VLC updates, and some infra bugs fix

mm_agents/gui_som/data_preparation/scrape_crawler.py

@@ -17,7 +17,7 @@ with open('get_tag_elem_dict.js', 'r') as f:
 def scrape_data(website_url, action_depth=10):
     # if file exists, skip
     if os.path.exists(os.path.join('collected_data', website_url.split("//")[1])):
-        print("Data already exists, skipping...")
+        # print("Data already exists, skipping...")
         return
 
     def click_random_link(page):
@@ -100,6 +100,7 @@ def scrape_data(website_url, action_depth=10):
 def run_one(url):
     try:
         scrape_data("https://" + url, action_depth=5)
+        scrape_data("http://" + url, action_depth=5)
     except Exception as e:
         print("Error scraping data:", e)
         print("Start next one...")
@@ -107,6 +108,7 @@ def run_one(url):
 
 def main():
     urls = read_csv("majestic_million.csv")[:20000]
+    random.shuffle(urls)
 
     # Number of processes
     num_processes = 50  # Adjust based on your system's capability, on my i9-13900k, 50 processes can be used