text-summarizer / app.py
BonusLockSMith's picture
security: log only exception type (never secrets); generic client errors
574569c verified
Raw History Blame Contribute Delete
21.7 kB
#!/usr/bin/env python
"""Text Summarizer — paste text or a URL, get a clean TL;DR + key points.
Streams the summary live. Backend auto-selects: Anthropic Claude API if
ANTHROPIC_API_KEY is set, otherwise a local Ollama model.
pip install flask requests anthropic beautifulsoup4
python app.py # http://127.0.0.1:8500
Project #2 of the "30 Projects in 15 Days" challenge — GritAI.
"""
import os, re, json, html
from flask import Flask, request, Response
PORT = int(os.environ.get("PORT", "8500"))
ANTHROPIC_KEY = os.environ.get("ANTHROPIC_API_KEY")
ANTHROPIC_MODEL = os.environ.get("ANTHROPIC_MODEL", "claude-sonnet-5")
OLLAMA_URL = os.environ.get("OLLAMA_URL", "http://127.0.0.1:11434")
OLLAMA_MODEL = os.environ.get("OLLAMA_MODEL", "qwen2.5:7b")
MAX_CHARS = 40000 # cap input to control tokens/cost
LENGTHS = {
"brief": "a tight 2-4 sentence TL;DR that captures the essence. No bullet points, no headings.",
"standard": "first a 2-3 sentence overview paragraph, then a blank line, then 4-6 key points, each on its own line starting with '- '.",
"detailed": "first a short overview paragraph, then a blank line, then 7-10 key points each on its own line starting with '- ', preserving important specifics (names, numbers, dates, outcomes).",
}
def system_prompt(length):
return (
"You are an expert editor who writes clear, coherent summaries.\n"
"OUTPUT FORMAT: " + LENGTHS.get(length, LENGTHS["standard"]) + "\n"
"RULES:\n"
"- Be faithful to the source; never add facts, opinions, or details not present.\n"
"- Write clean, natural plain text. Do NOT use markdown (**bold**, # headings). "
"Strip any citation markers like [1], footnote symbols, or wiki artifacts.\n"
"- Bullets (when used) start with '- ', are clear parallel phrases or sentences, and are non-redundant.\n"
"- Lead with the single most important point. Be specific, not vague. Do not restate these instructions."
)
_CITE = re.compile(r'\[(?:\d+|[a-z]{1,3}|note \d+|citation needed|clarification needed|edit|update|when\?|who\?|why\?)\]', re.I)
def _clean(text):
text = _CITE.sub("", text or "")
return "\n".join(l.strip() for l in text.splitlines() if l.strip())
def fetch_url_text(url):
"""Fetch a page and extract the main article text (trafilatura, bs4 fallback)."""
import requests
r = requests.get(url, timeout=20, headers={"User-Agent": "Mozilla/5.0 (compatible; GritAI-Summarizer/1.0)"})
r.raise_for_status()
doc = r.text
text = ""
try:
import trafilatura
text = trafilatura.extract(doc, include_comments=False, include_tables=False, favor_precision=True) or ""
except Exception:
text = ""
if len(text) < 200: # fallback: main-content via bs4
from bs4 import BeautifulSoup
soup = BeautifulSoup(doc, "html.parser")
for tag in soup(["script", "style", "nav", "header", "footer", "aside", "noscript", "form"]):
tag.decompose()
main = (soup.find("main") or soup.find("article") or soup.find(id="mw-content-text")
or soup.body or soup)
text = main.get_text("\n")
text = _clean(text)
if len(text) < 200:
raise ValueError("Couldn't extract readable text from that page (it may be JavaScript-only or blocked).")
return text
def summarize_stream(text, length):
sys = system_prompt(length)
user = "Summarize the following:\n\n" + text[:MAX_CHARS]
if ANTHROPIC_KEY:
import anthropic
client = anthropic.Anthropic(api_key=ANTHROPIC_KEY)
with client.messages.stream(model=ANTHROPIC_MODEL, max_tokens=800, system=sys,
messages=[{"role": "user", "content": user}]) as s:
for t in s.text_stream:
yield t
return
import requests
with requests.post(f"{OLLAMA_URL}/api/chat", stream=True, timeout=120, json={
"model": OLLAMA_MODEL, "stream": True,
"messages": [{"role": "system", "content": sys}, {"role": "user", "content": user}],
"options": {"temperature": 0.2}}) as r:
r.raise_for_status()
for line in r.iter_lines():
if not line:
continue
d = json.loads(line)
if d.get("message", {}).get("content"):
yield d["message"]["content"]
if d.get("done"):
break
app = Flask(__name__)
@app.route("/")
def home():
return Response(PAGE, mimetype="text/html")
@app.route("/api/summarize", methods=["POST"])
def api_summarize():
body = request.get_json(force=True)
text = (body.get("text") or "").strip()
url = (body.get("url") or "").strip()
length = body.get("length", "standard")
def gen():
import sys as _sys
try:
src = text
if url:
yield "data: " + json.dumps({"t": "Fetching the page…\n\n"}) + "\n\n"
src = fetch_url_text(url)
if not src:
yield "data: " + json.dumps({"t": "Please paste some text or a URL to summarize."}) + "\n\n"
yield "data: [DONE]\n\n"
return
if url:
yield "data: " + json.dumps({"reset": True}) + "\n\n" # clear the "fetching" note
for chunk in summarize_stream(src, length):
yield "data: " + json.dumps({"t": chunk}) + "\n\n"
except Exception as e:
print("summarize error:", type(e).__name__, file=_sys.stderr, flush=True)
yield "data: " + json.dumps({"t": "Sorry — something went wrong. Please try again."}) + "\n\n"
yield "data: [DONE]\n\n"
return Response(gen(), mimetype="text/event-stream",
headers={"Cache-Control": "no-cache", "X-Accel-Buffering": "no"})
PAGE = """<!doctype html><html lang="en"><head><meta charset="utf-8">
<title>Text Summarizer — GritAI</title>
<meta name="viewport" content="width=device-width,initial-scale=1">
<link rel="preconnect" href="https://fonts.googleapis.com">
<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin>
<link href="https://fonts.googleapis.com/css2?family=Archivo:wght@600;700;800;900&family=IBM+Plex+Mono:wght@400;500;600&family=IBM+Plex+Sans:wght@400;500;600&display=swap" rel="stylesheet">
<style>
/* ============================================================================
GRITAI DESIGN SYSTEM — "Engineered / Industrial"
Dark · grit-orange · Archivo + IBM Plex · blueprint grid + grain.
Canonical source of truth for every GritAI app (30-in-15 #1-30) + the hub.
Rob-approved 2026-09-05 (#9 pilot: design-critic 5.71 -> 7.57).
HOW TO USE: embed this <style> verbatim in an app's page, add the Google Fonts
<link> below, then build the body from the component classes here. Keep the
header (monogram + app name + tags), grit-orange as the ONLY accent, dark bg.
FONTS (add to <head>):
<link rel="preconnect" href="https://fonts.googleapis.com">
<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin>
<link href="https://fonts.googleapis.com/css2?family=Archivo:wght@600;700;800;900&family=IBM+Plex+Mono:wght@400;500;600&family=IBM+Plex+Sans:wght@400;500;600&display=swap" rel="stylesheet">
============================================================================ */
:root{
--bg:#0a0b0e; --bg2:#0e1015; --panel:#111318; --panel2:#15181f;
--ink:#eef0f4; --dim:#9aa1b0; --dim2:#5f6675; --line:#20242e; --line2:#2b303c;
--grit:#ff5a2a; --grit2:#ff7d54; --grit-dim:#c9451f; --ok:#5fd08a; --bad:#ff6b6b;
--disp:'Archivo',system-ui,sans-serif; --body:'IBM Plex Sans',system-ui,sans-serif;
--mono:'IBM Plex Mono',ui-monospace,monospace;
}
*{box-sizing:border-box}
html,body{height:100%}
body{margin:0;background:var(--bg);color:var(--ink);font-family:var(--body);font-size:15px;line-height:1.6;
-webkit-font-smoothing:antialiased;position:relative;overflow-x:hidden}
/* blueprint grid + vignette */
body::before{content:"";position:fixed;inset:0;z-index:0;pointer-events:none;
background:linear-gradient(0deg,transparent 95%,rgba(255,90,42,.04) 100%),
repeating-linear-gradient(90deg,transparent 0 63px,rgba(255,255,255,.018) 63px 64px),
repeating-linear-gradient(0deg,transparent 0 63px,rgba(255,255,255,.018) 63px 64px),
radial-gradient(120% 80% at 50% -10%,#141821 0%,var(--bg) 55%)}
/* film grain */
body::after{content:"";position:fixed;inset:0;z-index:0;pointer-events:none;opacity:.05;mix-blend-mode:overlay;
background-image:url("data:image/svg+xml,%3Csvg xmlns='http://www.w3.org/2000/svg' width='140' height='140'%3E%3Cfilter id='n'%3E%3CfeTurbulence type='fractalNoise' baseFrequency='.9' numOctaves='2'/%3E%3C/filter%3E%3Crect width='100%25' height='100%25' filter='url(%23n)'/%3E%3C/svg%3E")}
.wrap{position:relative;z-index:1;max-width:960px;margin:0 auto;padding:0 28px 70px}
/* ---- header band (monogram SVG + wordmark + tags) ---- */
header{display:flex;align-items:center;gap:16px;padding:22px 0 18px;border-bottom:1px solid var(--line);animation:fade .6s .02s both}
.mark{width:38px;height:38px;flex:none}.mark svg{display:block}
.brand{display:flex;flex-direction:column;line-height:1}
.brand .co{font-family:var(--disp);font-weight:900;font-size:19px;letter-spacing:.5px}.brand .co b{color:var(--grit)}
.brand .sub{font-family:var(--mono);font-size:10.5px;letter-spacing:.28em;text-transform:uppercase;color:var(--dim2);margin-top:5px}
.tags{margin-left:auto;display:flex;gap:8px}
.tag{font-family:var(--mono);font-size:10px;letter-spacing:.14em;text-transform:uppercase;color:var(--dim);border:1px solid var(--line2);border-radius:2px;padding:5px 9px}
.tag.hot{color:var(--grit);border-color:var(--grit-dim)}
/* canonical monogram SVG (paste in .mark):
<svg width="38" height="38" viewBox="0 0 38 38" fill="none"><rect x="1" y="1" width="36" height="36" rx="2" stroke="#2b303c"/><path d="M27 12.5A9 9 0 1 0 28 22H19" stroke="#ff5a2a" stroke-width="2.4" stroke-linecap="square"/><rect x="10.5" y="10.5" width="3" height="3" fill="#ff5a2a"/></svg> */
/* ---- hero ---- */
.hero{padding:34px 0 26px;animation:fade .6s .12s both}
.hero h1{font-family:var(--disp);font-weight:800;font-size:clamp(30px,5.4vw,52px);line-height:1.02;letter-spacing:-.02em;margin:0;max-width:16ch}
.hero h1 em{font-style:normal;color:var(--grit)}
.hero p{color:var(--dim);max-width:56ch;margin:16px 0 0;font-size:15.5px}
/* ---- section label (01 · NAME + rule) ---- */
.sec{display:flex;align-items:center;gap:14px;margin:30px 0 14px}
.sec .num{font-family:var(--mono);font-size:11px;font-weight:600;color:var(--grit);letter-spacing:.1em}
.sec .name{font-family:var(--mono);font-size:11px;font-weight:500;letter-spacing:.26em;text-transform:uppercase;color:var(--dim)}
.sec .rule{flex:1;height:1px;background:linear-gradient(90deg,var(--line2),transparent)}
/* ---- panels ---- */
.panel{border:1px solid var(--line);border-radius:3px;background:linear-gradient(180deg,var(--panel),var(--bg2))}
.card{border:1px solid var(--line2);border-radius:3px;background:var(--panel);padding:18px 20px}
.card.accent{border-left:2px solid var(--grit)}
/* ---- input field (terminal) ---- */
.field{display:flex;align-items:stretch;border:1px solid var(--line2);border-radius:3px;background:var(--panel);overflow:hidden;transition:border-color .18s}
.field:focus-within{border-color:var(--grit-dim)}
.field .car{font-family:var(--mono);color:var(--grit);padding:16px 0 16px 16px;font-size:15px;user-select:none}
.field input,.field textarea{flex:1;background:transparent;border:0;outline:none;color:var(--ink);font-family:var(--body);font-size:15.5px;padding:16px 14px;resize:vertical}
.field input::placeholder,.field textarea::placeholder{color:var(--dim2)}
textarea.ta{width:100%;min-height:140px;border:1px solid var(--line2);border-radius:3px;background:var(--panel);color:var(--ink);font-family:var(--body);font-size:15px;padding:14px 16px;outline:none;resize:vertical}
textarea.ta:focus{border-color:var(--grit-dim)}
/* ---- buttons ---- */
.run{border:0;background:var(--grit);color:#140a06;font-family:var(--mono);font-weight:600;font-size:13px;letter-spacing:.14em;text-transform:uppercase;padding:0 24px;cursor:pointer;transition:.16s;box-shadow:-1px 0 0 var(--grit-dim)}
.run:hover{background:var(--grit2);box-shadow:0 0 26px -4px rgba(255,90,42,.55)}
.run:disabled{opacity:.55;cursor:default;box-shadow:none}
.btn{display:inline-flex;align-items:center;gap:8px;border:0;border-radius:3px;background:var(--grit);color:#140a06;font-family:var(--mono);font-weight:600;font-size:13px;letter-spacing:.1em;text-transform:uppercase;padding:12px 22px;cursor:pointer;transition:.16s}
.btn:hover{background:var(--grit2);box-shadow:0 0 26px -4px rgba(255,90,42,.55)}
.btn.ghost{background:transparent;color:var(--dim);border:1px solid var(--line2)}
.btn.ghost:hover{color:var(--grit);border-color:var(--grit-dim);background:transparent;box-shadow:none}
/* ---- chips / controls ---- */
.chip{font-family:var(--mono);font-size:12px;color:var(--dim);background:var(--panel);border:1px solid var(--line);border-radius:2px;padding:8px 11px;cursor:pointer;transition:.15s}
.chip:hover{color:var(--grit);border-color:var(--grit-dim)}
.chip .pt{color:var(--dim2);margin-right:7px}
select,.select{padding:10px 12px;border:1px solid var(--line2);border-radius:3px;background:var(--panel);color:var(--ink);font-family:var(--mono);font-size:13px;outline:none;cursor:pointer}
select:focus{border-color:var(--grit-dim)}
label.lbl{font-family:var(--mono);font-size:11px;text-transform:uppercase;letter-spacing:.24em;color:var(--dim2);display:block;margin-bottom:6px}
/* ---- mono log / trace rows ---- */
.log{font-family:var(--mono);font-size:13px;line-height:1.75}
.row{display:grid;grid-template-columns:22px auto 1fr;gap:0 12px;padding:13px 18px;border-bottom:1px solid var(--line)}
.row:last-child{border-bottom:0}
.row .mk{color:var(--grit);font-weight:600}
.row .tn{color:var(--grit2);text-transform:uppercase;letter-spacing:.06em;font-weight:500}
.row .rd{color:var(--ink);word-break:break-word}.row .rd .arg{color:var(--dim2)}
/* ---- tables ---- */
table{width:100%;border-collapse:collapse;font-size:13.5px}
th{text-align:left;font-family:var(--mono);font-size:11px;text-transform:uppercase;letter-spacing:.12em;color:var(--dim2);font-weight:500;padding:11px 14px;border-bottom:1px solid var(--line2);background:var(--bg2)}
td{padding:11px 14px;border-bottom:1px solid var(--line);vertical-align:top}
tr:last-child td{border-bottom:0}
.tablewrap{border:1px solid var(--line);border-radius:3px;overflow:hidden;overflow-x:auto}
/* ---- chat bubbles ---- */
.msg{max-width:78%;padding:12px 15px;border-radius:3px;font-size:15px;line-height:1.55;margin-bottom:12px}
.msg.user{margin-left:auto;background:var(--panel2);border:1px solid var(--line2)}
.msg.bot{background:var(--panel);border:1px solid var(--line);border-left:2px solid var(--grit)}
/* ---- badges / pills ---- */
.badge{display:inline-block;font-family:var(--mono);font-size:11px;font-weight:500;letter-spacing:.06em;padding:3px 9px;border-radius:2px;border:1px solid var(--line2);color:var(--dim)}
.badge.on{color:var(--grit);border-color:var(--grit-dim)}
.hl{color:var(--grit);font-weight:600;font-family:var(--mono)}
/* ---- answer/output prose ---- */
.prose{font-size:16px;line-height:1.65}.prose p{margin:0 0 12px}.prose p:last-child{margin-bottom:0}.prose b{color:var(--ink)}
/* ---- spinner ---- */
.spin{display:inline-flex;gap:6px;padding:16px 18px}.spin span{width:8px;height:8px;border-radius:50%;background:var(--grit);opacity:.5;animation:bd 1.2s infinite}
.spin span:nth-child(2){animation-delay:.18s}.spin span:nth-child(3){animation-delay:.36s}
/* ---- footer ---- */
footer{margin-top:34px;padding-top:16px;border-top:1px solid var(--line);font-family:var(--mono);font-size:11px;letter-spacing:.06em;color:var(--dim2);display:flex;gap:16px;flex-wrap:wrap;animation:fade .6s .5s both}
footer .b{color:var(--dim)}footer .sp{margin-left:auto}
footer a{color:var(--dim);text-decoration:none}footer a:hover{color:var(--grit)}
/* ---- reveal animations ---- */
@keyframes fade{from{opacity:0;transform:translateY(10px)}to{opacity:1;transform:none}}
@keyframes slidein{from{opacity:0;transform:translateX(-8px)}to{opacity:1;transform:none}}
@keyframes bd{0%,60%,100%{transform:translateY(0);opacity:.35}30%{transform:translateY(-6px);opacity:1}}
.rvl{animation:fade .6s both}
/* ---- app-specific glue (Text Summarizer 30-in-15 #2) ---- */
textarea.ta{min-height:170px}
.orlink{font-family:var(--mono);font-size:11px;letter-spacing:.22em;text-transform:uppercase;color:var(--dim2);text-align:center;margin:16px 0}
.controls{display:flex;flex-wrap:wrap;gap:12px;align-items:stretch;justify-content:space-between;margin-top:6px}
.seg{display:inline-flex;gap:8px;flex-wrap:wrap}
.chip.on{color:var(--grit);border-color:var(--grit-dim);background:var(--panel2)}
.controls .run{padding:12px 26px}
.out{display:none}
.out.show{display:block;animation:fade .5s both}
.out .sec .btn{padding:7px 15px}
#result{white-space:pre-wrap;min-height:22px}
</style></head>
<body><div class="wrap">
<header>
<span class="mark"><svg width="38" height="38" viewBox="0 0 38 38" fill="none"><rect x="1" y="1" width="36" height="36" rx="2" stroke="#2b303c"/><path d="M27 12.5A9 9 0 1 0 28 22H19" stroke="#ff5a2a" stroke-width="2.4" stroke-linecap="square"/><rect x="10.5" y="10.5" width="3" height="3" fill="#ff5a2a"/></svg></span>
<span class="brand"><span class="co">GRIT<b>AI</b></span><span class="sub">Text Summarizer</span></span>
