Created
December 21, 2021 23:28
-
-
Save Brlaney/8161e86e229acc2bd63312480716ab48 to your computer and use it in GitHub Desktop.
A simple script that saves all rows of data for a specified page number. This endpoint contains 130 pages as of 12/21/2021.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
const cheerio = require('cheerio'); | |
const axios = require('axios'); | |
const fs = require('fs'); | |
async function obtainData(num) { | |
const endpoint = 'https://www.tbpr.org/news-publications/recent-disciplinary-actions?page=' + num; | |
const file = 'data/pg' + num + '.json'; | |
await axios.get(endpoint).then(urlResponse => { | |
const $ = cheerio.load(urlResponse.data); | |
let data = []; | |
$('.table tr').each(function (i, elem) { | |
data[i-1] = { | |
date: $(elem).find('td:nth-child(1)').text().trim(), | |
title: $(elem).find('td:nth-child(3)').text().trim(), | |
link: $(elem).find('td:nth-child(3) > a').attr('href'), | |
bpr: $(elem).find('td:nth-child(4)').text().trim(), | |
attorney: $(elem).find('td:nth-child(5)').text().trim(), | |
} | |
}); | |
// Output a json file containing the data obtained | |
fs.writeFile(file, | |
JSON.stringify(data, null, 4), | |
() => console.log('File for pg number ' + num + ' successfully saved.')) | |
}) | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment