Last active
June 21, 2023 20:55
-
-
Save Modder4869/89264212768240a43d1efb4764792d04 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| import requests | |
| import io | |
| import struct | |
| import zipfile | |
| import binascii | |
| import re | |
| import sys | |
| import os | |
| from tqdm import tqdm | |
| #copied from https://betterprogramming.pub/how-to-know-zip-content-without-downloading-it-87a5b30be20a | |
| EOCD_RECORD_SIZE = 22 | |
| ZIP64_EOCD_RECORD_SIZE = 56 | |
| ZIP64_EOCD_LOCATOR_SIZE = 20 | |
| MAX_STANDARD_ZIP_SIZE = 4_294_967_295 | |
| def retrieve_zip_content(url, regex_pattern, output_folder): | |
| zip_file = get_zip_file(url) | |
| extract_matching_files(zip_file, regex_pattern, output_folder) | |
| def get_zip_file(url): | |
| file_size = get_file_size(url) | |
| eocd_record = fetch(url, file_size - EOCD_RECORD_SIZE, EOCD_RECORD_SIZE) | |
| if file_size <= MAX_STANDARD_ZIP_SIZE: | |
| cd_start, cd_size = get_central_directory_metadata_from_eocd(eocd_record) | |
| central_directory = fetch(url, cd_start, cd_size) | |
| return zipfile.ZipFile(io.BytesIO(central_directory + eocd_record)) | |
| else: | |
| zip64_eocd_record = fetch( | |
| url, | |
| file_size - (EOCD_RECORD_SIZE + ZIP64_EOCD_LOCATOR_SIZE + ZIP64_EOCD_RECORD_SIZE), | |
| ZIP64_EOCD_RECORD_SIZE, | |
| ) | |
| zip64_eocd_locator = fetch( | |
| url, | |
| file_size - (EOCD_RECORD_SIZE + ZIP64_EOCD_LOCATOR_SIZE), | |
| ZIP64_EOCD_LOCATOR_SIZE, | |
| ) | |
| cd_start, cd_size = get_central_directory_metadata_from_eocd64(zip64_eocd_record) | |
| central_directory = fetch(url, cd_start, cd_size) | |
| return zipfile.ZipFile( | |
| io.BytesIO(central_directory + zip64_eocd_record + zip64_eocd_locator + eocd_record) | |
| ) | |
| def get_file_size(url): | |
| response = requests.head(url) | |
| if response.status_code == 200: | |
| content_length = response.headers.get("Content-Length") | |
| return int(content_length) | |
| else: | |
| raise ValueError("Error retrieving file size:", response.status_code) | |
| def fetch(url, start, length): | |
| end = start + length - 1 | |
| headers = {"Range": f"bytes={start}-{end}"} | |
| response = requests.get(url, headers=headers) | |
| return response.content | |
| def get_central_directory_metadata_from_eocd(eocd): | |
| cd_size = parse_little_endian_to_int(eocd[12:16]) | |
| cd_start = parse_little_endian_to_int(eocd[16:20]) | |
| return cd_start, cd_size | |
| def get_central_directory_metadata_from_eocd64(eocd64): | |
| cd_size = parse_little_endian_to_int(eocd64[40:48]) | |
| cd_start = parse_little_endian_to_int(eocd64[48:56]) | |
| return cd_start, cd_size | |
| def parse_little_endian_to_int(little_endian_bytes): | |
| format_character = "i" if len(little_endian_bytes) == 4 else "q" | |
| return struct.unpack("<" + format_character, little_endian_bytes)[0] | |
| def extract_matching_files(zip_file, regex_pattern, output_folder): | |
| central_directory = zip_file.filelist | |
| idk = central_directory[0].header_offset # first entry | |
| for zi in central_directory: | |
| local_header_offset = zi.header_offset - idk | |
| # print(zi.filename) | |
| if re.search(regex_pattern, zi.filename, re.IGNORECASE): | |
| file_name = zi.filename.split("/")[-1] | |
| print(f"downloading {file_name}") | |
| output_path = f"{output_folder}/{file_name}.zip" | |
| os.makedirs(os.path.dirname(output_path), exist_ok=True) # Create parent directories if they don't exist | |
| with open(output_path, "wb") as f: | |
| size = struct.unpack("<h", zi.FileHeader()[26:28])[0] + 28 + zi.compress_size + 2 | |
| # Download with progress bar and speed indicator | |
| headers = {"Range": f"bytes={local_header_offset}-{local_header_offset + size - 1}"} | |
| response = requests.get(zipUrl, stream=True, headers=headers) | |
| total_length = int(size) | |
| progress_bar = tqdm(total=total_length, unit="B", unit_scale=True, unit_divisor=1024, ncols=80) | |
| for data in response.iter_content(chunk_size=8192): | |
| progress_bar.update(len(data)) | |
| f.write(data) | |
| progress_bar.close() | |
| print(f"Extracted: {output_path}") | |
| zip_file.close() | |
| if __name__ == "__main__": | |
| if len(sys.argv) != 4: | |
| print("Usage: python script.py <zip_url> <regex_pattern> <output_folder>") | |
| sys.exit(1) | |
| zipUrl = sys.argv[1] | |
| regexPattern = sys.argv[2] | |
| outputFolder = sys.argv[3] | |
| retrieve_zip_content(zipUrl, regexPattern, outputFolder) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
very very crazy code