Files
plant-disease-id/apps/web/scripts/scrape-training-dataset.ts
2026-06-06 15:45:21 -04:00

661 lines
20 KiB
JavaScript
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
#!/usr/bin/env node
/**
* scrape-training-dataset.ts
*
* Collects a training dataset for fine-tuning by scraping DuckDuckGo image search.
*
* Targets:
* - 200 images per disease class (93 diseases)
* - 400 images for the "healthy" class
* - Full resolution images stored in data/dataset/{class_id}/
*
* DuckDuckGo approach (no API key needed):
* 1. Fetch the main search page to extract a vqd (query) token
* 2. Use the vqd token to paginate through image results
* 3. Download each image to the dataset directory
*
* Usage: cd apps/web && npx tsx scripts/scrape-training-dataset.ts
*
* Progress is tracked in data/dataset/.progress.json — interrupt and resume safely.
*/
import "dotenv/config";
import { readFileSync, writeFileSync, existsSync, mkdirSync, readdirSync, statSync } from "fs";
import { resolve, extname, join } from "path";
// ─── Config ─────────────────────────────────────────────────────────────────
const DISEASES_JSON = resolve(__dirname, "../src/data/diseases.json");
const PLANTS_JSON = resolve(__dirname, "../src/data/plants.json");
const DATASET_DIR = resolve(__dirname, "../data/dataset");
const PROGRESS_FILE = resolve(DATASET_DIR, ".progress.json");
/** Target images per disease class */
const TARGET_PER_DISEASE = 200;
/** Target images for the "healthy" class (2× normal) */
const TARGET_HEALTHY = 400;
/** Delay between DuckDuckGo search API calls (ms) */
const SEARCH_DELAY = 1500;
/** Delay between image downloads (ms) */
const DOWNLOAD_DELAY = 300;
/** Max concurrent downloads */
const CONCURRENT_DOWNLOADS = 5;
/** Minimum image size in bytes to accept (reject tiny placeholders) */
const MIN_IMAGE_SIZE = 10_000; // 10KB
/** Maximum image size in bytes */
const MAX_IMAGE_SIZE = 10 * 1024 * 1024; // 10MB
/** Allowed image content types */
const ALLOWED_CONTENT_TYPES = ["image/jpeg", "image/jpg", "image/png", "image/webp", "image/gif"];
/** Allowed file extensions */
const ALLOWED_EXTENSIONS = [".jpg", ".jpeg", ".png", ".webp"];
/** User agent for requests */
const UA =
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/131.0.0.0 Safari/537.36";
// ─── Types ──────────────────────────────────────────────────────────────────
interface DiseaseSeed {
id: string;
plantId: string;
name: string;
// eslint-disable-next-line @typescript-eslint/no-explicit-any
[key: string]: any;
}
interface PlantSeed {
id: string;
commonName: string;
scientificName: string;
// eslint-disable-next-line @typescript-eslint/no-explicit-any
[key: string]: any;
}
interface DuckDuckGoImageResult {
image: string;
title: string;
url: string;
thumbnail: string;
height: number;
width: number;
}
interface ClassProgress {
count: number;
downloaded: number;
failed: number;
skipped: number;
/** URLs we've already seen (to avoid duplicates) */
seenUrls: string[];
/** Whether we've exhausted search results */
exhausted: boolean;
}
interface Progress {
lastUpdated: string;
classes: Record<string, ClassProgress>;
}
/** Class ID for healthy plants */
const HEALTHY_CLASS = "healthy";
// ─── DuckDuckGo API ─────────────────────────────────────────────────────────
/**
* Extract the vqd token from DuckDuckGo's search page.
* Required for paginating image results.
