Last active
November 19, 2021 06:31
-
-
Save BytefishMedium/43100f3052dfdc41450224ee0eabcccf to your computer and use it in GitHub Desktop.
For details: https://medium.com/p/e6975491d8c0
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
var followers = []; | |
var totalFollowers = getTotalFollowers() | |
console.log(`You have ${totalFollowers} follower, crawler start now.`) | |
var timer = setInterval(() => { | |
let liElements = document.querySelectorAll("ul > li");; | |
let isEnding = followers.length + liElements.length == totalFollowers; | |
if (isEnding) { | |
for (let index = 0; index < liElements.length; index++) { | |
let follower = parseDataFromLiElement(liElements[index]); | |
followers.push(follower); | |
} | |
console.log("-- crawling over --"); | |
let result = count(followers) | |
console.log(count(followers)) | |
alert(count(followers)) | |
clearInterval(timer); | |
return; | |
} | |
// scroll down the webpage | |
window.scrollTo(0, document.body.scrollHeight); | |
if (liElements.length > 80) { | |
// parse first 50 | |
for (let index = 0; index < 50; index++) { | |
let follower = parseDataFromLiElement(liElements[index]); | |
// console.log('follower: ', follower) | |
followers.push(follower); | |
} | |
console.log(`The crawler have crawled ${followers.length} followers.`) | |
console.log(count(followers)) | |
// delete some element to reduce memory usage | |
for (let index = 0; index < 50; index++) { | |
liElements[index].remove(); | |
} | |
} | |
}, 100); | |
// parse data from li elements | |
function parseDataFromLiElement(li) { | |
return { | |
name: li.querySelector("h2").textContent, | |
url: li.querySelector("a").href, | |
isMembership: li.querySelector("svg") != null, | |
description: li.querySelector("p")?.textContent, | |
}; | |
} | |
function getTotalFollowers() { | |
let totalFollowersElement = document.querySelector("h2"); | |
let numberString = totalFollowersElement.innerText.split(" ")[0]; | |
return parseInt(numberString.split(",").join("")); | |
} | |
function count(followers){ | |
let membersCount = followers.filter((item) => item.isMembership).length; | |
let percentage = (membersCount / followers.length).toFixed(4) | |
return `total followers: ${followers.length}, total membership: ${membersCount}, percent: ${percentage * 100}%` | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment