123 lines
4.2 KiB
Python
123 lines
4.2 KiB
Python
"""Text hygiene: everything user- or web-supplied is reduced to plain text before it is stored.
|
|
Rendering escapes again (defence in depth)."""
|
|
from __future__ import annotations
|
|
|
|
import html
|
|
import re
|
|
import unicodedata
|
|
import urllib.parse
|
|
from html.parser import HTMLParser
|
|
|
|
_CTRL = re.compile(r"[\x00-\x08\x0b\x0c\x0e-\x1f\x7f\u200b-\u200f\u202a-\u202e\u2066-\u2069\ufeff]")
|
|
URL_RE = re.compile(r"https?://[^\s<>\"'`]+", re.I)
|
|
|
|
|
|
def plain(s, limit: int) -> str:
|
|
"""Unicode-normalised plain text: no tags, no control/bidi characters, collapsed spaces."""
|
|
if not isinstance(s, str):
|
|
return ""
|
|
s = unicodedata.normalize("NFKC", s)
|
|
s = strip_tags(s) if "<" in s else s
|
|
s = html.unescape(s)
|
|
s = re.sub(r"<[^>]*>?", "", s) # anything tag-like left after unescape
|
|
s = _CTRL.sub("", s.encode("utf-8", "ignore").decode("utf-8"))
|
|
s = re.sub(r"\s+", " ", s).strip()
|
|
return s[:limit].rstrip()
|
|
|
|
|
|
class _Strip(HTMLParser):
|
|
SKIP = {"script", "style", "noscript", "template", "svg", "iframe", "head", "nav", "footer", "aside", "form"}
|
|
|
|
def __init__(self):
|
|
super().__init__(convert_charrefs=True)
|
|
self.out: list[str] = []
|
|
self.paras: list[str] = []
|
|
self._buf: list[str] = []
|
|
self.depth = 0
|
|
self.title = ""
|
|
self._in_title = False
|
|
self.meta: dict[str, str] = {}
|
|
|
|
def handle_starttag(self, tag, attrs):
|
|
if tag in self.SKIP:
|
|
self.depth += 1
|
|
if tag == "title":
|
|
self._in_title = True
|
|
if tag == "meta":
|
|
a = dict(attrs)
|
|
k = (a.get("property") or a.get("name") or "").lower()
|
|
if k in ("og:title", "og:description", "description", "og:site_name", "article:published_time") and a.get("content"):
|
|
self.meta.setdefault(k, a["content"])
|
|
if tag in ("p", "br", "div", "li", "h1", "h2", "h3"):
|
|
self._flush()
|
|
|
|
def handle_endtag(self, tag):
|
|
if tag in self.SKIP and self.depth:
|
|
self.depth -= 1
|
|
if tag == "title":
|
|
self._in_title = False
|
|
if tag in ("p", "li", "div", "h1", "h2", "h3"):
|
|
self._flush()
|
|
|
|
def _flush(self):
|
|
t = " ".join("".join(self._buf).split())
|
|
if len(t) > 60:
|
|
self.paras.append(t)
|
|
self._buf = []
|
|
|
|
def handle_data(self, data):
|
|
if self._in_title:
|
|
self.title += data
|
|
if not self.depth:
|
|
self.out.append(data)
|
|
self._buf.append(data)
|
|
|
|
|
|
def strip_tags(s: str) -> str:
|
|
p = _Strip()
|
|
try:
|
|
p.feed(s)
|
|
p.close()
|
|
except Exception: # noqa: BLE001 - malformed markup: fall back to regex
|
|
return re.sub(r"<[^>]*>", " ", s)
|
|
return " ".join("".join(p.out).split())
|
|
|
|
|
|
def page_info(body: bytes, ctype: str) -> dict:
|
|
"""Title, description and the first readable paragraphs of an HTML page (for summarising)."""
|
|
m = re.search(r"charset=([\w-]+)", ctype or "")
|
|
try:
|
|
s = body.decode(m.group(1) if m else "utf-8", "replace")
|
|
except LookupError:
|
|
s = body.decode("utf-8", "replace")
|
|
p = _Strip()
|
|
try:
|
|
p.feed(s)
|
|
p.close()
|
|
except Exception: # noqa: BLE001
|
|
pass
|
|
p._flush()
|
|
return {"title": plain(p.meta.get("og:title") or p.title, 200),
|
|
"description": plain(p.meta.get("og:description") or p.meta.get("description"), 500),
|
|
"site": plain(p.meta.get("og:site_name"), 80),
|
|
"published": plain(p.meta.get("article:published_time"), 40),
|
|
"text": plain(" ".join(p.paras), 4000)}
|
|
|
|
|
|
def safe_url(u) -> str:
|
|
"""Only absolute http(s) URLs without credentials survive; anything else becomes ''."""
|
|
if not isinstance(u, str):
|
|
return ""
|
|
u = u.strip()
|
|
if len(u) > 2000 or _CTRL.search(u) or any(c in u for c in " <>\"'`\\"):
|
|
return ""
|
|
p = urllib.parse.urlsplit(u)
|
|
if p.scheme.lower() not in ("http", "https") or not p.hostname or p.username or p.password:
|
|
return ""
|
|
return urllib.parse.urlunsplit((p.scheme.lower(), p.netloc.lower(), p.path, p.query, ""))
|
|
|
|
|
|
def domain(u: str) -> str:
|
|
h = (urllib.parse.urlsplit(u).hostname or "").lower()
|
|
return h[4:] if h.startswith("www.") else h
|