pdf2txt.py

#!/home/veelion/.virtualenvs/py3.6/bin/python3.6

"""
Converts PDF text content (though not images containing text) to plain text, html, xml or "tags".
"""
import io
import sys
import pdfminer.settings
pdfminer.settings.STRICT = False
import pdfminer.high_level
import pdfminer.layout
from pdfminer.image import ImageWriter


def extract_text(file_name, outfile='-',
            _py2_no_more_posargs=None,  # Bloody Python2 needs a shim
            no_laparams=False, all_texts=None, detect_vertical=None, # LAParams
            word_margin=None, char_margin=None, line_margin=None, boxes_flow=None, # LAParams
            output_type='text', codec='utf-8', strip_control=False,
            maxpages=0, page_numbers=None, password="", scale=1.0, rotation=0,
            layoutmode='normal', output_dir=None, debug=False,
            disable_caching=False, **other):
    if _py2_no_more_posargs is not None:
        raise ValueError("Too many positional arguments passed.")
    if not file_name:
        raise ValueError("Must provide files to work upon!")

    # If any LAParams group arguments were passed, create an LAParams object and
    # populate with given args. Otherwise, set it to None.
    if not no_laparams:
        laparams = pdfminer.layout.LAParams()
        for param in ("all_texts", "detect_vertical", "word_margin", "char_margin", "line_margin", "boxes_flow"):
            paramv = locals().get(param, None)
            if paramv is not None:
                setattr(laparams, param, paramv)
    else:
        laparams = None

    imagewriter = None
    if output_dir:
        imagewriter = ImageWriter(output_dir)

    if output_type == "text" and outfile != "-":
        for override, alttype in (  (".htm", "html"),
                                    (".html", "html"),
                                    (".xml", "xml"),
                                    (".tag", "tag") ):
            if outfile.endswith(override):
                output_type = alttype

    outfp = io.StringIO()

    with open(file_name, "rb") as fp:
        pdfminer.high_level.extract_text_to_fp(fp, **locals())
    outfp.seek(0)
    return outfp.readlines()


if __name__ == '__main__':
    fn = sys.argv[1]
    lines = extract_text(fn)
    print(''.join(lines))
    pass