本文记录如何使用云函数实现微信公众号话题标签文章列表的抓取
# 实验准备
# 核心代码
需求是获取文章的标题、跳转链接、发布时间及文章配图的缩略图就可以了,具体代码如下。
'use strict';
const puppeteer = require('puppeteer')
exports.main = async (event, context) => {
const browser = await puppeteer.launch({
headless: true,
args: ['--no-sandbox', '--disable-setuid-sandbox'],
dumpio: false,
})
const page = await browser.newPage()
page.setUserAgent(
'Mozilla/5.0 (Linux; Android 10; Redmi K30 Pro Build/QKQ1.191117.002; wv) AppleWebKit/537.36 (KHTML, like Gecko) Version/4.0 Chrome/78.0.3904.62 XWEB/2581 MMWEBSDK/200801 Mobile Safari/537.36'
)
await page.goto('获取到的话题标签链接', {
waitUntil: 'networkidle0',
})
const articleInfo = await page.evaluate(() => {
const element = document.querySelector(".album__list");
let items = element.getElementsByClassName("album__list-item");
let title = [];
for (let i = 0; i < items.length; i++) {
let cover = items[i]
.getElementsByClassName("album__item-img")
.item(0)
.getAttribute("style").replace("background-image: url(", "");
cover = cover.substring(0, cover.length - 2);
title.push({
title: items[i].getAttribute("data-title"),
url: items[i].getAttribute("data-link"),
date: items[i].getElementsByClassName("album__item-info-item").item(0)
.innerHTML,
pic: cover,
});
}
return title;
});
await browser.close();
return articleInfo
};
# 访问示例地址
http://tcb.xuedingmiao.com/get_wx_articles (opens new window)