我想使用PDFminer将PDF中的文本提取到.text文件。我找到了代码，但我不知道如何使用

Question

这是我在这里找到的密码。我不知道怎么用。有人能带我看一下这个并帮我转换一个pdf格式的样本吗？

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

Answer 1

最后我找到了一个办法。最好的库是PDfminer，在pdf2txt.py中很少修改以有效使用。pdf2text.py位于pdfminer/tools中

在终端上安装PDfminer

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")

Answer 2

如果使用pdfminer并使用其页面中的代码并阅读其文档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

我认为你不应该有任何麻烦使用：

def convert（fname，pages=None）：它基本上为您转换pdf

使用如下：

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

使用示例pdf：