Initial commit

code/C2/01_unstructured_example.py

@@ -0,0 +1,25 @@
+from unstructured.partition.auto import partition
+
+# PDF文件路径
+pdf_path = "../../data/C2/pdf/rag.pdf"
+
+# 使用Unstructured加载并解析PDF文档
+elements = partition(
+    filename=pdf_path,
+    content_type="application/pdf"
+)
+
+# 打印解析结果
+print(f"解析完成: {len(elements)} 个元素, {sum(len(str(e)) for e in elements)} 字符")
+
+# 统计元素类型
+from collections import Counter
+types = Counter(e.category for e in elements)
+print(f"元素类型: {dict(types)}")
+
+# 显示所有元素
+print("\n所有元素:")
+for i, element in enumerate(elements, 1):
+    print(f"Element {i} ({element.category}):")
+    print(element)
+    print("=" * 60)