python/url1.py at main · dlotankar/python · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
import bs4
from selenium import webdriver
import getopt
import sys
import time
import os
from selenium.webdriver.common.desired_capabilities import DesiredCapabilities
from selenium.webdriver.chrome.options import Options


def printLogo():
    print("""
  ________        __  .__
 /  _____/_____ _/  |_|  |__   ___________
/   \  ___\__  \\\    _\  |  \_/ __ \_  __ \\
\    \_\  \/ __ \|  | |   |  \  ___/|  | \/
 \______  (____  /__| |___|  /\___  >__|
        \/     \/          \/     \/
        by Ben Heald
        https://healdb.tech
        https://github.com/Healdb/Gather
        https://twitter.com/heald_ben
        """)
    print("URL Screenshot Utility\n")


def checkURL(potentialUrl, driver, disallowed):
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/81.0.4044.122 Safari/537.36',
    }
    driver.get(potentialUrl)
    html = driver.page_source
    soup = bs4.BeautifulSoup(html, features="lxml")
    # Catch chrome error pages
    chromeErrorDivs = soup.findAll("div", {"class": "error-code"})
    if (any(ele in html for ele in disallowed) or len(chromeErrorDivs) > 0):
        return False
    return len(html) > 10


def assembleHTML(name, outputDir):
    urls = open(outputDir + "/" + name + "/" + name + ".txt", "r").readlines()
    outHTML = open(outputDir + "/" + name + "/" + name + ".html", "w")
    outHTML.write("<html><center>")
    outText = ""
    i = 0
    for url in urls:
        outText = outText + "<h3><a href='" + url + "' target='_blank'>" + url + "</a></h3><img src='" + outputDir + "/" + name + "/screenshots/" + str(
            i) + "_screenshot.png'><br>\n"
        i += 1
    outHTML.write(outText)
    outHTML.write("</center></html>")
    outHTML.close()


def gatherScreenshots(driver, urlFile, name, disallowed, ports, outputDir):
    i = 0
    total = len(urlFile)
    try:
        os.mkdir(outputDir + "/" + name)
    except FileExistsError:
        pass
    try:
        os.mkdir(outputDir + "/" + name + "/screenshots/")
    except FileExistsError:
        pass
    outputFile = open(outputDir + "/" + name + "/" + name + ".txt", "w")
    for url in urlFile:
        url = url.strip()
        try:
            for port in ports:
                if port == "80":
                    if checkURL("http://" + url.strip(), driver, disallowed):
                        print("http://" + url)
                        driver.save_screenshot(outputDir + "/" + name + "/screenshots/" + str(i) + "_screenshot.png")
                        outputFile.write('http://' + url.strip() + "\n")
                        i += 1
                elif port == "443":
                    if checkURL("https://" + url.strip(), driver, disallowed):
                        print("https://" + url)
                        driver.save_screenshot(outputDir + "/" + name + "/screenshots/" + str(i) + "_screenshot.png")
                        outputFile.write('https://' + url.strip() + "\n")
                        i += 1
                else:
                    if checkURL("http://" + url.strip() + ":" + port, driver, disallowed):
                        print("http://" + url + ":" + port)
                        driver.save_screenshot(outputDir + "/" + name + "/screenshots/" + str(i) + "_screenshot.png")
                        outputFile.write('https://' + url.strip() + ":" + port + "\n")
                        i += 1
        except Exception as e:
            print(e)
            pass
    outputFile.close()
    driver.close()


def gather(argv):
    desired_capabilities = DesiredCapabilities.CHROME.copy()
    desired_capabilities['acceptInsecureCerts'] = True
    fileName = ""
    outDirName = ""
    chromeDriver = ""
    verbose = False
    disallowed = []
    ports = ["80", "443"]
    outputDir = os.getcwd()

    try:
        (opts, args) = getopt.getopt(argv, 'h:f:c:d:p:o:')
    except getopt.GetoptError:
        print(
            'gather.py -f <url_file> -c <Chrome Driver Path> -d <Disallowed Words> -p <Ports to scan> -o <Output directory path>')
        sys.exit(2)
    for (opt, arg) in opts:
        if opt == '-h':
            print(
                'gather.py -f <url_file> -c <Chrome Driver Path> -d <Disallowed Words> -p <Ports to scan> -o <Output directory path>')
            sys.exit()
        elif opt in '-f':
            fileName = arg
            outDirName = (os.path.split(fileName)[1]).split(".")[0]
        elif opt in '-c':
            chromeDriver = arg
        elif opt in '-d':
            if arg != "":
                for word in arg.split(","):
                    disallowed.append(word)
        elif opt in '-p':
            if arg == "":
                arg = "80,443"
            for port in arg.split(","):
                ports = []
                ports.append(port)
        elif opt in '-v':
            verbose = True
        elif opt in '-o':
            outputDir = arg
    try:
        urlFile = open(fileName, "r").readlines()
    except:
        raise Exception("No file provided in the -f flag")
    options = Options()
    # options.headless = True
    driver = webdriver.Chrome(executable_path=chromeDriver, options=options, desired_capabilities=desired_capabilities,
                              service_args=["--headless", "--allow-running-insecure-content", "--test-type",
                                            "--ignore-certificate-errors", "--ignore-ssl-errors=true",
                                            "--ssl-protocol=any"])
    driver.set_page_load_timeout(8)

    gatherScreenshots(driver, urlFile, outDirName, disallowed, ports, outputDir)
    assembleHTML(outDirName, outputDir)


if __name__ == '__main__':
    printLogo()
    gather(sys.argv[1:])