github-beautiful.py

github-beautiful.py

#!/usr/bin/env python3
#Copyright 2023 - genr8eofl @IRC/gentoo
# github-beautiful.py - fetch GitHub repo "Description" (for many links at once)
#       Makes 1 HTTPS connection per line, retreives the HTML page and parses it for <Title>
import requests
from requests import ReadTimeout, ConnectTimeout, HTTPError, Timeout, ConnectionError
from bs4 import BeautifulSoup
import sys

urlprefix="https://github.com/"
#Usage: Takes 1 argument, a filename containing github repos
filename = sys.argv[1]
with open(filename) as file1:
  #loop, go
  while True:

    # get each next line from file
    line = file1.readline()
    # sanitize input strings, repo name
    repo = line.strip()

    # internet connection to github
    try:
      page = requests.get(urlprefix + repo)
    except (ConnectTimeout, HTTPError, ReadTimeout, Timeout, ConnectionError):
      continue
    # parse HTML, find <Title> tag
    soup = BeautifulSoup(page.text, 'html.parser')
    title = soup.find('title')
	# output
    if title:
      print(title.string)
    else:
      print("404_NOT_FOUND - ", repo)

    # if line is empty, EOF is reached, done, end loop.
    if not repo:
      break