Create services/scraper.py

app/services/scraper.py

@@ -0,0 +1,38 @@
+from selenium import webdriver
+from selenium.webdriver.common.by import By
+from selenium.webdriver.chrome.service import Service
+from webdriver_manager.chrome import ChromeDriverManager
+import time
+
+class FacebookScraper:
+    def __init__(self):
+        self.driver = self._setup_driver()
+
+    def _setup_driver(self):
+        options = webdriver.ChromeOptions()
+        options.add_argument("--headless")
+        options.add_argument("--no-sandbox")
+        options.add_argument("--disable-dev-shm-usage")
+        return webdriver.Chrome(service=Service(ChromeDriverManager().install()), options=options)
+
+    def scrape_ads(self, search_query, num_scrolls=3):
+        url = f"https://www.facebook.com/ads/library/?active_status=all&ad_type=all&country=ALL&q={search_query}&search_type=keyword"
+        self.driver.get(url)
+        time.sleep(5)  # Wait for page to load
+
+        ads = []
+        for _ in range(num_scrolls):
+            self.driver.execute_script("window.scrollTo(0, document.body.scrollHeight);")
+            time.sleep(3)
+        
+        ad_elements = self.driver.find_elements(By.CSS_SELECTOR, "div.x1yztbdb")
+        for ad in ad_elements:
+            try:
+                ads.append(ad.text)
+            except Exception as e:
+                print("Error extracting ad:", e)
+        
+        return ads
+
+    def close(self):
+        self.driver.quit()