonstrating how to save files directly to disk
🔗 Example of working with sessions
Using session functionality in JavaScript scrapers
🔗 Example of saving data in a session
Demonstration of the ability to store arbitrary data in a session
🔗 Using results.addElement()
Example of populating a data array using results.addElement() and demonstrating the difference from a regular .push()