Skip to content

Instantly share code, notes, and snippets.

@trylovetom
Last active November 26, 2023 05:17
Show Gist options
  • Save trylovetom/db3a1972bdf834727dd77d2cea89666e to your computer and use it in GitHub Desktop.
Save trylovetom/db3a1972bdf834727dd77d2cea89666e to your computer and use it in GitHub Desktop.
Parse HTML Table To JSON With Cheerio.
const text = `<table cellspacing=1 bordercolordark=#666666 cellpadding=0 width=100% align=center bgcolor=#D9D9D9 bordercolorlight=#ffffff border=0><tr class='chinese blue_t2'><td height=20>球队</td><td>球员</td><td>位置</td><td>原因</td><td>日期</td><td>备注</td></tr><tr bgcolor=#FFF0DF align=center><td height=20>波特兰拓荒者</td><td> 纽基</td><td>中锋</td><td>脚部</td><td>2019/03/26</td><td>赛季报销</td></tr><tr bgcolor=#FFF0DF align=center><td height=20>波特兰拓荒者</td><td> 麦高林</td><td>后卫</td><td>膝部</td><td>2019/03/17</td><td>预计缺阵</td></tr><tr bgcolor=#FFF0DF align=center><td height=20>芝加哥公牛</td><td> 赞达拿赫捷臣</td><td>前锋</td><td>膝部</td><td>2019/01/26</td><td>赛季报销</td></tr><tr bgcolor=#FFF0DF align=center><td height=20>芝加哥公牛</td><td> 奥图波达</td><td>前锋</td><td>肩部</td><td>2019/03/26</td><td>预计缺阵</td></tr><tr bgcolor=#FFF0DF align=center><td height=20>芝加哥公牛</td><td> 云度卡达</td><td>中锋</td><td>拇指</td><td>2019/01/16</td><td>预计缺阵</td></tr><tr bgcolor=#FFF0DF align=center><td height=20>芝加哥公牛</td><td> D.华伦天尼</td><td>前锋</td><td>足踝</td><td>2018/10/19</td><td>赛季报销</td></tr><tr bgcolor=#FFF0DF align=center><td height=20>芝加哥公牛</td><td> 查克拉维利</td><td>后卫</td><td>脚部</td><td>2019/03/26</td><td>预计缺阵</td></tr></table>`
console.log(tableToJSON(text, { useFirstRowForHeadings: true, headings: [ 'team', 'player', 'position', 'cause', 'date', 'note' ] }))
/**
* 在 node.js 中 轉換 html table 為 json 格式
* @param {String} html HTML Text
* @param {{ useFirstRowForHeadings: Boolean ,headings: [String] }} options 設定(userFirstRowForHeadings: 是否用第一行作為標題, headings: 可自行設定的標題)
* @return {[{ String: String }]} 回傳結果
*/
function tableToJSON (html, options = {}) {
const cheerio = require('cheerio')
const { useFirstRowForHeadings, headings = [] } = options
const trs = cheerio('table tr', html)
const rowCount = trs.length
const output = []
for (let rowIndex = 0; rowIndex < rowCount; rowIndex += 1) {
const children = trs[rowIndex].children
const colCount = children.length
const row = {}
for (let colIndex = 0; colIndex < colCount; colIndex += 1) {
const td = cheerio(children[colIndex])
if (rowIndex === 0 && useFirstRowForHeadings) {
headings.push(td.text())
} else {
row[headings[colIndex] || colIndex] = td.text()
}
}
if (!(rowIndex === 0 && useFirstRowForHeadings)) {
output.push(row)
}
}
return output
}
@bytemain
Copy link

here is a improved typescript version:

import { Cheerio, Element, load } from 'cheerio';

function tableToJSON(
  $: ReturnType<typeof load>,
  table: Cheerio<Element>,
  options: {
    useFirstRowForHeadings: boolean;
    headings: string[];
  },
) {
  const { useFirstRowForHeadings, headings = [] } = options;
  const trs = table.find('tr');
  const rowCount = trs.length;
  const output = [] as any[];

  for (let rowIndex = 0; rowIndex < rowCount; rowIndex += 1) {
    const tagName = rowIndex === 0 && useFirstRowForHeadings ? 'th' : 'td';
    const children = $(trs[rowIndex]).find(tagName);
    const colCount = children.length;
    const row = {};

    for (let colIndex = 0; colIndex < colCount; colIndex += 1) {
      const td = $(children[colIndex]);

      if (rowIndex === 0 && useFirstRowForHeadings) {
        headings.push(td.text());
      } else {
        row[headings[colIndex] || colIndex] = td.text();
      }
    }

    if (!(rowIndex === 0 && useFirstRowForHeadings)) {
      output.push(row);
    }
  }
  return output;
}


// usage
const $ = load(await fs.readFile(path.join(__dirname, 'fixtures', username, 'xxxx.html')));
const table = $('.xxx');
const json = tableToJSON($, table, { useFirstRowForHeadings: true, headings: [] });

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment