Skip to content

Crawlee—A web scraping and browser automation library for Node.js to build reliable crawlers. In JavaScript and TypeScript. Extract data for AI, LLMs, RAG, or GPTs. Download HTML, PDF, JPG, PNG, and other files from websites. Works with Puppeteer, Playwright, Cheerio, JSDOM, and raw HTTP. Both headful and headless mode. With proxy rotation.

chore: add ow validation for parseWithCheerio (#1419)

Andrey Bykov57c10df30bc3
diff --git a/packages/playwright-crawler/src/internals/utils/playwright-utils.ts b/packages/playwright-crawler/src/internals/utils/playwright-utils.ts
index 8046e1b3c..f28633599 100644
--- a/packages/playwright-crawler/src/internals/utils/playwright-utils.ts
+++ b/packages/playwright-crawler/src/internals/utils/playwright-utils.ts
@@ -204,6 +204,7 @@ export async function gotoExtended(page: Page, request: Request, gotoOptions: Di
* @param page Playwright [`Page`](https://playwright.dev/docs/api/class-page) object.
*/
export async function parseWithCheerio(page: Page): Promise<CheerioRoot> {
+ ow(page, ow.object.validate(validators.browserPage));
const pageContent = await page.content();
return cheerio.load(pageContent);
}
diff --git a/packages/puppeteer-crawler/src/internals/utils/puppeteer_utils.ts b/packages/puppeteer-crawler/src/internals/utils/puppeteer_utils.ts
index 9a5f57da3..49505401e 100644
--- a/packages/puppeteer-crawler/src/internals/utils/puppeteer_utils.ts
+++ b/packages/puppeteer-crawler/src/internals/utils/puppeteer_utils.ts
@@ -176,6 +176,7 @@ export function injectJQuery(page: Page): Promise<unknown> {
* @param page Puppeteer [`Page`](https://pptr.dev/api/puppeteer.page) object.
*/
export async function parseWithCheerio(page: Page): Promise<CheerioRoot> {
+ ow(page, ow.object.validate(validators.browserPage));
const pageContent = await page.content();
return cheerio.load(pageContent);
}