├── .gitignore ├── LICENSE ├── README.md ├── adsl_run.py ├── adsl_server ├── __init__.py ├── main.py └── settings.py ├── example ├── __init__.py └── spider.py ├── redis_run.py ├── redis_server ├── __init__.py ├── api.py ├── config.py └── db.py └── requirements.txt /.gitignore: -------------------------------------------------------------------------------- 1 | # Byte-compiled / optimized / DLL files 2 | __pycache__/ 3 | *.py[cod] 4 | *$py.class 5 | 6 | # C extensions 7 | *.so 8 | 9 | # Distribution / packaging 10 | .Python 11 | build/ 12 | develop-eggs/ 13 | dist/ 14 | downloads/ 15 | eggs/ 16 | .eggs/ 17 | lib/ 18 | lib64/ 19 | parts/ 20 | sdist/ 21 | var/ 22 | wheels/ 23 | pip-wheel-metadata/ 24 | share/python-wheels/ 25 | *.egg-info/ 26 | .installed.cfg 27 | *.egg 28 | MANIFEST 29 | 30 | # PyInstaller 31 | # Usually these files are written by a python script from a template 32 | # before PyInstaller builds the exe, so as to inject date/other infos into it. 33 | *.manifest 34 | *.spec 35 | 36 | # Installer logs 37 | pip-log.txt 38 | pip-delete-this-directory.txt 39 | 40 | # Unit test / coverage reports 41 | htmlcov/ 42 | .tox/ 43 | .nox/ 44 | .coverage 45 | .coverage.* 46 | .cache 47 | nosetests.xml 48 | coverage.xml 49 | *.cover 50 | *.py,cover 51 | .hypothesis/ 52 | .pytest_cache/ 53 | 54 | # Translations 55 | *.mo 56 | *.pot 57 | 58 | # Django stuff: 59 | *.log 60 | local_settings.py 61 | db.sqlite3 62 | db.sqlite3-journal 63 | 64 | # Flask stuff: 65 | instance/ 66 | .webassets-cache 67 | 68 | # Scrapy stuff: 69 | .scrapy 70 | 71 | # Sphinx documentation 72 | docs/_build/ 73 | 74 | # PyBuilder 75 | target/ 76 | 77 | # Jupyter Notebook 78 | .ipynb_checkpoints 79 | 80 | # IPython 81 | profile_default/ 82 | ipython_config.py 83 | 84 | # pyenv 85 | .python-version 86 | 87 | # pipenv 88 | # According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control. 89 | # However, in case of collaboration, if having platform-specific dependencies or dependencies 90 | # having no cross-platform support, pipenv may install dependencies that don't work, or not 91 | # install all needed dependencies. 92 | #Pipfile.lock 93 | 94 | # PEP 582; used by e.g. github.com/David-OConnor/pyflow 95 | __pypackages__/ 96 | 97 | # Celery stuff 98 | celerybeat-schedule 99 | celerybeat.pid 100 | 101 | # SageMath parsed files 102 | *.sage.py 103 | 104 | # Environments 105 | .env 106 | .venv 107 | env/ 108 | venv/ 109 | ENV/ 110 | env.bak/ 111 | venv.bak/ 112 | 113 | # Spyder project settings 114 | .spyderproject 115 | .spyproject 116 | 117 | # Rope project settings 118 | .ropeproject 119 | 120 | # mkdocs documentation 121 | /site 122 | 123 | # mypy 124 | .mypy_cache/ 125 | .dmypy.json 126 | dmypy.json 127 | 128 | # Pyre type checker 129 | .pyre/ 130 | -------------------------------------------------------------------------------- /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 [yyyy] [name of copyright owner] 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 | # AdslProxy 2 | 3 | * adsl拨号代理池 4 | * 支持版本: ![](https://img.shields.io/badge/Python-3.x-blue.svg) 5 | 6 | ### 下载安装 7 | 8 | * 下载源码: 9 | 10 | ``` 11 | https://github.com/pythonyhd/AdslProxy 12 | ``` 13 | 14 | * 安装依赖: 15 | 16 | ```shell 17 | pip install -r requirements.txt 18 | ``` 19 | 20 | ### 使用方法 21 | 22 | 1.购买拨号服务器，确保能正常连接网络 23 | 24 | 2.