Merge pull request #23 from LianjiaTech/opensource_fix

修复包仓库被移动，优化使用手册

Author: txl1290

README.md

@@ -57,12 +57,13 @@ Bella-Knowledge地址：https://github.com/LianjiaTech/bella-knowledge
 1. 安装依赖
 
    ```shell
-   pip install document_parser
+   pip install bella-domify
    ```
 
 2. 配置
 
    ```python
+   # ImageStorageProvider是个抽象类，需要自己实现图片的存储，内部有upload和down方法
    parser_config = ParserConfig(image_provider=ImageStorageProvider(),
                                 ocr_model_name="gtp-4o",
                                 # 是否开启OCR能力
@@ -75,11 +76,13 @@ Bella-Knowledge地址：https://github.com/LianjiaTech/bella-knowledge
 
 3. 执行解析
    ```python
-   converter = Converter(stream=stream) # 以文件流的形式传入
+   # Converter类型有PDFConverter、XlsExcelConverter、XlsxExcelConverter、TxtConverter等
+   converter = PDFConverter(stream=stream) # 以文件流的形式传入
    dom_tree = converter.dom_tree_parse( 
        remove_watermark=True,   # 是否开启去水印
        parse_stream_table=False # 是否解析流式表格
    )
+   print(dom_tree)
    ```
 
 ### 服务化运行

README_EN.md

@@ -49,11 +49,12 @@ The following environment variables need to be set:
 
 1. Install Dependencies
    ```shell
-   pip install document_parser
+   pip install bella-domify
    ```
 
 2. Configuration
    ```python
+    # ImageStorageProvider is ABC, you can implement your own image storage provider according to your business needs
    parser_config = ParserConfig(image_provider=ImageStorageProvider(),
                                ocr_model_name="gtp-4o",
                                # Whether to enable OCR capability
@@ -66,11 +67,13 @@ The following environment variables need to be set:
 
 3. Execute Parsing
    ```python
-   converter = Converter(stream=stream) # Pass in as file stream
-   dom_tree = converter.dom_tree_parse(
+   # Converter：PDFConverter、XlsExcelConverter、XlsxExcelConverter、TxtConverter etc.
+   converter = PDFConverter(stream=stream) # Pass in as bytes stream
+   dom_tree = converter.dom_tree_parse( 
        remove_watermark=True,   # Whether to enable watermark removal
-       parse_stream_table=False # Whether to parse streaming tables
+       parse_stream_table=False# Whether to parse streaming tables
    )
+   print(dom_tree)
    ```
 
 ### Running as a Service

setup.py

@@ -42,25 +42,28 @@ def load_long_description(fname):
 
 
 def load_requirements(fname):
-    try:
-        # pip >= 10.0
-        from pip._internal.req import parse_requirements        
-    except ImportError:
-        # pip < 10.0
-        from pip.req import parse_requirements
+    """纯文件读取，不依赖 pip"""
+    if not os.path.isfile(fname):
+        return []  # 文件不存在就当成空依赖
 
-    reqs = parse_requirements(fname, session=False)
-    try:
-        requirements = [str(ir.requirement) for ir in reqs]
-    except AttributeError:
-        requirements = [str(ir.req) for ir in reqs]
+    with open(fname, encoding="utf-8") as f:
+        lines = f.readlines()
 
-    return requirements
+    reqs = []
+    for line in lines:
+        line = line.strip()
+        if line == "" or line.startswith("#"):  # 去掉空行和注释
+            continue
+        # 简单处理 --find-links 等命令行参数（如果有）
+        if line.startswith("-"):
+            continue
+        reqs.append(line)
+    return reqs
 
 
 if __name__ == "__main__":
     setup(
-        name="document_parser",
+        name="bella-domify",
         version=get_version("version.txt"),
         keywords=["document-doc_parser"],
         description=DESCRIPTION,