import os
import re
import fnmatch
import glob
from pathlib import Path
# Replace 'directory_path' with the path to the directory you want to search
#d_directory_path = '../download_dir/pastnotes1982/WEB/HTML'
#u_directory_path = '../upload_dir/pastnotes1982/WEB/HTML'
d_htm_directory_path = './download_dir/pastnotes1982/WEB/HTML/'
u_htm_directory_path = './download_dir/pastnotes1982/WEB/HTML/'
u_vid_directory_path = './download_dir/pastnotes1982/WEB/videos/'
final_directory_path = '../videos/'
newtext_hls = """
"""
# Define the regular expression pattern
pattern1 = re.compile(r'Mirrored.{200}', re.DOTALL)
pattern2 = re.compile(r'BLOGGER-video-[\d\w-]*', re.DOTALL)
def version_two():
Path(u_htm_directory_path).mkdir(parents=True, exist_ok=True)
# Loop through each file in the directory
for filename in os.listdir(d_htm_directory_path):
# Check if the file extension is .htm
if fnmatch.fnmatch(filename, 'VIDEO*.HTM'):
#if filename.endswith('.HTM'):
# Open the file and read its contents
with open(os.path.join(d_htm_directory_path, filename), 'r') as file:
contents = file.read()
if pattern1.search(contents):
res1 = pattern1.search(contents).group(0)
res2 = pattern2.search(contents).group(0)
uvfilename = u_vid_directory_path + res2 + ".m3u8"
if os.path.exists(uvfilename):
final_file_path = final_directory_path + res2 + ".m3u8"
print (final_file_path)
newcontents = (newtext_hls % (res1, res2, final_file_path))
with open(os.path.join(u_htm_directory_path, filename), 'w') as new_file:
new_file.write(newcontents)
print(f"{filename} updated")
else:
print(f"{filename} failed to find corresponding m3u8")
version_two()