You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

46 lines
1.8 KiB

This file contains ambiguous Unicode characters!

This file contains ambiguous Unicode characters that may be confused with others in your current locale. If your use case is intentional and legitimate, you can safely ignore this warning. Use the Escape button to highlight these characters.

# 参考文档
# https://blog.csdn.net/make_progress/article/details/144490719
# 魔搭社区下载DoclingModels
# https://modelscope.cn/models/ds4sd/docling-models
# pip install modelscope
# modelscope download --model ds4sd/docling-models --local_dir D:\Model\docling
from docling.datamodel.base_models import InputFormat
from docling.datamodel.pipeline_options import PdfPipelineOptions, EasyOcrOptions
from docling.document_converter import PdfFormatOption, DocumentConverter, ImageFormatOption, PowerpointFormatOption, \
WordFormatOption, ExcelFormatOption, HTMLFormatOption
# 参考接口地址
# https://ds4sd.github.io/docling/v2/#access-document-structures
# 配置OCR模型设置EasyOCR模型的路径
easyocr_model_storage_directory = "D:/Model/ocr/EasyOCR/model"
easyocr_options = EasyOcrOptions()
easyocr_options.model_storage_directory = easyocr_model_storage_directory
# 配置pdf模型设置Docling模型的路径
pdf_artifacts_path = "D:/Model/docling"
pdf_pipeline_options = PdfPipelineOptions(artifacts_path=pdf_artifacts_path)
pdf_pipeline_options.ocr_options = easyocr_options
# 转换模型
converter = DocumentConverter(
format_options={
InputFormat.PDF: PdfFormatOption(pipeline_options=pdf_pipeline_options),
InputFormat.IMAGE: ImageFormatOption(pipeline_options=pdf_pipeline_options),
InputFormat.PPTX: PowerpointFormatOption(pipeline_options=pdf_pipeline_options),
InputFormat.DOCX: WordFormatOption(pipeline_options=pdf_pipeline_options),
InputFormat.XLSX: ExcelFormatOption(pipeline_options=pdf_pipeline_options),
InputFormat.HTML: HTMLFormatOption(pipeline_options=pdf_pipeline_options)
}
)
source = "E:/test/test.pdf"
result = converter.convert(source)
print(result.document.export_to_markdown())