使用Textract提取/刮擦PDF - 不打印文本

Question

我试图使用Textract在doem PDF文件中提取文本。但是，当我在代码末尾打印文本时，它只会打印出很多空白区域。任何人都可以指出我的方向发生了什么？ （顺便说一句，文字不是=“”）

import os
import codecs
import PyPDF2 
import textract
from nltk.tokenize import word_tokenize
from nltk.corpus import stopwords

for filename in os.listdir('Harbour PDF'):
    if '.DS_Store' == filename:
        continue
    filename = 'Harbour PDF/' + filename
    print(filename)

    pdfFileObj = open(filename,'rb')

    pdfReader = PyPDF2.PdfFileReader(pdfFileObj)

    num_pages = pdfReader.numPages
    count = 0
    text = ""

    while count < num_pages:
        pageObj = pdfReader.getPage(count)
        count +=1
        text += pageObj.extractText()


    if text != "":
        text = text
    else:
        text = textract.process(pdfFileObj, method='tesseract', language='eng')

    print(text)

Answer 1

我通过python使用的2个函数（第2个需要tesseract）。好吧，我实际上更喜欢tesseract而不是pdfminer，但他们有效地做同样的事情。不确定你的代码有什么问题，但这些是我认为的替代等价物。

from PIL import Image
import pytesseract
import cv2
import os
import subprocess

from pdfminer.converter import TextConverter
from pdfminer.pdfinterp import PDFPageInterpreter
from pdfminer.pdfinterp import PDFResourceManager
from pdfminer.pdfpage import PDFPage

#converts pdf, returns its text content as a string
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 = 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

def to_txt(pdf_path, output_dir, name=None):
    if not os.path.exists(output_dir):
        os.makedirs(output_dir)
    if name == None:
        parts = pdf_path.split('\\')
        fname = parts[-1][:-4] + '.txt'
        fname = fname.replace(" ", "_")
        end = output_dir + fname
    else:
        if name[-4:] != '.txt':
            name += '.txt'
        end = output_dir + name
    cmd = ['pdftotext', pdf_path,
           end]
    subprocess.call(cmd)
    print('Converted')