试试borb，一个纯python PDF库

import typing  
from borb.pdf.document import Document  
from borb.pdf.pdf import PDF  
from borb.toolkit.text.simple_text_extraction import SimpleTextExtraction  


def main():

    # variable to hold Document instance
    doc: typing.Optional[Document] = None  

    # this implementation of EventListener handles text-rendering instructions
    l: SimpleTextExtraction = SimpleTextExtraction()  

    # open the document, passing along the array of listeners
    with open("input.pdf", "rb") as in_file_handle:  
        doc = PDF.loads(in_file_handle, [l])  
  
    # were we able to read the document?
    assert doc is not None  

    # print the text on page 0
    print(l.get_text(0))  

if __name__ == "__main__":
    main()

我尝试过许多Python PDF转换器，我想更新这篇评论。蒂卡是最棒的之一。但是PyMuPDF是@ehsaneha用户的好消息。

我做了一个代码来比较一下:https://github.com/erfelipe/PDFtextExtraction希望对大家有所帮助。

Tika-Python是Apache Tika™REST服务的Python绑定 允许在Python社区中本地调用Tika。

from tika import parser

raw = parser.from_file("///Users/Documents/Textos/Texto1.pdf")
raw = str(raw)

safe_text = raw.encode('utf-8', errors='ignore')

safe_text = str(safe_text).replace("\n", "").replace("\\", "")
print('--- safe text ---' )
print( safe_text )

我在寻找一个简单的解决方案来使用python 3。X和窗口。textract似乎不支持，这是不幸的，但如果你正在寻找一个简单的解决方案的windows/python 3签出tika包，真的直接阅读pdf。

Tika-Python是绑定到Apache Tika™REST服务的Python，允许在Python社区中本地调用Tika。

from tika import parser # pip install tika

raw = parser.from_file('sample.pdf')
print(raw['content'])

注意，Tika是用Java编写的，因此需要安装Java运行时

使用pdfminer.six。这里是文档:https://pdfminersix.readthedocs.io/en/latest/index.html

将pdf转换为文本:

    def pdf_to_text():
        from pdfminer.high_level import extract_text

        text = extract_text('test.pdf')
        print(text)

在2020年，上述解决方案并不适用于我正在使用的特定pdf。下面是诀窍。我用的是Windows 10和Python 3.8

测试pdf文件:https://drive.google.com/file/d/1aUfQAlvq5hA9kz2c9CyJADiY3KpY3-Vn/view?usp=sharing

#pip install pdfminer.six
import io

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


def convert_pdf_to_txt(path):
    '''Convert pdf content from a file path to text

    :path the file path
    '''
    rsrcmgr = PDFResourceManager()
    codec = 'utf-8'
    laparams = LAParams()

    with io.StringIO() as retstr:
        with TextConverter(rsrcmgr, retstr, codec=codec,
                           laparams=laparams) as device:
            with open(path, 'rb') as fp:
                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)

                return retstr.getvalue()


if __name__ == "__main__":
    print(convert_pdf_to_txt('C:\\Path\\To\\Test_PDF.pdf')) 

如果您在Windows上的Anaconda中尝试它，PyPDF2可能无法处理一些具有非标准结构或unicode字符的pdf。如果您需要打开并阅读大量pdf文件，我建议使用以下代码-相对路径为。//pdfs//的文件夹中所有pdf文件的文本将存储在列表pdf_text_list中。

from tika import parser
import glob

def read_pdf(filename):
    text = parser.from_file(filename)
    return(text)


all_files = glob.glob(".\\pdfs\\*.pdf")
pdf_text_list=[]
for i,file in enumerate(all_files):
    text=read_pdf(file)
    pdf_text_list.append(text['content'])

print(pdf_text_list)