Created
August 24, 2024 10:05
-
-
Save YuryScript/e19974d46f0f3b2250de9b5d9b410c76 to your computer and use it in GitHub Desktop.
This file contains hidden or 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
| // twitter.com | x.com member user list scapper | |
| let tweets = []; // Initialize an empty array to hold all tweet elements | |
| const scrollInterval = 2000; | |
| const scrollStep = 5000; // Pixels to scroll on each step | |
| let previousTweetCount = 0; | |
| let unchangedCount = 0; | |
| const scrollToEndIntervalID = setInterval(() => { | |
| document.querySelector('[data-viewportview="true"]').scrollBy(0, scrollStep); | |
| const currentTweetCount = tweets.length; | |
| if (currentTweetCount === previousTweetCount) { | |
| unchangedCount++; | |
| if (unchangedCount >= 2) { // Stop if the count has not changed 5 times | |
| console.log('Scraping complete'); | |
| console.log('Total tweets scraped: ', tweets.length); | |
| console.log('Downloading tweets as JSON...'); | |
| clearInterval(scrollToEndIntervalID); // Stop scrolling | |
| observer.disconnect(); // Stop observing DOM changes | |
| downloadTweetsAsJson(tweets); // Download the tweets list as a JSON file | |
| } | |
| } else { | |
| unchangedCount = 0; // Reset counter if new tweets were added | |
| } | |
| previousTweetCount = currentTweetCount; // Update previous count for the next check | |
| }, scrollInterval); | |
| function updateTweets() { | |
| document.querySelectorAll('.css-175oi2r .r-1wbh5a2 .r-dnmrzs .r-1ny4l3l .r-1loqt21').forEach(tweet => { | |
| const text = tweet.innerText; // Extract text content | |
| const href = tweet.href; | |
| if (!tweets.includes(href)) { // Check if the tweet's text is not already in the array | |
| tweets.push(href); // Add new tweet's text to the array | |
| console.log("tweets scraped: ", tweets.length) | |
| } | |
| }); | |
| } | |
| // Initially populate the tweets array | |
| updateTweets(); | |
| // Create a MutationObserver to observe changes in the DOM | |
| const observer = new MutationObserver(mutations => { | |
| mutations.forEach(mutation => { | |
| if (mutation.addedNodes.length) { | |
| updateTweets(); // Call updateTweets whenever new nodes are added to the DOM | |
| } | |
| }); | |
| }); | |
| // Start observing the document body for child list changes | |
| observer.observe(document.body, { childList: true, subtree: true }); | |
| function downloadTweetsAsJson(tweetsArray) { | |
| const jsonData = JSON.stringify(tweetsArray); // Convert the array to JSON | |
| const blob = new Blob([jsonData], { type: 'application/json' }); | |
| const url = URL.createObjectURL(blob); | |
| const link = document.createElement('a'); | |
| link.href = url; | |
| link.download = 'tweets.json'; // Specify the file name | |
| document.body.appendChild(link); // Append the link to the document | |
| link.click(); // Programmatically click the link to trigger the download | |
| document.body.removeChild(link); // Clean up and remove the link | |
| } |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment