Python duplicate classes finder

find_duplicate_classes.py

import os
import re
from pprint import pprint

class_re = r'class (\w+)\((.*)\)'

classes = {}

for root, subdirs, files in os.walk('./homeowners'):
    for file in files:
        if file.endswith('.py'):
            filename = os.path.join(root, file)
            with open(filename, 'r') as f:
                content = f.read()
            for m in re.finditer(class_re, content):
                class_name = m.group(1)
                if class_name in ['in', 'for', 'Meta', 'Migration', 'is', 'Media', 'Command']:
                    continue
                if 'TestCase' in class_name:
                    continue
                if 'legacy' in filename:
                    continue

                baseclass = m.group(2)

                if class_name not in classes:
                    classes[class_name] = []
                if filename not in classes[class_name]:
                    classes[class_name].append(filename)

cl_items = classes.items()

for class_name, files in cl_items:
    if len(files) == 1:
        del classes[class_name]

pprint(classes)