softhauzpy 0.0.81__tar.gz → 0.0.91__tar.gz

{softhauzpy-0.0.81 → softhauzpy-0.0.91}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: softhauzpy
-Version: 0.0.81
+Version: 0.0.91
 Summary: is a comprehensive Python toolkit built for developers creating intelligent, data-driven web applications. It provides a powerful suite of web utilities including web scraping tools, crawling systems, content extraction pipelines, and search engine components that help developers build fully customizable in-house website search solutions.
 Home-page: https://softhauz.ca
 Author: Karen Urate

{softhauzpy-0.0.81 → softhauzpy-0.0.91}/setup.py

@@ -5,7 +5,7 @@ with open("README.md", "r", encoding="utf-8") as f:
 
 setup(
     name='softhauzpy',
-    version='0.0.81',
+    version='0.0.91',
     author='Karen Urate',
     author_email='karen.urate@softhauz.ca',
     packages=find_packages(),

{softhauzpy-0.0.81 → softhauzpy-0.0.91}/softhauzpy/main.py

@@ -94,12 +94,13 @@ def detect_input_type(value: str) -> str:
 
     Parameters
     ----------
-    url           : String - The URL to fetch.
+    page_url      : String - Accepts either the URL to fetch, a local path to an HTML file, or the text/HTML String content of the page.
     title         : String - Optional document title (included in the returned text header when provided).
     author        : String - Optional document author (included in the returned text header when provided).
     description   : String - Optional description (included in the returned text header when provided).
     creation_date : String - Optional creation date string (included in the returned text header when provided).
     modified_date : String - Optional last-modified date string (included in the returned text header when provided).
+    assigned_location : String - Optional the URL to assign if the value passed in page_url is the text/HTML String content of the page. 
 
 
     Returns
@@ -127,7 +128,8 @@ def extract_pure_text(
         author: str | None = None,
         description: str | None = None,
         creation_date: str | None = None,
-        modified_date: str | None = None) -> dict:
+        modified_date: str | None = None,
+        assigned_location: str | None = None) -> dict:
 
     input_type = detect_input_type(page_url)
 
@@ -163,11 +165,12 @@ def extract_pure_text(
     if modified_date:
         header_parts.append(f"Last Modified: {modified_date}")
     if page_url:
-        header_parts.append(f"URL:           {page_url}")
+        if (input_type == "url") or (input_type == "html"):
+            header_parts.append(f"URL:           {page_url}")
 
     header = " ".join(header_parts)
     result = {
-        "url": page_url,
+        "url": page_url if ((input_type == "url") or (input_type == "html")) else assigned_location,
         "title": title,
         "author": author,
         "description": description,
@@ -220,16 +223,20 @@ def get_search_results_list(page_list=[], keywords='') -> list:
 
         if len(url) == 0 or len(url) < 1:
             continue
-
+        
         title = page[1] or ''
         author = page[2] or ''
         description = page[3] or ''
         creation_date = page[4] or ''
         modified_date = page[5] or ''
-        
-        
-        if keywords in (extract_pure_text(url, title=title, author=author, description=description, creation_date=creation_date, modified_date=modified_date)["content"]).lower():
-            results.append((url, title, author, description, creation_date, modified_date))
+        assigned_location = page[6] if len(page[6])>3 else ''
+
+        if keywords in (extract_pure_text(url, title=title, author=author, description=description, creation_date=creation_date, modified_date=modified_date, assigned_location=assigned_location)["content"]).lower():
+            
+            if detect_input_type(url) != "url":
+                results.append((assigned_location, title, author, description, creation_date, modified_date))
+            else:
+                results.append((url, title, author, description, creation_date, modified_date))
 
     return results
 

{softhauzpy-0.0.81 → softhauzpy-0.0.91}/softhauzpy.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: softhauzpy
-Version: 0.0.81
+Version: 0.0.91
 Summary: is a comprehensive Python toolkit built for developers creating intelligent, data-driven web applications. It provides a powerful suite of web utilities including web scraping tools, crawling systems, content extraction pipelines, and search engine components that help developers build fully customizable in-house website search solutions.
 Home-page: https://softhauz.ca
 Author: Karen Urate