Unzips all zip Canvas submissions for webdev, reorganizes file structure, and validates all HTML & CSS files.

webdev_zip_grader.py

# 1. Download the submissions.zip file from Canvas.
# 2. Place it in an empty folder for the specific assignment. Make sure it is called submissions.zip.
# 3. Copy the webdev_zip_grader.py script into the folder.
# 4. Make sure the folder is empty except for webdev_zip_grader.py and submissions.zip because it will delete everything else.
# 5. Double-click the script to run.
# 6. Hit the enter key in the script window to advance it to the next page.


import os
import shutil
import requests
import subprocess
import webbrowser
from zipfile import ZipFile

dir = os.path.dirname(os.path.abspath(__file__))
filename = 'submissions.zip'
path = os.path.join(dir, filename)

# remove everything
for root, subdirs, _files in os.walk(dir):
    for d in subdirs:
        shutil.rmtree(os.path.join(dir, d))

# unzip
with ZipFile(path, 'r') as zip:
    zip.extractall(dir)

# rename zip files
submissions = [f for f in os.listdir(
    dir) if f.endswith(".zip") and f != filename]
for sub in submissions:
    sub = os.path.join(dir + '/' + sub)
    new = os.path.join(dir + '/' + sub.split('/')[-1].split('_')[0] + '.zip')
    os.rename(sub, new)

# extract and delete zips
submissions = [f for f in os.listdir(
    dir) if f.endswith(".zip") and f != filename]
for sub in submissions:
    path = os.path.join(dir, sub)
    with ZipFile(path, 'r') as zip:
        zip.extractall(path[:-4])
    os.remove(path)

# parse student folders and move all files
students = next(os.walk(dir))[1]
for sub in students:
    path = os.path.join(dir, sub)

    for root, subdirs, files in os.walk(path):
        if "__MACOSX" in subdirs:
            shutil.rmtree(os.path.join(path, "__MACOSX"))

    # find the files
    def find_folder(path):
        for root, subdirs, files in os.walk(path):
            print(path, root)
            if path == root:
                print(files)
                if [f for f in files if f.split('.')[-1].lower() in ['html', 'css']]:
                    return root
                else:
                    if len(subdirs) == 1:
                        return find_folder(os.path.join(path, subdirs[0]))
                    else:
                        print("Error: too many subfolders?")

    location = find_folder(path)

    # move and copy files/folders
    for _r, _s, _f in os.walk(location):
        _f = [f for f in _f if '.ds_store' not in f.lower()]
        for s in _s:
            shutil.move(os.path.join(_r, s),
                        os.path.join(path, s))
    for _r, _s, _f in os.walk(location):
        _f = [f for f in _f if '.ds_store' not in f.lower()]
        for f in _f:
            if f.split('.')[-1].lower() in ['html', 'css', 'js']:
                shutil.move(os.path.join(_r, f),
                            os.path.join(path, f))
            elif os.path.join(_r, f) != os.path.join(path, f):  # images
                shutil.copy2(os.path.join(_r, f),
                             os.path.join(path, f))
    if location != path:
        shutil.rmtree(location)


# check to see if it validates
def validate_file(filename):
    with open(filename, 'r', encoding='utf-8', errors='ignore') as f:
        raw = f.read()

    if filename.lower().endswith('.html'):
        r = requests.post('https://validator.nu/',
                          data=raw.encode('utf-8'),
                          params={'out': 'json'},
                          headers={'Content-Type': 'text/html; charset=UTF-8'})
        if r.json()['messages']:
            messages = [msg for msg in r.json()['messages']]
            try:
                [msg.pop('hiliteStart') for msg in messages]
                [msg.pop('hiliteLength') for msg in messages]
            except:
                pass
            messages = [str(msg) for msg in messages]
            messages = '\n\t\t'.join(messages)
            return f"{len(r.json()['messages'])} errors" "\n\t\t" + messages
        else:
            return False
    elif filename.lower().endswith('.css'):
        r = requests.get('https://jigsaw.w3.org/css-validator/validator',
                         params={"text": raw.encode('utf-8'),
                                 "output": "json"},
                         headers={'Content-Type': 'text/plain; charset=UTF-8'})
        data = r.json()['cssvalidation']
        if data['result']['errorcount']:
            messages = [msg for msg in data['errors']]
            [msg.pop('source') for msg in messages]
            messages = [str(msg) for msg in messages]
            messages = '\n\t\t'.join(messages)
            count = f"{data['result']['errorcount']} errors & {data['result']['warningcount']} warnings"
            return count + "\n\t\t" + messages
        else:
            return False


# main processing loop for each student
f = open(f"{dir}/{filename.split('.')[0]}.txt", 'w', encoding='utf-8')
for s in students:
    f.write(f'\n{s}\n')
    print(f'\n{s}')
    files = os.listdir(os.path.join(dir, s))
    html = [f for f in files if f.lower().endswith('.html')]
    files = [f for f in files if f.lower().endswith('.css')]
    files.extend(html)
    for p in files:
        f.write(f'\t{p}\n')
        print(f'\t{p}')
        p = os.path.join(dir, s, p)
        invalidated = validate_file(p)
        if invalidated:
            f.write('\t\tINVALID: ' + invalidated + '\n')
            print('\t\tINVALID: ' + invalidated)
        if not invalidated:
            f.write('\t\tVALID!\n')
            print('\t\tVALID!')
        # open
        subprocess.call(
            [r"C:\\Program Files\\Notepad++\\notepad++.exe", p, "-n1500"])
        if p.lower().endswith('.html'):
            webbrowser.open(p, new=2)
            input()
f.close()