*/
async function getVqdToken(query: string): Promise<string> {
const url = `https://duckduckgo.com/?q=${encodeURIComponent(query)}&t=h_&iax=images&ia=images`;
const res = await fetch(url, {
headers: { "User-Agent": UA, Accept: "text/html" },
signal: AbortSignal.timeout(15_000),
});
if (!res.ok) {
throw new Error(`Failed to get vqd token: ${res.status}`);
}
const html = await res.text();
// Extract vqd token from the HTML
// Format: vqd='<token>' or vqd="<token>"
const match = html.match(/vqd['"]?\s*[:=]\s*['"]([a-f0-9-]+)['"]/);
if (!match) {
throw new Error(`Could not extract vqd token from DuckDuckGo response for "${query}"`);
}
return match[1];
}
/**
* Fetch a page of DuckDuckGo image results.
*/
async function searchImagesDuckDuckGo(
query: string,
vqd: string,
page: number,
): Promise<DuckDuckGoImageResult[]> {
const url = `https://duckduckgo.com/i.js?q=${encodeURIComponent(query)}&vqd=${vqd}&o=json&p=${page}&f=,,,`;
const res = await fetch(url, {
headers: {
"User-Agent": UA,
Accept: "application/json",
Referer: `https://duckduckgo.com/?q=${encodeURIComponent(query)}&t=h_&iax=images&ia=images`,
},
signal: AbortSignal.timeout(15_000),
});
if (!res.ok) {
if (res.status === 429) {
console.warn(" ⚠ Rate limited (429). Waiting 10s...");
await sleep(10_000);
return searchImagesDuckDuckGo(query, vqd, page); // Retry
}
if (res.status === 403) {
console.warn(" ⚠ Forbidden (403). Token may have expired.");
return []; // Token expired — no more pages
}
throw new Error(`DuckDuckGo search failed: ${res.status}`);
}
const data = (await res.json()) as { results: DuckDuckGoImageResult[] };
return data.results ?? [];
}
/**
* Search DuckDuckGo images, automatically paginating to collect up to `target` results.
* Returns unique image URLs.
*/
async function collectImages(
query: string,
target: number,
seenUrls: Set<string>,
): Promise<{ urls: string[]; exhausted: boolean }> {
const results: string[] = [];
let page = 1;
let exhausted = false;
let consecutiveEmpty = 0;
// Get vqd token
let vqd: string;
try {
vqd = await getVqdToken(query);
} catch (err) {
console.warn(` ⚠ Failed to get vqd token: ${err instanceof Error ? err.message : "unknown"}`);
return { urls: [], exhausted: true };
}
while (results.length < target) {
await sleep(SEARCH_DELAY);
let pageResults: DuckDuckGoImageResult[];
try {
pageResults = await searchImagesDuckDuckGo(query, vqd, page);
} catch (err) {
console.warn(` ⚠ Search error: ${err instanceof Error ? err.message : "unknown"}`);
break;
}
if (pageResults.length === 0) {
consecutiveEmpty++;
if (consecutiveEmpty >= 3) {
exhausted = true;
break;
}
page++;
continue;
}
consecutiveEmpty = 0;
let newCount = 0;
for (const r of pageResults) {
if (results.length >= target) break;
const imgUrl = r.image || r.url;
// Skip if we've already seen this URL
if (seenUrls.has(imgUrl)) continue;
// Validate URL looks like an image
const ext = extname(new URL(imgUrl).pathname).toLowerCase();
if (!ALLOWED_EXTENSIONS.includes(ext) && !ext) {
// No extension - still try, could be a CDN URL
}
seenUrls.add(imgUrl);
results.push(imgUrl);
newCount++;
}
if (newCount === 0 && pageResults.every((r) => seenUrls.has(r.image || r.url))) {
// All results on this page were already seen
page++;
continue;
}
if (results.length < target) {
page++;
}
}
return { urls: results.slice(0, target), exhausted };
}
// ─── Image Download ─────────────────────────────────────────────────────────
/**
* Download a single image from a URL to the target path.
* Returns true if successful, false otherwise.
