使用pdfminer从pdf中提取文本可以提供多个副本

Question

我正在尝试使用PDFMiner（在Extracting text from a PDF file using PDFMiner in python?上找到的代码）从PDF文件中提取文本。除了path / to / pdf之外，我没有更改代码。令人惊讶的是，代码返回同一文档的多个副本。我得到了与其他pdf文件相同的结果。我是否需要传递其他论点或者我错过了什么？任何帮助都非常感谢。为了以防万一，我提供了代码：

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()
    fstr = ''
    for page in PDFPage.get_pages(fp, pagenos, maxpages=maxpages,    password=password,caching=caching, check_extractable=True):
        interpreter.process_page(page)

        str = retstr.getvalue()
        fstr += str

    fp.close()
    device.close()
    retstr.close()
    return fstr

print convert_pdf_to_txt("test.pdf")

Answer 1

我的答案在您引用的主题中有点不正确。我发现了这个错误并忘了更新我的回答。

因为pdfminer的文档很少，所以我无法完全解释为什么它的工作方式如此。希望能够更好地了解pdfminer库的人可以给我们一些见解。

我所知道的是你必须在for循环之外做text = retstr.getvalue()。我只能假设retstr正在更新，就像我们在for循环中做final_text += text一样，所以一旦完成，我们只需要做text = retstr.getvalue()从所有页面获取文本。

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

print convert_pdf_to_txt("test.pdf")

希望这有帮助！

Answer 2

对于python 3，DuckPuncher的代码只需要一个小调整：

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