Updated to include disk space checking

warc_wat_url_processor.py

@@ -4,6 +4,26 @@ import re
 import traceback
 from concurrent.futures import ProcessPoolExecutor, as_completed, wait
 import subprocess
+import time
+
+def check_disk_space(path, min_space_gb=20, check_interval=300):
+    while True:
+        try:
+            result = subprocess.run(['df', '-BG', path], stdout=subprocess.PIPE, stderr=subprocess.PIPE, text=True)
+            if result.returncode == 0:
+                output = result.stdout.split('\n')[1].split()
+                available_space_gb = int(output[3].replace('G', ''))
+                if available_space_gb >= min_space_gb:
+                    break
+                else:
+                    print(f"Waiting for more than {min_space_gb}GB free space on {path}. Current available space: {available_space_gb}GB")
+                    time.sleep(check_interval)
+            else:
+                print("Error checking disk space.")
+                time.sleep(check_interval)
+        except Exception as e:
+            print(f"An error occurred while checking disk space: {e}")
+            time.sleep(check_interval)
 
 def extract_urls_from_file(file_path):
     urls = []
@@ -78,7 +98,7 @@ def process_file(file_path):
 
 def download_and_process_file(url):
     try:
-        command = f'axel -n 4 {url}'
+        command = f'axel -n 3 {url}'
         result = subprocess.run(command, shell=True, check=True)
         if result.returncode == 0:
             file_path = os.path.join(os.getcwd(), os.path.basename(url))
@@ -90,6 +110,8 @@ def download_and_process_file(url):
         print(f"Error during download and processing {url}: {e}")
 
 def main():
+    check_disk_space('/dev/sda1')
+
     with open('urls_to_download.txt', 'r') as file:
         urls = file.readlines()
 
@@ -97,14 +119,11 @@ def main():
 
     download_concurrency_level = 40
 
-    # Start downloading and processing files in parallel
     with ProcessPoolExecutor(max_workers=download_concurrency_level) as executor:
         futures = [executor.submit(download_and_process_file, url) for url in urls]
 
-        # Wait for all downloads and processing to complete before starting the next iteration
         completed_futures, _ = wait(futures)
 
-        # Process results from completed futures
         for completed_future in completed_futures:
             try:
                 result = completed_future.result()