new

read_docx.py

@@ -0,0 +1,36 @@
+import zipfile
+import xml.etree.ElementTree as ET
+import sys
+import os
+
+def read_docx(file_path):
+    if not os.path.exists(file_path):
+        print(f"Error: {file_path} not found.")
+        return
+    
+    try:
+        with zipfile.ZipFile(file_path, 'r') as docx:
+            # The main text content is in word/document.xml
+            xml_content = docx.read('word/document.xml')
+            tree = ET.fromstring(xml_content)
+            
+            # Namespaces are important in docx XML
+            namespaces = {
+                'w': 'http://schemas.openxmlformats.org/wordprocessingml/2006/main'
+            }
+            
+            texts = []
+            for paragraph in tree.findall('.//w:p', namespaces):
+                t_elements = paragraph.findall('.//w:t', namespaces)
+                if t_elements:
+                    texts.append("".join([t.text for t in t_elements if t.text]))
+            
+            print("\n".join(texts))
+    except Exception as e:
+        print(f"Error reading {file_path}: {e}")
+
+if __name__ == "__main__":
+    if len(sys.argv) > 1:
+        read_docx(sys.argv[1])
+    else:
+        print("Usage: python read_docx.py <path_to_docx>")