Upload app.py

app.py

@@ -0,0 +1,52 @@
+import streamlit as st
+import re
+import pandas as pd
+from sklearn.feature_extraction.text import TfidfVectorizer
+from sklearn.metrics.pairwise import cosine_similarity
+
+# Streamlit app interface
+st.title('Site Migration URL Mapper')
+
+# Text areas for old and new site URLs
+old_site_urls = st.text_area('Enter the old site URLs (one per line)').split('\n')
+new_site_urls = st.text_area('Enter the new site URLs (one per line)').split('\n')
+
+def preprocess_url(url):
+    """Preprocess the URL to extract keywords."""
+    processed_url = re.sub(r'https?:\/\/(?:www\.)?[^\/]+', '', url)
+    processed_url = re.sub(r'\.\w+$', '', processed_url)
+    processed_url = re.sub(r'[^a-z0-9\s]', ' ', processed_url.lower())
+    return processed_url
+
+def map_urls(old_urls, new_urls):
+    """Map old site URLs to new site URLs based on content similarity using TF-IDF."""
+    old_urls_processed = [preprocess_url(url) for url in old_urls]
+    new_urls_processed = [preprocess_url(url) for url in new_urls]
+
+    vectorizer = TfidfVectorizer()
+    tfidf_matrix = vectorizer.fit_transform(old_urls_processed + new_urls_processed)
+
+    old_vectors = tfidf_matrix[:len(old_urls)]
+    new_vectors = tfidf_matrix[len(old_urls):]
+
+    similarity_matrix = cosine_similarity(old_vectors, new_vectors)
+    mappings = []
+
+    for idx, old_url in enumerate(old_urls):
+        best_match_idx = similarity_matrix[idx].argmax()
+        best_match_url = new_urls[best_match_idx]
+        mappings.append((old_url, best_match_url))
+
+    return mappings
+
+if st.button('Generate Mappings'):
+    if old_site_urls and new_site_urls:
+        mappings = map_urls(old_site_urls, new_site_urls)
+        df_mappings = pd.DataFrame(mappings, columns=['Old URL', 'New URL'])
+        st.dataframe(df_mappings)
+
+        # Download button for the mappings
+        csv = df_mappings.to_csv(index=False).encode('utf-8')
+        st.download_button("Download Mappings", csv, "url_mappings.csv", "text/csv", key='download-csv')
+    else:
+        st.error("Please enter URLs for both old and new sites.")