├── .gitignore ├── LICENSE ├── README.md ├── asn-country-ipv4.csv ├── deep-web-scanner.py └── requirements.txt /.gitignore: -------------------------------------------------------------------------------- 1 | deep-web.txt 2 | .vscode/launch.json 3 | .DS_Store 4 | -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | Apache License 2 | Version 2.0, January 2004 3 | http://www.apache.org/licenses/ 4 | 5 | TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 6 | 7 | 1. Definitions. 8 | 9 | "License" shall mean the terms and conditions for use, reproduction, 10 | and distribution as defined by Sections 1 through 9 of this document. 11 | 12 | "Licensor" shall mean the copyright owner or entity authorized by 13 | the copyright owner that is granting the License. 14 | 15 | "Legal Entity" shall mean the union of the acting entity and all 16 | other entities that control, are controlled by, or are under common 17 | control with that entity. For the purposes of this definition, 18 | "control" means (i) the power, direct or indirect, to cause the 19 | direction or management of such entity, whether by contract or 20 | otherwise, or (ii) ownership of fifty percent (50%) or more of the 21 | outstanding shares, or (iii) beneficial ownership of such entity. 22 | 23 | "You" (or "Your") shall mean an individual or Legal Entity 24 | exercising permissions granted by this License. 25 | 26 | "Source" form shall mean the preferred form for making modifications, 27 | including but not limited to software source code, documentation 28 | source, and configuration files. 29 | 30 | "Object" form shall mean any form resulting from mechanical 31 | transformation or translation of a Source form, including but 32 | not limited to compiled object code, generated documentation, 33 | and conversions to other media types. 34 | 35 | "Work" shall mean the work of authorship, whether in Source or 36 | Object form, made available under the License, as indicated by a 37 | copyright notice that is included in or attached to the work 38 | (an example is provided in the Appendix below). 39 | 40 | "Derivative Works" shall mean any work, whether in Source or Object 41 | form, that is based on (or derived from) the Work and for which the 42 | editorial revisions, annotations, elaborations, or other modifications 43 | represent, as a whole, an original work of authorship. For the purposes 44 | of this License, Derivative Works shall not include works that remain 45 | separable from, or merely link (or bind by name) to the interfaces of, 46 | the Work and Derivative Works thereof. 47 | 48 | "Contribution" shall mean any work of authorship, including 49 | the original version of the Work and any modifications or additions 50 | to that Work or Derivative Works thereof, that is intentionally 51 | submitted to Licensor for inclusion in the Work by the copyright owner 52 | or by an individual or Legal Entity authorized to submit on behalf of 53 | the copyright owner. For the purposes of this definition, "submitted" 54 | means any form of electronic, verbal, or written communication sent 55 | to the Licensor or its representatives, including but not limited to 56 | communication on electronic mailing lists, source code control systems, 57 | and issue tracking systems that are managed by, or on behalf of, the 58 | Licensor for the purpose of discussing and improving the Work, but 59 | excluding communication that is conspicuously marked or otherwise 60 | designated in writing by the copyright owner as "Not a Contribution." 61 | 62 | "Contributor" shall mean Licensor and any individual or Legal Entity 63 | on behalf of whom a Contribution has been received by Licensor and 64 | subsequently incorporated within the Work. 65 | 66 | 2. Grant of Copyright License. Subject to the terms and conditions of 67 | this License, each Contributor hereby grants to You a perpetual, 68 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 69 | copyright license to reproduce, prepare Derivative Works of, 70 | publicly display, publicly perform, sublicense, and distribute the 71 | Work and such Derivative Works in Source or Object form. 72 | 73 | 3. Grant of Patent License. Subject to the terms and conditions of 74 | this License, each Contributor hereby grants to You a perpetual, 75 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 76 | (except as stated in this section) patent license to make, have made, 77 | use, offer to sell, sell, import, and otherwise transfer the Work, 78 | where such license applies only to those patent claims licensable 79 | by such Contributor that are necessarily infringed by their 80 | Contribution(s) alone or by combination of their Contribution(s) 81 | with the Work to which such Contribution(s) was submitted. If You 82 | institute patent litigation against any entity (including a 83 | cross-claim or counterclaim in a lawsuit) alleging that the Work 84 | or a Contribution incorporated within the Work constitutes direct 85 | or contributory patent infringement, then any patent licenses 86 | granted to You under this License for that Work shall terminate 87 | as of the date such litigation is filed. 88 | 89 | 4. Redistribution. You may reproduce and distribute copies of the 90 | Work or Derivative Works thereof in any medium, with or without 91 | modifications, and in Source or Object form, provided that You 92 | meet the following conditions: 93 | 94 | (a) You must give any other recipients of the Work or 95 | Derivative Works a copy of this License; and 96 | 97 | (b) You must cause any modified files to carry prominent notices 98 | stating that You changed the files; and 99 | 100 | (c) You must retain, in the Source form of any Derivative Works 101 | that You distribute, all copyright, patent, trademark, and 102 | attribution notices from the Source form of the Work, 103 | excluding those notices that do not pertain to any part of 104 | the Derivative Works; and 105 | 106 | (d) If the Work includes a "NOTICE" text file as part of its 107 | distribution, then any Derivative Works that You distribute must 108 | include a readable copy of the attribution notices contained 109 | within such NOTICE file, excluding those notices that do not 110 | pertain to any part of the Derivative Works, in at least one 111 | of the following places: within a NOTICE text file distributed 112 | as part of the Derivative Works; within the Source form or 113 | documentation, if provided along with the Derivative Works; or, 114 | within a display generated by the Derivative Works, if and 115 | wherever such third-party notices normally appear. The contents 116 | of the NOTICE file are for informational purposes only and 117 | do not modify the License. You may add Your own attribution 118 | notices within Derivative Works that You distribute, alongside 119 | or as an addendum to the NOTICE text from the Work, provided 120 | that such additional attribution notices cannot be construed 121 | as modifying the License. 122 | 123 | You may add Your own copyright statement to Your modifications and 124 | may provide additional or different license terms and conditions 125 | for use, reproduction, or distribution of Your modifications, or 126 | for any such Derivative Works as a whole, provided Your use, 127 | reproduction, and distribution of the Work otherwise complies with 128 | the conditions stated in this License. 129 | 130 | 5. Submission of Contributions. Unless You explicitly state otherwise, 131 | any Contribution intentionally submitted for inclusion in the Work 132 | by You to the Licensor shall be under the terms and conditions of 133 | this License, without any additional terms or conditions. 134 | Notwithstanding the above, nothing herein shall supersede or modify 135 | the terms of any separate license agreement you may have executed 136 | with Licensor regarding such Contributions. 137 | 138 | 6. Trademarks. This License does not grant permission to use the trade 139 | names, trademarks, service marks, or product names of the Licensor, 140 | except as required for reasonable and customary use in describing the 141 | origin of the Work and reproducing the content of the NOTICE file. 142 | 143 | 7. Disclaimer of Warranty. Unless required by applicable law or 144 | agreed to in writing, Licensor provides the Work (and each 145 | Contributor provides its Contributions) on an "AS IS" BASIS, 146 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or 147 | implied, including, without limitation, any warranties or conditions 148 | of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A 149 | PARTICULAR PURPOSE. You are solely responsible for determining the 150 | appropriateness of using or redistributing the Work and assume any 151 | risks associated with Your exercise of permissions under this License. 