Node.js爬虫 CheerioJS ‌轻量级解析、操作和渲染HTML及XML文档

发布于:2025-06-23 ⋅ 阅读:(21) ⋅ 点赞:(0)

简介

‌ CheerioJS ‌ 是一个专为 Node.js 设计的轻量级库,用于解析、操作和渲染 HTML 及 XML 文档,语法类似 Jquery。

安装

npm install cheerio

示例

const cheerio = require("cheerio");

const html = `
<html>
  <head>
    <title>Example</title>
  </head>
  <body>
    <h1>Hello, world!</h1>
  </body>
</html>
`;

const $ = cheerio.load(html);

console.log($("h1").text()); // 输出: Hello, world!

加载文档

load

解析 HTML 或 XML 文档的最基本方式

import * as cheerio from "cheerio";

const html = `
<html>
  <head>
    <title>Example</title>
  </head>
  <body>
    <div class="container">
      <div class="item">React.js</div>
      <div class="item">Vue.js</div>
      <div class="item">Angular.js</div>
    </div>
  </body>
</html>
`;

const $ = cheerio.load(html);
console.log(111, $("div.container .item:first-child").text()); // 输出: React.js

loadBuffer

解析存储文档内容的 buffer 类型数据结构

import * as cheerio from "cheerio";
import * as fs from "fs";

const buffer = fs.readFileSync("document.html");
const $ = cheerio.loadBuffer(buffer);
console.log(111, $("div.container .item:first-child").text()); // 输出: React.js

fromURL

从 URL 加载文档

import * as cheerio from "cheerio";

const $ = await cheerio.fromURL("https://example.com");

选择元素

Cheerio 允许用户使用 CSS 选择器 从文档中选择元素。方法语法与 jquery 基本一样。

$("p"); // 选择所有 <p> 元素
$("p.item"); // 选择所有 class 为 item 的 <p> 元素
$("p.item:first-child"); // 选择第一个 class 为 item 的 <p> 元素
$("p.item:last-child"); // 选择最后一个 class 为 item 的 <p> 元素
$(".selected"); // 选择所有 class 为 selected 的元素
$("[data-selected=true]"); // 选择所有 data-selected 属性为 true 的元素
$('[xml\\:id="main"'); // 选择所有 xml:id 属性为 main 的元素
$("p.selected"); // 选择所有 class 为 selected 的 <p> 元素
$("div p"); // 选择所有 <div> 元素中的 <p> 元素
$("div > p"); // 选择所有直接子元素为 <p> 的 <div> 元素
$('p:contains("hello")'); // 选择所有包含 "hello" 文字的 <p> 元素

find 查找元素

import * as cheerio from "cheerio";

const html = `
<html>
  <head>
    <title>Example</title>
  </head>
  <body>
    <div class="container">
      <div class="item">React.js</div>
      <div class="item">Vue.js</div>
      <div class="item">Angular.js</div>
    </div>
  </body>
</html>
`;

const $ = cheerio.load(html);
const items = $(".container").find(".item");
items.each((index, element) => {
  console.log($(element).text());
});

children 查找子元素

import * as cheerio from "cheerio";

const html = `
<html>
  <head>
    <title>Example</title>
  </head>
  <body>
    <div class="container">
      <div class="item">React.js</div>
      <div class="item">Vue.js</div>
      <div class="item">Angular.js</div>
    </div>
  </body>
</html>
`;

const $ = cheerio.load(html);
const items = $(".container").children(".item");
items.each((index, element) => {
  console.log($(element).text());
});

find vs children 区别

  • find 方法会递归查找所有符合条件的元素,包括子元素、子元素的子元素等。
  • children 方法只会查找直接子元素,不会查找子元素的子元素。

contents 查找所有子节点

所有子元素,包括文本和注释节点。

import * as cheerio from "cheerio";

const html = `
    <div class="container">
      <div class="item">1</div>
      <div class="item">2</div>
      <div class="item">3</div>
    </div>
    `;
const $ = cheerio.load(html);
const items = $(".container").contents();
console.log(items.length); // 输出: 7

parent 查找父元素

import * as cheerio from "cheerio";

