[Python] Using Python to go through picture files and identify duplicates

My picture files are considered duplicates if the name contains "-edited" and/or "(n)", where n is a number between 1 and 9. The following does not work for me:

• Sample file_name1 "IMAG0320-edited(1).jpg"
• Sample file_name2 "IMAG0320-edited.jpg"
• Sample file_name3 "IMAG0320-edited.jpg"

The following code works to identify "-edited" files:

edited_pattern = re.compile(r"(.+)-edited\.jpg$", re.IGNORECASE)


I cannot get the following code to work.

numbered_pattern = re.compile(r"(.+)$$(\d)$$\.jpg$", re.IGNORECASE)


Here is the whole thing:

#!/usr/bin/env python
import os
import re

# Hash containers
hash1 = {}
hash2 = {}
hash3 = {}

# Regex patterns
edited_pattern = re.compile(r"(.+)-edited\.jpg$", re.IGNORECASE)
numbered_pattern = re.compile(r"(.+)$$(\d)$$\.jpg$", re.IGNORECASE)
base_pattern = re.compile(r"(.+)\.jpg$", re.IGNORECASE)

# Step 1: Traverse and populate the hashes
def traverse_and_collect(directory):
for root, _, files in os.walk(directory):
for file in files:
file_path = os.path.join(root, file)
file_lower = file.lower()
#print ("ALL file" + file + ") file_path" + file_path + ")\n")

if edited_pattern.match(file_lower):
base_name = edited_pattern.match(file_lower).group(1) + ".jpg"
hash1[file_path] = os.path.join(root, base_name)
print ("EDT file" + file + ") file_path" + file_path + ")\n")

elif numbered_pattern.match(file_lower):
base_name = numbered_pattern.match(file_lower).group(1) + ".jpg"
hash2[file_path] = os.path.join(root, base_name)
print ("NBR file" + file + ") file_path" + file_path + ")\n")

elif base_pattern.match(file_lower):
if not "-edited.jpg" in file_lower and not numbered_pattern.match(file_lower):
hash3[file_path] = file_path
print ("CLN file" + file + ") file_path" + file_path + ")\n")

# Step 2: Replace keys in hash1 based on matches in hash2 or hash3
def update_hash1_keys():
value_to_alt_key = {}

# Build reverse lookup from hash2 and hash3
for k, v in hash2.items():
value_to_alt_key[v] = k
for k, v in hash3.items():
value_to_alt_key[v] = k # hash3 takes priority if same value appears in both

# Replace keys in hash1 if value found in either hash2 or hash3
new_hash1 = {}
for k, v in hash1.items():
if v in value_to_alt_key:
new_key = value_to_alt_key[v]
new_hash1[new_key] = v
else:
new_hash1[k] = v

return new_hash1

# Main logic
if __name__ == "__main__":
#directory = input("Enter directory to scan: ").strip()
directory = "/mnt/sdb1/google_photos/"
traverse_and_collect(directory)

print("\n--- Initial Hash1 ---")
for k, v in hash1.items():
print(f"{k} -> {v}")

hash1_updated = update_hash1_keys()

print("\n--- Updated Hash1 (after replacement) ---")
for k, v in hash1_updated.items():
print(f"{k} -> {v}")

Continue reading...