import sys, re

html = sys.stdin.read()

print("SIZE:", len(html))

# Check for public/239 links
links = re.findall(r'href=["\'](/public/239/[^"\']+)["\'][^>]*>(.*?)</a>', html, re.S)
print(f"Direct 239 links: {len(links)}")
for href, txt_html in links[:10]:
    txt = re.sub(r'<[^>]+>', ' ', txt_html)
    txt = re.sub(r'\s+', ' ', txt).strip()
    if len(txt) > 5:
        print(f"  {txt[:80]} -> {href}")

# Check for any content div
for m in re.finditer(r'<div[^>]*id=["\']([^"\']+)["\'][^>]*>(.*?)</div>', html, re.S):
    txt = re.sub(r'<[^>]+>', ' ', m.group(2))
    txt = re.sub(r'\s+', ' ', txt).strip()
    if len(txt) > 200:
        print(f"DIV #{m.group(1)}: {txt[:150]}")

# Also check if list items are in a different format - maybe ul + li pattern
items = re.findall(r'class=["\'](?:title|xxgk-tit|list-title)["\'][^>]*>(.*?)</a>', html, re.S)
print(f"Title class links: {len(items)}")

# Look for year navigation
navs = re.findall(r'/public/column/239[^"\']*', html)
print(f"Column 239 nav links: {len(navs)}")
for n in navs[:5]:
    print(f"  {n[:120]}")