Python 3.10+ asyncio
# Using pip
$ python -m pip install df-extract
# Manual install
$ python -m pip install .from df_extract.pdf import ExtractPDF
path = "/home/test/ABC.pdf"
extract_pdf = ExtractPDF(file_path=path)
# By default, output as text
await extract_pdf.extract() # Output will be located `/home/test/ABC.pdf.txt`
# Output as json
await extract_pdf.extract(as_json=True) # Output will be located `/home/test/ABC.pdf.json`You can change the output directory with simply pass
output_dirparam
from df_extract.pdf import ExtractPDF
path = "/home/test/ABC.pdf"
extract_pdf = ExtractPDF(file_path=path, output_dir="/home/test/output")
await extract_pdf.extract()This requires
easyocr
from df_extract.base import ImageExtract
from df_extract.pdf import ExtractPDF
path = "/home/test/ABC.pdf"
image_extract = ImageExtract(model_download_enabled=True)
extract_pdf = ExtractPDF(file_path=path, image_extract=image_extract)
await extract_pdf.extract()from df_extract.pptx import ExtractPPTx
path = "/home/test/DEF.pptx"
extract_pptx = ExtractPPTx(file_path=path)
# By default, output as text
await extract_pptx.extract() # Output will be located `/home/test/DEF.pptx.txt`
# Output as json
await extract_pptx.extract(as_json=True) # Output will be located `/home/test/DEF.pptx.json`from df_extract.docx import ExtractDocx
path = "/home/test/GHI.docx"
extract_docx = ExtractDocx(file_path=path)
# By default, output as text
await extract_docx.extract() # Output will be located `/home/test/GHI.docx.txt`
# Output as json
await extract_docx.extract(as_json=True) # Output will be located `/home/test/GHI.docx.json`from df_extract.image import ExtractImage
path = "/home/test/JKL.png"
extract_png = ExtractImage(file_path=path)
# By default, output as text
await extract_png.extract() # Output will be located `/home/test/JKL.png.txt`
# Output as json
await extract_png.extract(as_json=True) # Output will be located `/home/test/JKL.png.json`