Monitoring and downloading of github-exploitdb vulnerability Library Based on python crawler

Keywords: Python github Selenium

Offensive.py (crawling project history updates)

#!/usr/bin/env python

# -*- coding:utf-8 -*-

import re

import time

import urllib.request

import conf as cf

BASE_URL = 'https://github.com/offensive-security/exploitdb/releases'

DOWNLOAD_LINK_PATTERN = 'href="(.*?)zip" rel="nofollow">'

FIRST_PATTERN = r'</span><a rel="nofollow" href="(.*?)">Next.*'

PAGE_PATTERN = r'>Previous</a><a rel="nofollow" href="(.*?)">Next.*'

class MyCrawler:

    def __init__(self, base_url=BASE_URL, start_page="first 1 page"):

        self.base_url = base_url

        self.start_page = start_page

        # self.headers = apache_request_headers();

# Crawling Home Page

    def first_page(self):

        try:

            req = urllib.request.Request(self.base_url)

            html = urllib.request.urlopen(req)

            doc = html.read().decode('utf8', 'ignore')

            next_page = re.search(FIRST_PATTERN, doc, re.M | re.I)

            print('Now working on page = {}\n'.format(self.start_page))

            time.sleep(5)

            self.fetch_download_link(self.base_url)

            self.start_page = next_page.group(1)

            # re.search(r'after = (.*?) ">Next.*', next_page.group(1), re.M | re.I).group(1)

            self.base_url = next_page.group(1)

            # self.fetch_download_link(next_url)

        except urllib.error.HTTPError as err:

            print(err.msg)

        self.fetch_next_page()

# Page turning

    def fetch_next_page(self):

        while True:

            try:

                req = urllib.request.Request(self.base_url)

                html = urllib.request.urlopen(req)

                doc = html.read().decode('utf8', 'ignore')

                next_page = re.search(PAGE_PATTERN, doc, re.M | re.I)

                print('Now working on page {}\n'.format(self.start_page))

                time.sleep(5)

                #Wait 5 seconds while turning pages

                self.fetch_download_link(self.base_url)

                self.start_page = next_page.group(1)

                # re.search(r'after = (.*?) ">Next.*', next_page.group(1), re.M | re.I).group(1)

                self.base_url = next_page.group(1)

                # self.fetch_download_link(next_url)

            except urllib.error.HTTPError as err:

                print(err.msg)

                break

# File Download: Save Download Links to Files

    def fetch_download_link(self, Aurl):

        f = open('result.txt', 'a')

        req = urllib.request.Request(Aurl)

        html = urllib.request.urlopen(req)

        doc = html.read().decode('utf8')

        alist = list(set(re.findall(DOWNLOAD_LINK_PATTERN, doc)))

        for item in alist:

            url = "https://github.com/" + item + "zip"

            print('Storing {}'.format(url))

            f.write(url + '\n')

            time.sleep(7)

        f.close()

    def run(self):

        self.fetch_download_link()

if __name__ == '__main__':

    mc = MyCrawler()

    mc.first_page()

Tex.py (Monitor Home Page Updates and Crawl)

#!/usr/bin/env python

# -*- coding:utf-8 -*

from selenium import webdriver

import re

import time

import urllib.request

import conf as cf

BASE_URL = 'https://github.com/offensive-security/exploitdb/releases'

DOWNLOAD_LINK_PATTERN = 'href="(.*?)zip" rel="nofollow">'

FIRST_PATTERN = r'</span><a rel="nofollow" href="(.*?)">Next.*'

# Monitoring Project Home Page Update

def jiankong_page():

    print("star monitoring ")

    req = urllib.request.Request(BASE_URL)

    html = urllib.request.urlopen(req)

    doc = html.read().decode('utf8', 'ignore')

    next_page = re.search(FIRST_PATTERN, doc, re.M | re.I)

    flag_page = next_page.group(1)

    flag_list = []

# Crawl the url of the homepage item for the first time

    alist = list(set(re.findall(DOWNLOAD_LINK_PATTERN, doc)))

    for item in alist:

        url = "https://github.com/" + item + "zip"

        flag_list.append(url)

# Timing Scanning Monitoring (5h/time)

    while True:

        try:

            time.sleep(5 * 60* 60)

            req = urllib.request.Request(BASE_URL)

            html = urllib.request.urlopen(req)

            doc = html.read().decode('utf8', 'ignore')

            next_page = re.search(FIRST_PATTERN, doc, re.M | re.I)

# Determine whether pageflip links have changed to determine whether they have been updated

            if next_page.group(1) != flag_page:

                print("have update")

                item = re.rearch(DOWNLOAD_LINK_PATTERN, doc, re.M | re.I)

                #Grab the first matching newly updated project url

                new_url = "https://github.com/" + item.group(1) + "zip"

                print("new url = " + new_url)

                flag_list.append(new_url)

                f = open('result.txt', 'a')

                f.write(new_url + '\n')

                f.close()

                flag_page = next_page.group(1)

            else:

                print("No update")

        except urllib.error.HTTPError as err:

            print(err.msg)

            break

if __name__ == '__main__':

    jiankong_page()

Introduce myself. I'm Fisher, the author of Internet Security. I share interesting security technologies and stories everyday. Of course, I also record the gains of learning. Interested in the security field, you can pay close attention to my personal public address: austfish. If you don't want to lose it, please pay attention to Fisher's Safety Diary! (Don't forget to add stars) or personal blog: www.austfish.cn

 

Posted by doctor_james on Mon, 30 Sep 2019 02:14:10 -0700