Last active
April 6, 2023 01:01
-
-
Save ilovefreesw/fa763e1f84cd9f7101dc4816e293beda to your computer and use it in GitHub Desktop.
A script to check links in all the WordPress posts to find out broken ones. Saves the report in CSV file. Based on WordPress API and only needs domain as input.
This file contains 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 | |
import csv | |
import concurrent.futures | |
import sys, time | |
import bs4 | |
domain = sys.argv[1] | |
csv_file = sys.argv[2] | |
headers = { | |
'authority': 'www.'+domain, | |
'referer': 'https://'+domain, | |
'user-agent': 'Mozilla/5.0 (Linux; Android 6.0; Nexus 5 Build/MRA58N) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/99.0.4844.51 Mobile Safari/537.36', | |
'accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9', | |
'sec-fetch-dest': 'document', | |
'accept-language': 'en-US,en;q=0.9,tr;q=0.8', | |
} | |
links404 = [] | |
pages = int(requests.get('https://www.' + domain + '/wp-json/wp/v2/posts', headers=headers).headers['X-WP-TotalPages']) | |
def getLinks(rendered_content): | |
soup = bs4.BeautifulSoup(rendered_content, 'html.parser') | |
return [link['href'] for link in soup('a') if 'href' in link.attrs] | |
def getStatusCode(link, headers, timeout=5): | |
try: | |
r = requests.head(link, headers=headers, timeout=timeout) | |
except (requests.exceptions.SSLError, requests.exceptions.HTTPError, requests.exceptions.ConnectionError, requests.exceptions.MissingSchema, requests.exceptions.Timeout) as errh: | |
print("Error in URL, ", link) | |
return errh.__class__.__name__ | |
else: | |
if r.status_code not in [200, 500, 503]: | |
return str(r.status_code) | |
with concurrent.futures.ThreadPoolExecutor(max_workers = 4) as executor: | |
futures = [] | |
for i in range(pages): | |
post_data = requests.get('https://www.' + domain + '/wp-json/wp/v2/posts?page='+str(i+1), headers=headers).json() | |
for data in post_data: | |
print(data["link"]) | |
post_links = getLinks(data["content"]["rendered"]) | |
for url in post_links: | |
futures.append(executor.submit(getStatusCode, url, headers)) | |
for future in concurrent.futures.as_completed(futures): | |
info = { | |
"Post ID": data['id'], | |
"Post Link": data['link'], | |
"Broken Link": url, | |
"Status Code":future.result(), | |
} | |
links404.append(info) | |
with open(csv_file, 'w+') as file: | |
csvwriter = csv.DictWriter(file, fieldnames=list(links404[0].keys())) | |
csvwriter.writeheader() | |
csvwriter.writerows(links404) | |
print("Report saved in file: ", csv_file) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Run:
pip install requests bs4
python wpbroken.py <domain> <filename>
python wpbroken.py example.com example.csv