在不创建文件的情况下将pdf转换为文本

Question

res=requests.get（url,timeout=none)

Answer 1

faik,您将必须至少创建一个临时文件,以便您可以执行您的过程。

您可以使用以下代码获取/读取PDF文件并将其转换为文本文件。这就利用了PDFMINER和Python3.7。

from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
from pdfminer.converter import HTMLConverter,TextConverter,XMLConverter
from pdfminer.layout import LAParams
from pdfminer.pdfpage import PDFPage
import io

def convert(case,fname, pages=None):
    if not pages:
        pagenums = set()
    else:
        pagenums = set(pages)
    manager = PDFResourceManager()
    codec = 'utf-8'
    caching = True
    output = io.StringIO()
    converter = TextConverter(manager, output, codec=codec, laparams=LAParams())
    interpreter = PDFPageInterpreter(manager, converter)
    infile = open(fname, 'rb')
    for page in PDFPage.get_pages(infile, pagenums, caching=caching, check_extractable=True):
        interpreter.process_page(page)

    convertedPDF = output.getvalue()
    print(convertedPDF)

    infile.close()
    converter.close()
    output.close()
    return convertedPDF

调用上述程序的主要函数：

import os
import converter
import sys, getopt

class ConvertMultiple:
    def convert_multiple(pdf_dir, txt_dir):
        if pdf_dir == "": pdf_dir = os.getcwd() + "\\"  # if no pdfDir passed in
        for pdf in os.listdir(pdf_dir):  # iterate through pdfs in pdf directory
            print("File name is %s", os.path.basename(pdf))
            file_extension = pdf.split(".")[-1]
            print("file extension is %s", file_extension)
            if file_extension == "pdf":
                pdf_file_name = pdf_dir + pdf
                path = 'E:/pdf/' + os.path.basename(pdf)
                print(path)
                text = converter.convert('text', path)  # get string of text content of pdf
                text_file_name = txt_dir + pdf + ".txt"
                text_file = open(text_file_name, "w")  # make text file
                text_file.write(text)  # write text to text file


pdf_dir = "E:/pdf"
txt_dir = "E:/text"
ConvertMultiple.convert_multiple(pdf_dir, txt_dir)