Update app.py

app.py

@@ -2,58 +2,88 @@ import streamlit as st
 from transformers import pipeline
 import re
 
-# تحميل النموذجssssss
+# تحميل النموذج
 classifier = pipeline("zero-shot-classification", model="cross-encoder/nli-distilroberta-base")
 
 # عنوان التطبيق
-st.title("URL Analysis App")
+st.title("Keyword & URL Analysis App")
+
+# اختيار العملية
+operation = st.radio("Choose an operation:", ["Filter Keywords", "Analyze URLs"])
 
 # إدخال الملف النصي
-uploaded_file = st.file_uploader("Upload a text file containing URLs", type=["txt"])
+uploaded_file = st.file_uploader("Upload a text file", type=["txt"])
 
 if uploaded_file is not None:
     # قراءة الملف النصي
     content = uploaded_file.read().decode("utf-8")
-    urls = [line.strip() for line in content.splitlines() if line.strip()]
+    items = [line.strip() for line in content.splitlines() if line.strip()]
+
+    # تحديد الفئات
+    categories = ["shop", "game", "stream"]
 
     # قوائم لتخزين النتائج
+    shopping_items = []
+    gaming_items = []
+    streaming_items = []
+    unknown_items = []
+
+    # قوائم خاصة بالروابط
     parameters = []
     domains = []
     full_page_types = []
     file_extensions = []
 
+    # دالة تصنيف الكلمات المفتاحية
+    def classify_keywords(items, categories):
+        results = classifier(items, categories)
+        for i, result in enumerate(results):
+            best_category = result['labels'][0]
+            score = result['scores'][0]
+
+            if best_category == "shop" and score > 0.5:
+                shopping_items.append(items[i])
+            elif best_category == "game" and score > 0.5:
+                gaming_items.append(items[i])
+            elif best_category == "stream" and score > 0.5:
+                streaming_items.append(items[i])
+            else:
+                unknown_items.append(items[i])
+
     # دالة تحليل الروابط
     def analyze_urls(urls):
         for url in urls:
             # استخراج الباراميترات باستخدام RegEx
-            params = re.findall(r'(\w+)=', url)
+            params = re.findall(r'(\w+)=', url)  # استخراج الأسماء فقط (بدون '=')
             parameters.extend(params)
 
-            # استخtraction نطاقات (.com, .uk, .au)
-            domain_match = re.search(r'\.([a-zA-Z]+)', url)
+            # استخراج الدومينات (مثل .com, .org)
+            domain_match = re.search(r'\.([a-zA-Z]{2,})$', url)
             if domain_match:
                 domain = domain_match.group(1)
                 if domain not in domains:
                     domains.append(domain)
 
-            # استخراج أنماط الصفحات الكاملة (product_detail.php?, viewtopic.php?)
+            # استخراج أنماط الصفحات الكاملة (مثل product_detail.php?, index.php?)
             page_type_match = re.search(r'(\w+\.[a-z]+)\?', url)
             if page_type_match:
                 page_type = page_type_match.group(1)
                 if page_type not in full_page_types:
                     full_page_types.append(page_type)
 
-            # استخراج الصيغ (php, phtml, asp) بدون علامات الاستفهام
-            extension_match = re.search(r'(\w+\.[a-z]+)(\?|$)', url)
+            # استخراج الصيغ (مثل php, phtml, asp) بدون باقي الرابط
+            extension_match = re.search(r'\.([a-z]+)(\?|$)', url)
             if extension_match:
-                extension = extension_match.group(1).split('?')[0]
+                extension = extension_match.group(1)
                 if extension not in file_extensions:
                     file_extensions.append(extension)
 
     # زر البدء
     if st.button("Start"):
-        # تحليل الروابط
-        analyze_urls(urls)
+        if operation == "Filter Keywords":
+            classify_keywords(items, categories)
+        elif operation == "Analyze URLs":
+            analyze_urls(items)
 
