Class ChromiumScrapePostRoute

src/shared/scrape.http.ts:225–502

};

export default class ChromiumScrapePostRoute extends BrowserHTTPRoute {
  name = BrowserlessRoutes.ChromiumScrapePostRoute;
  accepts = [contentTypes.json];
  auth = true;
  browser = ChromiumCDP;
  concurrency = true;
  contentTypes = [contentTypes.json];
  description = dedent(`
    A JSON-based API that returns text, html, and meta-data from a given list of selectors.
    Debugging information is available by sending in the appropriate flags in the "debugOpts"
    property. Responds with an array of JSON objects.
  `);
  method = Methods.post;
  path = [HTTPRoutes.chromiumScrape, HTTPRoutes.scrape];
  tags = [APITags.browserAPI];
  async handler(
    req: Request,
    res: ServerResponse,
    logger: Logger,
    browser: BrowserInstance,
  ) {
    logger.debug(
      'Scrape API invoked with body:',
      redactSensitiveBodyFields(req.body),
    );
    const contentType =
      !req.headers.accept || req.headers.accept?.includes('*')
        ? contentTypes.html
        : req.headers.accept;

    if (!req.body) {
      throw new BadRequest(`Couldn't parse JSON body`);
    }

    res.setHeader('Content-Type', contentType);

    const {
      bestAttempt = false,
      url,
      gotoOptions,
      authenticate,
      addScriptTag = [],
      addStyleTag = [],
      cookies = [],
      debugOpts,
      elements,
      emulateMediaType,
      html,
      rejectRequestPattern = [],
      requestInterceptors = [],
      rejectResourceTypes = [],
      setExtraHTTPHeaders,
      setJavaScriptEnabled,
      userAgent,
      viewport,
      waitForTimeout,
      waitForFunction,
      waitForSelector,