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')) 

下面是提取文本的最简单代码

代码:

# importing required modules
import PyPDF2

# creating a pdf file object
pdfFileObj = open('filename.pdf', 'rb')

# creating a pdf reader object
pdfReader = PyPDF2.PdfFileReader(pdfFileObj)

# printing number of pages in pdf file
print(pdfReader.numPages)

# creating a page object
pageObj = pdfReader.getPage(5)

# extracting text from page
print(pageObj.extractText())

# closing the pdf file object
pdfFileObj.close()

一种更健壮的方法，假设有多个PDF或只有一个!

import os
from PyPDF2 import PdfFileWriter, PdfFileReader
from io import BytesIO

mydir = # specify path to your directory where PDF or PDF's are

for arch in os.listdir(mydir): 
    buffer = io.BytesIO()
    archpath = os.path.join(mydir, arch)
    with open(archpath) as f:
            pdfFileObj = open(archpath, 'rb')
            pdfReader = PyPDF2.PdfFileReader(pdfFileObj)
            pdfReader.numPages
            pageObj = pdfReader.getPage(0) 
            ley = pageObj.extractText()
            file1 = open("myfile.txt","w")
            file1.writelines(ley)
            file1.close()
            

在尝试textract(似乎有太多依赖项)和pypdf2(无法从我测试的pdf中提取文本)和tika(太慢)后，我最终使用xpdf中的pdftotext(正如已经在另一个答案中建议的那样)，并直接从python中调用二进制(您可能需要调整路径到pdftotext):

import os, subprocess
SCRIPT_DIR = os.path.dirname(os.path.abspath(__file__))
args = ["/usr/local/bin/pdftotext",
        '-enc',
        'UTF-8',
        "{}/my-pdf.pdf".format(SCRIPT_DIR),
        '-']
res = subprocess.run(args, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
output = res.stdout.decode('utf-8')

有pdftotext，它基本上相同，但这假设pdftotext在/usr/local/bin中，而我在AWS lambda中使用这个，并希望从当前目录使用它。

顺便说一句:要在lambda上使用这个，你需要把二进制文件和依赖项放到libstdc++中。到函数中。我个人需要编译xpdf。由于这方面的说明会让这个答案变得更糟，我把它们放在了我的个人博客上。

目的:从PDF中提取文本

所需工具:

Poppler for windows: windows中pdftotext文件的包装器 对于anaanaconda: conda install -c conda-forge pdftotext实用程序转换PDF到文本。

步骤: 安装荡漾。windows操作系统:在env路径下增加“xxx/bin/” PIP安装pdftotext

import pdftotext
 
# Load your PDF
with open("Target.pdf", "rb") as f:
    pdf = pdftotext.PDF(f)
 
# Save all text to a txt file.
with open('output.txt', 'w') as f:
    f.write("\n\n".join(pdf))

多页pdf可以提取为文本在单一延伸，而不是给个别页码作为参数使用下面的代码

import PyPDF2
import collections
pdf_file = open('samples.pdf', 'rb')
read_pdf = PyPDF2.PdfFileReader(pdf_file)
number_of_pages = read_pdf.getNumPages()
c = collections.Counter(range(number_of_pages))
for i in c:
   page = read_pdf.getPage(i)
   page_content = page.extractText()
   print page_content.encode('utf-8')