-
Notifications
You must be signed in to change notification settings - Fork 125
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
Showing
21 changed files
with
332 additions
and
508 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -1,125 +1,82 @@ | ||
| #!/usr/bin/env python2 | ||
| # Copyright (c) 2016 Jonathan Broche (@g0jhonny) | ||
| # Copyright (c) 2018 Jonathan Broche (@LeapSecurity) | ||
|
|
||
| from lib.logger import * | ||
| from lib.soupify import * | ||
| import argparse, sys, os | ||
| from lib.http import * | ||
| from lib.workbench import * | ||
| from lib.crawler import * | ||
| import os, argparse, sys, time | ||
| from lib.soup import * | ||
| from lib.export import * | ||
| from lib.logger import * | ||
|
|
||
| parser = argparse.ArgumentParser(description='InSpy - A LinkedIn enumeration tool by Jonathan Broche (@g0jhonny)', version="2.0.2") | ||
| parser.add_argument('company', help="Company name to use for tasks.") | ||
| techgroup = parser.add_argument_group(title="Technology Search") | ||
| techgroup.add_argument('--techspy', metavar='file', const="wordlists/tech-list-small.txt", nargs='?', help="Crawl LinkedIn job listings for technologies used by the company. Technologies imported from a new line delimited file. [Default: tech-list-small.txt]") | ||
| techgroup.add_argument('--limit', metavar='int', type=int, default=50, help="Limit the number of job listings to crawl. [Default: 50]") | ||
| empgroup = parser.add_argument_group(title="Employee Harvesting") | ||
| empgroup.add_argument('--empspy', metavar='file', const="wordlists/title-list-small.txt", nargs='?', help="Discover employees by title and/or department. Titles and departments are imported from a new line delimited file. [Default: title-list-small.txt]") | ||
| empgroup.add_argument('--emailformat', metavar='string', help="Create email addresses for discovered employees using a known format. [Accepted Formats: first.last@xyz.com, last.first@xyz.com, firstl@xyz.com, lfirst@xyz.com, flast@xyz.com, lastf@xyz.com, first@xyz.com, last@xyz.com]") | ||
|
|
||
| parser = argparse.ArgumentParser(description='InSpy - A LinkedIn enumeration tool by Jonathan Broche (@LeapSecurity)', version="3.0.0") | ||
| parser.add_argument('company', help="Company name to use for tasks.") | ||
| parser.add_argument('--domain', help="Company domain to use for searching.") | ||
| parser.add_argument('--email', help="Email format to create email addresses with. [Accepted Formats: first.last@xyz.com, last.first@xyz.com, firstl@xyz.com, lfirst@xyz.com, flast@xyz.com, lastf@xyz.com, first@xyz.com, last@xyz.com]") | ||
| parser.add_argument('--titles', metavar='file', default="wordlists/title-list-small.txt", nargs='?', help="Discover employees by title and/or department. Titles and departments are imported from a new line delimited file. [Default: title-list-small.txt]") | ||
| outgroup = parser.add_argument_group(title="Output Options") | ||
| outgroup.add_argument('--html', metavar='file', help="Print results in HTML file.") | ||
| outgroup.add_argument('--csv', metavar='file', help="Print results in CSV format.") | ||
| outgroup.add_argument('--json', metavar='file', help="Print results in JSON.") | ||
| outgroup.add_argument('--xml', metavar='file', help="Print results in XML.") | ||
|
|
||
| if len(sys.argv) == 1: | ||
| parser.print_help() | ||
| sys.exit(1) | ||
|
|
||
| args = parser.parse_args() | ||
| start_logger(args.company) | ||
| hunterapi = "" #insert hunterio api key here | ||
|
|
||
| print "\nInSpy {}\n".format(parser.version) | ||
|
|
||
| if not args.techspy and not args.empspy: | ||
| print "You didn't provide any work for me to do." | ||
| sys.exit(1) | ||
|
|
||
| stime = time.time() | ||
| tech_html, employee_html, tech_csv, employee_csv, tech_json, employee_json = [], [], [], [], [], [] | ||
|
|
||
| if args.techspy: | ||
| if os.path.exists(os.path.abspath(args.techspy)): | ||
| initial_crawl = crawl_jobs(args.company) | ||
| if initial_crawl: | ||
| soup = soupify(initial_crawl) | ||
| job_links = [] | ||
| for link in get_job_links(soup, args.company): | ||
| if len(job_links) < args.limit: | ||
| job_links.append(link) | ||
| if len(job_links) != args.limit: | ||
| page_links = get_page_links(soup) | ||
| for page in range(len(page_links)): | ||
| if len(job_links) == args.limit: break | ||
| urlcrawl = crawl_url(page_links[page]) | ||
| if urlcrawl: | ||
| for link in get_job_links(soupify(urlcrawl), args.company): | ||
| if len(job_links) < args.limit: | ||
| job_links.append(link) | ||
| print "\nInSpy {}".format(parser.version) | ||
|
|
||
| pstatus("{} Jobs identified".format(len(job_links))) | ||
| if job_links: | ||
| techs = {} | ||
| for job in range(len(job_links)): | ||
| jobresponse = crawl_url(job_links[job]) | ||
| if jobresponse: | ||