安装squid，配置代理账号密码高匿https，配置教程 25 | 26 | #### 安装 27 | 28 | yum install squid -y 29 | yum install httpd-tools -y 30 | 31 | #### 生成密码文件 32 | 33 | htpasswd -cd /etc/squid/passwords martindu //账号martindu 34 | fy1812!! //提示输入密码 35 | 36 | #### 生成证书 37 | 38 | cd /etc/squid 39 | openssl req -x509 -nodes -days 3650 -newkey rsa:2048 -keyout private.key -out public.crt 40 | 41 | #### 配置squid.conf文件 42 | 43 | acl指令用来定义访问列表，http_access指令用来定义接收还是拒绝来自acl的访问 44 | 45 | vi /etc/squid/squid.conf 46 | 47 | 在最后添加，添加账号密码，添加账号密码必须注释配置文件中的http_access allow all 48 | 49 | auth_param basic program /usr/lib64/squid/basic_ncsa_auth /etc/squid/passwords 50 | auth_param basic realm welecome //设置认证时返回头里夹带的信息 51 | acl authenticated proxy_auth REQUIRED 52 | http_access allow authenticated 53 | 54 | 设置高匿名 55 | 56 | request_header_access Via deny all 57 | request_header_access X-Forwarded-For deny all 58 | request_header_access From deny all 59 | 60 | 注意：监听的端口号必须设为443.否则squid启动不了。 61 | 62 | https_port 443 cert=/etc/squid/public.crt key=/etc/squid/private.key 63 | 64 | #### 日志 65 | 66 | squid的日志位于/var/log/squid/目录下。 67 | 68 | #### 启动 69 | 70 | systemctl enable squid 71 | yum update openssl 72 | systemctl start squid 73 | 74 | squid -k reconfigure //重新加载配置文件 75 | squid -k parse //验证配置 76 | squid -s //启动 77 | 78 | #### 其他 79 | 80 | service squid start 81 | service squid stop 82 | service squid restart 83 | 84 | 3.利用Flask跟nginx搭建redis，确保拨号机跟公司服务器之间可以通信，能够把拨号机IP存储到公司服务器，具体教程不详述 85 | 86 | 4.测试使用 87 | 88 | 89 | 90 | ### 问题反馈 91 | 92 | 　　任何问题欢迎在[Issues](https://github.com/pythonyhd/AdslProxy/issues) 中反馈。 93 | 94 | 　　你的反馈会让此项目变得更加完美。 95 | 96 | --- 97 | 98 | ### TODO 99 | - [x] 兼容py2 100 | 101 | --- 102 | 103 | 104 | ### 赞助作者 105 | 甲鱼说，咖啡是灵魂的饮料，买点咖啡 106 | 107 | [谢谢这些人的☕️](./coffee.md) 108 | 109 | 直接转账打赏作者的辛苦劳动： 110 | 111 | -------------------------------------------------------------------------------- /adsl_run.py: -------------------------------------------------------------------------------- 1 | # -*- coding: utf-8 -*- 2 | from adsl_server.main import SenderAdsl 3 | 4 | 5 | def main(): 6 | SenderAdsl().adsl() 7 | 8 | 9 | if __name__ == '__main__': 10 | main() -------------------------------------------------------------------------------- /adsl_server/__init__.py: -------------------------------------------------------------------------------- 1 | # -*- coding: utf-8 -*- 2 | # @Time : 2019/12/12 11:16 3 | # @Author : King life 4 | # @Email : 18353626676@163.com 5 | # @File : __init__.py.py 6 | # @Software: PyCharm -------------------------------------------------------------------------------- /adsl_server/main.py: -------------------------------------------------------------------------------- 1 | # -*- coding: utf-8 -*- 2 | import re 3 | import platform 4 | import time 5 | 6 | import requests 7 | from requests.exceptions import ConnectionError, ConnectTimeout, ReadTimeout 8 | from fake_useragent import UserAgent 9 | 10 | from adsl_server.settings import ADSL_NETMASK, TEST_URL, TEST_TIMEOUT, VALID_STATUS_CODES, CLIENT_NAME, ADSL_BASH, \ 11 | PROXY_PORT, USER_NAME, PASSWORD, REDIS_URI, ADSL_ERROR_CYCLE, ADSL_CYCLE, ADSL_KEEP_USE 12 | 13 | if platform.python_version().startswith('2.'): 14 | import commands as subprocess 15 | elif platform.python_version().startswith('3.'): 16 | import subprocess 17 | else: 18 | raise ValueError('python version must be 2 or 3') 19 | 20 | 21 | class SenderAdsl(object): 22 | 23 | def get_ip(self, netname=ADSL_NETMASK): 24 | """ 25 | 获取拨号IP 26 | :param netname: 网卡名称 27 | :return: 拨号ip 28 | """ 29 | (status, output) = subprocess.getstatusoutput('ifconfig') 30 | if status == 0: 31 | pattern = re.compile(netname + '.