Files & data

import zipfile
from pathlib import Path
import xml.etree.ElementTree as ET

def extract_hyperlinks_from_docx(filepath: str) -> list[dict]:
    """
    Extract all hyperlinks from a .docx file.
    Returns a list of dicts with 'text' and 'target' keys.
    """
    hyperlinks = []
    with zipfile.ZipFile(Path(filepath)…

import requests
from bs4 import BeautifulSoup

def scrape_headlines(url: str, selector: str) -> list:
    """
    Scrape headlines from a news website using Beautiful Soup.
    
    Args:
        url: The URL of the news website.
        selector: CSS selector for headline elements.
    
    Returns:
        List of h…