Node.js使用cheerio解析html

原创

彭世瑜 2021-07-12 10:22:42 ©著作权

©著作权归作者所有：来自51CTO博客作者彭世瑜的原创作品，请联系作者获取转载授权，否则将追究法律责任

cheerio语法类似jQuery

doc

doc-zh: https://github.com/cheeriojs/cheerio/wiki/Chinese-README

安装

npm i cheerio

代码实例


const cheerio = require("cheerio");

const doc = cheerio.load('<h2 class="title">Hello world</h2>', {
  xmlMode: true,
  decodeEntities: false
});

doc("h2.title").text("Hello there!");
doc("h2").addClass("welcome");

console.log(doc.xml());
// <h2 class="title welcome">Hello there!</h2>

项目实战

import cheerio from "cheerio";

/**
 *  将外链图片转为本站连接
 * @param {*} html
 * @returns
 */
export async function replaceImage(html) {

  const doc = cheerio.load(html, {
    xmlMode: true,
    decodeEntities: false
  });

  let elems = [];

  // each不等待promise
  doc("img").each(function(index, elem) {
    elems.push(doc(this));
  });

  for (let elem of elems) {
    let src = elem.attr("src");

    if (src && src.indexOf(process.env.VUE_APP_BASE_URL) == -1) {
      // 修改为自己的替换方法
      let imageSrc = await saveImage(src);

      if (imageSrc) {
        elem.attr("src", imageSrc);
      }
    }
  }

  return doc.xml();
}

/**
 *  提取图片连接
 * @param {*} html
 * @returns
 */
export function extractImages(html) {

  const doc = cheerio.load(html, {
    xmlMode: true,
    decodeEntities: false
  });

  let images = [];

  doc("img").each(function(index, elem) {
    let src = doc(this).attr("src");
    if (src) {
      images.push(src);
    }
  });

  return images;
}