import { Website, pageTitle } from "@spider-rs/spider-rs";

const website = new Website("https://rsseau.fr")
  .withHeaders({
    authorization: "somerandomjwt",
  })
  .withBudget({
    "*": 20, // limit max request 20 pages for the website
    "/docs": 10, // limit only 10 pages on the `/docs` paths
  })
  .withBlacklistUrl(["/resume"]) // regex or pattern matching to ignore paths
  .build();

// optional: page event handler
const onPageEvent = (_err, page) => {
  const title = pageTitle(page); // comment out to increase performance if title not needed
  console.info(`Title of ${page.url} is '${title}'`);
  website.pushData({
    status: page.statusCode,
    html: page.content,
    url: page.url,
    title,
  });
};

await website.crawl(onPageEvent);
await website.exportJsonlData("./storage/rsseau.jsonl");
console.log(website.getLinks());

import { Website } from "@spider-rs/spider-rs";

const website = new Website("https://rsseau.fr")
  .withBudget({
    "*": 20,
    "/docs": 10,
  })
  // you can use regex or string matches to ignore paths
  .withBlacklistUrl(["/resume"])
  .build();

await website.scrape();
console.log(website.getPages());

import { Website } from "@spider-rs/spider-rs";

const website = new Website("https://rsseau.fr");

const onPageEvent = (_err, page) => {
  console.log(page);
};

await website.crawl(onPageEvent, true);
// runs immediately

import { Website } from "@spider-rs/spider-rs";

const website = new Website("https://rsseau.fr").withChromeIntercept(
  true,
  true,
);

const onPageEvent = (_err, page) => {
  console.log(page);
};

// the third param determines headless chrome usage.
await website.crawl(onPageEvent, false, true);
console.log(website.getLinks());

import { Website } from "@spider-rs/spider-rs";

const website = new Website("https://choosealicense.com").withCron(
  "1/5 * * * * *",
);
// sleep function to test cron
const stopCron = (time: number, handle) => {
  return new Promise((resolve) => {
    setTimeout(() => {
      resolve(handle.stop());
    }, time);
  });
};

const links = [];

const onPageEvent = (err, value) => {
  links.push(value);
};

const handle = await website.runCron(onPageEvent);

// stop the cron in 4 seconds
await stopCron(4000, handle);

import { crawl } from "@spider-rs/spider-rs";

const { links, pages } = await crawl("https://rsseau.fr");
console.log(pages);