*/
async function downloadImage(url: string, destPath: string): Promise<boolean> {
try {
const res = await fetch(url, {
headers: { "User-Agent": UA, Accept: "image/webp,image/png,image/jpeg" },
signal: AbortSignal.timeout(15_000),
});
if (!res.ok) return false;
const contentType = res.headers.get("content-type") || "";
const contentLength = parseInt(res.headers.get("content-length") || "0", 10);
// Validate content type
if (!ALLOWED_CONTENT_TYPES.some((t) => contentType.includes(t))) {
return false;
}
// Validate size
if (contentLength > 0 && contentLength < MIN_IMAGE_SIZE) return false;
if (contentLength > MAX_IMAGE_SIZE) return false;
const buffer = Buffer.from(await res.arrayBuffer());
// Double-check actual buffer size
if (buffer.length < MIN_IMAGE_SIZE) return false;
if (buffer.length > MAX_IMAGE_SIZE) return false;
// Determine correct extension from content type or URL
let ext = extname(new URL(url).pathname).toLowerCase();
if (!ALLOWED_EXTENSIONS.includes(ext)) {
// Map from content type
if (contentType.includes("jpeg") || contentType.includes("jpg")) ext = ".jpg";
else if (contentType.includes("png")) ext = ".png";
else if (contentType.includes("webp")) ext = ".webp";
else ext = ".jpg"; // Default
}
const filePath = destPath.replace(/\.\w+$/, ext);
writeFileSync(filePath, buffer);
return true;
} catch {
return false;
}
}
/**
* Download multiple images concurrently, respecting a per-download delay.
*/
async function downloadBatch(
urls: string[],
classDir: string,
startIndex: number,
): Promise<{ downloaded: number; failed: number; lastIndex: number }> {
let downloaded = 0;
let failed = 0;
let index = startIndex;
// Process in chunks to control concurrency
for (let i = 0; i < urls.length; i += CONCURRENT_DOWNLOADS) {
const chunk = urls.slice(i, i + CONCURRENT_DOWNLOADS);
const results = await Promise.all(
chunk.map(async (url) => {
const paddedIndex = String(index).padStart(4, "0");
const destPath = resolve(classDir, `img_${paddedIndex}.jpg`);
const success = await downloadImage(url, destPath);
await sleep(DOWNLOAD_DELAY);
return { success, index: index++ };
}),
);
for (const r of results) {
if (r.success) downloaded++;
else failed++;
}
}
return { downloaded, failed, lastIndex: index };
}
// ─── Progress Tracking ──────────────────────────────────────────────────────
function loadProgress(): Progress {
if (!existsSync(PROGRESS_FILE)) {
return { lastUpdated: new Date().toISOString(), classes: {} };
}
return JSON.parse(readFileSync(PROGRESS_FILE, "utf-8")) as Progress;
}
function saveProgress(progress: Progress): void {
progress.lastUpdated = new Date().toISOString();
writeFileSync(PROGRESS_FILE, JSON.stringify(progress, null, 2));
}
function getClassProgress(progress: Progress, classId: string): ClassProgress {
if (!progress.classes[classId]) {
progress.classes[classId] = {
count: 0,
downloaded: 0,
failed: 0,
skipped: 0,
seenUrls: [],
exhausted: false,
};
}
return progress.classes[classId];
}
// ─── Search Query Building ──────────────────────────────────────────────────
function buildSearchQueries(disease: DiseaseSeed, plant: PlantSeed | null): string[] {
const name = disease.name;
const plantName = plant?.commonName || disease.plantId;
return [
`${name} ${plantName} leaf disease`,
`${plantName} ${name} symptoms`,
`${name} plant disease`,
`${plantName} diseased leaf`,
];
}
function buildHealthyQueries(plant: PlantSeed): string[] {
return [
`healthy ${plant.commonName} leaf`,
`${plant.commonName} leaf closeup`,
`healthy ${plant.commonName} plant`,
`${plant.commonName} foliage`,
];
}
