Grab URLs

urls.py

#!/bin/python3

from sys import argv
from typing import Optional
from dataclasses import dataclass
from datetime import datetime
from bs4 import BeautifulSoup
from urllib import request


@dataclass
class Entry(object):
    timestamp: datetime
    title: str
    url: str

    def __repr__(self) -> str:
        return f" - [{self.timestamp}] [{self.title}]({self.url})\n\n---\n"


def fetch_title(url: str) -> Optional[str]:
    return BeautifulSoup(
        request.urlopen(url).read().decode('utf8'),
        "html.parser"
    ).find("title").text


def main() -> None:
    if len(argv) != 2:
        print("usage: wiki_urls.py infile")
        exit(1)

    with open(argv[1], "r") as f:
        entries = [
            Entry(
                datetime.now().isoformat(),
                fetch_title(line.strip()),
                line.strip()
            ) for line in f.readlines()
        ]

        print("---")
        
        for entry in entries:
            print(entry)


if __name__ == "__main__":
    main()