Last active
August 1, 2023 17:06
-
-
Save diragb/5a5cc95360d364ecfbacb03978fce1dd to your computer and use it in GitHub Desktop.
Quick scraper for Instagram profiles.
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 getInstagramHeaders = async () => { | |
const options = { | |
method: 'GET', | |
credentials: 'same-origin', | |
} | |
const response = await fetch('https://www.instagram.com/a.thousand.apologies/', options) | |
const parser = new DOMParser() | |
const html = await response.text() | |
const document = parser.parseFromString(html, 'text/html') | |
return { | |
...Object.fromEntries(response.headers.entries()), | |
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:104.0) 20100101 Firefox/103.0', | |
'Accept': '*/*', | |
'Accept-Language': 'en,en-US;q=0.3', | |
'X-Csrftoken': document.body.innerHTML.split('csrf_token')[1].split('\\"')[2], | |
'X-IG-App-ID': document.body.innerHTML.split('X-IG-App-ID')[1].split(',')[0].replaceAll('"', '').replace(':', ''), | |
'X-ASBD-ID': '198337', | |
'X-IG-WWW-Claim': '0', | |
'Origin': 'https://www.instagram.com', | |
'DNT': '1', | |
'Alt-Used': 'i.instagram.com', | |
'Connection': 'keep-alive', | |
'Referer': 'https://www.instagram.com/', | |
'Sec-Fetch-Dest': 'empty', | |
'Sec-Fetch-Mode': 'cors', | |
'Sec-Fetch-Site': 'same-site', | |
'Sec-GPC': '1', | |
} | |
} | |
// | |
const getInstagramProfile = async (username) => { | |
const fetchedHeaders = await getInstagramHeaders() | |
const headers = new Headers(fetchedHeaders); | |
const response = await fetch(`https://www.instagram.com/api/v1/users/web_profile_info/?username=${username}`, { | |
method: 'GET', | |
headers | |
}) | |
return await response.json() | |
} | |
const getInstagramPhotoIDs = async (username) => { | |
const profile = await getInstagramProfile(username) | |
const edges = profile.data.user.edge_owner_to_timeline_media.edges | |
const shortCodes = edges.map(edge => edge.node.shortcode) | |
return shortCodes | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment