convert_old_zoo_download.py

from tempfile import mkstemp
from shutil import move, copymode
from os import fdopen, remove
import os
import re

def has_old_style(file_path):

    pattern = "CODE="

    with open(file_path, encoding="utf8") as f:

        # Read the old script
        script = f.read()

        return pattern in script

# https://stackoverflow.com/a/3368991/13706271
def find_between_r( s, first, last ):
    try:
        start = s.rindex( first ) + len( first )
        end = s.rindex( last, start )
        return s[start:end]
    except ValueError:
        return ""


# Ref: https://stackoverflow.com/a/39110/13706271
def replace_download_pattern(file_path):

    #Create temp file
    fh, abs_path = mkstemp()
    with fdopen(fh,'w',encoding="utf8") as new_file:

        with open(file_path,encoding="utf8") as old_file:

            # Read the old script
            old_lines = old_file.readlines()
            new_lines = old_lines.copy()  

            curl_lines =  [i for i,line in enumerate(old_lines) if "curl -sc" in line]
            for curl_line in curl_lines:

                # Extract file id
                file_id = find_between_r(old_lines[curl_line], "id=", "\" ")
                new_lines[curl_line] = f"fileid=\"{file_id}\"\n"

                # Read file name:
                file_name = find_between_r(old_lines[curl_line+2], "-o ", "\n")

                new_lines[curl_line+1] = "html=`curl -c ./cookie -s -L \"https://drive.google.com/uc?export=download&id=${fileid}\"`\n"
                new_lines[curl_line+2] = f"curl -Lb ./cookie \"https://drive.google.com/uc?export=download&`echo ${{html}}|grep -Po '(confirm=[a-zA-Z0-9\\-_]+)'`&id=${{fileid}}\" -o {file_name}\n"

            [new_file.write(new_line) for new_line in new_lines]

    #Copy the file permissions from the old file to the new file
    copymode(file_path, abs_path)
    #Remove original file
    remove(file_path)
    #Move new file
    move(abs_path, file_path)


if __name__ == '__main__':

    rootdir = 'PINTO_model_zoo'

    for subdir, dirs, files in os.walk(rootdir):
        for file in files:
            if "download" in file and file.endswith(".sh"):

                file_path = os.path.join(subdir, file)

                if has_old_style(file_path):
                    replace_download_pattern(file_path)
            else:
                continue