const html = `
    <div class="container">
      <div class="item">1</div>
      <div class="item">2</div>
      <div class="item">3</div>
    </div>
    `;
const $ = cheerio.load(html);
const parent = $(".item").parent();
console.log(parent.prop("class")); // 输出: container

parents 查找所有父元素

import * as cheerio from "cheerio";

const html = `
    <div class="container">
      <div class="item">1</div>
      <div class="item">2</div>
      <div class="item">3</div>
    </div>
    `;
const $ = cheerio.load(html);
const parents = $(".item").parents();
parents.each((index, element) => {
  console.log($(element).prop("tagName"));
});
// 输出:DIV、BODY、HTML

parentsUntil 查找父元素直到指定元素

import * as cheerio from "cheerio";

const html = `
    <div class="container">
      <div class="item">1</div>
      <div class="item">2</div>
      <div class="item">3</div>
    </div>
    `;
const $ = cheerio.load(html);
const parents = $(".item").parentsUntil("body");
parents.each((index, element) => {
  console.log($(element).prop("tagName"));
});

closest 查找最近的父元素

import * as cheerio from "cheerio";

const html = `
    <div class="container">
      <div class="item">1</div>
      <div class="item">2</div>
      <div class="item">3</div>
    </div>
    `;
const $ = cheerio.load(html);
const result = $(".item").closest(".container");
console.log(result.prop("class")); // 输出: container

next, prev 查找下一个或上一个兄弟元素

import * as cheerio from "cheerio";

const html = `
    <div class="container">
      <div class="item">1</div>
      <div class="item">2</div>
      <div class="item">3</div>
    </div>
    `;
const $ = cheerio.load(html);

const next = $(".item:first-child").next();
console.log(next.text()); // 输出: 2

const prev = $(".item:last-child").prev();
console.log(prev.text()); // 输出: 3

nextAll, prevAll 查找所有下一个或上一个兄弟元素

import * as cheerio from "cheerio";

const html = `
    <div class="container">
      <div class="item">1</div>
      <div class="item">2</div>
      <div class="item">3</div>
    </div>
    `;
const $ = cheerio.load(html);

const nextAll = $(".item:first-child").nextAll();
nextAll.each((index, element) => {
  console.log($(element).text());
});
// 输出: 2、3

const prevAll = $(".item:last-child").prevAll();
prevAll.each((index, element) => {
  console.log($(element).text());
});
// 输出: 1、2

siblings 查找所有兄弟元素

import * as cheerio from "cheerio";

const html = `
    <div class="container">
      <div class="item">1</div>
      <div class="item">2</div>
      <div class="item">3</div>
    </div>
    `;
const $ = cheerio.load(html);

const siblings = $(".item:first-child").siblings(); // 输出: 2、3

nextUntil, prevUntil 查找下一个或上一个兄弟元素直到指定元素

import * as cheerio from "cheerio";

const html = `
    <div class="container">
      <div class="item">1</div>
      <div class="item">2</div>
      <div class="item">3</div>
    </div>
    `;
const $ = cheerio.load(html);

const nextUntil = $(".item:first-child").nextUntil(".item:last-child");
nextUntil.each((index, element) => {
  console.log($(element).text());
});
// 输出: 2

const prevUntil = $(".item:last-child").prevUntil(".item:first-child");
prevUntil.each((index, element) => {
  console.log($(element).text()
})
// 输出: 3

eq 查找指定索引的元素

import * as cheerio from "cheerio";

const html = `
    <div class="container">
      <div class="item">1</div>
      <div class="item">2</div>
      <div class="item">3</div>
    </div>
    `;
const $ = cheerio.load(html);

const result = $(".item").eq(1);
console.log(result.text()); // 输出: 2

filter 查找符合条件的元素

import * as cheerio from "cheerio";

const html = `
    <div class="container">
      <div class="item">1</div>
      <div class="item book">2</div>
      <div class="item">3</div>
    </div>
    `;
const $ = cheerio.load(html);
const result = $(".item").filter(".book");
console.log(result.text()); // 输出: 2

not 查找不符合条件的元素

import * as cheerio from "cheerio";

const html = `
    <div class="container">
      <div class="item">1</div>
      <div class="item book">2</div>
      <div class="item">3</div>
    </div>
    `;
const $ = cheerio.load(html);

