肥皂的小屋

# !/usr/bin/python
# -  *  - coding:utf-8 -  *  -
'''
@author: soapffz
@fucntion: 批量提取pdf中所有單詞(python2)
@time: 2019-01-06
'''

from cStringIO 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 re


def convert(path):
    rsrcmgr = PDFResourceManager()
    retstr = StringIO()
    device = TextConverter(rsrcmgr, retstr, codec = 'utf-8', laparams = LAParams())
    interpreter = PDFPageInterpreter(rsrcmgr, device)
    with open(path, 'rb')as fp:
        for page in PDFPage.get_pages(fp, set()):
            interpreter.process_page(page)
        text = retstr.getvalue()
    device.close()
    retstr.close()
    return text

def main(path):
    os.chdir(path)# 切換工作目錄
    pdf_path = [i for i in os.listdir("./")if i.endswith("pdf")]
    words_list = []
    for i in pdf_path:
        print "Searching word in " + i
        pdf_text = convert(i)
        words = re.findall('[A-Za-z]+', pdf_text)
        for i in words:
            if i not in words_list:
                words_list.append(i)
    #print words_list
    # 返回包含所有單詞的一個list
    return words_list


if __name__ == "__main__":
    path = r"C:\Users\soapffz\Desktop\to_dir"
    # 注意複製的目錄前面可能有一個看不見的特殊符號
    main(path)