| jobsoup = soupify(jobresponse) | ||
| description = get_job_description(jobsoup) | ||
| matches = identify_tech(description, os.path.abspath(args.techspy)) | ||
| if matches: | ||
| title = get_job_title(jobsoup) | ||
| techs[title] = {job_links[job]:matches} | ||
| if args.domain and not args.email: #search hunterio for email format | ||
| domain = args.domain | ||
| email = get_email_format(args.domain, hunterapi).replace("{", "").replace("}","") | ||
| elif args.email and not args.domain: #search clearbit for domain | ||
| email = args.email | ||
| domain = get_domain(args.company) | ||
| else: #no domain or email provided - fully automate it | ||
| domain = get_domain(args.company) | ||
| if domain: | ||
| email = get_email_format(domain, hunterapi) | ||
| if email: email = email.replace("{", "").replace("}","") | ||
|
|
||
| tech_html, tech_csv, tech_json = craft_tech(techs) | ||
| else: | ||
| perror("No such file or directory: '{}'".format(args.techspy)) | ||
| if domain and email: | ||
| print "\nDomain: {}, Email Format: {}\n".format(domain, email) | ||
| employees = {} | ||
|
|
||
| if args.empspy: | ||
| if os.path.exists(os.path.abspath(args.empspy)): | ||
| employees = {} | ||
| emails = [] | ||
| for response in crawl_employees(args.company, os.path.abspath(args.empspy)): | ||
| for name, title in get_employees(soupify(response)).items(): | ||
| if args.company.lower() in title.lower(): | ||
| if not name in employees: | ||
| employees[name] = title | ||
| if os.path.exists(os.path.abspath(args.titles)): | ||
| for response in search_linkedin(args.company, os.path.abspath(args.titles)): | ||
| for name, title in get_employees(soupify(response)).items(): | ||
| if args.company.lower() in title.lower(): | ||
| if not name in employees: | ||
| employees[name] = title | ||
| print "\n{} Employees identified".format(len(employees.keys())) | ||
| else: | ||
| print os.path.abspath(args.titles) | ||
| print "No such file or directory: '{}'".format(args.titles) | ||
|
|
||
| pstatus("{} Employees identified".format(len(employees.keys()))) | ||
| if employees: | ||
| if args.emailformat: | ||
| if args.emailformat[:args.emailformat.find('@')] in ['first.last', 'last.first', 'firstlast', 'lastfirst', 'first_last', 'last_first', 'first', 'last', 'firstl', 'lfirst', 'flast', 'lastf']: | ||
| employee_html, employee_csv, employee_json = craft_employees(employees, args.emailformat) | ||
| else: | ||
| pwarning("You didn't provide a valid e-mail format. See help (-h) for acceptable formats.") | ||
| employee_html, employee_csv, employee_json = craft_employees(employees, None) | ||
| else: | ||
| employee_html, employee_csv, employee_json = craft_employees(employees, None) | ||
| else: | ||
| print os.path.abspath(args.empspy) | ||
| perror("No such file or directory: '{}'".format(args.empspy)) | ||
| if employees: | ||
| #output employees | ||
| for name, title in employees.iteritems(): | ||
| print "{} {}".format(name, title[:50].replace('&', '&')) | ||
|
|
||
| #craft emails | ||
| emails = create_emails(employees, domain, email) | ||
|
|
||
| #output | ||
| if args.html: | ||
| if tech_html or employee_html: | ||
| if tech_html and employee_html: | ||
| craft_html(args.company, tech_html, employee_html, args.html) | ||
| elif tech_html and not employee_html: | ||
| craft_html(args.company, tech_html, None, args.html) | ||
| else: | ||
| craft_html(args.company, None, employee_html, args.html) | ||
| if args.csv: | ||
| if tech_csv or employee_csv: | ||
| if tech_csv and employee_csv: | ||
| craft_csv(tech_csv, employee_csv, args.csv) | ||
| elif tech_csv and not employee_csv: | ||
| craft_csv(tech_csv, None, args.csv) | ||
| else: | ||
| craft_csv(None, employee_csv, args.csv) | ||
| if args.json: | ||
| if tech_json or employee_json: | ||
| if tech_json and employee_json: | ||
| craft_json(tech_json, employee_json, args.json) | ||
| elif tech_json and not employee_json: | ||
| craft_json(tech_json, None, args.json) | ||
| else: | ||
| craft_json(None, employee_json, args.json) | ||
| if emails: | ||
| #output emails | ||
| print "\nEmails crafted\n".format(len(emails.keys())) | ||
| for name, email in emails.items(): | ||
| print email | ||
|
|
||
| print "Completed in {:.1f}s".format(time.time()-stime) | ||
| #export results | ||
| if args.html: | ||
| output("html", args.html, args.company, domain, employees, emails) | ||
| if args.xml: | ||
| output("xml", args.xml, args.company, domain, employees, emails) | ||
| if args.json: | ||
| output("json", args.json, args.company, domain, employees, emails) | ||
| if args.csv: | ||
| output("csv", args.csv, args.company, domain, employees, emails) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Binary file not shown.
This file was deleted.
Oops, something went wrong.
Binary file not shown.
Oops, something went wrong.