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.

fix: ignore errors from iframe content extraction (#2714)

Aryan Gupta627e5c2fbadc
diff --git a/packages/playwright-crawler/src/internals/utils/playwright-utils.ts b/packages/playwright-crawler/src/internals/utils/playwright-utils.ts
index 775aa9f5a..e6191a6c5 100644
--- a/packages/playwright-crawler/src/internals/utils/playwright-utils.ts
+++ b/packages/playwright-crawler/src/internals/utils/playwright-utils.ts
@@ -609,18 +609,22 @@ export async function parseWithCheerio(
await Promise.all(
frames.map(async (frame) => {
- const iframe = await frame.contentFrame();
-
- if (iframe) {
- const contents = await iframe.content();
-
- await frame.evaluate((f, c) => {
- const replacementNode = document.createElement('div');
- replacementNode.innerHTML = c;
- replacementNode.className = 'crawlee-iframe-replacement';
-
- f.replaceWith(replacementNode);
- }, contents);
+ try {
+ const iframe = await frame.contentFrame();
+
+ if (iframe) {
+ const contents = await iframe.content();
+
+ await frame.evaluate((f, c) => {
+ const replacementNode = document.createElement('div');
+ replacementNode.innerHTML = c;
+ replacementNode.className = 'crawlee-iframe-replacement';
+
+ f.replaceWith(replacementNode);
+ }, contents);
+ }
+ } catch (error) {
+ log.warning(`Failed to extract iframe content: ${error}`);
}
}),
);
diff --git a/packages/puppeteer-crawler/src/internals/utils/puppeteer_utils.ts b/packages/puppeteer-crawler/src/internals/utils/puppeteer_utils.ts
index 390e1fc1d..51a4d7b7c 100644
--- a/packages/puppeteer-crawler/src/internals/utils/puppeteer_utils.ts
+++ b/packages/puppeteer-crawler/src/internals/utils/puppeteer_utils.ts
@@ -200,18 +200,21 @@ export async function parseWithCheerio(
await Promise.all(
frames.map(async (frame) => {
- const iframe = await frame.contentFrame();
-
- if (iframe) {
- const contents = await iframe.content();
-
- await frame.evaluate((f, c) => {
- const replacementNode = document.createElement('div');
- replacementNode.innerHTML = c;
- replacementNode.className = 'crawlee-iframe-replacement';
-
- f.replaceWith(replacementNode);
- }, contents);
+ try {
+ const iframe = await frame.contentFrame();
+ if (iframe) {
+ const contents = await iframe.content();
+
+ await frame.evaluate((f, c) => {
+ const replacementNode = document.createElement('div');
+ replacementNode.innerHTML = c;
+ replacementNode.className = 'crawlee-iframe-replacement';
+
+ f.replaceWith(replacementNode);
+ }, contents);
+ }
+ } catch (error) {
+ log.warning(`Failed to extract iframe content: ${error}`);
}
}),
);