python实现大批量pdf格式论文的重命名与目录制作功能

Python实现批量PDF文件统计处理：https://www.jianshu.com/p/1ec8f4314611
第一步：批量读取pdf文件

# -*- coding: utf-8 -*-
"""
Created on Sat Jun  8 15:30:22 2019
@author: Administrator
"""import os
from io import StringIO
from io import open
from pdfminer.converter import TextConverter
from pdfminer.layout import LAParams
from pdfminer.pdfinterp import PDFResourceManager, process_pdf
from docx import Document
from docx.shared import Pt
from docx.shared import RGBColordef read_pdf(pdf):# resource managerrsrcmgr = PDFResourceManager()retstr = StringIO()laparams = LAParams()# devicedevice = TextConverter(rsrcmgr, retstr, laparams=laparams)process_pdf(rsrcmgr, device, pdf)device.close()content = retstr.getvalue()retstr.close()# 获取所有行lines = str(content).split("\n")return lines#%%#coding=utf-8#%%
article_name = os.listdir('G:\婴儿识别项目\TEMP')
article_name.sort()
i=1
test = Document()
p = test.add_paragraph(u'目录')
for article in article_name:
#    if i<=8 :
#        i=i+1
#        continuerun = p.add_run(article[:len(article)-4])run.font.size = Pt(12)run.font.name=u'Arial'run.font.color.rgb=RGBColor(0,0,255)run.bold=Truerun = p.add_run('\n')if __name__ == '__main__':with open(article, "rb") as my_pdf:lines=read_pdf(my_pdf)count=0for line in lines:if count==0:count=1continueif line==u'∗':breakif line=='Contents lists available at ScienceDirect' or line=='' or line=='International Journal of Refrigeration ' or line=='journal homepage: www.elsevier.com/locate/ijrefrig ' or line=='a , ' or line=='b , ' or line=='c , ' or line=='d , ' or line=='e , ':continuerun = p.add_run(line)run.font.size = Pt(12)run.font.name=u'Arial'#print (lines[0])run = p.add_run('\n')run = p.add_run(lines[0])run.font.size = Pt(12)run.font.name=u'Arial'run = p.add_run('\n')run = p.add_run('\n')#text.close()test.save(u'C:/Users/Administrator/Desktop/目录.docx')#print(read_pdf(my_pdf)[0])#%%
article_name = os.listdir('G:\婴儿识别项目\TEMP')
article_name.sort()article=article_name[2]
#    if i<=8 :
#        i=i+1
#        continueif __name__ == '__main__':with open(article, "rb") as my_pdf:lines=read_pdf(my_pdf)

第二步：
批量重命名文件

# -*- coding: utf-8 -*-
"""
Created on Wed Jun  5 14:37:46 2019
@author: Administrator
"""import os
movie_name = os.listdir('./July')
i=1
for temp in movie_name:new_name = '2019 Jul-' + str(i)+'.pdf'i=i+1os.rename('./July/'+temp,'./July/'+new_name)