To redact student names from `.html` comparison files

redact-student-names.py

from bs4 import BeautifulSoup
import re
import os
import zipfile

def redact_names(html_filename, OUTPUT_DIR='.'):

    ## Load html file
    with open(html_filename, 'r') as f:
        txt = f.read()

    soup = BeautifulSoup(txt, 'html.parser')

    # Change path references
    for tag in soup.find_all(href=True):
        if tag['href'].startswith('../assets/'):
            tag['href'] = './' + tag['href'][3:]

    for tag in soup.find_all(src=True):
        if tag['src'].startswith('../assets/'):
            tag['src'] = './' + tag['src'][3:]

    ## Redact student names from title
    title = soup.find('title')
    title.string = re.sub(r'^.* x .* : ', '', title.text)

    ## Get student names
    student_left = soup.select_one('.split .header')
    student_left_original = student_left.string

    student_right = soup.select_one('.split-right .header')
    student_right_original = student_right.string

    ## Redact student left
    student_left.string = 'OTHER STUDENT'
    # Save to directory
    unikey = re.sub(r'^.*- (.*)@.*', '\g<1>', student_right_original)
    directory = unikey
    if not os.path.exists(directory):
        os.makedirs(directory)
    # with filename
    out_filename = re.sub('.*(\.q.\.html)', f'{unikey}\g<1>', html_filename)
    with open(f'{OUTPUT_DIR}/{directory}/{out_filename}', 'w') as f:
        f.write(str(soup))
    print('Written: ', f'{OUTPUT_DIR}/{directory}/{out_filename}')

    ## Redact student right
    student_left.string = student_left_original
    student_right.string = 'OTHER STUDENT'
    # Save to directory
    unikey = re.sub(r'^.*- (.*)@.*', '\g<1>', student_left_original)
    directory = unikey
    if not os.path.exists(directory):
        os.makedirs(directory)
    # with filename
    out_filename = re.sub('.*(\.q.\.html)', f'{unikey}\g<1>', html_filename)
    with open(f'{OUTPUT_DIR}/{directory}/{out_filename}', 'w') as f:
        f.write(str(soup))
    print('Written: ', f'{OUTPUT_DIR}/{directory}/{out_filename}')

    ## Reset
    student_right.string = student_right_original

    
# ----------------------------------------------------------------------
INPUT_BASE_DIR = '../path-of-dir'
input_dirs = [
    os.path.join(INPUT_BASE_DIR, d) for d in os.listdir(INPUT_BASE_DIR)
    if re.match('^[a-z]{4}\d{4}-', d)
]

for input_dir in input_dirs:
    for filename in os.listdir(input_dir):
        if filename.endswith('.html'):
            html_filename = os.path.join(input_dir, filename)
            print('Input: ', html_filename)
            redact_names(html_filename)
    
filtered_list = [d for d in os.listdir('.') if re.match(r'^[a-z]{4}[\d]{4}$', d)]

for directory in filtered_list:
    zip_filename = f'{directory}-files.zip'

    with zipfile.ZipFile(zip_filename, 'w') as zipf:
        
        # Copy HTML files into zip file
        for root, dirs, files in os.walk(directory):
            for file in files:
                file_path = os.path.join(root, file)
                print(file_path)
                zipf.write(file_path, os.path.relpath(file_path, directory))
        
        # Copy assets into zip file
        for root, dirs, files in os.walk('assets'):
            for file in files:
                file_path = os.path.join(root, file)
                print(file_path)
                zipf.write(file_path, os.path.relpath(file_path, '.'))