const result = $(".item").not(".book");
result.each((index, element) => {
  console.log($(element).text());
});
// 输出: 1、3

has 查找包含指定子元素的元素

import * as cheerio from "cheerio";

const html = `
    <div class="container">
      <div class="item">1</div>
      <div class="item book">
        <b>2</b>
      </div>
      <div class="item">3</div>
    </div>
    `;
const $ = cheerio.load(html);

const result = $(".item").has("b");
console.log(result.length); // 输出: 1

first, last 查找第一个或最后一个元素

import * as cheerio from "cheerio";

const html = `
    <div class="container">
      <div class="item">1</div>
      <div class="item">2</div>
      <div class="item">3</div>
    </div>
    `;
const $ = cheerio.load(html);

const first = $(".item").first();
console.log(first.text()); // 输出: 1

const last = $(".item").last();
console.log(last.text()); // 输出: 3

操作元素

attr 获取或设置属性

import * as cheerio from "cheerio";

const html = `
    <div class="container">
      <div class="item">1</div>
      <div class="item">2</div>
      <div class="item">3</div>
    </div>
    `;
const $ = cheerio.load(html);
const result = $(".item").attr("class");
console.log(result); // 输出: item

$(".img").attr("src", "imgUrl");
console.log($(".img").attr("src")); // 输出: imgUrl

class 属性

$("div").addClass("new-class");
$("div").removeClass("old-class");
$("div").toggleClass("toggle-class");

text 获取或设置文本内容

$("div").text("new text");
console.log($("div").text()); // 输出: new text

html 获取或设置 HTML 内容

$("div").html("<p>new html</p>");
console.log($("div").html()); // 输出: <p>new html</p>

append, prepend 在元素内部追加或前置内容

$(".item").append("<p>append content</p>");
$(".item").prepend("<p>prepend content</p>");

after, before 在元素外部追加或前置内容

$(".item").after("<p>after content</p>");
$(".item").before("<p>before content</p>");

insertAfter, insertBefore 在元素外部追加或前置内容

$("<p>insertAfter content</p>").insertAfter("item");
$("<p>insertBefore content</p>").insertBefore("item");

prependTo, appendTo 在元素内部追加或前置内容

$("<p>prependTo content</p").prependTo(".item");
$("<p>appendTo content</p").appendTo(".item");

wrap, wrapInner 在元素外部包裹内容

$("div").wrap("<div class='wrapper'></div>");
$("div").wrapInner("<div class='wrapper'></div>");

unwrap 移除包裹的元素

$("div").unwrap();

replaceWith 替换元素

$("div").replaceWith("<p>new content</p>");

empty 清空元素内容

$("div").empty();

remove 移除元素

$("div").remove();

更多用法

extract

import * as cheerio from "cheerio";

const html = `
    <div class="container">
      <div class="item">1</div>
      <div class="item book">
        <b>2</b>
      </div>
      <div class="item">3</div>
    </div>
    `;
const $ = cheerio.load(html);
const data = $.extract({
  book: ".book",
});
console.log(data); // 输出: {"book": "\n        2\n      "}

Configuring 配置

类型 默认值 描述
scriptingEnabled false 是否启用脚本
xmlMode true 启用 htmlparser2 的 XML 模式
decodeEntities true 解码 HTML 实体。
withStartIndices false 为节点添加一个startIndex属性
withEndIndices false 为节点添加一个endIndex属性

Extending 扩展

自定义选择器

const html = `
    <div class="container">
      <div class="item">1</div>
      <div class="item book">
        <b>2</b>
      </div>
      <div class="item">3</div>
    </div>
    `;

const $ = cheerio.load(html, {
  pseudos: {
    book: "div.book",
  },
});
console.log($(":book").text()); // 2

自定义方法

import * as cheerio from "cheerio";

const html = `
    <div class="container">
      <div class="item">1</div>
      <div class="item book">
        <b>2</b>
      </div>
      <div class="item">3</div>
    </div>
    `;

const $ = cheerio.load(html);
$.prototype.myFunction = function () {
  return "Hello, World!";
};

console.log($(".container").myFunction()); // 输出: Hello, World!

 更多用法


网站公告

今日签到

点亮在社区的每一天
去签到