78 lines
2.6 KiB
Python
78 lines
2.6 KiB
Python
import subprocess
|
|
import os
|
|
import gzip
|
|
import zstandard as zstd
|
|
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}")
|
|
|
|
# Compress the output file using zstd with compression level -18
|
|
with open(output_file_path, 'rb') as input_file, open(output_file_path + '.zst', 'wb') as output_zstd_file:
|
|
cctx = zstd.ZstdCompressor(level=18)
|
|
output_zstd_file.write(cctx.compress(input_file.read()))
|
|
print(f"Compressed file saved as '{output_file_path}.zst'")
|
|
|
|
# Remove the original gzipped file
|
|
os.remove(file_path)
|
|
print(f"Original file removed: {file_path}")
|
|
|
|
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())
|