[example] Add examples

examples/convert_folder_pdfs.py

@@ -0,0 +1,19 @@
+# This is an example of how to convert all PDF files in a folder to DOCX files.
+# 这是一个将文件夹中的所有 PDF 文件转换为 DOCX 文件的示例。
+
+from pdfdeal import Doc2X
+
+# gets API Key from environment variable DOC2X_APIKEY, or you can pass it as a string to the apikey parameter
+# 从环境变量 DOC2X_APIKEY 获取 API Key, 或者您可以将其作为字符串传递给 apikey 参数
+
+# client = Doc2X(apikey="Your API key",debug=True)
+client = Doc2X(debug=True)
+
+success, failed, flag = client.pdf2file(
+    pdf_file="tests/pdf/test",
+    output_path="./Output",
+    output_format="docx",
+)
+print(success)
+print(failed)
+print(flag)

examples/convert_pdfs_multiple_types.py

@@ -0,0 +1,19 @@
+# This is an example of how to convert all PDF files in a folder to multiple types of files.
+# 这是一个将文件夹中的所有 PDF 文件转换为多种类型文件的示例。
+
+from pdfdeal import Doc2X
+
+# gets API Key from environment variable DOC2X_APIKEY, or you can pass it as a string to the apikey parameter
+# 从环境变量 DOC2X_APIKEY 获取 API Key, 或者您可以将其作为字符串传递给 apikey 参数
+
+# client = Doc2X(apikey="Your API key",debug=True)
+client = Doc2X(debug=True)
+
+success, failed, flag = client.pdf2file(
+    pdf_file="/home/menghuan/文档/Test/pdf",
+    output_path="./Output",
+    output_format="docx,md",
+)
+print(success)
+print(failed)
+print(flag)

examples/convert_single_pdf.py

@@ -0,0 +1,19 @@
+# This is an example of how to convert a single PDF file to a single DOCX file.
+# 这是一个将单个 PDF 文件转换为单个 DOCX 文件的示例。
+
+from pdfdeal import Doc2X
+
+# gets API Key from environment variable DOC2X_APIKEY, or you can pass it as a string to the apikey parameter
+# 从环境变量 DOC2X_APIKEY 获取 API Key, 或者您可以将其作为字符串传递给 apikey 参数
+
+# client = Doc2X(apikey="Your API key",debug=True)
+client = Doc2X(debug=True)
+
+success, failed, flag = client.pdf2file(
+    pdf_file="tests/pdf/sample.pdf",
+    output_path="Output",
+    output_format="docx",
+)
+print(success)
+print(failed)
+print(flag)

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "pdfdeal"
-version = "0.4.8"
+version = "0.4.9"
 authors = [{ name = "Menghuan1918", email = "[email protected]" }]
 description = "A python wrapper for the Doc2X API and comes with native texts processing (to improve texts recall in RAG)."
 readme = "README.md"
@@ -13,8 +13,8 @@ classifiers = [
 dependencies = ["httpx[http2]>=0.23.1, <1", "pypdf"]
 
 [project.optional-dependencies]
-rag = ["emoji", "Pillow", "reportlab", "oss2", "boto3"]
-dev = ["pytest", "emoji", "Pillow", "reportlab", "oss2", "boto3"]
+rag = ["emoji", "Pillow", "reportlab", "oss2", "boto3", "minio"]
+dev = ["pytest", "emoji", "Pillow", "reportlab", "oss2", "boto3", "minio"]
 
 [project.urls]
 Issues = "https://github.com/Menghuan1918/pdfdeal/issues"