File size: 5,759 Bytes
00be35b |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 |
import datetime as dt
import html
import textwrap
from typing import List, Tuple
import feedparser
import gradio as gr
import requests
DEFAULT_URL = "https://sachet.ndma.gov.in/cap_public_website/rss/rss_india.xml"
UA = "MinimalRSS/1.0 (+https://huggingface.co/spaces)"
def _fetch(url: str, timeout: int = 12) -> bytes:
resp = requests.get(url, headers={"User-Agent": UA}, timeout=timeout)
resp.raise_for_status()
return resp.content
def _truncate(text: str, n: int = 220) -> str:
text = " ".join(text.split())
return text if len(text) <= n else text[: n - 1].rstrip() + "…"
def _format_time(struct_time) -> str:
if not struct_time:
return ""
# Display in IST by default (Asia/Kolkata = UTC+5:30). We’ll label UTC to avoid timezone assumptions.
# Feed times are usually UTC; to stay unambiguous, show ISO 8601/Z.
try:
return dt.datetime(*struct_time[:6], tzinfo=dt.timezone.utc).isoformat().replace("+00:00", "Z")
except Exception:
return ""
def render_feed(url: str, max_items: int, show_summaries: bool) -> Tuple[str, str]:
try:
raw = _fetch(url.strip() or DEFAULT_URL)
parsed = feedparser.parse(raw)
except Exception as e:
return "", f"⚠️ Could not load the feed. {type(e).__name__}: {e}"
title = parsed.feed.get("title", "Feed")
subtitle = parsed.feed.get("subtitle", "")
updated = parsed.feed.get("updated_parsed")
header_html = f"""
<div class="header">
<div class="feed-title">{html.escape(title)}</div>
{"<div class='feed-sub'>"+html.escape(subtitle)+"</div>" if subtitle else ""}
<div class="feed-meta">Updated: {html.escape(_format_time(updated) or "—")}</div>
</div>
"""
items_html: List[str] = []
for entry in parsed.entries[:max_items]:
etitle = html.escape(entry.get("title", "Untitled"))
link = entry.get("link", "#")
published = _format_time(entry.get("published_parsed"))
summary = entry.get("summary", "") or entry.get("description", "")
# Remove very long XML artifacts
summary = html.escape(_truncate(summary, 500))
caps = []
for key in ("category", "tags"):
if key in entry and entry[key]:
if key == "category":
caps.append(str(entry["category"]))
else:
for t in entry["tags"]:
lab = t.get("term") or t.get("label")
if lab:
caps.append(str(lab))
caps = [c for c in [c.strip() for c in caps] if c]
cap_html = (
"<div class='caps'>" + " ".join(f"<span class='cap'>{html.escape(c)}</span>" for c in caps) + "</div>"
if caps
else ""
)
item = f"""
<li class="item">
<a class="title" href="{html.escape(link)}" target="_blank" rel="noopener noreferrer">{etitle}</a>
<div class="meta">{("Published: " + published) if published else ""}</div>
{cap_html}
{f"<div class='summary'>{summary}</div>" if show_summaries and summary else ""}
</li>
"""
items_html.append(item)
if not items_html:
items_html.append("<li class='item empty'>No items found.</li>")
body_html = "<ul class='list'>" + "\n".join(items_html) + "</ul>"
full_html = f"""
<div class="wrap">
{header_html}
{body_html}
</div>
"""
return full_html, ""
MINIMAL_CSS = """
:root { --fg:#111; --muted:#666; --bg:#fff; --card:#fafafa; --link:#0b57d0; }
@media (prefers-color-scheme: dark) {
:root { --fg:#eee; --muted:#aaa; --bg:#0b0b0b; --card:#141414; --link:#7fb0ff; }
}
*{box-sizing:border-box}
body{{background:var(--bg)}}
.wrap{max-width:920px;margin:24px auto;padding:0 16px;color:var(--fg);font:16px/1.55 system-ui,-apple-system,Segoe UI,Roboto,Helvetica,Arial}
.header{margin:12px 0 8px 0}
.feed-title{font-weight:700;font-size:20px}
.feed-sub{color:var(--muted);margin-top:2px}
.feed-meta{color:var(--muted);font-size:13px;margin-top:6px}
.list{list-style:none;padding:0;margin:16px 0}
.item{background:var(--card);border:1px solid rgba(127,127,127,.2);border-radius:12px;padding:14px 16px;margin:10px 0}
.item .title{font-weight:600;text-decoration:none;color:var(--link)}
.item .title:hover{text-decoration:underline}
.item .meta{color:var(--muted);font-size:13px;margin-top:6px}
.caps{margin-top:8px;display:flex;gap:6px;flex-wrap:wrap}
.cap{border:1px solid rgba(127,127,127,.25);padding:2px 8px;border-radius:999px;font-size:12px;color:var(--muted)}
.summary{margin-top:10px;white-space:pre-wrap}
.empty{color:var(--muted);text-align:center}
.footer{max-width:920px;margin:8px auto 24px auto;padding:0 16px;color:var(--muted);font:12px/1.4 system-ui}
"""
with gr.Blocks(css=MINIMAL_CSS, fill_height=True, theme=gr.themes.Soft()) as demo:
gr.Markdown("### NDMA Sachet — Minimal RSS Viewer")
with gr.Row():
url_in = gr.Textbox(
label="RSS URL",
value=DEFAULT_URL,
placeholder="Paste an RSS/Atom URL…",
max_lines=1
)
max_items = gr.Slider(5, 50, value=20, step=1, label="Items")
show_summaries = gr.Checkbox(value=True, label="Show summaries")
refresh = gr.Button("Refresh", variant="primary")
out_html = gr.HTML()
out_err = gr.Markdown(elem_classes=["footer"])
def _go(u, m, s):
return render_feed(u, int(m), bool(s))
# Initial load
demo.load(_go, [url_in, max_items, show_summaries], [out_html, out_err])
# Manual refresh
refresh.click(_go, [url_in, max_items, show_summaries], [out_html, out_err])
if __name__ == "__main__":
demo.launch()
|