Update scraper.py

scraper.py

@@ -1,20 +1,20 @@
 from selenium import webdriver
 from selenium.webdriver.chrome.service import Service
 from selenium.webdriver.chrome.options import Options
-import time
 from bs4 import BeautifulSoup
 
 def scrape_website(website):
     print("Launching chromium browser...")
 
-    chrome_driver_path = "/usr/lib/chromium/chromedriver"
+    chrome_driver_path = "/usr/lib/chromium/chromedriver"  # dépend de ton Dockerfile
 
     options = Options()
-    options.binary_location = "/usr/bin/chromium"
+    options.binary_location = "/usr/bin/chromium"  # important !
     options.add_argument("--headless")
     options.add_argument("--no-sandbox")
     options.add_argument("--disable-dev-shm-usage")
 
+    # ✅ C’est ici qu’il fallait mettre options
     driver = webdriver.Chrome(service=Service(chrome_driver_path), options=options)
 
     try:
@@ -25,19 +25,3 @@ def scrape_website(website):
     finally:
         driver.quit()
 
-
-def extract_body_content(html_content):
-    soup = BeautifulSoup(html_content, "html.parser")
-    body_content = soup.body
-    return str(body_content) if body_content else ""
-
-def clean_body_content(body_content):
-    soup = BeautifulSoup(body_content, "html.parser")
-    for script_or_style in soup(["script", "style"]):
-        script_or_style.extract()
-
-    cleaned_content = soup.get_text(separator="\n")
-    return "\n".join(line.strip() for line in cleaned_content.splitlines() if line.strip())
-
-def split_dom_content(dom_content, max_length=60000):
-    return [dom_content[i:i + max_length] for i in range(0, len(dom_content), max_length)]