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: add start:fast script for faster docs development (#2080)

Jindřich Bär34a6d94f903f
diff --git a/website/docusaurus.config.js b/website/docusaurus.config.js
index 9b9f315a8..6f97f49f3 100644
--- a/website/docusaurus.config.js
+++ b/website/docusaurus.config.js
@@ -66,6 +66,7 @@ module.exports = {
path: '../docs',
sidebarPath: './sidebars.js',
rehypePlugins: [externalLinkProcessor],
+ disableVersioning: !!process.env.CRAWLEE_DOCS_FAST,
},
theme: {
customCss: '/src/css/custom.css',
diff --git a/website/package.json b/website/package.json
index d2ab91626..f207db16a 100644
--- a/website/package.json
+++ b/website/package.json
@@ -2,6 +2,7 @@
"scripts": {
"examples": "docusaurus-examples",
"start": "rimraf .docusaurus && docusaurus start",
+ "start:fast": "rimraf .docusaurus && CRAWLEE_DOCS_FAST=1 docusaurus start",
"build": "rimraf .docusaurus && node --max_old_space_size=16000 node_modules/@docusaurus/core/bin/docusaurus.mjs build",
"publish-gh-pages": "docusaurus-publish",
"write-translations": "docusaurus write-translations",
diff --git a/website/roa-loader/index.js b/website/roa-loader/index.js
index fe67266f4..188485fd0 100644
--- a/website/roa-loader/index.js
+++ b/website/roa-loader/index.js
@@ -60,6 +60,9 @@ async function encodeAndSign(source) {
}
module.exports = async function (code) {
+ if (process.env.CRAWLEE_DOCS_FAST) {
+ return { code, hash: 'fast' };
+ }
console.log(`Signing ${urlToRequest(this.resourcePath)}...`, { working, queue: queue.length });
const hash = await encodeAndSign(code);
return { code, hash };