Last active
December 13, 2019 20:29
-
-
Save slaughtr/626e4066b344bbc42a0d5f8aabc9978a to your computer and use it in GitHub Desktop.
Twitter JS Scraper
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 fetch = require('node-fetch'); | |
const cheerio = require('cheerio'); | |
const getTweets = async username => { | |
const req = await fetch(`https://twitter.com/${username}`); | |
const page = await req.text(); | |
const $ = cheerio.load(page, {xmlMode: true}); | |
const actualTweets = []; | |
const tweetHTML = $('.tweet-text').toArray(); | |
// TODO: this could be a reduce | |
tweetHTML.forEach(x => { | |
const tweet = []; | |
if (x.type === 'tag' && x.name === 'p') { | |
if (x.children) { | |
x.children.forEach(child => { | |
if (child.type === 'text' && child.data) { | |
const trimmed = child.data.trim(); | |
if (trimmed) { | |
tweet.push(child.data); | |
// TODO: something with newlines? | |
if (trimmed.includes('\n')) null; | |
} | |
} | |
if (child.type === 'tag' && child.name === 'a') { | |
if (child.attribs.href && child.attribs.href.includes('hashtag')) { | |
const realHashTag = child.attribs.href.slice(9).split('?')[0]; | |
tweet.push(`#${realHashTag}`); | |
} else if (child.attribs.href && child.attribs['data-mentioned-user-id']) { | |
tweet.push(child.attribs.href.replace('/', '@')); | |
} | |
} | |
}); | |
} | |
} | |
if (tweet && tweet.length) actualTweets.push(tweet.join(' ')); | |
}); | |
console.log(actualTweets); | |
}; | |
getTweets('iamdevloper').then(res => res); |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment