使用python pdfminer提取整个pdf数据

Question

我正在使用pdfminer使用python从pdf文件中提取数据。我想提取pdf中存在的所有数据，而不管它是图像还是文本，无论它是什么。我们可以在一行中执行此操作吗（如果需要，可以执行两条操作，而无需进行大量工作）。任何帮助表示赞赏。提前致谢

Answer 1

对于Python 3：

点安装pdfminer.six

from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter

from pdfminer.converter import TextConverter

from pdfminer.layout import LAParams

from pdfminer.pdfpage import PDFPage

from io import StringIO

def convert_pdf_to_txt(path, codec='utf-8'):

    rsrcmgr = PDFResourceManager()

    retstr = StringIO()

    laparams = LAParams()

    device = TextConverter(rsrcmgr, retstr, codec=codec, laparams=laparams)

    fp = open(path, 'rb')

    interpreter = PDFPageInterpreter(rsrcmgr, device)

    password = ""

    maxpages = 0

    caching = True

    pagenos=set()

    for page in PDFPage.get_pages(fp, pagenos, maxpages=maxpages, password=password,caching=caching, check_extractable=True):

        interpreter.process_page(page)

    text = retstr.getvalue()

    fp.close()

    device.close()

    retstr.close()

    return text

Answer 2

对于python3，还有另一个：pip install pdfminer3k

from pdfminer.pdfinterp import PDFResourceManager, process_pdf

from pdfminer.converter import TextConverter

from pdfminer.layout import LAParams

from io import StringIO

import time

from functools import wraps

def fn_timer(function)://this is for calculating the run time(function)

    @wraps(function)

    def function_timer(*args, **kwargs):

        t0 = time.time()

        result = function(*args, **kwargs)

        t1 = time.time()

        print ("Total time running %s: %s seconds" %

                ('test', str(t1-t0))

                )

        return result

    return function_timer

@fn_timer

def convert_pdf(path, pages):

    rsrcmgr = PDFResourceManager()

    retstr = StringIO()

    laparams = LAParams()

    device = TextConverter(rsrcmgr, retstr, laparams=laparams)

    fp = open(path, 'rb')

    process_pdf(rsrcmgr, device, fp,pages)

    fp.close()

    device.close()

    str = retstr.getvalue()

    retstr.close()

    return str

file = r'M:\a.pdf'

print(convert_pdf(file,[1,]))