python自动读取pdf文件（用pdfminer库）

之前自己瞎玩儿，在网上搜索半天，找到了不少资料，但是每次代码都无法正确运行。为了方便大家日后研究，我把自己能运行起来的代码贴进来，供大家参考，说实话好多都是自己copy别人的，弄不太清楚。但是编译过程中自己解决了一些打开文件open和utf-8编码的问题。

python 版本3.8.2

pycharm版本2020.1.4

pdfminer版本20191125

代码如下：

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):
    rsrcmgr = PDFResourceManager()
    retstr = StringIO()
    codec = 'utf-8'
    laparams = LAParams()
    device = TextConverter(rsrcmgr, retstr, 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

if __name__ == '__main__':
    outputString = convert_pdf_to_txt("D:\develop\douban\PAY-ICH-OA-1-20200729.pdf")
    with open(r'D:\develop\douban\3.txt', 'a',encoding='utf-8') as f:
        f.write(outputString)
        # f.write(outputString.replace(u'\xa0', u''))# 写入文件
    print(outputString)