Allows for scraping using Browserless (browserless.io) from Google sheets. Outputs {selector: text} or just {text} if noHeaders is TRUE. Allows for several selectors.

browserless-appscript.gs

/**
 * Scrapes web content using specified selectors, handling multiple results
 * @param {string} url The URL to scrape
 * @param {string} selectors CSS selectors (comma separated)
 * @param {string} apiUrl API endpoint URL incl. /scrape and ?token= if set
 * @param {number} timeout (Optional) Timeout in milliseconds
 * @param {boolean} noHeaders (Optional) If true, only returns values without selectors
 * @return {Array} Scraped content
 * @customfunction
 */
function WEBSCRAPE(url, selectors, apiUrl, timeout, noHeaders = false) {
  const DEFAULT_API_URL = "YOUR_DEFAULT_API_URL";
  const DEFAULT_TIMEOUT = 30000;
  
  try {
    const finalApiUrl = apiUrl || DEFAULT_API_URL;
    const finalTimeout = parseInt(timeout) || DEFAULT_TIMEOUT;
    
    const results = wScrape(url, finalApiUrl, selectors, finalTimeout);
    const flattenedResults = results.flatMap(item => {
      const texts = item.results.map(result => result.text);
      return texts.map(text => [item.selector, text]);
    });
    
    if (noHeaders) {
      return flattenedResults.map(row => row[1]);
    }
    return flattenedResults;
    
  } catch (error) {
    return `Error: ${error.message}`;
  }
}

function wScrape(url, apiURL, selectors, timeout) {
  if (!url) throw new Error("URL is required");
  if (!selectors) throw new Error("Selectors are required");
  
  const selectorArray = selectors.split(',')
    .map(selector => selector.trim())
    .filter(selector => selector)
    .map(selector => ({ "selector": selector }));
    
  if (selectorArray.length === 0) {
    throw new Error("At least one valid selector is required");
  }
  
  const payload = {
    "url": url,
    "elements": selectorArray,
    "gotoOptions": {
      "timeout": timeout || 30000
    }
  };
  
  const options = {
    method: "post",
    headers: {
      "Content-Type": "application/json"
    },
    payload: JSON.stringify(payload),
    muteHttpExceptions: true
  };
  
  try {
    const response = UrlFetchApp.fetch(apiURL, options);
    const responseCode = response.getResponseCode();
    
    if (responseCode !== 200) {
      throw new Error(`API returned status code ${responseCode}`);
    }

    const resp = JSON.parse(response.getContentText());
    
    if (!resp.data || !Array.isArray(resp.data)) {
      throw new Error('Invalid API response structure');
    }

    return resp.data;
    
  } catch (error) {
    throw error;
  }
}