Created
March 17, 2025 19:46
-
-
Save skeptrunedev/175dd4bde4a1c2babd3dc739aee39040 to your computer and use it in GitHub Desktop.
ingest-amplify-voice-to-trieve.ts
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
import { Window } from "happy-dom"; | |
import { TrieveSDK, type ChunkReqPayload } from "trieve-ts-sdk"; | |
const trieve = new TrieveSDK({ | |
datasetId: process.env.TRIEVE_DATASET_ID, | |
apiKey: process.env.TRIEVE_API_KEY ?? "", | |
}); | |
const fetchPageOfPosts = async ({ page }: { page: number }) => { | |
const htmlPageResp = await fetch( | |
`https://www.skool.com/amplify-voice-ai?p=${page}`, | |
{ | |
headers: { | |
accept: | |
"text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8", | |
"accept-language": "en-US,en;q=0.7", | |
"cache-control": "no-cache", | |
pragma: "no-cache", | |
priority: "u=0, i", | |
"sec-ch-ua": | |
'"Not(A:Brand";v="99", "Brave";v="133", "Chromium";v="133"', | |
"sec-ch-ua-mobile": "?0", | |
"sec-ch-ua-platform": '"Linux"', | |
"sec-fetch-dest": "document", | |
"sec-fetch-mode": "navigate", | |
"sec-fetch-site": "same-origin", | |
"sec-fetch-user": "?1", | |
"sec-gpc": "1", | |
"upgrade-insecure-requests": "1", | |
}, | |
body: null, | |
method: "GET", | |
} | |
); | |
const html = await htmlPageResp.text(); | |
const window = new Window({ | |
settings: { | |
disableJavaScriptEvaluation: true, | |
disableJavaScriptFileLoading: true, | |
}, | |
}); | |
const document = window.document; | |
document.body.innerHTML = html; | |
const NEXT_DATA = document.querySelector("#__NEXT_DATA__"); | |
const pageProps = JSON.parse(NEXT_DATA?.innerHTML || "{}").props.pageProps; | |
const chunkReqPayloads: ChunkReqPayload[] = []; | |
for (const postObj of pageProps.postTrees) { | |
const curPost = postObj.post; | |
const image_urls = []; | |
if (curPost.metadata.imagePreview) { | |
image_urls.push(curPost.metadata.imagePreview); | |
} | |
const reqPayload: ChunkReqPayload = { | |
tracking_id: curPost.id, | |
link: `https://www.skool.com/amplify-voice-ai/${curPost.name}`, | |
num_value: Number(curPost.metadata.upvotes), | |
time_stamp: curPost.createdAt, | |
chunk_html: `<div> | |
<h1>${curPost.metadata.title}</h1> | |
<p>${curPost.metadata.content}</p> | |
<p>By ${curPost.user.firstName} ${curPost.user.lastName}</p> | |
</div> | |
`, | |
image_urls, | |
upsert_by_tracking_id: true, | |
metadata: curPost, | |
}; | |
chunkReqPayloads.push(reqPayload); | |
} | |
await trieve.createChunk(chunkReqPayloads); | |
console.log(`Queued ${chunkReqPayloads.length} chunks for page ${page}`); | |
return !!chunkReqPayloads.length; | |
}; | |
let page = 1; | |
while (true) { | |
const hasNext = await fetchPageOfPosts({ page }); | |
if (!hasNext) { | |
break; | |
} | |
page++; | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment