Spaces:
Sleeping
Sleeping
Create app.py
Browse files
app.py
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import streamlit as st
|
2 |
+
import pandas as pd
|
3 |
+
from urllib.parse import urlparse
|
4 |
+
|
5 |
+
def extract_keywords_from_url(url: str) -> list[str]:
|
6 |
+
parsed = urlparse(url)
|
7 |
+
path = parsed.path.strip("/")
|
8 |
+
|
9 |
+
for ext in (".html", ".htm", ".php"):
|
10 |
+
if path.endswith(ext):
|
11 |
+
path = path[: -len(ext)]
|
12 |
+
|
13 |
+
cleaned = path.replace("_", " ").replace("-", " ").replace(".", " ")
|
14 |
+
segments = cleaned.split("/") if cleaned else []
|
15 |
+
|
16 |
+
keywords = []
|
17 |
+
for seg in segments:
|
18 |
+
tokens = seg.split()
|
19 |
+
keywords.extend([token.lower() for token in tokens if token.strip()])
|
20 |
+
return keywords
|
21 |
+
|
22 |
+
st.title("🔗 URL Keywords Extractor")
|
23 |
+
|
24 |
+
urls_input = st.text_area("Enter one or more URLs (one per line):", height=200)
|
25 |
+
|
26 |
+
if st.button("Extract Keywords"):
|
27 |
+
if urls_input.strip():
|
28 |
+
urls = [url.strip() for url in urls_input.strip().splitlines() if url.strip()]
|
29 |
+
results = [{"URL": url, "Keywords": extract_keywords_from_url(url)} for url in urls]
|
30 |
+
df = pd.DataFrame(results)
|
31 |
+
st.dataframe(df, use_container_width=True)
|
32 |
+
else:
|
33 |
+
st.warning("Please enter at least one URL.")
|