github-featured / unstructured-io--unstructured

发布

0 发布 249 Git 标签

RSS 订阅源
  • 0.14.4 1dede5029d
    比较

    fix: parsing pdf error - new_cells as str has no "copy" (#3130)

    frostbyte_neo 发布于 2024-06-03 18:49:38 +00:00

    Closes #3119.

    Testing

    Parsing the provided PDF should be successful.

    testing_brochure_2.pdf

    filename = "testing_brochure_2.pdf"
with open(filename, "rb") as pdf_content:
    elements = partition_pdf(
        file=pdf_content,
        infer_table_structure=True,
        extract_image_block_types=["Image", "Table"],
        chunking_strategy="by_title",
        max_characters=1000,
        new_after_n_chars=3000,
        combine_text_under_n_chars=1000,
    )
print("\n\n".join([str(el) for el in elements]))
    下载附件