├── .gitignore
├── README.md
└── pastefind.py


/.gitignore:
--------------------------------------------------------------------------------
 1 | *.py[co]
 2 | 
 3 | # Packages
 4 | *.egg
 5 | *.egg-info
 6 | dist
 7 | build
 8 | eggs
 9 | parts
10 | bin
11 | var
12 | sdist
13 | develop-eggs
14 | .installed.cfg
15 | 
16 | # Installer logs
17 | pip-log.txt
18 | 
19 | # Unit test / coverage reports
20 | .coverage
21 | .tox
22 | 
23 | #Translations
24 | *.mo
25 | 
26 | #Mr Developer
27 | .mr.developer.cfg
28 | 


--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
 1 | pastebin-find
 2 | =============
 3 | 
 4 | Python script to monitor new Pastebin pastes for a provided search term
 5 | 
 6 | Usage: python pastefind.py search_regex
 7 | 
 8 | Edit the "time_between" variable to change the time between requests. Currently it is at 5s. If the value is too low, pastebin may block your IP address for repeated queries. If it is too high, you may miss a paste since the program only scans the top 10 pastes on the recently added page.
 9 | 
10 | Regex should be the regex itself in quotes. For example, to search for formatted phone numbers, use '\(?(\d{3})\)?-?(\d{3})-(\d{4})' as the search input.
11 | 


--------------------------------------------------------------------------------
/pastefind.py:
--------------------------------------------------------------------------------
 1 | #!/usr/bin/python
 2 | # Python file to monitor pastebin for pastes containing the passed regex
 3 | 
 4 | import sys
 5 | import time
 6 | import urllib
 7 | import re
 8 | 
 9 | # User-defined variables
10 | time_between = 7       #Seconds between iterations (not including time used to fetch pages - setting below 5s may cause a pastebin IP block, too high may miss pastes)
11 | error_on_cl_args = "Please provide a single regex search via the command line"   #Error to display if improper command line arguments are provided
12 | 
13 | # Check for command line argument (a single regex)
14 | if len(sys.argv) != 1:
15 |     search_term = sys.argv[1]
16 | else:
17 |     print error_on_cl_args
18 |     exit()
19 | 
20 | iterater = 1
21 | 
22 | while(1):
23 |     counter = 0
24 | 
25 |     print "Scanning pastebin - iteration " + str(iterater) + "..."
26 |     
27 |     #Open the recently posted pastes page
28 |     try:
29 |         url = urllib.urlopen("http://pastebin.com/archive")
30 |         html = url.read()
31 |         url.close()
32 |         html_lines = html.split('\n')
33 |         for line in html_lines:
34 |             if counter < 10:
35 |                 if re.search(r'<td><img src=\"/i/t.gif\"  class=\"i_p0\" alt=\"\" border=\"0\" /><a href=\"/[0-9a-zA-Z]{8}">.*</a></td>', line):
36 |                     link_id = line[72:80]
37 |                     #print link_id
38 |                     
39 |                     #Begin loading of raw paste text
40 |                     url_2 = urllib.urlopen("http://pastebin.com/raw.php?i=" + link_id)
41 |                     raw_text = url_2.read()
42 |                     url_2.close()
43 |                     
44 |                     #if search_term in raw_text:
45 |                     if re.search(r''+search_term, raw_text):
46 |                         print "FOUND " + search_term + " in http://pastebin.com/raw.php?i=" + link_id
47 |                     
48 |                     counter += 1
49 |     except(IOError):
50 |         print "Network error - are you connected?"
51 |     except:
52 |         print "Fatal error! Exiting."
53 |         exit()
54 |     iterater += 1
55 |     time.sleep(time_between)


--------------------------------------------------------------------------------