add scraper

This commit is contained in:
Seth Trowbridge 2026-01-17 10:11:34 -05:00
commit e1875058fc
2 changed files with 119 additions and 0 deletions

8
deno.json Normal file
View File

@ -0,0 +1,8 @@
{
"tasks": {
"scrape": "deno run --watch scraper.ts"
},
"imports": {
"@std/assert": "jsr:@std/assert@1"
}
}

111
scraper.ts Normal file
View File

@ -0,0 +1,111 @@
#!/usr/bin/env -S deno run --allow-net
// ------------------------------------------------------------
// Utility: simple linear regression
// ------------------------------------------------------------
function linearRegression(xs: number[], ys: number[]) {
const n = xs.length;
const meanX = xs.reduce((a, b) => a + b, 0) / n;
const meanY = ys.reduce((a, b) => a + b, 0) / n;
let num = 0;
let den = 0;
for (let i = 0; i < n; i++) {
num += (xs[i] - meanX) * (ys[i] - meanY);
den += (xs[i] - meanX) ** 2;
}
const slope = num / den;
const intercept = meanY - slope * meanX;
// Compute R²
let ssTot = 0;
let ssRes = 0;
for (let i = 0; i < n; i++) {
const yPred = slope * xs[i] + intercept;
ssTot += (ys[i] - meanY) ** 2;
ssRes += (ys[i] - yPred) ** 2;
}
const r2 = 1 - ssRes / ssTot;
return { slope, intercept, r2 };
}
// ------------------------------------------------------------
// Fetch S&P 500 constituents
// ------------------------------------------------------------
async function fetchSP500Tickers(): Promise<string[]> {
const url =
"https://datahub.io/core/s-and-p-500-companies/_r/-/data/constituents.csv";
const res = await fetch(url);
if (!res.ok) throw new Error("Failed to fetch S&P 500 CSV");
const csv = await res.text();
// Simple CSV parsing
const lines = csv.trim().split("\n");
const header = lines.shift(); // remove header row
const tickers: string[] = [];
for (const line of lines) {
const [symbol] = line.split(",");
tickers.push(symbol);
}
return tickers;
}
// ------------------------------------------------------------
// Fetch last 30 days of closes for a ticker
// ------------------------------------------------------------
async function fetchLast30Closes(ticker: string): Promise<number[]> {
const now = Math.floor(Date.now() / 1000);
const thirtyDaysAgo = now - 30 * 24 * 60 * 60;
const url =
`https://query1.finance.yahoo.com/v8/finance/chart/${ticker}?period1=${thirtyDaysAgo}&period2=${now}&interval=1d`;
const res = await fetch(url);
if (!res.ok) throw new Error(`Failed to fetch data for ${ticker}`);
const json = await res.json();
const closes = json.chart.result?.[0]?.indicators?.quote?.[0]?.close;
if (!closes) return [];
return closes.filter((x: number | null) => x != null);
}
// ------------------------------------------------------------
// Main
// ------------------------------------------------------------
const tickers = await fetchSP500Tickers();
console.log(`Loaded ${tickers.length} S&P 500 tickers\n`);
for (const ticker of tickers) {
try {
const closes = await fetchLast30Closes(ticker);
if (closes.length < 5) {
console.log(`${ticker}: insufficient data`);
continue;
}
// xs = 0..n-1
const xs = closes.map((_, i) => i);
const ys = closes;
const { slope, intercept, r2 } = linearRegression(xs, ys);
console.log(
`${ticker}: slope=${slope.toFixed(4)}, intercept=${intercept.toFixed(
2,
)}, r2=${r2.toFixed(3)}`,
);
} catch (err) {
console.log(`${ticker}: error (${err.message})`);
}
}