NLP_MalwareFamilyAnalysis

NLP Project for spring 2018

1. Scrapper:

   • Requires:
     • Python 3.5
     • Selenium
     • Beautiful-Soup 4
   • Usage:
     python3 main.py <malware_name>
     Generates a csv file with Titles and Blog posts from Symantec website

2. Malware Information extractor:

   • Requires:
     • Java 1.8
     • practNLPTools
       Get the directory practnlpools from GitHub and put it inside this projects python directory.
   • Usage:
     1. Compile the java code:
        javac -cp required_jars\* src\cse576\ExtractDateCVEfromReport.java -d .\
     2. Run the code:
        java -cp ".;.\required_jars\*" cse576.ExtractDateCVEfromReport <malware_name>
     3. Read the output file: program_output.output

Batch file

The Scrapper (part 1) and the Information Extractor (part 2) are combined in the batch file.
So, running the batch file alone will excute the above 2 parts

MalwareFamilyAnalysis.bat <malware_name>

Sample Result