From c72e2b334adba98c2fcbe995cb189688f98e5edb Mon Sep 17 00:00:00 2001
From: Anirudh Hegde <hegdeanirudh2003@gmail.com>
Date: Wed, 27 Dec 2023 20:27:26 +0530
Subject: [PATCH] Update scrape.py

---
 scrape.py | 87 +++++++++++++++++++++++++++++++++----------------------
 1 file changed, 53 insertions(+), 34 deletions(-)

diff --git a/scrape.py b/scrape.py
index a82e7be..ebd5ce0 100644
--- a/scrape.py
+++ b/scrape.py
@@ -2,41 +2,60 @@
 from selenium.webdriver.common.by import By
 import json
 import time
-from scrappers.devfolio import Devfolio 
+hackathons = []
+driver = None
 
 def scrape_data():
-    options = webdriver.ChromeOptions()
-    options.add_argument('--ignore-ssl-errors=yes')
-    options.add_argument('--ignore-certificate-errors')
-    driver = webdriver.Remote(
-    command_executor='http://localhost:4444/wd/hub',
-    options=options
-    )
-    driver.get("https://mlh.io/seasons/2024/events")
-    links = driver.find_elements(By.CLASS_NAME, "event-link") # Fetching links of hackathon websites
-    images = driver.find_elements(By.CSS_SELECTOR, ".image-wrap img") # Fetching images of hackathons
-    names = driver.find_elements(By.CLASS_NAME, "event-name") # Fetching names of hackathons
-    dates = driver.find_elements(By.CLASS_NAME, "event-date") # Fetching dates
-    locs = driver.find_elements(By.CLASS_NAME, "event-location") # Fetching location
-    modes = driver.find_elements(By.CLASS_NAME,"event-hybrid-notes") # Fetching modes
-    hackathons = []
-    for i in range(len(links)):
-        hackathon = {
-            "name": names[i].text,
-            "link": links[i].get_attribute("href"),
-            "image": images[i].get_attribute("src"),
-            "date": dates[i].text,
-            "location": locs[i].text,
-            "mode":modes[i].text
-        }
-        hackathons.append(hackathon)
-    with open("hackathons.json","w") as f:
-        json.dump(hackathons,f,indent=4); 
-    driver.quit()
+    global hackathons, driver
 
-# scrape_data()
-while(1):
+    # Update this path with the correct path of your system
+    # chrome_path = "/usr/bin/google-chrome" - # Linux and MacOS
+    chrome_path="/path/to/google-chrome"
+    # install chromedriver version compatible with yoyr google-chrome version
+
+    # Update this path with the correct path of your system
+    
+    #chromedriver_path = "/usr/local/bin/chromedriver" - # Linux and MacOS
+    chromedriver_path = "/path/to/chromedriver"
+
+    try:
+        options = webdriver.ChromeOptions()
+        options.add_argument('--ignore-ssl-errors=yes')
+        options.add_argument('--ignore-certificate-errors')
+        
+        driver = webdriver.Chrome(options=options)
+        
+        driver.get("https://mlh.io/seasons/2024/events")
+        links = driver.find_elements(By.CLASS_NAME, "event-link") # Fetching links of hackathon websites
+        images = driver.find_elements(By.CSS_SELECTOR, ".image-wrap img") # Fetching images of hackathons
+        names = driver.find_elements(By.CLASS_NAME, "event-name") # Fetching names of hackathons
+        dates = driver.find_elements(By.CLASS_NAME, "event-date") # Fetching dates
+        locs = driver.find_elements(By.CLASS_NAME, "event-location") # Fetching location
+        modes = driver.find_elements(By.CLASS_NAME,"event-hybrid-notes") # Fetching modes
+        hackathons = []
+        for i in range(len(links)):
+            hackathon = {
+                "name": names[i].text,
+                "link": links[i].get_attribute("href"),
+                "image": images[i].get_attribute("src"),
+                "date": dates[i].text,
+                "location": locs[i].text,
+                "mode":modes[i].text
+            }
+            hackathons.append(hackathon)
+    except Exception as e:
+        print(f"Error: {e}")
+    finally:
+        try:
+            if driver:
+                with open("hackathons.json","w") as f:
+                    json.dump(hackathons,f,indent=4); 
+                driver.quit()
+                print("Webdriver quit successfully")
+                exit()
+        except Exception as e:
+            print(f"Error in final block: {e}")
+
+while True:
     scrape_data()
-    devfolio=Devfolio()
-    devfolio.findall()
-    time.sleep(86400)
\ No newline at end of file
+    time.sleep(86400)