├── api ├── __init__.py └── web.py ├── backend ├── __init__.py ├── const.py ├── util.py ├── spider.py ├── conn.py └── task.py ├── requirements.txt ├── README.md ├── launcher.py ├── .gitignore └── LICENSE /api/__init__.py: -------------------------------------------------------------------------------- 1 | # coding: utf8 2 | 3 | """ 4 | http api 5 | """ 6 | -------------------------------------------------------------------------------- /backend/__init__.py: -------------------------------------------------------------------------------- 1 | # coding: utf8 2 | 3 | """ 4 | Web spiders, for crawling free ip proxies. 5 | """ 6 | -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- 1 | beautifulsoup4==4.6.0 2 | certifi==2017.11.5 3 | chardet==3.0.4 4 | click==6.7 5 | Flask==0.12.3 6 | gevent==1.2.2 7 | greenlet==0.4.12 8 | idna==2.6 9 | itsdangerous==0.24 10 | Jinja2==2.10.1 11 | MarkupSafe==1.0 12 | redis==2.10.6 13 | requests==2.20.0 14 | urllib3==1.24.2 15 | Werkzeug==0.13 16 | -------------------------------------------------------------------------------- /backend/const.py: -------------------------------------------------------------------------------- 1 | # coding: utf8 2 | 3 | """ 4 | System constants. 5 | """ 6 | 7 | USER_AGENT = 'Mozilla/5.0(iPad; U; CPU iPhone OS 3_2 like Mac OS X; en-us) AppleWebKit/531.21.10 (KHTML, like Gecko) ' \ 8 | 'Version/4.0.4 Mobile/7B314 Safari/531.21.10' 9 | REFER_URL = 'http://www.xicidaili.com' 10 | 11 | VERIFY_URL = 'https://httpbin.org' 12 | 13 | REDIS_KEY = 'proxies' 14 | 15 | PROXY_CRITICAL_NUM = 100 16 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # x-proxies™ 2 | 3 | There exists many cases for crawling some websites, but there are not enough ip proxies to use, so i maintain the repo to keep track of a fresh and usable proxies list. 4 | 5 | ## Technology 6 | 7 | Going to keep it pretty basic, and use this as an excuse to get familiar with Flask. 8 | 9 | - Flask 10 | - Redis 11 | - Gevent 12 | - Supervisor 13 | 14 | That's basically it! 15 | 16 | **Please note:** *this is a work in progress*. 17 | 18 | -------------------------------------------------------------------------------- /backend/util.py: -------------------------------------------------------------------------------- 1 | # coding: utf8 2 | 3 | """ 4 | Common tool functions. 5 | """ 6 | 7 | import requests 8 | 9 | 10 | def request_html(url, method='GET', headers=None, proxies=None): 11 | """ 12 | :param url: 13 | :param method: 14 | :param headers: 15 | :param proxies: 16 | :return: 17 | """ 18 | resp = None 19 | try: 20 | r = requests.request(method, url, headers=headers, proxies=proxies) 21 | if r.status_code == 200: 22 | resp = r.text 23 | except requests.RequestException as e: 24 | print(e) 25 | 26 | return resp 27 | -------------------------------------------------------------------------------- /api/web.py: -------------------------------------------------------------------------------- 1 | # coding: utf8 2 | 3 | """ 4 | Support get, refresh requests. 5 | """ 6 | 7 | from flask import ( 8 | Flask, jsonify, make_response 9 | ) 10 | 11 | from backend import ( 12 | conn, const 13 | ) 14 | 15 | app = Flask(__name__) 16 | 17 | 18 | @app.route('/proxies') 19 | def get_proxies(): 20 | """ 21 | :return: 22 | """ 23 | proxies = conn.RedisConnection().smembers(const.REDIS_KEY) 24 | return jsonify({'proxies': list(proxies)}) 25 | 26 | 27 | @app.errorhandler(404) 28 | def not_found(error): 29 | """ 30 | :return: 31 | """ 32 | return make_response(jsonify({'error': 'Not found'}), 404) 33 | -------------------------------------------------------------------------------- /launcher.py: -------------------------------------------------------------------------------- 1 | # coding: utf8 2 | 3 | """ 4 | launcher.py: start web crawler service, flask api service. 5 | """ 6 | import os 7 | 8 | import gevent 9 | from gevent import ( 10 | monkey, pywsgi 11 | ) 12 | 13 | from api import web 14 | from backend import task 15 | 16 | # checkout to project directory 17 | project = os.path.split(os.path.realpath(__file__))[0] 18 | os.chdir(project) 19 | 20 | monkey.patch_all() 21 | 22 | 23 | def master(): 24 | """ 25 | :return: 26 | """ 27 | while True: 28 | gevent.sleep(600) 29 | 30 | 31 | def loop(): 32 | """ 33 | :return: 34 | """ 35 | gevent.joinall([gevent.spawn(master)]) 36 | 37 | 38 | if __name__ == '__main__': 39 | port = 5000 40 | http_server = pywsgi.WSGIServer(('', port), web.app) 41 | print('Running on http://127.0.0.1:%s' % port) 42 | gevent.spawn(http_server.start) 43 | task.start() 44 | loop() 45 | -------------------------------------------------------------------------------- /backend/spider.py: -------------------------------------------------------------------------------- 1 | # coding: utf8 2 | 3 | """ 4 | Web spiders, for crawling free ip proxies. 5 | """ 6 | 7 | from bs4 import BeautifulSoup 8 | 9 | from . import ( 10 | conn, const, util 11 | ) 12 | 13 | 14 | class Spider(object): 15 | url = 'http://www.xicidaili.com/wt' 16 | 17 | def __init__(self, page_num=5): 18 | """ 19 | :param page_num: 20 | """ 21 | self.page_num = page_num 22 | 23 | @property 24 | def proxies(self): 25 | """ 26 | :return: 27 | """ 28 | headers = { 29 | 'user-agent': const.USER_AGENT, 30 | 'referer': const.REFER_URL 31 | } 32 | urls = ['{url}/{page}'.format(url=self.url, page=i + 1) for i in xrange(self.page_num)] 33 | for url in urls: 34 | html = util.request_html(url, headers=headers) 35 | if not html: 36 | print('fetch html of url {0} failed.'.format(url)) 37 | continue 38 | soup = BeautifulSoup(html, 'html.parser') 39 | tr = soup.find('table', {'id': 'ip_list'}).find_all('tr')[1:] 40 | for proxy in tr: 41 | td = proxy.find_all('td') 42 | ip = td[1].get_text() 43 | port = td[2].get_text() 44 | yield ':'.join([ip, port]) 45 | 46 | def publish(self): 47 | """ 48 | :return: 49 | """ 50 | proxies = [proxy for proxy in self.proxies] 51 | conn.RedisConnection().sadd(const.REDIS_KEY, *proxies) 52 | -------------------------------------------------------------------------------- /backend/conn.py: -------------------------------------------------------------------------------- 1 | # coding: utf8 2 | 3 | """ 4 | Redis connection pool management. 5 | """ 6 | 7 | import redis 8 | 9 | 10 | class RedisConfig(object): 11 | HOST = '127.0.0.1' 12 | PORT = 6379 13 | DB = 0 14 | 15 | 16 | class RedisConnection(object): 17 | 18 | def __init__(self): 19 | if not hasattr(RedisConnection, 'pool'): 20 | RedisConnection.create_pool() 21 | self.connection_pool = redis.Redis(connection_pool=RedisConnection.pool) 22 | 23 | @staticmethod 24 | def create_pool(): 25 | """ 26 | :return: 27 | """ 28 | RedisConnection.pool = redis.ConnectionPool( 29 | host=RedisConfig.HOST, 30 | port=RedisConfig.PORT, 31 | db=RedisConfig.DB 32 | ) 33 | 34 | def get(self, key): 35 | """ 36 | :param key: 37 | :return: 38 | """ 39 | return self.connection_pool.get(key) 40 | 41 | def set(self, key, value): 42 | """ 43 | :param key: 44 | :param value: 45 | :return: 46 | """ 47 | return self.connection_pool.set(key, value) 48 | 49 | def sadd(self, key, *values): 50 | """ 51 | :param key: 52 | :param values: 53 | :return: 54 | """ 55 | return self.connection_pool.sadd(key, *values) 56 | 57 | def srem(self, key, *values): 58 | """ 59 | :param key: 60 | :param values: 61 | :return: 62 | """ 63 | return self.connection_pool.srem(key, *values) 64 | 65 | def smembers(self, key): 66 | """ 67 | :param key: 68 | :return: 69 | """ 70 | return self.connection_pool.smembers(key) 71 | -------------------------------------------------------------------------------- /.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 | env/ 12 | build/ 13 | develop-eggs/ 14 | dist/ 15 | downloads/ 16 | eggs/ 17 | .eggs/ 18 | lib/ 19 | lib64/ 20 | parts/ 21 | sdist/ 22 | var/ 23 | wheels/ 24 | *.egg-info/ 25 | .installed.cfg 26 | *.egg 27 | 28 | # PyInstaller 29 | # Usually these files are written by a python script from a template 30 | # before PyInstaller builds the exe, so as to inject date/other infos into it. 31 | *.manifest 32 | *.spec 33 | 34 | # Installer logs 35 | pip-log.txt 36 | pip-delete-this-directory.txt 37 | 38 | # Unit test / coverage reports 39 | htmlcov/ 40 | .tox/ 41 | .coverage 42 | .coverage.* 43 | .cache 44 | nosetests.xml 45 | coverage.xml 46 | *.cover 47 | .hypothesis/ 48 | 49 | # Translations 50 | *.mo 51 | *.pot 52 | 53 | # Django stuff: 54 | *.log 55 | local_settings.py 56 | 57 | # Flask stuff: 58 | instance/ 59 | .webassets-cache 60 | 61 | # Scrapy stuff: 62 | .scrapy 63 | 64 | # Sphinx documentation 65 | docs/_build/ 66 | 67 | # PyBuilder 68 | target/ 69 | 70 | # Jupyter Notebook 71 | .ipynb_checkpoints 72 | 73 | # pyenv 74 | .python-version 75 | 76 | # celery beat schedule file 77 | celerybeat-schedule 78 | 79 | # SageMath parsed files 80 | *.sage.py 81 | 82 | # dotenv 83 | .env 84 | 85 | # virtualenv 86 | .venv 87 | venv/ 88 | ENV/ 89 | 90 | # Spyder project settings 91 | .spyderproject 92 | .spyproject 93 | 94 | # Rope project settings 95 | .ropeproject 96 | 97 | # mkdocs documentation 98 | /site 99 | 100 | # mypy 101 | .mypy_cache/ 102 | 103 | # pycharm project settings 104 | .idea/ 105 | 106 | # macos 107 | .DS_Store 108 | -------------------------------------------------------------------------------- /backend/task.py: -------------------------------------------------------------------------------- 1 | # coding: utf8 2 | 3 | """ 4 | Usage for check usability of proxies, remove unavailable items, and expand if not enough. 5 | """ 6 | 7 | import gevent 8 | 9 | from . import ( 10 | conn, const, spider, util 11 | ) 12 | 13 | 14 | def patch_greenlet(func): 15 | """ 16 | :param func: 17 | :return: 18 | """ 19 | 20 | def wrapper(*args, **kwargs): 21 | return gevent.spawn(func, *args, **kwargs) 22 | 23 | return wrapper 24 | 25 | 26 | def timer(after, repeat): 27 | """ 28 | :param after: 29 | :param repeat: 30 | :return: 31 | """ 32 | return gevent.get_hub().loop.timer(after, repeat) 33 | 34 | 35 | class Task(object): 36 | CRON = { 37 | 'update_proxies': (0, 60), 38 | 'verify_proxies': (15, 15) 39 | } 40 | 41 | @staticmethod 42 | @patch_greenlet 43 | def do_update_proxies(): 44 | """ 45 | :return: 46 | """ 47 | proxies = conn.RedisConnection().smembers(const.REDIS_KEY) 48 | if len(proxies) < const.PROXY_CRITICAL_NUM: 49 | s = spider.Spider() 50 | s.publish() 51 | 52 | @staticmethod 53 | @patch_greenlet 54 | def do_verify_proxies(): 55 | """ 56 | :return: 57 | """ 58 | proxies = conn.RedisConnection().smembers(const.REDIS_KEY) 59 | if not proxies: 60 | return 61 | headers = { 62 | 'user-agent': const.USER_AGENT, 63 | 'referer': const.REFER_URL 64 | } 65 | unused = list() 66 | for proxy in proxies: 67 | p = {'proxies': 'http://{0}'.format(proxy)} 68 | resp = util.request_html(const.VERIFY_URL, headers=headers, proxies=p) 69 | if not resp: 70 | unused.append(proxy) 71 | if unused: 72 | conn.RedisConnection().srem(const.REDIS_KEY, *unused) 73 | 74 | 75 | def start(): 76 | """ 77 | :return: 78 | """ 79 | print('cron start') 80 | for f, t in Task.CRON.iteritems(): 81 | print('task {0} is loading.'.format(f)) 82 | func = getattr(Task, 'do_{0}'.format(f)) 83 | timer(t[0] * 60, t[1] * 60).start(func) 84 | -------------------------------------------------------------------------------- /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 | --------------------------------------------------------------------------------