// ─── Dataset Collection ─────────────────────────────────────────────────────
async function collectClassImages(
classId: string,
queries: string[],
target: number,
progress: Progress,
classDir: string,
): Promise<void> {
const cp = getClassProgress(progress, classId);
const seenUrls = new Set(cp.seenUrls);
if (cp.count >= target) {
console.log(` ✓ Already have ${cp.count}/${target} images`);
return;
}
if (cp.exhausted) {
console.log(` ✓ Already exhausted search results (${cp.count}/${target} images)`);
return;
}
mkdirSync(classDir, { recursive: true });
const totalUrls: string[] = [];
let exhausted = false;
// Search with each query until we hit the target
for (const query of queries) {
if (totalUrls.length >= target) break;
console.log(` Searching: "${query}"...`);
const result = await collectImages(query, target - totalUrls.length, seenUrls);
totalUrls.push(...result.urls);
cp.seenUrls = Array.from(seenUrls);
if (result.exhausted) {
exhausted = true;
}
if (totalUrls.length >= target) break;
}
if (totalUrls.length === 0) {
cp.exhausted = exhausted;
saveProgress(progress);
console.log(` ✗ No images found for "${classId}"`);
return;
}
console.log(` Found ${totalUrls.length} unique image URLs. Downloading...`);
// Download the images
const { downloaded, failed } = await downloadBatch(totalUrls, classDir, cp.count);
cp.count += downloaded;
cp.downloaded += downloaded;
cp.failed += failed;
cp.exhausted = exhausted;
saveProgress(progress);
const pct = Math.round((cp.count / target) * 100);
console.log(
` ${downloaded > 0 ? "✓" : "✗"} Got ${downloaded} images (${failed} failed). Total: ${cp.count}/${target} (${pct}%)`,
);
}
// ─── Main ───────────────────────────────────────────────────────────────────
async function main() {
console.log("=".repeat(60));
console.log("PLANT DISEASE DATASET COLLECTOR");
console.log("=".repeat(60));
// Load knowledge base
const diseases = JSON.parse(readFileSync(DISEASES_JSON, "utf-8")) as DiseaseSeed[];
const plants = JSON.parse(readFileSync(PLANTS_JSON, "utf-8")) as PlantSeed[];
const plantMap = new Map<string, PlantSeed>();
for (const p of plants) {
plantMap.set(p.id, p);
}
console.log(`\nLoaded ${diseases.length} diseases, ${plants.length} plants`);
console.log(
`Target: ${TARGET_PER_DISEASE} images/disease (×${diseases.length} = ${diseases.length * TARGET_PER_DISEASE})`,
);
console.log(`Target: ${TARGET_HEALTHY} images for "healthy" class`);
console.log(`Output: ${DATASET_DIR}/`);
console.log("");
// Load progress
mkdirSync(DATASET_DIR, { recursive: true });
const progress = loadProgress();
const startTime = Date.now();
// ── Phase 1: Disease classes ──────────────────────────────────────────────
console.log("─".repeat(60));
console.log("PHASE 1: Disease Images");
console.log("─".repeat(60));
for (let i = 0; i < diseases.length; i++) {
const disease = diseases[i];
const plant = plantMap.get(disease.plantId) ?? null;
const classDir = resolve(DATASET_DIR, disease.id);
const queries = buildSearchQueries(disease, plant);
const pct = Math.round((i / diseases.length) * 100);
console.log(`\n[${i + 1}/${diseases.length}] (${pct}%) ${disease.name} (${disease.id})`);
await collectClassImages(disease.id, queries, TARGET_PER_DISEASE, progress, classDir);
}
// ── Phase 2: Healthy class ────────────────────────────────────────────────
console.log("\n" + "─".repeat(60));
console.log("PHASE 2: Healthy Plant Images");
console.log("─".repeat(60));
const healthyDir = resolve(DATASET_DIR, HEALTHY_CLASS);
const healthyCp = getClassProgress(progress, HEALTHY_CLASS);
const healthySeen = new Set(healthyCp.seenUrls);
