将 PDF 转换为文本：“不允许提取文本”

Question

我正在尝试将 PDF 转换为 Python 中的文本。但它给了我一个错误：

PDFTextExtractionNotAllowed：不允许提取文本：<_io.bufferedreader name="C:\Users\Downloads\Facts_for_2017.pdf">

我使用的代码是：

import sys
from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
from pdfminer.pdfpage import PDFPage
from pdfminer.converter import XMLConverter, HTMLConverter, TextConverter
from pdfminer.layout import LAParams
import io    


def pdfparser(data):
    fp = open(data, 'rb')      
    rsrcmgr = PDFResourceManager()
    retstr = io.StringIO()
    codec = 'utf-8'
    laparams = LAParams()
    device = TextConverter(rsrcmgr, retstr, codec=codec, laparams=laparams)
    interpreter = PDFPageInterpreter(rsrcmgr, device)

    for page in PDFPage.get_pages(fp):
        interpreter.process_page(page)
        data = retstr.getvalue()

    return data


if __name__ == '__main__':
    text = pdfparser(Input_path)

谁能帮帮我？

文件路径是：

https://drive.google.com/file/d/1RyR-J-EwMywL6BqsYbl4Ocm96VzCYrM7/view?usp=sharing

Answer 1

问题在于PDFPage.get_pages() 按照惯例检查文本是否可提取。您必须将标志设置为check_extractable=False 才能使其工作。此外，如果您尝试转换为 txt 的 PDF 受密码保护，您也可以在此处进行更改。很遗憾，PDFPage 的documentation 不是很清楚。

password = ""
for page in PDFPage.get_pages(fp, check_extractable=False, password=password):
    interpreter.process_page(page)
data = retstr.getvalue()

您的整个代码如下所示：

import io

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

def pdfparser(data):
    rsrcmgr = PDFResourceManager()
    retstr = io.StringIO()
    codec = 'utf-8'
    laparams = LAParams()
    device = TextConverter(rsrcmgr, retstr, codec=codec, laparams=laparams)

    interpreter = PDFPageInterpreter(rsrcmgr, device)
    password = ""
    maxpages = 0
    caching = True
    pagenos = set()

    with open(data, 'rb') as fp:
        for page in PDFPage.get_pages(fp,
                                      pagenos, 
                                      maxpages=maxpages,
                                      password=password,
                                      caching=caching,
                                      check_extractable=False):
            interpreter.process_page(page)

    # As pointed out in another answer, this goes outside the loop
    text = retstr.getvalue()

    device.close()
    retstr.close()
    return text

注意：Python 的 with open ...: 模式实现对于正确处理文件对象很有用。

Answer 2

您收到错误是因为，data = retstr.getvalue() 行中的缩进错误，它应该在 for 循环之外。

但是，在修复之后，我遇到了一些其他问题，所以我提供了下面的完整代码：

import sys
from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
from pdfminer.pdfpage import PDFPage
from pdfminer.converter import XMLConverter, HTMLConverter, TextConverter
from pdfminer.layout import LAParams
import io    


def pdfparser(data):
    fp = open(data, 'rb')      
    rsrcmgr = PDFResourceManager()
    # retstr = io.StringIO() #This will cause -- `TypeError: unicode argument expected, got 'str'`
    retstr = io.BytesIO()
    codec = 'utf-8'
    laparams = LAParams()
    device = TextConverter(rsrcmgr, retstr, codec=codec, laparams=laparams)
    interpreter = PDFPageInterpreter(rsrcmgr, device)

    for page in PDFPage.get_pages(fp):
        interpreter.process_page(page)

    data = retstr.getvalue() #Indentation was worng here
    fp.close()
    #print(data)
    return data


if __name__ == '__main__':
    #PDF file you provied is encrypted with blank password, we need to decrypt it
    path = sys.argv[1]
    from subprocess import call
    import os
    pdf_filename = os.path.basename(path)
    file_name, extension = os.path.splitext(pdf_filename)
    pdf_filename_decr = str(file_name) + "_decr" + extension
    call('qpdf --password=%s --decrypt %s %s' %('', path, pdf_filename_decr), shell=True)

    text = pdfparser(pdf_filename_decr)