python-3.x - 从 PDF 文档中提取特定片段

Question

我有一些 pdf 格式的研究论文，我想从论文中提取介绍/背景等。另外，我只能使用python。有人可以帮忙吗？

Answer 1

我得到了帮助，就在这里，几周前有类似的事情。使用 PDF 文件可能很容易，也可能非常困难，而且有各种不同类型的 PDF 文件。话虽如此，您应该考虑将所有 PDF 文件转换为文本文件。试试下面的代码示例。

首先，将 PDF 转换为文本。

from io import StringIO
from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
from pdfminer.converter import TextConverter
from pdfminer.layout import LAParams
from pdfminer.pdfpage import PDFPage
import os
import sys, getopt

#converts pdf, returns its text content as a string
def convert(fname, pages=None):
    if not pages:
        pagenums = set()
    else:
        pagenums = set(pages)

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

    infile = open(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 

#converts all pdfs in directory pdfDir, saves all resulting txt files to txtdir
def convertMultiple(pdfDir, txtDir):
    if pdfDir == "": pdfDir = os.getcwd() + "\\" #if no pdfDir passed in 
    for pdf in os.listdir(pdfDir): #iterate through pdfs in pdf directory
        fileExtension = pdf.split(".")[-1]
        if fileExtension == "pdf":
            pdfFilename = pdfDir + pdf 
            text = convert(pdfFilename) #get string of text content of pdf
            textFilename = txtDir + pdf + ".txt"
            textFile = open(textFilename, "w") #make text file
            textFile.write(text) #write text to text file

# set paths accordingly:
pdfDir = "C:/your_path_here/PDF_in/"
txtDir = "C:/your_path_here/TEXT_out/"
convertMultiple(pdfDir, txtDir)

其次，查找开始标签（“纽约州不动产法”）和结束标签（“物业的共同元素”）之间的所有文本。

# Loop through all TEXT files in a folder
# Pull out all text between two anchors: "New York State Real Property Law" & "common elements of the property."
import re
import os
myRegex=re.compile("New York State Real Property Law.*?common elements of the property\.",re.DOTALL)
for foldername,subfolders,files in os.walk(r"C:/your_path_here/text_files/"):
    for file in files:
        print(file)
        object=open(os.path.join(foldername,file))
        Text=object.read()
        for subText in myRegex.findall(Text):
            print(subText)

object.close()

也许您可以在不将 PDF 转换为文本文件的情况下完成所有工作，但我还没有找到任何方法来做到这一点。