spiderforce4ai 1.6__tar.gz → 1.7__tar.gz

{spiderforce4ai-1.6 → spiderforce4ai-1.7}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: spiderforce4ai
-Version: 1.6
+Version: 1.7
 Summary: Python wrapper for SpiderForce4AI HTML-to-Markdown conversion service
 Home-page: https://petertam.pro
 Author: Piotr Tamulewicz

{spiderforce4ai-1.6 → spiderforce4ai-1.7}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "spiderforce4ai"
-version = "1.6"
+version = "1.7"
 description = "Python wrapper for SpiderForce4AI HTML-to-Markdown conversion service"
 readme = "README.md"
 authors = [{name = "Piotr Tamulewicz", email = "pt@petertam.pro"}]

{spiderforce4ai-1.6 → spiderforce4ai-1.7}/setup.py

@@ -3,7 +3,7 @@ from setuptools import setup, find_packages
 
 setup(
     name="spiderforce4ai",
-    version="1.6",
+    version="1.7",
     author="Piotr Tamulewicz",
     author_email="pt@petertam.pro",
     description="Python wrapper for SpiderForce4AI HTML-to-Markdown conversion service",

{spiderforce4ai-1.6 → spiderforce4ai-1.7}/spiderforce4ai/__init__.py

@@ -23,26 +23,55 @@ from multiprocessing import Pool
 console = Console()
 
 def extract_metadata_headers(markdown: str) -> str:
-    """Extract metadata and headers from markdown content."""
+    """Extract metadata and headers from markdown content with SEO formatting."""
     lines = markdown.split('\n')
     extracted = []
     in_metadata = False
+    metadata = {
+        'title': '',
+        'description': '',
+        'canonical_url': '',
+        'language': ''
+    }
     
+    # First pass - collect metadata
+    for line in lines:
+        if line.strip().startswith('title:'):
+            metadata['title'] = line.split(':', 1)[1].strip()
+        elif line.strip().startswith('description:'):
+            metadata['description'] = line.split(':', 1)[1].strip()
+        elif line.strip().startswith('canonical_url:'):
+            metadata['canonical_url'] = line.split(':', 1)[1].strip()
+        elif line.strip().startswith('language:'):
+            metadata['language'] = line.split(':', 1)[1].strip()
+    
+    # Add formatted metadata section
+    extracted.append(f"Title: {metadata['title']}")
+    extracted.append(f"Description: {metadata['description']}")
+    extracted.append(f"CanonicalUrl: {metadata['canonical_url']}")
+    extracted.append(f"Language: {metadata['language']}")
+    extracted.append("")  # Empty line after metadata
+    
+    # Second pass - process headers
     for line in lines:
-        # Check for metadata block
-        if line.strip() == '---':
-            in_metadata = not in_metadata
-            extracted.append(line)
-            continue
-        
-        # Include metadata
-        if in_metadata:
-            extracted.append(line)
-            continue
-            
-        # Include headers (lines starting with #)
         if line.strip().startswith('#'):
-            extracted.append(line)
+            # Count the number of # symbols
+            level = len(line) - len(line.lstrip('#'))
+            text = line.lstrip('#').strip()
+            
+            # Format header according to level
+            if level == 1:
+                extracted.append(f"H1: {text}")
+            elif level == 2:
+                extracted.append(f"H2: {text}")
+            elif level == 3:
+                extracted.append(f"H3: {text}")
+            elif level == 4:
+                extracted.append(f"H4: {text}")
+            elif level == 5:
+                extracted.append(f"H5: {text}")
+            elif level == 6:
+                extracted.append(f"H6: {text}")
     
     return '\n'.join(extracted)
 

{spiderforce4ai-1.6 → spiderforce4ai-1.7}/spiderforce4ai.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: spiderforce4ai
-Version: 1.6
+Version: 1.7
 Summary: Python wrapper for SpiderForce4AI HTML-to-Markdown conversion service
 Home-page: https://petertam.pro
 Author: Piotr Tamulewicz