blog and backlinks

tmp/clean_articles.py

@@ -0,0 +1,47 @@
+import os
+import re
+
+def clean_articles(directory):
+    for filename in os.listdir(directory):
+        if filename.endswith(".md"):
+            path = os.path.join(directory, filename)
+            with open(path, "r", encoding="utf-8") as f:
+                content = f.read()
+
+            # Remove *Target: ...* line
+            content = re.sub(r"^\*Target:.*?\*[\r\n]*", "", content, flags=re.MULTILINE)
+            
+            # Remove footer metadata starting with bolded targets or notes
+            # Usually starts after the last separator --- or near the end
+            # Patterns to remove:
+            # - Word count target: ...
+            # - Internal links to add: ...
+            # - Note: AI-assisted draft ...
+            # - Author bio: ... (We might want to keep author bio, but the user said "draft doesn't look good", 
+            #   so let's remove the "meta" parts and keep only the content.)
+            
+            # Remove specific lines
+            content = re.sub(r"\*\*Word count target:\*\*.*", "", content)
+            content = re.sub(r"\*\*Internal links to add:\*\*.*", "", content)
+            content = re.sub(r"\*\*Author bio:\*\*.*", "", content)
+            content = re.sub(r"\*\*Note:\*\* AI-assisted draft.*", "", content)
+            
+            # Also catch these patterns without bold
+            content = re.sub(r"\*Target:.*", "", content)
+            content = re.sub(r"Word count target:.*", "", content)
+            content = re.sub(r"Internal links to add:.*", "", content)
+            content = re.sub(r"Author bio:.*", "", content)
+            content = re.sub(r"Note: AI-assisted draft.*", "", content)
+            content = re.sub(r"Screenshots to include:.*", "", content)
+
+            # Clean up trailing whitespace and empty separators at the end
+            content = content.replace("---", "\n---\n") # Ensure space around separators
+            content = re.sub(r"---[\s\n]*$", "", content) # Remove trailing separators
+            content = content.strip()
+
+            with open(path, "w", encoding="utf-8") as f:
+                f.write(content)
+            print(f"Cleaned {filename}")
+
+if __name__ == "__main__":
+    clean_articles(r"c:\Users\a931627\Documents\QRMASTER\articles")