Created
September 21, 2022 16:28
-
-
Save ataki/c10f367d6607d1d84e7eda562a123710 to your computer and use it in GitHub Desktop.
Scrapes TikTok results for a certain hashtag. Paste into chrome console
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
let seen = new Set() | |
async function getBioLink(row) { | |
try { | |
const { signature, uniqueId } = row | |
const secUid = row.secUid | |
const url = `https://us.tiktok.com/api/user/detail/?aid=1988&app_language=en&app_name=tiktok_web&battery_info=1&browser_language=en-US&browser_name=Mozilla&browser_online=true&browser_platform=MacIntel&browser_version=5.0%20%28Macintosh%3B%20Intel%20Mac%20OS%20X%2010_15_7%29%20AppleWebKit%2F537.36%20%28KHTML%2C%20like%20Gecko%29%20Chrome%2F105.0.0.0%20Safari%2F537.36&channel=tiktok_web&cookie_enabled=true&device_id=7137341942917350955&device_platform=web_pc&focus_state=true&from_page=user&history_len=2&is_fullscreen=false&is_page_visible=true&language=en&os=mac&priority_region=US&referer=®ion=US&screen_height=1440&screen_width=2560&secUid=${secUid}&tz_name=America%2FNew_York&uniqueId=${uniqueId}&webcast_language=en&msToken=J9m3_eBf4GKuBDGa063BDCsjVBzMBmcFqJvEGf0M62WHW9yPzXAHzcFhc8-X5-DLAkVoNH7CKKi-Jkp1Kb7ua75MV6btEfjcZPAbhZJKirSwPlP_CTcRrSMHocUTnU4=&X-Bogus=DFSzswjOWETANyuDSse9PcYEO920&_signature=${signature}` | |
console.log(url) | |
const res = await fetch(url) | |
// const userData: { userInfo?: { user?: { bioLink?: { link?: string } } } } = await res.json() | |
const userData = await res.json() | |
return userData?.userInfo?.user?.bioLink?.link || '' | |
} catch (e) { | |
return '' | |
} | |
} | |
// CHANGE THIS | |
let kw = `%23fintok` | |
let offset = 0 | |
let base = "https://us.tiktok.com/api/search/general/full" | |
let cumulativeDataAsRows = [] | |
while (true) { | |
let url = `${base}/?aid=1988&app_language=en&app_name=tiktok_web&battery_info=1&browser_language=en-US&browser_name=Mozilla&browser_online=true&browser_platform=MacIntel&browser_version=5.0%20%28Macintosh%3B%20Intel%20Mac%20OS%20X%2010_15_7%29%20AppleWebKit%2F537.36%20%28KHTML%2C%20like%20Gecko%29%20Chrome%2F105.0.0.0%20Safari%2F537.36&channel=tiktok_web&cookie_enabled=true&device_id=7137341942917350955&device_platform=web_pc&focus_state=true&from_page=search&history_len=3&is_fullscreen=false&is_page_visible=true&keyword=${kw}&offset=${offset}&os=mac&priority_region=US&referer=®ion=US&screen_height=1440&screen_width=2560&tz_name=America%2FNew_York&verifyFp=verify_l87zdu3e_nNaNTe9g_D9vP_4RCK_A5cT_pgAfD4S7NYIG&webcast_language=en&msToken=fUMZm-eMlonGgkjPrjICpJQb92Ga0-LWGWh8ekEP_qpSzIdDyg0UerAT61T0Te1a1ZanpHSLLCupEgTdGIXVVGms7P61eeirsuRx8_8itZNnYtJdWgP_brrZIjUNoUc=&X-Bogus=DFSzswjL0NJANyxRSsayYkzpc1rT&_signature=_02B4Z6wo00001M81y4wAAIDD1EnMjOQHBBjPNccAAFDse5` | |
let res = await fetch(url, { | |
"headers": { | |
"accept": "*/*", | |
"accept-language": "en-US,en;q=0.9", | |
"sec-fetch-dest": "empty", | |
"sec-fetch-mode": "cors", | |
"sec-fetch-site": "same-site", | |
"sec-gpc": "1" | |
}, | |
"referrer": "https://www.tiktok.com/", | |
"referrerPolicy": "strict-origin-when-cross-origin", | |
"body": null, | |
"method": "GET", | |
"mode": "cors", | |
"credentials": "include" | |
}); | |
const rowToCsv = (row) => { | |
return [row.url, row.link].join(',') | |
} | |
const parseBio = (desc) => { | |
// linktree | |
if (desc.includes("linktr.ee")) { | |
const match = desc.match(/linktr.ee\/(.*)/) | |
if (match && match.length > 0) return match[0] | |
} | |
// beacons | |
if (desc.includes("linktr.ee")) { | |
const match = desc.match(/beacons.ai\/(.*)/) | |
if (match && match.length > 0) return match[0] | |
} | |
// hoo.be | |
if (desc.includes("hoo.be")) { | |
const match = desc.match(/hoo.be\/(.*)/) | |
if (match && match.length > 0) return match[0] | |
} | |
return '' | |
} | |
let payload = await res.json() | |
if (payload.data.length === 0) { | |
break | |
} | |
let _dataAsRows = await Promise.all(payload.data.map(async (item) => { | |
if (!item.item) { | |
return '' | |
} | |
const key = item.item.author.uniqueId | |
if (seen.has(key)) return '' | |
seen.add(key) | |
const row = { | |
url: `https://www.tiktok.com/@${item.item.author.uniqueId}`, | |
link: parseBio(item.item.author.signature) || await getBioLink(item.item.author) | |
} | |
return rowToCsv(row) | |
})) | |
let dataAsRows = _dataAsRows.filter((row) => row !== null) | |
cumulativeDataAsRows = cumulativeDataAsRows.concat(dataAsRows) | |
offset += 1 | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment