new-codigoparallevar/scripts/test-links.py
Sergio Martínez Portela 23f8fcefe5 Improve link checking.
2023-10-03 00:09:30 +02:00

60 lines
1.9 KiB
Python

#!/usr/bin/env python3
import logging
import os
import sys
import urllib.parse
from bs4 import BeautifulSoup as bs4
from tqdm import tqdm
def main(files_top):
print("Listing files...")
found_files = []
for root, dirs, files in os.walk(files_top):
for name in files:
if name.endswith('.html'):
found_files.append(os.path.join(root, name))
print("\r{} files".format(len(found_files)), end='', flush=True)
print()
found_broken = 0
for fpath in tqdm(found_files):
with open(fpath) as f:
tree = bs4(f.read(), features='lxml', parser='html5')
for tag, attr in [('a', 'href'), ('img', 'src'), ('audio', 'src'), ('video', 'src')]:
for link in tree.find_all(tag):
if attr not in link.attrs:
continue
link.attrs[attr] = link.attrs[attr].split('#')[0]
if not link.attrs[attr]:
continue
if ':' in link[attr]:
continue
if link[attr].startswith('/'):
target = os.path.join(os.path.abspath(files_top), urllib.parse.unquote(link[attr].lstrip('/')))
else:
target = os.path.join(os.path.dirname(fpath), urllib.parse.unquote(link[attr]))
if os.path.isdir(target):
pass
elif not os.path.exists(target):
print("[{}] -[ error ]-> {} | {}".format(fpath, target, link[attr]))
found_broken += 1
if found_broken:
print(f"Found {found_broken} broken links")
exit(1)
else:
exit(0)
if __name__ == "__main__":
if len(sys.argv) != 2:
print("Usage: {} FILES_TOP".format(sys.argv[0]))
exit(0)
logging.basicConfig(level=logging.INFO, format="%(levelname)-8s %(message)s")
exit(main(sys.argv[1]))