*?inet.*?(\d+\.\d+\.\d+\.\d+).*?netmask', re.S) 32 | result = re.search(pattern, output) 33 | if result: 34 | ip = result.group(1) 35 | return ip 36 | 37 | def test_proxy(self, proxy): 38 | """ 39 | 测试代理 40 | :param proxy: 代理 41 | :return: 测试结果 42 | """ 43 | proxies = { 44 | 'http': 'http://{}:{}@{}:{}'.format(USER_NAME, PASSWORD, proxy, PROXY_PORT), 45 | 'https': 'https://{}:{}@{}:{}'.format(USER_NAME, PASSWORD, proxy, PROXY_PORT), 46 | } 47 | headers = {'User-Agent': UserAgent().random} 48 | try: 49 | response = requests.get(url=TEST_URL, headers=headers, proxies=proxies, timeout=TEST_TIMEOUT) 50 | if response.status_code in VALID_STATUS_CODES: 51 | # print(response.text) 52 | return True 53 | except (ConnectTimeout, ReadTimeout, ConnectionError): 54 | return False 55 | 56 | def remove_proxy(self): 57 | """ 移除代理 """ 58 | url = '{}/remove?name={}'.format(REDIS_URI, CLIENT_NAME) 59 | res = requests.get(url=url) 60 | print(res.text) 61 | 62 | def add_proxy(self, proxy): 63 | """ 添加代理 """ 64 | url = '{}/put?name={}&proxy={}'.format(REDIS_URI, CLIENT_NAME, proxy) 65 | res = requests.get(url=url) 66 | print(res.text) 67 | 68 | def adsl(self): 69 | """ 70 | 拨号主进程 71 | ADSL代码优化，保证拨号前把IP删掉， 72 | 确保入库的IP在拨号前都是可用的。 73 | 执行删除后再次休眠10秒，确保取出来的IP最少能用10秒 74 | """ 75 | while True: 76 | try: 77 | self.remove_proxy() 78 | # 删除之后再次休眠10秒，万一在刚要拨号的时候取到那个IP，那么取出来就拨号了，IP直接不能使用 79 | # 再次休眠确保即使已经删除，取到之后还能用，但是删除后会有一段时间没有IP进来，所以需要开尽可能多的服务器 80 | # 确保池子里面有IP可用 81 | time.sleep(ADSL_KEEP_USE) 82 | except: 83 | while True: 84 | (status, output) = subprocess.getstatusoutput(ADSL_BASH) 85 | if status == 0: 86 | self.remove_proxy() 87 | break 88 | (status, output) = subprocess.getstatusoutput(ADSL_BASH) 89 | if status == 0: 90 | print('ADSL拨号成功') 91 | ip = self.get_ip() 92 | if ip: 93 | if self.test_proxy(ip): 94 | proxies = str(ip) + ":" + PROXY_PORT 95 | self.add_proxy(proxies) 96 | time.sleep(ADSL_CYCLE) 97 | else: 98 | print('代理IP不可用，测试不通过，上次已经拨号成功的IP已经不可用，删除') 99 | self.remove_proxy() 100 | else: 101 | print('没有匹配到IP') 102 | time.sleep(ADSL_ERROR_CYCLE) 103 | else: 104 | print('ADSL拨号失败') 105 | time.sleep(ADSL_ERROR_CYCLE) 106 | self.adsl() 107 | 108 | 109 | if __name__ == '__main__': 110 | conn = SenderAdsl() 111 | conn.adsl() -------------------------------------------------------------------------------- /adsl_server/settings.py: -------------------------------------------------------------------------------- 1 | # -*- coding: utf-8 -*- 2 | """ 3 | IP存活时间保持在10-120秒之间 4 | """ 5 | """"""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""" 6 | 需要修改的配置 7 | """"""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""" 8 | 9 | # 拨号间隔 10 | ADSL_CYCLE = 110 11 | 12 | # 拨号出错重试间隔 13 | ADSL_ERROR_CYCLE = 3 14 | 15 | # 删除之后IP还可以用10秒 16 | ADSL_KEEP_USE = 10 17 | 18 | # 每台拨号机对应一个名字，不同机器需要更改 19 | CLIENT_NAME = 'adsl1' 20 | 21 | # ADSL命令 22 | # ADSL_BASH = 'adsl-stop;adsl-start' 23 | ADSL_BASH = 'pppoe-stop;pppoe-start' 24 | 25 | # 代理配置，根据squid的配置文件填写 26 | USER_NAME = 'martindu' 27 | PASSWORD = 'fy1812!!' 