here we are looking for files whose names are in the form of 2020-01-01-upload.pdf
below script was taken from github
Python Script to Create and acess Filenames in the form of Date
#!/usr/bin/python3 import requests import os url = 'http://10.10.10.10/documents/' for i in range(2020,2022): for j in range(1,13): for k in range(1,31):
#File name date = f'{i}-{j:02}-{k:02}-upload.pdf' r = requests.get(url+date) #print (r.text) if (r.status_code == 200): print (date) #text = r.text os.system('mkdir pdf') os.system(f'wget {url}{date} -O pdf/{date}')
Using Exif to find the Author of the files
#!/usr/bin/python3 from pwn import * io = process('/bin/sh') io.sendline('ls -al pdf/') lst = io.recvrepeat(1).decode().strip().split('\n') files = [] for i in range(3,len(lst)): tmp = lst[i].split(' ') files.append(tmp[9]) #print (files) f = open('users.txt','w') for i in files: io.sendline(f'exiftool pdf/{i}') tmp = (io.recvrepeat(1).decode().strip().split(': ')) f.write(tmp[-1] + '\n') print (tmp[-1]) f.close()
Extract Specific keywords from a set of files
#!/usr/bin/python3 from pdfminer.high_level import extract_text files = ['1.pdf','2.pdf','3.pdf','4.pdf','5.pdf','6.pdf','7.pdf','8.pdf'] #keywords = ['user','username','pass','password'] keywords = 'user' for i in files: text = extract_text('pdf/'+i) if(keywords in text): print (i) print (text)
Comments
Post a Comment