added inlude and exclude websites

app.py

@@ -416,7 +416,8 @@ def generate_and_format(
     month_to,
     day_to,
     domains_to_include,
-    search_keywords,
+    include_sites,
+    exclude_sites,
     pdf_file_input,
     generated_article: str = None,
     user_comments: str = None,
@@ -426,10 +427,14 @@ def generate_and_format(
     sorted_date = f"date:r:{date_from}:{date_to}"
     content_string = ""
     final_query = topic
-    if search_keywords != "":
-        quoted_keywords = [f'"{keyword.strip()}"' for keyword in search_keywords.split(",")]
-        final_query = final_query + " " + " ".join(quoted_keywords)
-    print(final_query)
+    if include_sites:
+        site_queries = [f"site:{site.strip()}" for site in include_sites.split(",")]
+        final_query += " " + " OR ".join(site_queries)
+    if exclude_sites:
+        exclude_queries = [f"-site:{site.strip()}" for site in exclude_sites.split(",")]
+        final_query += " " + " ".join(exclude_queries)
+    print(f"Final Query: {final_query}")
+
     if google_search_check:
         url_content = google_search(final_query, sorted_date, domains_to_include)
         content_string = "\n".join(
@@ -630,8 +635,14 @@ def create_interface():
                                 label="Domains To Include",
                             )
                         with gr.Row():
-                            search_keywords = gr.Textbox(
-                                label="Keywords",
+                            include_sites = gr.Textbox(
+                                label="Include Specific Websites",
+                                placeholder="Enter comma-separated keywords",
+                                elem_classes="input-highlight-yellow",
+                            )
+                        with gr.Row():
+                            exclude_sites = gr.Textbox(
+                                label="Exclude Specific Websites",
                                 placeholder="Enter comma-separated keywords",
                                 elem_classes="input-highlight-yellow",
                             )
@@ -747,7 +758,8 @@ def create_interface():
                 month_to,
                 day_to,
                 domains_to_include,
-                search_keywords,
+                include_sites,
+                exclude_sites,
                 pdf_file_input,
             ],
             outputs=[output_article],
@@ -781,7 +793,8 @@ def create_interface():
                 domains_to_include,
                 pdf_file_input,
                 output_article,
-                search_keywords,
+                include_sites,
+                exclude_sites,
                 ai_comments,
             ],
             outputs=[output_article],

plagiarism.py

@@ -114,6 +114,7 @@ def google_search(
         api_key,
         cse_id,
     )
+    print("URLS: ", url_list)
     print("GOOGLE SEARCH PROCESSING TIME: ", time.perf_counter() - start_time)
     # Scrape URLs in list
     start_time = time.perf_counter()