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.

docs: missing `url` param on page view [internal] (#3197)

Tomas Katzf65890491f5d
diff --git a/website/src/plugins/docusaurus-plugin-segment/segment.js b/website/src/plugins/docusaurus-plugin-segment/segment.js
index 3fa600468..0cf574c65 100644
--- a/website/src/plugins/docusaurus-plugin-segment/segment.js
+++ b/website/src/plugins/docusaurus-plugin-segment/segment.js
@@ -1,15 +1,18 @@
import ExecutionEnvironment from '@docusaurus/ExecutionEnvironment';
export default ExecutionEnvironment.canUseDOM ? {
- onRouteUpdate({ location }) {
- // Don't track page views on development
- if (process.env.NODE_ENV === 'production' && window.analytics) {
- window.analytics.page({
- app: 'crawlee',
- path: location.pathname,
- url: location.href,
- search: location.search,
- });
- }
+ onRouteUpdate() {
+ // this forces deferred execution that ensures `window.location` is in sync
+ setTimeout(() => {
+ // Don't track page views on development
+ if (process.env.NODE_ENV === 'production' && window.analytics) {
+ window.analytics.page({
+ app: 'crawlee',
+ path: window.location.pathname,
+ url: window.location.href,
+ search: window.location.search,
+ });
+ }
+ }, 0);
},
} : null;