     # إزالة التكرارات من القوائم
     parameters = list(set(parameters))
@@ -61,22 +91,48 @@ if uploaded_file is not None:
     full_page_types = list(set(full_page_types))
     file_extensions = list(set(file_extensions))
 
-    # عرض النتائج
-    st.header("Parameters")
-    st.text_area("Copy the parameters here:", value="\n".join(parameters), height=200, key="parameters")
-    st.button("Copy Parameters", on_click=lambda: st.clipboard.copy("\n".join(parameters)))
-
-    st.header("Domains")
-    st.text_area("Copy the domains here:", value="\n".join(domains), height=200, key="domains")
-    st.button("Copy Domains", on_click=lambda: st.clipboard.copy("\n".join(domains)))
-
-    st.header("Full PageType")
-    st.text_area("Copy the full page types here:", value="\n".join(full_page_types), height=200, key="full_page_types")
-    st.button("Copy Full PageTypes", on_click=lambda: st.clipboard.copy("\n".join(full_page_types)))
-
-    st.header("File Extensions")
-    st.text_area("Copy the file extensions here:", value="\n".join(file_extensions), height=200, key="file_extensions")
-    st.button("Copy File Extensions", on_click=lambda: st.clipboard.copy("\n".join(file_extensions)))
+    # دالة تصدير النتائج
+    def export_results(key, filename):
+        with open(filename, "w") as f:
+            f.write("\n".join(st.session_state[key]))
+        st.success(f"Results exported to {filename}")
+
+    # عرض النتائج بناءً على الخيار المختار
+    if operation == "Filter Keywords":
+        # عرض النتائج للكلمات المفتاحية
+        st.header("Shopping Keywords")
+        st.text_area("Copy the shopping keywords here:", value="\n".join(shopping_items), height=200, key="shopping")
+        st.button("Export Shopping Keywords", on_click=export_results, args=("shopping", "shopping_keywords.txt"))
+
+        st.header("Gaming Keywords")
+        st.text_area("Copy the gaming keywords here:", value="\n".join(gaming_items), height=200, key="gaming")
+        st.button("Export Gaming Keywords", on_click=export_results, args=("gaming", "gaming_keywords.txt"))
+
+        st.header("Streaming Keywords")
+        st.text_area("Copy the streaming keywords here:", value="\n".join(streaming_items), height=200, key="streaming")
+        st.button("Export Streaming Keywords", on_click=export_results, args=("streaming", "streaming_keywords.txt"))
+
+        st.header("Unknown Keywords")
+        st.text_area("Copy the unknown keywords here:", value="\n".join(unknown_items), height=200, key="unknown")
+        st.button("Export Unknown Keywords", on_click=export_results, args=("unknown", "unknown_keywords.txt"))
+
+    elif operation == "Analyze URLs":
+        # عرض النتائج للروابط
+        st.header("Parameters")
+        st.text_area("Copy the parameters here:", value="\n".join(parameters), height=200, key="parameters")
+        st.button("Export Parameters", on_click=export_results, args=("parameters", "parameters.txt"))
+
+        st.header("Domains")
+        st.text_area("Copy the domains here:", value="\n".join(domains), height=200, key="domains")
+        st.button("Export Domains", on_click=export_results, args=("domains", "domains.txt"))
+
+        st.header("Full PageType")
+        st.text_area("Copy the full page types here:", value="\n".join(full_page_types), height=200, key="full_page_types")
+        st.button("Export Full PageTypes", on_click=export_results, args=("full_page_types", "full_page_types.txt"))
+
+        st.header("File Extensions")
+        st.text_area("Copy the file extensions here:", value="\n".join(file_extensions), height=200, key="file_extensions")
+        st.button("Export File Extensions", on_click=export_results, args=("file_extensions", "file_extensions.txt"))
 
 else:
-    st.warning("Please upload a text file containing URLs to start analysis.")
+    st.warning("Please upload a text file to start analysis.")