spiderforce4ai 1.6__py3-none-any.whl → 1.7__py3-none-any.whl

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.dist-info → spiderforce4ai-1.7.dist-info}/METADATA

@@ -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-1.7.dist-info/RECORD

@@ -0,0 +1,5 @@
+spiderforce4ai/__init__.py,sha256=7YpJdZfmy4z5wUFGTBsvi5VOxGGX594oVul3Q5Ngdko,34906
+spiderforce4ai-1.7.dist-info/METADATA,sha256=ON-lQ4BARmNOrHwT2Xbl2oc1hoo8FyMQWxl6T0LbClA,7183
+spiderforce4ai-1.7.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
+spiderforce4ai-1.7.dist-info/top_level.txt,sha256=Kth7A21Js7DCp0j5XBBi-FE45SCLouZkeNZU__Yr9Yk,15
+spiderforce4ai-1.7.dist-info/RECORD,,

spiderforce4ai-1.6.dist-info/RECORD

@@ -1,5 +0,0 @@
-spiderforce4ai/__init__.py,sha256=yNyBz8-HjENlAZ1NSy072Ir71T68xulTRj19Yxr1aEQ,33573
-spiderforce4ai-1.6.dist-info/METADATA,sha256=pelYvJYMzC8W-P2ORQNWwP2Fyc5KshnzQ6edoYEYZQU,7183
-spiderforce4ai-1.6.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
-spiderforce4ai-1.6.dist-info/top_level.txt,sha256=Kth7A21Js7DCp0j5XBBi-FE45SCLouZkeNZU__Yr9Yk,15
-spiderforce4ai-1.6.dist-info/RECORD,,