一個簡單的puppeteer例子

作用是抓取掌閱書城裏男頻女頻各分類的已完結書籍信息。
前面的pids和cids這兩個常數數組都是事先在頁面上查看超鏈接收集的。
這個頁面沒有任何反爬措施，適合作爲簡單例子。

const fs = require("fs")
const puppeteer = require('puppeteer');

const url = "http://www.ireader.com/index.php?ca=booksort.index&pca=booksort.index&pid=$pid&order=score&status=3&cid=$cid&page=$page"
const pids = [10, 68]; // 男頻，女頻
const cids = [[11, 27, 19, 22, 16, 39, 42, 50, 54, 57, 60], [69, 74, 82, 86, 89, 90, 91, 723]]; // 頻道中的分類ID

(async () => {
    const browser = await puppeteer.launch({
        // headless: false, 
        ignoreDefaultArgs: ["--enable-automation"], 
    });
    const page = await browser.newPage();
    const f = () => {
        return Array.from($('.bookMation')).map(e => {
            const id = $('h3 a', e).attr('href').match(/bid=(\d+)/)[1]
            const title = $('h3 a', e).text()
            const author = $('p.tryread', e).text().replace('試讀', '').trim()
            const desc = $('p.introduce', e).text()
            return {id, title, author, desc}
        })
    }
    let result = [];
    for (const i in pids) {
        const pid = pids[i]
        for (cid of cids[i]) {
            for (let pg = 1; pg < 4; pg++) { // 只抓前三頁
                const u = url.replace("$cid", cid).replace("$pid", pid).replace("$page", pg)
                await page.goto(u);
                const res = await page.evaluate("(" + f + ")()")
                res.forEach(e => { e.cid = cid; e.pid = pid })
                result = result.concat(res)
                console.log("page " + pg + " done")
            }
            console.log("cid " + cid + " done")
        }
        console.log("pid " + pid + " done")
    }
    fs.writeFileSync("d:/tmp/ireader_hot.json", JSON.stringify(result), {encoding: "utf-8"})
    console.log("all done")
      await browser.close();
})();