lichenblankie/tinyweb
2
0
Fork 0
Code Issues Pull requests Projects 1 Releases Packages Wiki Activity Actions

rns: store cleaned text instead of raw HTML body

Browse source
This commit is contained in:
blankie 2026-07-02 23:27:05 +00:00
parent 21264b941f
commit 5c208ce3e3
2 changed files with 22 additions and 14 deletions
Download patch file Download diff file Expand all files Collapse all files

2
src/tinyweb/handlers/pages.py
View file

@ -90,7 +90,7 @@ def handle_add_submit(body):
return handle_add_form(f"Error: {esc(str(e))}") return handle_add_form(f"Error: {esc(str(e))}")
except Exception as e: except Exception as e:
error_msg = str(e).lower() error_msg = str(e).lower()
if any(x in error_msg for x in ("block", "cloudflare", "403", "ssl", "handshake", "max retries", "timeout", "connection")): if any(x in error_msg for x in ("block", "cloudflare", "403", "429", "ssl", "handshake", "max retries", "timeout", "connection")):
return _respond( return _respond(
f"<h1>add url (manual entry)</h1>" f"<h1>add url (manual entry)</h1>"
f"<p><strong>{esc(url)}</strong> blocks automated access. " f"<p><strong>{esc(url)}</strong> blocks automated access. "

34
src/tinyweb/handlers/rns.py
View file

@ -2,6 +2,8 @@ import json
import time import time
import threading import threading
import traceback import traceback
import datetime
from bs4 import BeautifulSoup
from tinyweb.db import get_db, return_db from tinyweb.db import get_db, return_db
from tinyweb.rns_client import fetch_remote_page from tinyweb.rns_client import fetch_remote_page
from tinyweb.templates import esc from tinyweb.templates import esc
@ -69,26 +71,32 @@ def handle_rns_add_hash(dest_hash, name=""):
try: try:
resp = fetch_remote_page(dest_hash, "/") resp = fetch_remote_page(dest_hash, "/")
if resp.get("status") == 200: if resp.get("status") == 200:
body = resp.get("body", "") body_raw = resp.get("body", "")
soup = BeautifulSoup(body_raw, 'html.parser')
for tag in soup(["script", "style", "nav", "footer", "header", "noscript", "aside"]):
tag.decompose()
cleaned = soup.get_text(separator=" ", strip=True)
title = name or dest_hash[:16] title = name or dest_hash[:16]
import re if soup.title and soup.title.string:
m = re.search(r"<title[^>]*>(.*?)</title>", body, re.IGNORECASE | re.DOTALL) title = soup.title.string.strip()
if m:
title = m.group(1).strip()
desc = "" desc = ""
m = re.search(r'<meta\s+name="description"\s+content="([^"]*)"', body, re.IGNORECASE) m = soup.find("meta", attrs={"name": "description"})
if m: if m and m.get("content"):
desc = m.group(1).strip() desc = m["content"].strip()
if not desc: if not desc:
text = re.sub(r"<[^>]+>", " ", body) m = soup.find("meta", attrs={"property": "og:description"})
text = re.sub(r"\s+", " ", text).strip() if m and m.get("content"):
desc = text[:200].strip() desc = m["content"].strip()
if not desc:
desc = cleaned[:200].strip()
url = f"rns:{dest_hash}" url = f"rns:{dest_hash}"
import datetime
now = datetime.datetime.now().strftime("%Y-%m-%dT%H:%M:%S") now = datetime.datetime.now().strftime("%Y-%m-%dT%H:%M:%S")
db.execute( db.execute(
"INSERT OR REPLACE INTO pages (url, title, body, last_modified, summary) VALUES (?, ?, ?, ?, ?)", "INSERT OR REPLACE INTO pages (url, title, body, last_modified, summary) VALUES (?, ?, ?, ?, ?)",
(url, title, body, now, desc), (url, title, cleaned, now, desc),
) )
else: else:
errors.append(f"Remote returned status {resp.get('status')}") errors.append(f"Remote returned status {resp.get('status')}")