Simple helper for iservice.by

parser.py

from csv import writer
from os import listdir
from os.path import isfile
from sys import argv
import logging
import re

logger = logging.getLogger('iservice')


HTML_FILENAME_REGEX = re.compile(r'.*\.html?')
TITLES = [
    'Имя компьютера',
    'Тип ЦП',
    'Системная плата',
    'Дисковый накопитель',
    'Тип ядра ОС',
]
TITLES_REGEXPS = [
    (
        title,
        re.compile(
            f'<TR>.*<TD>{title}&nbsp;&nbsp;<TD>'
            r'(?:<A.*?>)?(?P<value>.*?)(?:</A>)?$',
            re.MULTILINE
        )
    ) for title in TITLES
]
SUMMARY_REGEXP = re.compile(
    r'<A NAME="summary">.*?</TABLE>'
    r'<TABLE>(?P<summary>.*?)</TABLE>',
    re.DOTALL
)


def parse(filename):
    with open(filename, encoding='cp1251', errors='ignore') as input_file:
        data = input_file.read()
    summary = SUMMARY_REGEXP.search(data).group('summary')
    row = []
    for title, regex in TITLES_REGEXPS:
        values = []
        for match in regex.finditer(summary):
            value = match.group('value')
            if title != 'Дисковый накопитель' or 'USB Device' not in value:
                values.append(value)
            if title == 'Имя компьютера':
                break
        if values:
            row.append('\n'.join(values))
        else:
            match = regex.search(data)
            row.append(match.group('value') if match else '')
    return row


def main(files):
    if not files:
        files = [
            filename for filename in listdir('.')
            if HTML_FILENAME_REGEX.match(filename) and isfile(filename)
        ]
    with open('report.csv', 'w', encoding='cp1251') as output_file:
        csv = writer(output_file)
        csv.writerow(TITLES)
        for filename in files:
            try:
                row = parse(filename)
            except:
                logger.error(f'Can not parse the "{filename}" file')
            else:
                csv.writerow(row)


if __name__ == '__main__':
    main(argv[1:])

Requirements

Python 3.6 or higher

How to use

python parser.py <filename1> <filename2> …
or
python parser.py (will parse all html and htm files at current directory)

Output

report.csv file