-
-
Save reubano/92b0bc1131d8284a2a3b46a3406fa3a6 to your computer and use it in GitHub Desktop.
This code shows how to check a sitemap to make sure there are no links pointing to missing pages and to see if 301s are working correctly. It is explained at https://www.webucator.com/blog/2016/05/checking-your-sitemap-for-broken-links-with-python/
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import requests | |
from bs4 import BeautifulSoup | |
sitemap = 'http://www.nasa.gov/sitemap/sitemap_nasa.html' | |
r = requests.get(sitemap) | |
html = r.content | |
soup = BeautifulSoup(html, 'html.parser') | |
links = soup.find_all('a') | |
hrefs = filter(None, (link.get('href') for link in links)) | |
urls = (href for href in hrefs if href.startswith('http')) | |
reqs = (requests.head(url) for url in external) | |
results = sorted(reqs, key=lambda r: (r.status_code, len(r.history))) | |
print('\n==========\OK') | |
for r in results: | |
if r.ok and not r.history: | |
print(' - '.join([str(r.status_code), r.reason, r.url])) | |
print('\n==========\REDIRECTS') | |
for r in results: | |
if r.ok and r.history: | |
print('{} redirected'.format(r.url)) | |
for response in result['history']: | |
print('>> Redirect to {}'.format(response.url)) | |
print('\n==========\nERRORS') | |
for r in results: | |
if not r.ok: | |
print(' - '.join([str(r.status_code), r.reason, r.url])) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment