Web Scraping Table data from HTML file. / Sumant Pattanaik

Sumant Pattanaik

Workspace

Published

Edited

Mar 24, 2021

Importers

4 stars

Table(tableData)

tableData = getTableData(data[0])

getTableData = (data, start = 1) => {

const d = tableToJson(data, start);

const t = d.slice(1);

const columns = d[0];

return t.map(d =>

columns.reduce((acc, e, i) => {

acc[e] = d[i];

return acc;

}, {})

);

}

function tableToJson(table,start=1) {

//Code from : https://stackoverflow.com/questions/9927126/how-to-convert-the-following-table-to-json-with-javascript

var data = [];

for (var i = start; i < table.rows.length; i++) {

var tableRow = table.rows[i];

var rowData = [];

for (var j = 0; j < tableRow.cells.length; j++) {

rowData.push(tableRow.cells[j].innerHTML);

}

data.push(rowData);

}

return data;

}

data = scrapeTableData("https://www.cdc.gov/asthma/mmsa/table_2017.html")

async function scrapeTableData(url) {

const response = await soFetch(url);

const text = await response.text();

//const domparser = new DOMParser();

//const dom = domparser.parseFromString(text, "text/html");

const dom = html`${text}`;

const tables = await dom.querySelectorAll('table');

if (tables.length <= 0) {

throw new Error('Could not find any tables.');

}

const tablesLen = tables.length;

const tablesData = [];

for (let i = 0; i < tablesLen; i++) {

let tableEl = tables[i];

tablesData.push(tableEl);

}

return tablesData;

}

Table(getTableData(scrapedPandemicData[0], 0))

scrapedPandemicData = scrapeTableData(

"https://www.visualcapitalist.com/history-of-pandemics-deadliest/"

)

md`### External Libraries and Imports`

import {Table} from "@observablehq/table"

import { soFetch } from '@alecglassford/so-fetch'

d3 = require("d3@6")

One platform to build and deploy the best data apps

Experiment and prototype by building visualizations in live JavaScript notebooks. Collaborate with your team and decide which concepts to build out.

Use Observable Framework to build data apps locally. Use data loaders to build in any language or library, including Python, SQL, and R.

Seamlessly deploy to Observable. Test before you ship, use automatic deploy-on-commit, and ensure your projects are always up-to-date.

Learn more