<span class="tags"><span class="tag hot">▸ Live</span><span class="tag">SDVOSB</span><span class="tag">Lawton OK</span></span>
</header>
<section class="hero">
<h1>Get the <em>gist</em> in seconds.</h1>
<p>Paste an article, email, or notes — or drop in a link — and get a faithful TL;DR with the key points, streamed live.</p>
</section>
<div class="sec"><span class="num">01</span><span class="name">Source</span><span class="rule"></span></div>
<textarea id="src" class="ta" placeholder="Paste text here…"></textarea>
<div class="orlink">— or summarize a link —</div>
<div class="field"><span class="car">›</span><input id="url" placeholder="https://…" autocomplete="off"></div>
<div class="sec"><span class="num">02</span><span class="name">Length</span><span class="rule"></span></div>
<div class="controls">
<div class="seg" id="seg">
<button class="chip" data-v="brief">Brief</button>
<button class="chip on" data-v="standard">Standard</button>
<button class="chip" data-v="detailed">Detailed</button>
</div>
<button class="run" id="go" onclick="run()">Summarize</button>
</div>
<div class="out" id="out">
<div class="sec"><span class="num">03</span><span class="name">Summary</span><span class="rule"></span><button class="btn ghost" id="copy" onclick="copyOut()" style="display:none">Copy</button></div>
<div class="card accent"><div id="result" class="prose"></div></div>
</div>
<footer>
<span class="b">Faithful summaries · your text isn't stored</span>
<span class="sp">GRITAI SOLUTIONS · 30-in-15 №2</span>
</footer>
</div><script>
let length="standard",busy=false;
const src=document.getElementById('src'),url=document.getElementById('url'),go=document.getElementById('go'),
out=document.getElementById('out'),result=document.getElementById('result'),copy=document.getElementById('copy');
document.getElementById('seg').addEventListener('click',e=>{const b=e.target.closest('button');if(!b)return;
length=b.dataset.v;[...seg.children].forEach(x=>x.classList.toggle('on',x===b));});
function copyOut(){navigator.clipboard.writeText(result.textContent);copy.textContent='Copied!';setTimeout(()=>copy.textContent='Copy',1400);}
async function run(){if(busy)return;const text=src.value.trim(),u=url.value.trim();
if(!text&&!u){src.focus();return;}
busy=true;go.disabled=true;go.textContent='Summarizing…';out.classList.add('show');copy.style.display='none';
result.innerHTML='<span class="spin"><span></span><span></span><span></span></span>';
let full='';
try{
const r=await fetch('/api/summarize',{method:'POST',headers:{'Content-Type':'application/json'},
body:JSON.stringify({text,url:u,length})});
const rd=r.body.getReader(),dec=new TextDecoder();let buf='';
while(true){const {value,done}=await rd.read();if(done)break;buf+=dec.decode(value,{stream:true});
let i;while((i=buf.indexOf('\\n\\n'))>=0){const line=buf.slice(0,i).trim();buf=buf.slice(i+2);
if(!line.startsWith('data:'))continue;const p=line.slice(5).trim();if(p==='[DONE]')continue;
try{const o=JSON.parse(p);if(o.reset){full='';result.textContent='';}
else if(o.t){full+=o.t;result.textContent=full;}}catch(e){}}}
if(full.trim())copy.style.display='inline-block';else result.textContent='No summary produced — try again.';
}catch(e){result.textContent='Sorry — something went wrong. Please try again.';}
busy=false;go.disabled=false;go.textContent='Summarize';}
</script></body></html>"""
if __name__ == "__main__":
backend = "Claude API" if ANTHROPIC_KEY else f"Ollama ({OLLAMA_MODEL} @ {OLLAMA_URL})"
print(f"Text Summarizer on http://127.0.0.1:{PORT} [backend: {backend}]", flush=True)
app.run(host="0.0.0.0", port=PORT, threaded=True)