28 | PROXY_PORT = '8881' 29 | 30 | # 代理保存到自己公司redis接口 31 | REDIS_URI = 'http://3.112.239.215' 32 | 33 | """"""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""" 34 | 基本不需要改的配置 35 | """"""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""" 36 | 37 | # 拨号网卡 38 | ADSL_NETMASK = 'ppp0' 39 | 40 | # 拨号成功后的IP检测地址 41 | TEST_URL = 'http://httpbin.org/get' 42 | 43 | # 测试超时时间 44 | TEST_TIMEOUT = 20 45 | 46 | # 遇到以下状态码，测试通过，认定为可用IP 47 | VALID_STATUS_CODES = [200, 201, 202] -------------------------------------------------------------------------------- /example/__init__.py: -------------------------------------------------------------------------------- 1 | # -*- coding: utf-8 -*- 2 | # @Time : 2019/12/13 11:16 3 | # @Author : King life 4 | # @Email : 18353626676@163.com 5 | # @File : __init__.py.py 6 | # @Software: PyCharm -------------------------------------------------------------------------------- /example/spider.py: -------------------------------------------------------------------------------- 1 | # -*- coding: utf-8 -*- 2 | import random 3 | 4 | import redis 5 | import requests 6 | from fake_useragent import UserAgent 7 | 8 | pool = redis.ConnectionPool(host="localhost", port=6379, db=15, password='admin') 9 | redis_client = redis.Redis(connection_pool=pool, decode_responses=True) 10 | REDIS_KEY = "proxies" 11 | headers = {'User-Agent': UserAgent().random} 12 | 13 | 14 | def get_proxy_from_redis(): 15 | proxy_list = redis_client.hvals(REDIS_KEY) 16 | proxy = random.choice(proxy_list).decode('utf-8') 17 | proxies = { 18 | 'http': 'http://martindu:fy1812!!@{}'.format(proxy), 19 | 'https': 'https://martindu:fy1812!!@{}'.format(proxy), 20 | } 21 | 22 | return proxies 23 | 24 | 25 | def crawler(url): 26 | res = requests.get(url=url, headers=headers, proxies=proxies) 27 | print(res.text) 28 | 29 | 30 | if __name__ == '__main__': 31 | proxies = get_proxy_from_redis() 32 | print(proxies) 33 | crawler('https://www.baidu.com/') -------------------------------------------------------------------------------- /redis_run.py: -------------------------------------------------------------------------------- 1 | # -*- coding: utf-8 -*- 2 | from redis_server.api import app 3 | from redis_server.config import API_PORT, API_HOST 4 | 5 | 6 | def main(): 7 | app.run(host=API_HOST, port=API_PORT, debug=True) 8 | 9 | 10 | if __name__ == '__main__': 11 | main() -------------------------------------------------------------------------------- /redis_server/__init__.py: -------------------------------------------------------------------------------- 1 | # -*- coding: utf-8 -*- 2 | # @Time : 2019/12/11 15:49 3 | # @Author : King life 4 | # @Email : 18353626676@163.com 5 | # @File : __init__.py.py 6 | # @Software: PyCharm -------------------------------------------------------------------------------- /redis_server/api.py: -------------------------------------------------------------------------------- 1 | # -*- coding: utf-8 -*- 2 | """ 3 | flask提供代理的增删接口 4 | 需要nginx部署，保证redis能被访问，才能进行对应的增删操作 5 | """ 6 | from flask import Flask, g 7 | from flask import request 8 | 9 | from redis_server.db import RedisClient 10 | 11 | __all__ = ['app'] 12 | app = Flask(__name__) 13 | 14 | 15 | def get_conn(): 16 | if not hasattr(g, 'redis'): # 用于判断对象是否包含对应的属性 17 | g.redis = RedisClient() 18 | return g.redis 19 | 20 | 21 | @app.route('/') 22 | def index(): 23 | return '

欢迎来到华东的代理池系统

