LWN Calendar data extraction

lwn_calendar_extract.py

import requests
from lxml import html
import re
year = "2024" 
month = "09"  

response = requests.get(f'https://lwn.net/Calendar/Monthly/{year}-{month}/')

if response.status_code==200:
    document_root =html.fromstring(response.content)
    # Find all <a> elements (links)
    links = document_root.xpath('/html/body/div[4]/div[1]/div[2]/div/table//a')

    # Use a set to store unique links
    unique_links = set()

    # Extract and store unique href attributes
    for link in links:
        href = link.get('href')
        text = link.text_content().strip()
        if href:
            unique_links.add((href, text))

    # Print the unique links
    for href, text in unique_links:
        #filtering external url from the calander
        if re.match("/^http|https://(.*)/",href):
            print(f"Link: {href}, Text: {text}")
    else:
        print(response.status_code)