Table extraction from PDF

from unstructured.partition.pdf import partition_pdf

fname = "example-docs/pdf/layout-parser-paper.pdf"

elements = partition_pdf(filename=fname,
                         skip_infer_table_types=False,
                         strategy='hi_res',
           )

tables = [el for el in elements if el.category == "Table"]

print(tables[0].text)
print(tables[0].metadata.text_as_html)

from unstructured.partition.auto import partition

filename = "example-docs/pdf/layout-parser-paper.pdf"

elements = partition(filename=filename,
                     strategy='hi_res',
           )

tables = [el for el in elements if el.category == "Table"]

print(tables[0].text)
print(tables[0].metadata.text_as_html)

curl -X 'POST' \
    'https://api.unstructured.io' \
    -H 'accept: application/json' \
    -H 'Content-Type: multipart/form-data' \
    -F 'files=@sample-docs/layout-parser-paper-with-table.jpg' \
    -F 'strategy=hi_res' \
    | jq -C . | less -R