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.
TypeScript apifyautomationcrawlercrawlingheadlessheadless-chromejavascriptnodejsnpmplaywrightpuppeteerscraperscrapingtypescriptweb-crawlerweb-crawlingweb-scraping
fix: make CLI work on Windows too with `--no-purge` (#2244)
Vlad Frangu83f3179d6963
diff --git a/packages/cli/src/commands/RunProjectCommand.ts b/packages/cli/src/commands/RunProjectCommand.tsindex 9ed56daf7..3df505a03 100644--- a/packages/cli/src/commands/RunProjectCommand.ts+++ b/packages/cli/src/commands/RunProjectCommand.ts@@ -29,15 +29,13 @@ export class RunProjectCommand<T> implements CommandModule<T, RunProjectArgs> {* @inheritDoc*/async handler(args: ArgumentsCamelCase<RunProjectArgs>) {- let cmd = '';+ const env = { ...process.env };if (!args.purge) {- cmd += 'CRAWLEE_PURGE_ON_START=0 ';+ env.CRAWLEE_PURGE_ON_START = '0';}// TODO detect the right package manager (e.g. based on package.json's `packageManager` field)- cmd += `npm run ${args.script}`;-- execSync(cmd, { stdio: 'inherit' });+ execSync(`npm run ${args.script}`, { stdio: 'inherit', env });}}