文档解析 - Parse

{
    "code": 200,
    "message": "success",
    "x_request_id": "81017abf0fdd3f63ca5c42872cd09a0b",
    "data": {
        "elements": [
            {
                "element_id": "13a9939f23e485ca20a16c741658bcf64efd82309a6f0a8cf35679a65b2fd0dc",
                "type": "NarrativeText",
                "text": "xParse 是一个端到端文档处理 AI 基础设施，致力于将非结构化文档高效转化为可查询、可分析的向量数据资产。",
                "metadata": {
                    "filename": "example.pdf",
                    "filetype": "application/pdf",
                    "last_modified": "1758624866230",
                    "page_number": 1,
                    "page_width": 1191,
                    "page_height": 1684,
                    "parent_id": "23a9939f23e485ca20a16c741658bcf64efd82309a6f0a8cf35679a65b2fd0dc",
                    "category_depth": 1,
                    "coordinates": [0.1822, 0.2316, 0.6717, 0.2316, 0.6717, 0.2732, 0.1822, 0.2732],
                    "text_as_html": "<p>...</p>",
                    "data_source": {
                        "record_locator": {
                            "protocol": "file",
                            "remote_file_path": "/projects/demo/example.pdf"
                        },
                        "url": "file:///projects/demo/example.pdf",
                        "version": "1758624866230967485",
                        "date_created": "1764555574237",
                        "date_modified": "1758624866230",
                        "date_processed": "1764742970688"
                    }
                }
            },
            // ... more elements
        ]
    },
}

from xparse_client import (
    Pipeline,
    LocalSource,
    LocalDestination,
    Stage,
    ParseConfig
)

# 创建数据源
source = LocalSource(
    directory='./documents',
    pattern=['*.pdf']
)

# 创建目标存储
destination = LocalDestination(
    output_dir='./output'
)

# 创建解析配置
parse_config = ParseConfig(
    provider='textin',
    parse_mode='auto'
)

# 创建 Pipeline
pipeline = Pipeline(
    source=source,
    destination=destination,
    api_base_url='https://api.textin.com/api/xparse',
    api_headers={
        'x-ti-app-id': 'your-app-id',
        'x-ti-secret-code': 'your-secret-code'
    },
    stages=[
        Stage(
            type='parse',
            config=parse_config
        )
    ]
)

pipeline.run()

from xparse_client import ParseConfig

# 创建解析配置，包含 PDF 密码
parse_config = ParseConfig(
    provider='textin',
    pdf_pwd='your-password'  # 提供 PDF 密码
)

# 在 Pipeline 中使用
# pipeline = Pipeline(
#     source=source,
#     destination=destination,
#     stages=[
#         Stage(type='parse', config=parse_config)
#     ],
#     # ... 其他配置
# )

from xparse_client import ParseConfig

# 创建解析配置，指定解析页面范围
parse_config = ParseConfig(
    provider='textin',
    page_ranges='5-7'  # 解析第 5 页到第 7 页
)

# 在 Pipeline 中使用
# pipeline = Pipeline(
#     source=source,
#     destination=destination,
#     stages=[
#         Stage(type='parse', config=parse_config)
#     ],
#     # ... 其他配置
# )

from xparse_client import ParseConfig

# 创建解析配置，启用图片存储功能
parse_config = ParseConfig(
    provider='textin',
    get_page_image=True,  # 返回页面图片
    get_sub_image=True,    # 返回子图
    image_storage_config={
        'endpoint': 'https://s3.oss-cn-beijing.aliyuncs.com',
        'access_key': 'your-access-key',
        'secret_key': 'your-secret-key',
        'bucket': 'your-bucket-name',
        'region': 'cn-beijing',
        'prefix': '',
        'url_prefix': 'https://your-file-server.com/download?filename='
    }
)

# 在 Pipeline 中使用
# pipeline = Pipeline(
#     source=source,
#     destination=destination,
#     stages=[
#         Stage(type='parse', config=parse_config)
#     ],
#     # ... 其他配置
# )