152 | 153 | 8. Limitation of Liability. In no event and under no legal theory, 154 | whether in tort (including negligence), contract, or otherwise, 155 | unless required by applicable law (such as deliberate and grossly 156 | negligent acts) or agreed to in writing, shall any Contributor be 157 | liable to You for damages, including any direct, indirect, special, 158 | incidental, or consequential damages of any character arising as a 159 | result of this License or out of the use or inability to use the 160 | Work (including but not limited to damages for loss of goodwill, 161 | work stoppage, computer failure or malfunction, or any and all 162 | other commercial damages or losses), even if such Contributor 163 | has been advised of the possibility of such damages. 164 | 165 | 9. Accepting Warranty or Additional Liability. While redistributing 166 | the Work or Derivative Works thereof, You may choose to offer, 167 | and charge a fee for, acceptance of support, warranty, indemnity, 168 | or other liability obligations and/or rights consistent with this 169 | License. However, in accepting such obligations, You may act only 170 | on Your own behalf and on Your sole responsibility, not on behalf 171 | of any other Contributor, and only if You agree to indemnify, 172 | defend, and hold each Contributor harmless for any liability 173 | incurred by, or claims asserted against, such Contributor by reason 174 | of your accepting any such warranty or additional liability. 175 | 176 | END OF TERMS AND CONDITIONS 177 | 178 | APPENDIX: How to apply the Apache License to your work. 179 | 180 | To apply the Apache License to your work, attach the following 181 | boilerplate notice, with the fields enclosed by brackets "[]" 182 | replaced with your own identifying information. (Don't include 183 | the brackets!) The text should be enclosed in the appropriate 184 | comment syntax for the file format. We also recommend that a 185 | file or class name and description of purpose be included on the 186 | same "printed page" as the copyright notice for easier 187 | identification within third-party archives. 188 | 189 | Copyright 2022 1337core 190 | 191 | Licensed under the Apache License, Version 2.0 (the "License"); 192 | you may not use this file except in compliance with the License. 193 | You may obtain a copy of the License at 194 | 195 | http://www.apache.org/licenses/LICENSE-2.0 196 | 197 | Unless required by applicable law or agreed to in writing, software 198 | distributed under the License is distributed on an "AS IS" BASIS, 199 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 200 | See the License for the specific language governing permissions and 201 | limitations under the License. 202 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # Deep Web Scanner 2 | Dieses Script findet Websites, die per IPv4-Adresse erreichbar sind und speichert 3 | deren Metadaten. Die Ausgabe im Terminal wird nach bestimmten Keywords gefiltert, 4 | aber in der Logdatei sind alle erreichten Websites drin. 5 | 6 | Was findet man damit? Webcams, Nischen-Websites und interessante Dashboards. 7 | 8 | Die gleichen Ergebnisse können mit der Internetsuchmaschine Shodan oder teilweise 9 | auch mit Google erreicht werden. 10 | 11 | ## Ip-Adressen 12 | Die Eingabedatei ist eine CSV, die IP-Adressen aus Deutschland enthält. 13 | Das IP-Ranges sollten im Format: 1.1.1.1-2.2.2.2 sein. Die IP-Adressen stammen 14 | von diesem Projekt: https://github.com/sapics/ip-location-db 15 | 16 | ## Vorraussetzung 17 | * Python 3.9 18 | 19 | Wenn du auf Python 3.8 bist, kannst du Python 3.9 parallel installieren. Dann 20 | muss die gewünschte Version explizit angegeben werden. `python3` bleibt weiterhin 21 | die Version 3.8: 22 | 23 | ``` bash 24 | sudo apt install python3.9 25 | python3.9 -m pip install -r requirements.txt 26 | python3.9 deep-web-scanner.py 27 | ``` 28 | 29 | ## Installation 30 | Installiere die benötigten Pakete: 31 | ``` bash 32 | pip3 install -r requirements.txt 33 | ``` 34 | 35 | ## Starten 36 | Startet den Scanner mit Standardwerten. Im Terminal und im richtigen Ordner ausführen: 37 | ``` bash 38 | python3 deep-web-scanner.py 39 | ``` 40 | 41 | Optionen: 42 | * -i input.txt: Eingabedatei 43 | * -o output.txt: Ausgabedatei 44 | * -indexof true: Logs index of files (default: False) 45 | 46 | ## "Index of" 47 | Diese Option zeigt verfügbare Dateien an: `-indexof true`: 48 | ``` bash 49 | python3 deep-web-scanner.py -indexof true 50 | ``` 51 | 52 | ## Suche 53 | Über die Textdatei lässt sich schnell mit `grep`suchen. 