' 24 | 25 | 26 | @app.route('/put') 27 | def upload_proxy(): 28 | """ 将proxy上传到redis数据库中 """ 29 | conn = get_conn() 30 | proxy = request.args.get("proxy") 31 | name = request.args.get("name") 32 | # remote_ip = request.remote_addr 33 | # port = proxy.split(":")[1] 34 | proxy = "{}".format(proxy) 35 | if not proxy: 36 | return "上传代理不能为空" 37 | conn.add(name, proxy) 38 | return "已成功上传代理: {}".format(proxy) 39 | 40 | 41 | @app.route('/remove') 42 | def remove_proxy(): 43 | """ 删除redis中的代理 """ 44 | conn = get_conn() 45 | name = request.args.get("name") 46 | if not name: 47 | return "键不能为空" 48 | conn.remove(name) 49 | return "已成功删除代理:{}".format(name) 50 | 51 | 52 | @app.route('/random') 53 | def random_proxy(): 54 | """ 55 | 随机获取可用代理 56 | :return: redis里面的代理IP 57 | """ 58 | connection = get_conn() 59 | return connection.random() 60 | 61 | 62 | if __name__ == '__main__': 63 | app.run() -------------------------------------------------------------------------------- /redis_server/config.py: -------------------------------------------------------------------------------- 1 | # -*- coding: utf-8 -*- 2 | 3 | 4 | # redis连接配置 5 | REDIS_HOST = '127.0.0.1' 6 | REDIS_PORT = 6379 7 | REDIS_DB = 15 8 | REDIS_PASSWORD = '' 9 | 10 | # 代理池hash名 11 | PROXY_KEY = 'proxies' 12 | 13 | # flask服务 14 | API_HOST = '127.0.0.1' 15 | API_PORT = 5000 -------------------------------------------------------------------------------- /redis_server/db.py: -------------------------------------------------------------------------------- 1 | # -*- coding: utf-8 -*- 2 | """ 3 | 存储器，存储拨号成功后的IP，Hash监控每台拨号机器拨号情况 4 | """ 5 | import random 6 | 7 | import redis 8 | 9 | from redis_server.config import REDIS_HOST, REDIS_PORT, REDIS_DB, REDIS_PASSWORD, PROXY_KEY 10 | 11 | 12 | class RedisClient(object): 13 | def __init__(self): 14 | """ 15 | 初始化Redis连接 16 | :param host: Redis 地址 17 | :param port: Redis 端口 18 | :param password: Redis 密码 19 | :param db: Redis 数据库 20 | :param proxy_key: Redis 哈希表名 21 | """ 22 | if REDIS_PASSWORD: 23 | self.db = redis.StrictRedis(host=REDIS_HOST, port=REDIS_PORT, db=REDIS_DB, password=REDIS_PASSWORD, decode_responses=True) 24 | else: 25 | self.db = redis.StrictRedis(host=REDIS_HOST, port=REDIS_PORT, db=REDIS_DB, decode_responses=True) 26 | 27 | self.proxy_key = PROXY_KEY 28 | 29 | def add(self, name, proxy): 30 | """ 31 | 添加代理 32 | :param name:主机名 33 | :param proxy:代理 34 | :return:存储结果 35 | """ 36 | return self.db.hset(self.proxy_key, name, proxy) 37 | 38 | def get(self, name): 39 | """ 40 | 获取代理 41 | :param name: 主机名称 42 | :return: 代理 43 | """ 44 | return self.db.hget(self.proxy_key, name) 45 | 46 | def count(self): 47 | """ 48 | 获取代理总数 49 | :return: 代理总数 50 | """ 51 | return self.db.hlen(self.proxy_key) 52 | 53 | def remove(self, name): 54 | """ 55 | 删除代理 56 | :param name: 主机名称 57 | :return: 删除结果 58 | """ 59 | return self.db.hdel(self.proxy_key, name) 60 | 61 | def names(self): 62 | """ 63 | 获取主机名称列表 64 | :return:主机名称列表 65 | """ 66 | return self.db.hkeys(self.proxy_key) 67 | 68 | def proxies(self): 69 | """ 70 | 获取代理列表 71 | :return: 代理列表 72 | """ 73 | return self.db.hvals(self.proxy_key) 74 | 75 | def random(self): 76 | """ 随机获取代理 """ 77 | proxies = self.proxies() 78 | return random.choice(proxies) 79 | 80 | def all(self): 81 | """ 获取字典 """ 82 | return self.db.hgetall(self.proxy_key) 83 | 84 | 85 | if __name__ == '__main__': 86 | conn = RedisClient() 87 | conn.add('adsl1', '81.163.123.233:8080') 88 | # conn.remove('adsl') -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- 1 | requests==2.22.0 2 | fake-useragent==0.1.11 3 | redis==3.3.6 4 | Flask==1.1.1 --------------------------------------------------------------------------------