eddd9d2a80
- Successfully imported 1731 WordPress posts to Hugo markdown format - Migrated 204+ images from archive to static directory - Copied standalone directories (curtain, farm, gobbler, house, images, party, revcemetery, railsday, birthday) - Fixed all internal links to use /legacy prefix for archived content - Remapped archive links to point to correct Hugo posts - Fixed Louisville Georgia Cemetery post rendering issue 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com>
54 lines
1.2 KiB
Python
54 lines
1.2 KiB
Python
#!/usr/bin/env python3
|
|
"""
|
|
Quick check of external links
|
|
"""
|
|
|
|
import re
|
|
from pathlib import Path
|
|
from collections import defaultdict
|
|
|
|
POSTS_DIR = Path('/Users/ericwagoner/Sites/blog/content/posts')
|
|
|
|
# Just check a sample of posts first
|
|
sample_posts = list(POSTS_DIR.glob('*.md'))[:50]
|
|
|
|
all_links = set()
|
|
|
|
for post in sample_posts:
|
|
with open(post, 'r', encoding='utf-8') as f:
|
|
content = f.read()
|
|
|
|
# Find all ericwagoner.com links
|
|
links = re.findall(r'http://www\.ericwagoner\.com[^\s\)"]+', content)
|
|
all_links.update(links)
|
|
|
|
# Categorize
|
|
images = []
|
|
html_pages = []
|
|
other = []
|
|
|
|
for url in all_links:
|
|
if re.search(r'\.(jpg|jpeg|gif|png)$', url, re.IGNORECASE):
|
|
images.append(url)
|
|
elif url.endswith('.html') or url.endswith('.htm'):
|
|
html_pages.append(url)
|
|
else:
|
|
other.append(url)
|
|
|
|
print(f"Sample from first 50 posts:")
|
|
print(f" Total unique links: {len(all_links)}")
|
|
print(f" Images: {len(images)}")
|
|
print(f" HTML pages: {len(html_pages)}")
|
|
print(f" Other: {len(other)}")
|
|
|
|
print("\nSample image links:")
|
|
for url in images[:5]:
|
|
print(f" {url}")
|
|
|
|
print("\nSample HTML page links:")
|
|
for url in html_pages[:5]:
|
|
print(f" {url}")
|
|
|
|
print("\nSample other links:")
|
|
for url in other[:5]:
|
|
print(f" {url}") |