fix: make property-assessor safer for whatsapp runs

This commit is contained in:
2026-03-28 01:28:59 -05:00
parent 2deeb31369
commit 3d7ce7617c
15 changed files with 640 additions and 217 deletions

View File

@@ -10,6 +10,7 @@ import {
gotoListing,
normalizeImageCandidates,
parseTarget,
runWithOperationTimeout,
scrollUntilSettled,
sleep,
waitForPhotoExperience,
@@ -107,77 +108,82 @@ async function collectZillowStructuredPhotoCandidates(page) {
export async function extractZillowPhotos(rawUrl) {
const requestedUrl = parseTarget(rawUrl);
const { context, page } = await createPageSession({ headless: process.env.HEADLESS !== "false" });
const closeContext = async () => {
await context.close().catch(() => {});
};
try {
await gotoListing(page, requestedUrl);
await dismissCommonOverlays(page);
return await runWithOperationTimeout(
"Zillow photo extraction",
async () => {
await gotoListing(page, requestedUrl);
await dismissCommonOverlays(page);
const expectedPhotoCount = await getAnnouncedPhotoCount(page);
const beforeUrl = page.url();
let clickedLabel = null;
let clickError = null;
const expectedPhotoCount = await getAnnouncedPhotoCount(page);
const beforeUrl = page.url();
let clickedLabel = null;
let clickError = null;
try {
clickedLabel = await clickPhotoEntryPoint(page, ZILLOW_LABELS);
await waitForPhotoExperience(page, beforeUrl);
await scrollUntilSettled(page);
await sleep(1200);
} catch (error) {
clickError = error instanceof Error ? error.message : String(error);
}
try {
clickedLabel = await clickPhotoEntryPoint(page, ZILLOW_LABELS);
await waitForPhotoExperience(page, beforeUrl);
await scrollUntilSettled(page);
await sleep(1200);
} catch (error) {
clickError = error instanceof Error ? error.message : String(error);
}
const [structuredCandidates, renderedCandidates] = await Promise.all([
collectZillowStructuredPhotoCandidates(page),
collectZillowPhotoCandidates(page),
]);
const candidates = [...structuredCandidates, ...renderedCandidates];
const normalized = normalizeImageCandidates(candidates, {
hostIncludes: ["photos.zillowstatic.com"],
minWidth: 240,
minHeight: 180,
});
const photos = collapseZillowPhotos(normalized);
const [structuredCandidates, renderedCandidates] = await Promise.all([
collectZillowStructuredPhotoCandidates(page),
collectZillowPhotoCandidates(page),
]);
const candidates = [...structuredCandidates, ...renderedCandidates];
const normalized = normalizeImageCandidates(candidates, {
hostIncludes: ["photos.zillowstatic.com"],
minWidth: 240,
minHeight: 180,
});
const photos = collapseZillowPhotos(normalized);
if (!photos.length) {
fail(
"Zillow photo extraction failed.",
clickError || "No Zillow image URLs were found on the rendered listing page."
);
}
if (!photos.length) {
fail(
"Zillow photo extraction failed.",
clickError || "No Zillow image URLs were found on the rendered listing page."
);
}
const complete = expectedPhotoCount ? photos.length >= expectedPhotoCount : true;
const notes = [];
if (clickedLabel) {
notes.push("Opened Zillow all-photos flow and extracted direct Zillow image URLs.");
} else {
notes.push("The rendered Zillow listing shell already exposed the Zillow photo stream, so extraction completed without relying on the all-photos click path.");
}
if (clickError) {
notes.push(`All-photos click path was not required: ${clickError}`);
}
const complete = expectedPhotoCount ? photos.length >= expectedPhotoCount : true;
const notes = [];
if (clickedLabel) {
notes.push("Opened Zillow all-photos flow and extracted direct Zillow image URLs.");
} else {
notes.push("The rendered Zillow listing shell already exposed the Zillow photo stream, so extraction completed without relying on the all-photos click path.");
}
if (clickError) {
notes.push(`All-photos click path was not required: ${clickError}`);
}
const result = {
source: "zillow",
requestedUrl,
finalUrl: page.url(),
title: await page.title(),
clickedLabel,
expectedPhotoCount,
complete,
photoCount: photos.length,
imageUrls: photos.map((photo) => photo.url),
notes,
};
await context.close();
return result;
return {
source: "zillow",
requestedUrl,
finalUrl: page.url(),
title: await page.title(),
clickedLabel,
expectedPhotoCount,
complete,
photoCount: photos.length,
imageUrls: photos.map((photo) => photo.url),
notes,
};
},
{
onTimeout: closeContext
}
);
} catch (error) {
try {
await context.close();
} catch {
// Ignore close errors after the primary failure.
}
throw new Error(error instanceof Error ? error.message : String(error));
} finally {
await closeContext();
}
}