naive-check-alt-text.py

#!/usr/bin/env python3

# NOTE: this is a really naive solution that just checks for alt="" in the returned html from the page, 
# it would probably give a lot of erroneous results on other projects but got the job done for me.

import urllib.request as urllib2

base_path = "https://gatsbyjs.com"
blog_paths = 'blog_paths.txt'

with open(blog_paths) as fp:
    line = fp.readline()
    while line:
        path = line.strip()
        response = urllib2.urlopen(f'{base_path}{path}')
        html = response.read()
        raw_html = html.decode("utf-8")
        if 'alt=""' in raw_html:
            print(f'!!! alt text missing in {path} !!!')
        else:
            print(f'No missing alt text in {path}')
        line = fp.readline()