ScrapPY：一款功能强大的文档数据爬取和字典生成工具

$ mkdir ScrapPY
$ cd ScrapPY/
$ sudo git clone https://github.com/RoseSecurity/ScrapPY.git

$ pip3 install -r requirements.txt

usage: ScrapPY.py [-h] [-f FILE] [-m {word-frequency,full,metadata,entropy}] [-o OUTPUT]

$ python3 ScrapPY.py -f example.pdf -m metadata

$ python3 ScrapPY.py -f example.pdf -m word-frequency -o Top_100_Keywords.txt

$ python3 ScrapPY.py -f example.pdf

$ python3 ScrapPY.py -f example.pdf -m entropy

# ScrapPY outputs the ScrapPY.txt file or specified name file to the directory in which the tool was ran. To view the first fifty lines of the file, run this command:
 
$ head -50 ScrapPY.txt
 
# To see how many words were generated, run this command:
 
$ wc -l ScrapPY.txt

root@RoseSecurity:~# dirb http://192.168.1.123/ /root/ScrapPY/ScrapPY.txt
 
-----------------
DIRB v2.21
By The Dark Raver
-----------------
 
START_TIME: Fri May 16 13:41:45 2014
URL_BASE: http://192.168.1.123/
WORDLIST_FILES: /root/ScrapPY/ScrapPY.txt
 
-----------------
 
GENERATED WORDS: 4592
 
---- Scanning URL: http://192.168.1.123/ ----
==> DIRECTORY: http://192.168.1.123/vi/
+ http://192.168.1.123/programming (CODE:200|SIZE:2726)
+ http://192.168.1.123/s7-logic/ (CODE:403|SIZE:1122)
==> DIRECTORY: http://192.168.1.123/config/
==> DIRECTORY: http://192.168.1.123/docs/
==> DIRECTORY: http://192.168.1.123/external/

root@RoseSecurity:~# hydra -l root -P /root/ScrapPY/ScrapPY.txt -t 6 ssh://192.168.1.123
Hydra v7.6 (c)2013 by van Hauser/THC & David Maciejak - for legal purposes only
 
Hydra (http://www.thc.org/thc-hydra) starting at 2014-05-19 07:53:33
[DATA] 6 tasks, 1 server, 1003 login tries (l:1/p:1003), ~167 tries per task
[DATA] attacking service ssh on port 22

nmap -p445 --script smb-brute.nse --script-args userdb=users.txt,passdb=ScrapPY.txt 192.168.1.123