Exercise 1 solution

    import re

    acc_re = re.compile(
        r'(?P<ip>\S+) \S+ \S+ \[(?P<when>[^\]]+)\] '
        r'"(?P<method>[A-Z]+) (?P<path>\S+) [^"]*" '
        r'(?P<status>\d{3}) (?P<size>\d+|-)'
    )

    def parse_access(line):
        m = acc_re.fullmatch(line)
        if not m:
            return None
        d = m.groupdict()
        d["status"] = int(d["status"])
        d["size"] = 0 if d["size"] == "-" else int(d["size"])
        return d

    lines = [
        '192.168.1.5 - - [02/Nov/2026:09:15:03] "GET /index.html HTTP/1.1" 200 512',
        '10.0.0.8 - - [02/Nov/2026:09:15:09] "POST /login HTTP/1.1" 302 -',
        'not an access line',
    ]
    for l in lines:
        print(parse_access(l))
    # {'ip': '192.168.1.5', 'when': '02/Nov/2026:09:15:03', 'method': 'GET', 'path': '/index.html', 'status': 200, 'size': 512}
    # {'ip': '10.0.0.8', 'when': '02/Nov/2026:09:15:09', 'method': 'POST', 'path': '/login', 'status': 302, 'size': 0}
    # None

(All lines were run and printed exactly what is shown.)

Explanation: [^\]]+ takes everything up to the closing bracket, and [^"]*
takes the rest of the quoted request without crossing the closing quote.
The size group allows digits or a single hyphen, and the dictionary values
for status and size are converted afterwards, once we know they matched.