From 2d30cc6117b993aa37f12cf29d9563f9f1dc8b0b Mon Sep 17 00:00:00 2001
From: Nicolas <nicolascamara29@gmail.com>
Date: Wed, 3 Jul 2024 18:01:54 -0300
Subject: [PATCH] Nick: comments

---
 apps/api/src/scraper/WebScraper/scrapers/fetch.ts      |  7 +++++++
 apps/api/src/scraper/WebScraper/scrapers/fireEngine.ts | 10 ++++++++++
 apps/api/src/scraper/WebScraper/scrapers/playwright.ts |  8 ++++++++
 .../api/src/scraper/WebScraper/scrapers/scrapingBee.ts |  9 ++++++++-
 4 files changed, 33 insertions(+), 1 deletion(-)

diff --git a/apps/api/src/scraper/WebScraper/scrapers/fetch.ts b/apps/api/src/scraper/WebScraper/scrapers/fetch.ts
index 562fa6e7..9badfd91 100644
--- a/apps/api/src/scraper/WebScraper/scrapers/fetch.ts
+++ b/apps/api/src/scraper/WebScraper/scrapers/fetch.ts
@@ -3,6 +3,13 @@ import { logScrape } from "../../../services/logging/scrape_log";
 import { fetchAndProcessPdf } from "../utils/pdfProcessor";
 import { universalTimeout } from "../global";
 
+
+/**
+ * Scrapes a URL with Axios
+ * @param url The URL to scrape
+ * @param pageOptions The options for the page
+ * @returns The scraped content
+ */
 export async function scrapWithFetch(
   url: string,
   pageOptions: { parsePDF?: boolean } = { parsePDF: true }
diff --git a/apps/api/src/scraper/WebScraper/scrapers/fireEngine.ts b/apps/api/src/scraper/WebScraper/scrapers/fireEngine.ts
index f6121861..ce3cd2da 100644
--- a/apps/api/src/scraper/WebScraper/scrapers/fireEngine.ts
+++ b/apps/api/src/scraper/WebScraper/scrapers/fireEngine.ts
@@ -5,6 +5,16 @@ import { generateRequestParams } from "../single_url";
 import { fetchAndProcessPdf } from "../utils/pdfProcessor";
 import { universalTimeout } from "../global";
 
+/**
+ * Scrapes a URL with Fire-Engine
+ * @param url The URL to scrape
+ * @param waitFor The time to wait for the page to load
+ * @param screenshot Whether to take a screenshot
+ * @param pageOptions The options for the page
+ * @param headers The headers to send with the request
+ * @param options The options for the request
+ * @returns The scraped content
+ */
 export async function scrapWithFireEngine({
   url,
   waitFor = 0,
diff --git a/apps/api/src/scraper/WebScraper/scrapers/playwright.ts b/apps/api/src/scraper/WebScraper/scrapers/playwright.ts
index fd1aef53..03a6728d 100644
--- a/apps/api/src/scraper/WebScraper/scrapers/playwright.ts
+++ b/apps/api/src/scraper/WebScraper/scrapers/playwright.ts
@@ -4,6 +4,14 @@ import { generateRequestParams } from "../single_url";
 import { fetchAndProcessPdf } from "../utils/pdfProcessor";
 import { universalTimeout } from "../global";
 
+/**
+ * Scrapes a URL with Playwright
+ * @param url The URL to scrape
+ * @param waitFor The time to wait for the page to load
+ * @param headers The headers to send with the request
+ * @param pageOptions The options for the page
+ * @returns The scraped content
+ */
 export async function scrapWithPlaywright(
   url: string,
   waitFor: number = 0,
diff --git a/apps/api/src/scraper/WebScraper/scrapers/scrapingBee.ts b/apps/api/src/scraper/WebScraper/scrapers/scrapingBee.ts
index 5ab0e061..63e8a082 100644
--- a/apps/api/src/scraper/WebScraper/scrapers/scrapingBee.ts
+++ b/apps/api/src/scraper/WebScraper/scrapers/scrapingBee.ts
@@ -4,7 +4,14 @@ import { fetchAndProcessPdf } from "../utils/pdfProcessor";
 import { universalTimeout } from "../global";
 import { ScrapingBeeClient } from "scrapingbee";
 
-
+/**
+ * Scrapes a URL with ScrapingBee
+ * @param url The URL to scrape
+ * @param wait_browser The browser event to wait for
+ * @param timeout The timeout for the scrape
+ * @param pageOptions The options for the page
+ * @returns The scraped content
+ */
 export async function scrapWithScrapingBee(
     url: string,
     wait_browser: string = "domcontentloaded",