54 | 55 | ``` bash 56 | grep -i "nginx" deep-web.txt 57 | ``` 58 | -------------------------------------------------------------------------------- /deep-web-scanner.py: -------------------------------------------------------------------------------- 1 | import argparse 2 | import bs4 3 | import os 4 | import colorama 5 | from concurrent.futures import ThreadPoolExecutor 6 | import threading 7 | import ipaddress 8 | import socket 9 | import time 10 | import random 11 | from typing import Optional, Union 12 | import requests 13 | requests.packages.urllib3.disable_warnings() # type: ignore 14 | colorama.init(autoreset=True) 15 | 16 | folder = os.path.dirname(__file__) 17 | output_strings: list[str] = [] 18 | ports = [80, 443, 8080, 8081, 4434, 3443, 8443, 3000, 4000, 5000] 19 | workers = len(ports) * 20 20 | keywords = ["cam", "rasp", " hp ", "system", "index of", "dashboard"] 21 | output_tmp = "" 22 | last_write = time.time() 23 | global_lock = threading.Lock() 24 | banner_targets: list[dict[str, Union[str, int]]] = [] 25 | 26 | 27 | def main(): 28 | print("----------------------------") 29 | print(" Deep Web Scanner! ") 30 | print("----------------------------\n") 31 | print("Every active webserver url will be logged in the output file.") 32 | print("This terminal will only show urls/metadata with the following keywords: " + ", ".join(keywords)) 33 | if indexof.lower() == "true": 34 | print("'Index of /' filenames will be logged!") 35 | print("Scan will start...") 36 | 37 | with open(input_file, "r") as myfile: 38 | content = myfile.readlines() 39 | 40 | # randomize this list if arg is true 41 | if randomize: 42 | random.shuffle(content) 43 | 44 | for line in content: 45 | # split ip range 2.56.20.0-2.56.23.255 46 | if "-" in line: 47 | ip_range_array = line.split("-") 48 | ip_range_start = ip_range_array[0].strip() 49 | ip_range_end = ip_range_array[1].strip() 50 | print( 51 | f"Start scan from range: {ip_range_start} - {ip_range_end}") 52 | 53 | current_ip = ipaddress.IPv4Address(ip_range_start) 54 | end_ip = ipaddress.IPv4Address(ip_range_end) 55 | 56 | with ThreadPoolExecutor(max_workers=workers) as executor_portcheck: 57 | while current_ip < end_ip: 58 | executor_portcheck.submit( 59 | start_portcheck, current_ip.exploded) 60 | current_ip += 1 61 | 62 | elif "/" in line: 63 | ip_range = ipaddress.ip_network(line.strip()) 64 | with ThreadPoolExecutor(max_workers=workers) as executor_portcheck: 65 | for ip in ip_range.hosts(): 66 | executor_portcheck.submit(start_portcheck, ip.exploded) 67 | else: 68 | print( 69 | "No valid input file! Should be something like 2.56.20.0-2.56.23.255 per line!") 70 | 71 | global banner_targets 72 | print(f"{len(banner_targets)} responses") 73 | with ThreadPoolExecutor(max_workers=10) as executor_getbanner: 74 | for target in banner_targets: 75 | executor_getbanner.submit( 76 | start_request, target["ip"], target["port"]) # type: ignore 77 | banner_targets.clear() 78 | write_line("", True) 79 | 80 | 81 | def start_portcheck(ip: str) -> None: 82 | global banner_targets 83 | # fast webserver port checking 84 | for port in ports: 85 | with socket.socket(socket.AF_INET, socket.SOCK_STREAM) as sock: 86 | sock.settimeout(2) 87 | result = sock.connect_ex((ip, port)) 88 | if result == 0: 89 | # queue normal browser request 90 | banner_targets.append({"ip": ip, "port": port}) 91 | 92 | 93 | def start_request(ip: str, port: int) -> None: 94 | # check for running websites 95 | try: 96 | url = "https://" + ip + ":" + str(port) 97 | if str(port).__contains__("80"): 98 | url = "http://" + ip + ":" + str(port) 99 | 100 | site_result = request_url(url) 101 | if not isinstance(site_result, bool) and site_result is not False: 102 | # if the site is reachable get some information 103 | get_banner(site_result[0], site_result[1]) 104 | except Exception as e: 105 | print(f"IP: {ip}, Port: {str(port)}") 106 | print(e) 107 | 108 | 109 | def request_url(url: str) -> Union[tuple[requests.Response, bs4.BeautifulSoup], bool]: 110 | # request url and return the response 111 | session = requests.session() 112 | session.headers[ 113 | "User-Agent" 114 | ] = "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/42.0.2311.152 Safari/537.36" 115 | header = session.head(url=url, timeout=5, verify=False) 116 | 117 | # check content type 118 | one_allowed_content_type = False 119 | content_type_header = header.headers.get("content-type") 120 | if content_type_header is not None: 121 | for allowed_content_type in ["html", "plain", "text", "json"]: 122 | if allowed_content_type in content_type_header.lower(): 123 | one_allowed_content_type = True 124 | if not one_allowed_content_type: 125 | return False 126 | else: 127 | return False 128 | 129 | response = session.get(url=url, timeout=10, verify=False) 130 | session.close() 131 | try: 132 | soup = bs4.BeautifulSoup(response.text, "html.parser") 133 | return (response, soup) 134 | except Exception: 135 | soup = bs4.BeautifulSoup("", "html.parser") 136 | return (response, soup) 137 | 138 | 139 | def get_banner(request: requests.Response, soup: bs4.BeautifulSoup): 140 | # get banner information, show console output and save them to file 141 | banner_array: list[str] = [] 142 | banner_array.append(request.url) 143 | 144 | if soup: 145 | server_header = request.headers.get("Server") 146 | if isinstance(server_header, str): 147 | banner_array.append(server_header) 148 | title = soup.find("title") 149 | if isinstance(title, bs4.Tag): 150 | title = title.get_text().strip().replace("\n", "") 151 | banner_array.append(title) 152 | 153 | meta_tags: bs4.element.ResultSet[bs4.Tag] = soup.find_all( 154 | "meta", attrs={"name": "generator"}) 155 | if len(meta_tags) > 0: 156 | for meta_tag in meta_tags: 157 | attrs = meta_tag.attr 158 | if isinstance(attrs, bs4.Tag): 159 | generator = attrs.get("content") 160 | if isinstance(generator, str): 161 | banner_array.append(generator) 162 | 163 | # has this site a password field? 164 | password_fields = soup.find_all(attrs={"type": "password"}) 165 | if len(password_fields) > 0: 166 | banner_array.append("login required") 167 | 168 | # check for "index of" websites and show root files/folders 169 | global indexof 170 | if indexof.lower() == "true" and "index of" in request.text.lower(): 171 | a_array: list[bs4.Tag] = soup.find_all("a") 172 | for a in a_array: 173 | href = a.attrs.get("href") 174 | if isinstance(href, str): 175 | if href.find("?") != 0: 176 | banner_array.append(href) 177 | 178 | banner_array.append(f"{str(len(request.content))} content size") 179 | 180 | fullstring = ", ".join(banner_array) 181 | if fullstring not in output_strings: 182 | output_strings.append(fullstring) 183 | for keyword in keywords: 184 | if keyword in fullstring.lower(): 185 | if "login required" in fullstring: 186 | print(colorama.Fore.RED + fullstring) 187 | elif "Index of /" in fullstring: 188 | print(colorama.Fore.YELLOW + fullstring) 189 | else: 190 | print(colorama.Fore.GREEN + fullstring) 191 | write_line(fullstring) 192 | 193 | 194 | def write_line(line: str, force: Optional[bool] = False): 195 | # buffers and writes output to file 196 | global output_tmp, last_write 197 | output_tmp += line + "\n" 198 | 199 | if last_write + 30 < time.time() or force: 200 | last_write = time.time() 201 | 202 | while global_lock.locked(): 203 | continue 204 | 205 | global_lock.acquire() 206 | 207 | lines_to_write = output_tmp.count("\n") 208 | with open(output_file, "a") as output_1: 209 | output_1.write(output_tmp) 210 | output_tmp = "" 211 | 212 | if lines_to_write > 1: 213 | print(f"{lines_to_write} webservers found and written to file") 214 | else: 215 | print(f"{lines_to_write} webserver found and written to file") 216 | 217 | global_lock.release() 218 | 219 | 220 | if __name__ == "__main__": 221 | parser = argparse.ArgumentParser( 222 | description="Check if domain has an active website and grab banner." 223 | ) 224 | parser.add_argument( 225 | "-i", type=str, default="./asn-country-ipv4.csv", help="Path to input file" 226 | ) 227 | parser.add_argument( 228 | "-o", type=str, default="./deep-web.txt", help="Path to output file" 229 | ) 230 | parser.add_argument( 231 | "-indexof", type=str, default="true", help="Show files from index of sites" 232 | ) 233 | parser.add_argument( 234 | "-randomize", type=str, default="true", help="Randomize input list entries" 235 | ) 236 | args = parser.parse_args() 237 | input_file = args.i 238 | output_file = args.o 239 | indexof = args.indexof 240 | randomize = args.randomize 241 | main() 242 | -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- 1 | colorama==0.4.4 2 | requests==2.27.1 3 | beautifulsoup4==4.11.1 --------------------------------------------------------------------------------