tjstavenger-pnnl / pdflib Goto Github PK

git clone --branch poppler-0.63.0 --depth 1 https://anongit.freedesktop.org/git/poppler/poppler.git poppler_src
cd poppler_src/
cmake -DENABLE_SPLASH=OFF -DENABLE_UTILS=OFF -DENABLE_LIBOPENJPEG=none .
make

export POPPLER_ROOT=/pdflib/poppler_src/

pip install cython

python setup.py build_ext --inplace

>>> from pdflib import Document
>>> doc = Document("path/to/file.pdf")

>>> print(doc.metadata)
>>> print(doc.xmp_metadata)

>>> for page in doc:
        print(' \n'.join(page.lines).strip())

>>> for page in doc:
        page.extract_images(path='images', prefix='img')