-4

这是我在这里某处找到的代码。我不知道如何使用它。有人可以帮我完成这个并帮助我转换样本 pdf 吗？

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

def convert_pdf_to_txt(path):
    rsrcmgr = PDFResourceManager()
    retstr = StringIO()
    codec = 'utf-8'
    laparams = LAParams()
    device = TextConverter(rsrcmgr, retstr, codec=codec, laparams=laparams)
    fp = file(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
4

2 回答 2

3

如果您使用 pdfminer 并使用他们页面中的代码并阅读他们的文档https://www.binpress.com/tutorial/manipulating-pdfs-with-python/167：

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

def convert(fname, pages=None):
    if not pages:
        pagenums = set()
    else:
        pagenums = set(pages)

    output = StringIO()
    manager = PDFResourceManager()
    converter = TextConverter(manager, output, laparams=LAParams())
    interpreter = PDFPageInterpreter(manager, converter)

    infile = file(fname, 'rb')
    for page in PDFPage.get_pages(infile, pagenums):
        interpreter.process_page(page)
    infile.close()
    converter.close()
    text = output.getvalue()
    output.close
    return text

我不认为你应该有任何问题使用：

def convert(fname, pages=None)：它基本上为你转换了 pdf

使用如下：

some_variable = convert("filename.pdf") 
print(some_variable)
#do something with your variable

使用您的示例pdf： 在此处输入图像描述

于 2016-05-21T21:46:43.540 回答
-1

最后我找到了解决办法。最好的库是 PDfminer，在 pdf2txt.py 中几乎没有修改即可有效使用。pdf2text.py 位于 pdfminer/tools

在终端上安装 PDfminer 使用

pip install PDfminer

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

def convert(fname):
    pages=None
    if not pages:
        pagenums = set()
    else:
        pagenums = set(pages)

    output = StringIO()
    manager = PDFResourceManager()
    converter = TextConverter(manager, output, laparams=LAParams())
    interpreter = PDFPageInterpreter(manager, converter)

    infile = file(fname, 'rb')
    for page in PDFPage.get_pages(infile, pagenums):
        interpreter.process_page(page)
    infile.close()
    converter.close()
    text = output.getvalue()
    output.close
    print text 

    # write Content to .txt
    text_file = open("Output_1.txt", "w")
    text = re.sub("\s\s+", " ", text)
    text_file.write("%s" % text)
    text_file.close()

convert("xyz.pdf")
于 2017-04-24T07:05:09.663 回答