Update app.py

app.py

@@ -2,55 +2,47 @@ import gradio as gr
 from bs4 import BeautifulSoup
 from urllib.parse import urlencode
 from fastmcp import FastMCP
-import undetected_chromedriver as uc
-from selenium.webdriver.chrome.options import Options
-import time
+import requests
 
 # Initialize FastMCP agent
-mcp = FastMCP("Indeed Web Scraper Agent")
+mcp = FastMCP("Canada Job Bank Scraper Agent")
 
 @mcp.tool(name="search_jobs")
 def search_jobs_tool(query: str, location: str, limit: int = 10, salary: str = None, job_type: str = None):
-    base_url = "https://ca.indeed.com/jobs?"
+    base_url = "https://www.jobbank.gc.ca/jobsearch/jobsearch?"
 
     params = {
-        "q": query,
-        "l": location,
-        "sort": "date",
+        "searchstring": query,
+        "locationstring": location,
+        "sort": "M",  # Sort by most recent
     }
     url = base_url + urlencode(params)
 
-    options = Options()
-    options.headless = True
-    options.add_argument("--no-sandbox")
-    options.add_argument("--disable-dev-shm-usage")
-    options.add_argument("--disable-blink-features=AutomationControlled")
-    options.add_argument("--disable-gpu")
-
-    # 你電腦 Chrome 路徑（下面係 Windows 舉例）
-    options.binary_location = "C:/Program Files/Google/Chrome/Application/chrome.exe"
-    # macOS 路徑範例：'/Applications/Google Chrome.app/Contents/MacOS/Google Chrome'
-    # Linux 路徑範例：'/usr/bin/google-chrome'
+    headers = {
+        "User-Agent": (
+            "Mozilla/5.0 (Windows NT 10.0; Win64; x64) "
+            "AppleWebKit/537.36 (KHTML, like Gecko) "
+            "Chrome/114.0.0.0 Safari/537.36"
+        ),
+        "Accept-Language": "en-US,en;q=0.9",
+    }
 
     try:
-        driver = uc.Chrome(options=options)
-        driver.get(url)
-        time.sleep(5)
-
-        html = driver.page_source
-        driver.quit()
+        response = requests.get(url, headers=headers, timeout=15)
+        response.raise_for_status()
 
-        soup = BeautifulSoup(html, "html.parser")
+        soup = BeautifulSoup(response.text, "html.parser")
 
         jobs = []
-        cards = soup.find_all("a", class_="tapItem")
+        cards = soup.find_all("article", class_="resultJobItem")  # Job listings container
+
         for card in cards[:limit]:
-            title_elem = card.find("h2", class_="jobTitle")
-            company_elem = card.find("span", class_="companyName")
-            location_elem = card.find("div", class_="companyLocation")
-            link = card.get("href")
+            title_elem = card.find("a", class_="resultJobItem-title")
+            company_elem = card.find("span", class_="resultJobItem-employer")
+            location_elem = card.find("li", class_="resultJobItem-location")
+            link = title_elem.get("href") if title_elem else None
             if link and not link.startswith("http"):
-                link = "https://ca.indeed.com" + link
+                link = "https://www.jobbank.gc.ca" + link
 
             job = {
                 "title": title_elem.get_text(strip=True) if title_elem else "No Title",
@@ -65,6 +57,7 @@ def search_jobs_tool(query: str, location: str, limit: int = 10, salary: str = N
     except Exception as e:
         return {"error": str(e)}
 
+
 def search_jobs_ui(query, location, limit=10, salary=None, job_type=None):
     result = search_jobs_tool(query, location, limit, salary, job_type)
 
@@ -93,8 +86,8 @@ app = gr.Interface(
         gr.Textbox(label="Job Type (optional, ignored)")
     ],
     outputs="markdown",
-    title="Indeed Job Search (with Selenium) + FastMCP",
-    description="Search jobs by scraping Indeed.ca using Selenium and BeautifulSoup."
+    title="Canada Job Bank Job Search (with requests & BeautifulSoup) + FastMCP",
+    description="Search jobs by scraping Canada Job Bank using requests and BeautifulSoup."
 )
 
 if __name__ == "__main__":