Python使用PDFMiner.six解析PDF数据详解

pip install pdfminer.six
pip install 'pdfminer.six[image]'

from pdfminer.high_level import extract_text
from os import path

path = path.abspath(path.dirname(__file__))
print(path)

pdf_file = path + '/sample01.pdf'
text = extract_text(pdf_file)
print(text)

from io import StringIO

from pdfminer.converter import TextConverter
from pdfminer.layout import LAParams
from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
from pdfminer.pdfpage import PDFPage
from pdfminer.utils import open_filename

from os import path

path = path.abspath(path.dirname(__file__))
print(path)


def iter_text_per_page(pdf_file, password='', page_numbers=None, maxpages=0,
                 caching=True, codec='utf-8', laparams=None):
    if laparams is None:
        laparams = LAParams()

    with open_filename(pdf_file, "rb") as fp:
        rsrcmgr = PDFResourceManager(caching=caching)

        idx = 1
        for page in PDFPage.get_pages(
                fp,
                page_numbers,
                maxpages=maxpages,
                password=password,
                caching=caching,
        ):
            with StringIO() as output_string:
                device = TextConverter(rsrcmgr, output_string, codec=codec,
                                       laparams=laparams)
                interpreter = PDFPageInterpreter(rsrcmgr, device)
                interpreter.process_page(page)
                yield idx, output_string.getvalue()
                idx += 1


def main():
    pdf_file = path + '/sample02.pdf'
    for count, page_text in iter_text_per_page(pdf_file):
        print(f'page# {count}:\n{page_text}')
        print()


if __name__ == "__main__":
    main()

usage: pdf2txt.py [-h] [--version] [--debug] [--disable-caching] [--page-numbers PAGE_NUMBERS [PAGE_NUMBERS ...]]
                  [--pagenos PAGENOS] [--maxpages MAXPAGES] [--password PASSWORD] [--rotation ROTATION] [--no-laparams]
                  [--detect-vertical] [--line-overlap LINE_OVERLAP] [--char-margin CHAR_MARGIN] [--word-margin WORD_MARGIN]
                  [--line-margin LINE_MARGIN] [--boxes-flow BOXES_FLOW] [--all-texts] [--outfile OUTFILE]
                  [--output_type OUTPUT_TYPE] [--codec CODEC] [--output-dir OUTPUT_DIR] [--layoutmode LAYOUTMODE]
                  [--scale SCALE] [--strip-control]
                  files [files ...]

To extract all text from pdf:
pdf2txt.py --all-texts ../samples/manual.pdf

To extract all images from pdf:
pdf2txt.py --output-dir images ../sample03.pdf

from pdfminer.pdfdocument import PDFDocument
from pdfminer.pdfparser import PDFParser
from pdfminer.pdftypes import resolve1

pdf_file = '../samples/brocher1.pdf'

with open(pdf_file, 'rb') as f:
    parser = PDFParser(f)
    doc = PDFDocument(parser)
    parser.set_document(doc)
    pages = resolve1(doc.catalog['Pages'])
    pages_count = pages.get('Count', 0)
    print(pages_count)

from io import StringIO
from pdfminer.high_level import extract_text_to_fp
from pdfminer.layout import LAParams

output = StringIO()
with open('example.pdf', 'rb') as pdf_file:
    extract_text_to_fp(pdf_file, output, laparams=LAParams(), output_type='html', codec=None)
with open('example.html', 'a') as html_file:
    html_file.write(output.getvalue())