Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 5 additions & 3 deletions packages/browser-crawler/src/internals/browser-crawler.ts
Original file line number Diff line number Diff line change
Expand Up @@ -686,16 +686,18 @@ export abstract class BrowserCrawler<
}

/**
* Marks session bad in case of navigation timeout.
* Marks session bad on navigation timeout, and stops in-flight page loading on any navigation error.
*/
protected async _handleNavigationTimeout(crawlingContext: Context, error: Error): Promise<void> {
const { session } = crawlingContext;
const { session, page } = crawlingContext;

if (error && error.constructor.name === 'TimeoutError') {
handleRequestTimeout({ session, errorMessage: error.message });
}

await crawlingContext.page.close();
// Fire-and-forget: no user code will run on this page after a failed navigation.
// Swallow rejections: the page may already be detached.
void page.evaluate(() => window.stop()).catch(() => {});
}

/**
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -42,6 +42,7 @@ export interface CommonBrowser {
export interface CommonPage {
close(...args: unknown[]): Promise<unknown>;
url(): string | Promise<string>;
evaluate(pageFunction: ((...args: any[]) => unknown) | string, ...args: unknown[]): Promise<unknown>;
}

export interface BrowserPluginOptions<LibraryOptions> {
Expand Down
37 changes: 37 additions & 0 deletions test/core/crawlers/browser_crawler.test.ts
Original file line number Diff line number Diff line change
Expand Up @@ -291,6 +291,43 @@ describe('BrowserCrawler', () => {
}
});

test.concurrent('errorHandler has open page after non-timeout navigation error', async () => {
const localStorageEmulator = new MemoryStorageEmulator();
await localStorageEmulator.init();
const puppeteerPlugin = new PuppeteerPlugin(puppeteer);

try {
const requestList = await RequestList.open({
sources: [{ url: `${serverAddress}/?q=1` }],
});

const pageClosedStates: boolean[] = [];

const browserCrawler = new (class extends BrowserCrawlerTest {
protected override async _navigationHandler(): Promise<HTTPResponse | null | undefined> {
throw new Error('net::ERR_NAME_NOT_RESOLVED');
}
})({
browserPoolOptions: {
browserPlugins: [puppeteerPlugin],
},
requestList,
requestHandler: async () => {},
maxRequestRetries: 1,
errorHandler: async (ctx) => {
pageClosedStates.push(ctx.page.isClosed());
},
});

await browserCrawler.run();

expect(pageClosedStates).toHaveLength(1);
expect(pageClosedStates[0]).toBe(false);
} finally {
await localStorageEmulator.destroy();
}
});

test.concurrent('should correctly track request.state', async () => {
const localStorageEmulator = new MemoryStorageEmulator();
await localStorageEmulator.init();
Expand Down
Loading