CommonCrawl_URL_Processor/warc_wat_url_processor.py

import subprocess
import os
import gzip
import re
import traceback
from multiprocessing import Pool

def extract_urls_from_file(file_path):
    urls = []
    try:
        with gzip.open(file_path, 'rt', encoding='latin-1') as file:
            for line in file:
                url_pattern = re.compile(r'http[s]?://(?:[a-zA-Z]|[0-9]|[$-_@.&+]|[!*\\(\\),]|(?:%[0-9a-fA-F][0-9a-fA-F]))+')
                line_urls = re.findall(url_pattern, line)
                urls.extend(line_urls)
    except (gzip.BadGzipFile, EOFError) as e:
        print(f"Error while reading the compressed file '{file_path}': {e}")
    except Exception as e:
        print(f"An unexpected error occurred while processing '{file_path}': {e}")
        print("Full traceback:")
        traceback.print_exc()

    return urls

def process_file(file_path):
    print(f"Processing file: {file_path}")

    # Extract URLs from the gzipped file
    urls = extract_urls_from_file(file_path)

    # Create the output file path with '_urls.txt' extension
    output_file_path = os.path.splitext(file_path)[0] + '_urls.txt'
    print(f"Output file path: {output_file_path}")

    # Write the URLs to the output file
    with open(output_file_path, 'w') as output_file:
        output_file.write('\n'.join(urls))
    print(f"URLs written to {output_file_path}")

    # Use zstd command-line tool for compression
    compressed_file_path = f'{output_file_path}.zst'
    command_compress = f'zstd -T0 -12 --long {output_file_path} -o {compressed_file_path}'
    subprocess.run(command_compress, shell=True)
    print(f"Compressed file saved as '{compressed_file_path}'")

    # Remove the original gzipped file
    os.remove(file_path)
    print(f"Original file removed: {file_path}")

    # Remove the original _urls.txt file
    os.remove(output_file_path)
    print(f"Original file removed: {output_file_path}")

    # Remove the line containing the filename (without "_urls.txt") from urls_to_download.txt
    filename = os.path.basename(output_file_path).replace('_urls.txt', '')
    command = f'sed -i "/{filename}/d" "urls_to_download.txt"'
    if subprocess.run(command, shell=True).returncode == 0:
        print(f"File {filename} has been successfully removed from urls_to_download.txt")
        with open('urls_to_download.txt', 'r') as file:
            remaining_count = sum(1 for line in file)
        print(f"URLs remaining to be processed: {remaining_count}")
    else:
        print(f"Failed to remove {filename} from urls_to_download.txt")

def extract_urls_from_directory(directory_path):
    file_list = sorted(os.listdir(directory_path))
    pool = Pool(processes=7)
    pool.map(process_file, [os.path.join(directory_path, filename) for filename in file_list if filename.endswith('.warc.gz')])
    pool.close()
    pool.join()

with open('urls_to_download.txt', 'r') as file:
    urls = file.readlines()

urls = [url.strip() for url in urls]

batch_size = 48
concurrency_level = 4
batches = [urls[i:i+batch_size] for i in range(0, len(urls), batch_size)]

for batch in batches:
    pool = Pool(processes=concurrency_level)

    for url in batch:
        command = f'axel -n 4 {url}'
        pool.apply_async(subprocess.run, args=(command,), kwds={'shell': True})

    pool.close()
    pool.join()

extract_urls_from_directory(os.getcwd())