searchhtml.py

#!/usr/bin/env python3
# Copyright 2025 Marcus Müller
# SPDX-License-Identifier: EUPL-1.2
#
from bs4 import BeautifulSoup
from itertools import chain
import logging
import re
import sys


if len(sys.argv) < 3:
    logging.error(
        "USAGE:\n%s REGEX FILE1 [FILE2…]",
        sys.argv[0],
    )
    sys.exit(1)

regex = re.compile(sys.argv[1])

for filename in sys.argv[2:]:
    try:
        file_handle = open(filename)
    except FileNotFoundError:
        continue
    try:
        soup = BeautifulSoup(file_handle, "html.parser")
        findings = []
        try:
            findings += soup.head.title.find_all(string=regex)
        except:
            pass
        try:
            findings += soup.body.find_all(string=regex)
        except:
            pass
        for finding in chain(findings):
            print(f"{filename+':':20s}{finding.text}")
    except:
        pass
    finally:
        file_handle.close()