softhauzpy 0.0.91__tar.gz → 0.1.0__tar.gz

{softhauzpy-0.0.91 → softhauzpy-0.1.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: softhauzpy
-Version: 0.0.91
+Version: 0.1.0
 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-0.0.91 → softhauzpy-0.1.0}/setup.py

@@ -5,7 +5,7 @@ with open("README.md", "r", encoding="utf-8") as f:
 
 setup(
     name='softhauzpy',
-    version='0.0.91',
+    version='0.1.0',
     author='Karen Urate',
     author_email='karen.urate@softhauz.ca',
     packages=find_packages(),

{softhauzpy-0.0.91 → softhauzpy-0.1.0}/softhauzpy/main.py

@@ -68,21 +68,31 @@ except Exception:
     url             : String - 'url', 'html_file', or 'raw_string'
 """
 def detect_input_type(value: str) -> str:
-    # Check if it's a URL (http/https/ftp scheme)
-    try:
-        parsed = urlparse(value)
-        if parsed.scheme in ("http", "https", "ftp", "ftps"):
-            return "url"
-    except Exception:
-        pass
-
-    # Check if it's a path to an existing HTML file
-    if os.path.isfile(value) and value.lower().endswith((".html", ".htm")):
-        return "html_file"
+    
+    if not value:
+        return "raw_string"
 
-    # Check if it looks like an HTML string even if not a file
     stripped = value.strip()
-    if stripped.startswith("<") and stripped.endswith(">"):
+    
+    # Safeguard: Real network URLs are never massive HTML texts, 
+    # and they don't start with standard layout angle brackets.
+    if stripped.startswith("<") or len(stripped) > 2048:
+        return "raw_string"
+
+    # Enforce standard prefix matching before relying on urlparse split tokens
+    if stripped.lower().startswith(("http://", "https://", "ftp://", "ftps://")):
+        try:
+            parsed = urlparse(stripped)
+            if parsed.scheme in ("http", "https", "ftp", "ftps") and parsed.netloc:
+                return "url"
+        except Exception:
+            pass
+
+    # Check file path references safely
+    try:
+        if os.path.isfile(value) and value.lower().endswith((".html", ".htm")):
+            return "html_file"
+    except Exception:
         return "raw_string"
 
     # Default: treat as plain raw string
@@ -165,12 +175,12 @@ def extract_pure_text(
     if modified_date:
         header_parts.append(f"Last Modified: {modified_date}")
     if page_url:
-        if (input_type == "url") or (input_type == "html"):
+        if (input_type == "url") or (input_type == "html_file"):
             header_parts.append(f"URL:           {page_url}")
 
     header = " ".join(header_parts)
     result = {
-        "url": page_url if ((input_type == "url") or (input_type == "html")) else assigned_location,
+        "url": page_url if ((input_type == "url") or (input_type == "html_file")) else assigned_location,
         "title": title,
         "author": author,
         "description": description,

{softhauzpy-0.0.91 → softhauzpy-0.1.0}/softhauzpy.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: softhauzpy
-Version: 0.0.91
+Version: 0.1.0
 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