图形导出

In [ ]

import logging
import time
from pathlib import Path

import logging import time from pathlib import Path

In [ ]

from docling_core.types.doc import ImageRefMode, PictureItem, TableItem

from docling_core.types.doc import ImageRefMode, PictureItem, TableItem

In [ ]

from docling.datamodel.base_models import InputFormat
from docling.datamodel.pipeline_options import PdfPipelineOptions
from docling.document_converter import DocumentConverter, PdfFormatOption

from docling.datamodel.base_models import InputFormat from docling.datamodel.pipeline_options import PdfPipelineOptions from docling.document_converter import DocumentConverter, PdfFormatOption

In [ ]

_log = logging.getLogger(__name__)

_log = logging.getLogger(__name__)

In [ ]

IMAGE_RESOLUTION_SCALE = 2.0

IMAGE_RESOLUTION_SCALE = 2.0

In [ ]

def main():
    logging.basicConfig(level=logging.INFO)

    input_doc_path = Path("./tests/data/pdf/2206.01062.pdf")
    output_dir = Path("scratch")

    # Important: For operating with page images, we must keep them, otherwise the DocumentConverter
    # will destroy them for cleaning up memory.
    # This is done by setting PdfPipelineOptions.images_scale, which also defines the scale of images.
    # scale=1 correspond of a standard 72 DPI image
    # The PdfPipelineOptions.generate_* are the selectors for the document elements which will be enriched
    # with the image field
    pipeline_options = PdfPipelineOptions()
    pipeline_options.images_scale = IMAGE_RESOLUTION_SCALE
    pipeline_options.generate_page_images = True
    pipeline_options.generate_picture_images = True

    doc_converter = DocumentConverter(
        format_options={
            InputFormat.PDF: PdfFormatOption(pipeline_options=pipeline_options)
        }
    )

    start_time = time.time()

    conv_res = doc_converter.convert(input_doc_path)

    output_dir.mkdir(parents=True, exist_ok=True)
    doc_filename = conv_res.input.file.stem

    # Save page images
    for page_no, page in conv_res.document.pages.items():
        page_no = page.page_no
        page_image_filename = output_dir / f"{doc_filename}-{page_no}.png"
        with page_image_filename.open("wb") as fp:
            page.image.pil_image.save(fp, format="PNG")

    # Save images of figures and tables
    table_counter = 0
    picture_counter = 0
    for element, _level in conv_res.document.iterate_items():
        if isinstance(element, TableItem):
            table_counter += 1
            element_image_filename = (
                output_dir / f"{doc_filename}-table-{table_counter}.png"
            )
            with element_image_filename.open("wb") as fp:
                element.get_image(conv_res.document).save(fp, "PNG")

        if isinstance(element, PictureItem):
            picture_counter += 1
            element_image_filename = (
                output_dir / f"{doc_filename}-picture-{picture_counter}.png"
            )
            with element_image_filename.open("wb") as fp:
                element.get_image(conv_res.document).save(fp, "PNG")

    # Save markdown with embedded pictures
    md_filename = output_dir / f"{doc_filename}-with-images.md"
    conv_res.document.save_as_markdown(md_filename, image_mode=ImageRefMode.EMBEDDED)

    # Save markdown with externally referenced pictures
    md_filename = output_dir / f"{doc_filename}-with-image-refs.md"
    conv_res.document.save_as_markdown(md_filename, image_mode=ImageRefMode.REFERENCED)

    # Save HTML with externally referenced pictures
    html_filename = output_dir / f"{doc_filename}-with-image-refs.html"
    conv_res.document.save_as_html(html_filename, image_mode=ImageRefMode.REFERENCED)

    end_time = time.time() - start_time

    _log.info(f"Document converted and figures exported in {end_time:.2f} seconds.")

def main(): logging.basicConfig(level=logging.INFO) input_doc_path = Path("./tests/data/pdf/2206.01062.pdf") output_dir = Path("scratch") # 重要提示：要处理页面图片，我们必须保留它们，否则 DocumentConverter # 会销毁它们以清理内存。 # 这通过设置 PdfPipelineOptions.images_scale 来完成，它也定义了图片的比例。 # scale=1 对应于标准的 72 DPI 图片 # PdfPipelineOptions.generate_* 是用于选择将被增强的文档元素的字段 # 带有图片字段 pipeline_options = PdfPipelineOptions() pipeline_options.images_scale = IMAGE_RESOLUTION_SCALE pipeline_options.generate_page_images = True pipeline_options.generate_picture_images = True doc_converter = DocumentConverter( format_options={ InputFormat.PDF: PdfFormatOption(pipeline_options=pipeline_options) } ) start_time = time.time() conv_res = doc_converter.convert(input_doc_path) output_dir.mkdir(parents=True, exist_ok=True) doc_filename = conv_res.input.file.stem # 保存页面图片 for page_no, page in conv_res.document.pages.items(): page_no = page.page_no page_image_filename = output_dir / f"{doc_filename}-{page_no}.png" with page_image_filename.open("wb") as fp: page.image.pil_image.save(fp, format="PNG") # 保存图形和表格的图片 table_counter = 0 picture_counter = 0 for element, _level in conv_res.document.iterate_items(): if isinstance(element, TableItem): table_counter += 1 element_image_filename = ( output_dir / f"{doc_filename}-table-{table_counter}.png" ) with element_image_filename.open("wb") as fp: element.get_image(conv_res.document).save(fp, "PNG") if isinstance(element, PictureItem): picture_counter += 1 element_image_filename = ( output_dir / f"{doc_filename}-picture-{picture_counter}.png" ) with element_image_filename.open("wb") as fp: element.get_image(conv_res.document).save(fp, "PNG") # 保存包含内嵌图片的 markdown 文件 md_filename = output_dir / f"{doc_filename}-with-images.md" conv_res.document.save_as_markdown(md_filename, image_mode=ImageRefMode.EMBEDDED) # 保存包含外部引用图片的 markdown 文件 md_filename = output_dir / f"{doc_filename}-with-image-refs.md" conv_res.document.save_as_markdown(md_filename, image_mode=ImageRefMode.REFERENCED) # 保存包含外部引用图片的 HTML 文件 html_filename = output_dir / f"{doc_filename}-with-image-refs.html" conv_res.document.save_as_html(html_filename, image_mode=ImageRefMode.REFERENCED) end_time = time.time() - start_time _log.info(f"文档已转换，图形已导出，耗时 {end_time:.2f} 秒。")

In [ ]

if __name__ == "__main__":
    main()

if __name__ == "__main__": main()