if (healthyCp.count >= TARGET_HEALTHY) {
console.log(`\n ✓ Already have ${healthyCp.count}/${TARGET_HEALTHY} healthy images`);
} else {
// Build a pool of healthy plant queries
const allHealthyQueries: string[] = [];
for (const plant of plants) {
allHealthyQueries.push(...buildHealthyQueries(plant));
}
const totalHealthyUrls: string[] = [];
let healthyExhausted = false;
for (const query of allHealthyQueries) {
if (totalHealthyUrls.length >= TARGET_HEALTHY) break;
if (healthyExhausted) break;
console.log(`\n Searching: "${query}"...`);
const result = await collectImages(
query,
TARGET_HEALTHY - totalHealthyUrls.length,
healthySeen,
);
totalHealthyUrls.push(...result.urls);
if (result.exhausted) {
healthyExhausted = true;
}
}
healthyCp.seenUrls = Array.from(healthySeen);
if (totalHealthyUrls.length > 0) {
console.log(`\n Found ${totalHealthyUrls.length} healthy image URLs. Downloading...`);
const { downloaded, failed } = await downloadBatch(
totalHealthyUrls,
healthyDir,
healthyCp.count,
);
healthyCp.count += downloaded;
healthyCp.downloaded += downloaded;
healthyCp.failed += failed;
healthyCp.exhausted = healthyExhausted;
const pct = Math.round((healthyCp.count / TARGET_HEALTHY) * 100);
console.log(
` Got ${downloaded} images (${failed} failed). Total: ${healthyCp.count}/${TARGET_HEALTHY} (${pct}%)`,
);
} else {
healthyCp.exhausted = true;
console.log(` ✗ No healthy images found`);
}
saveProgress(progress);
}
// ── Summary ────────────────────────────────────────────────────────────────
const elapsed = Math.round((Date.now() - startTime) / 1000);
const mins = Math.floor(elapsed / 60);
const secs = elapsed % 60;
let totalDownloaded = 0;
let totalFailed = 0;
let totalTarget = 0;
for (const [classId, cp] of Object.entries(progress.classes)) {
totalDownloaded += cp.downloaded || 0;
totalFailed += cp.failed || 0;
totalTarget += classId === HEALTHY_CLASS ? TARGET_HEALTHY : TARGET_PER_DISEASE;
}
const totalSize = await getDatasetSize();
const sizeGb = (totalSize / (1024 * 1024 * 1024)).toFixed(2);
console.log("\n" + "=".repeat(60));
console.log("COMPLETE");
console.log("=".repeat(60));
console.log(` Time: ${mins}m ${secs}s`);
console.log(` Downloaded: ${totalDownloaded} images`);
console.log(` Failed: ${totalFailed} images`);
console.log(` Target: ${totalTarget} images`);
console.log(` Dataset size: ${sizeGb} GB`);
console.log(` Dataset location: ${DATASET_DIR}/`);
console.log("");
console.log("Next steps:");
console.log(" 1. Run the fine-tuning script to train on this dataset");
console.log(" 2. The fine-tuning script will resize to 160×160 and augment");
console.log("=".repeat(60));
}
/**
* Calculate total size of the dataset directory.
*/
async function getDatasetSize(): Promise<number> {
let total = 0;
if (!existsSync(DATASET_DIR)) return 0;
const entries = readdirSync(DATASET_DIR, { withFileTypes: true });
for (const entry of entries) {
if (!entry.name.startsWith(".")) {
const fullPath = resolve(DATASET_DIR, entry.name);
if (entry.isDirectory()) {
total += dirSize(fullPath);
}
}
}
return total;
}
function dirSize(dirPath: string): number {
let total = 0;
try {
const entries = readdirSync(dirPath, { withFileTypes: true });
for (const entry of entries) {
const fullPath = join(dirPath, entry.name);
if (entry.isFile()) {
total += statSync(fullPath).size;
} else if (entry.isDirectory()) {
total += dirSize(fullPath);
}
}
} catch {
// skip errors
}
return total;
}
function sleep(ms: number): Promise<void> {
return new Promise((resolve) => setTimeout(resolve, ms));
}
main().catch((err) => {
console.error("Fatal error:", err);
process.exit(1);
});