全面架构重构：建立分层架构与高度可扩展的插件系统
后端重构： - 新增分层架构：API Routes -> Services -> Repositories -> Infrastructure - 彻底移除全局单例，全面采用 FastAPI 依赖注入 - 新增 api/ 目录拆分路由（proxies, plugins, scheduler, settings, stats） - 新增 services/ 业务逻辑层：ProxyService, PluginService, SchedulerService, ValidatorService, SettingsService - 新增 repositories/ 数据访问层：ProxyRepository, SettingsRepository, PluginSettingsRepository - 新增 models/ 层：Pydantic Schemas + Domain Models - 重写 core/config.py：采用 Pydantic Settings 管理配置 - 新增 core/db.py：基于 asynccontextmanager 的连接管理，支持数据库迁移 - 新增 core/exceptions.py：统一业务异常体系 插件系统重构（核心）： - 新增 core/plugin_system/：BaseCrawlerPlugin + PluginRegistry - 采用显式注册模式（装饰器 + plugins/__init__.py），类型安全、测试友好 - 新增 plugins/base.py：BaseHTTPPlugin 通用 HTTP 爬虫基类 - 迁移全部 7 个插件到新架构（fate0, proxylist_download, ip3366, ip89, kuaidaili, speedx, yundaili） - 插件状态持久化到 plugin_settings 表 任务调度重构： - 新增 core/tasks/queue.py：ValidationQueue + WorkerPool - 解耦爬取与验证：爬虫只负责爬取，代理提交队列后由 Worker 异步验证 - 调度器定时从数据库拉取存量代理并分批投入验证队列 前端调整： - 新增 frontend/src/services/ 层拆分 API 调用逻辑 - 调整 stores/ 和 views/ 使用 Service 层 - 保持 API 兼容性，页面无需大幅修改 其他： - 新增 main.py 作为新入口 - 新增 DESIGN.md 架构设计文档 - 更新 requirements.txt 增加 pydantic-settings
This commit is contained in:
祀梦
19
plugins/__init__.py
Normal file
19
plugins/__init__.py
Normal file
@@ -0,0 +1,19 @@
|
||||
"""插件包 - 在这里显式注册所有爬虫插件"""
|
||||
from core.plugin_system import registry
|
||||
|
||||
from .fate0 import Fate0Plugin
|
||||
from .proxylist_download import ProxyListDownloadPlugin
|
||||
from .ip3366 import Ip3366Plugin
|
||||
from .ip89 import Ip89Plugin
|
||||
from .kuaidaili import KuaiDaiLiPlugin
|
||||
from .speedx import SpeedXPlugin
|
||||
from .yundaili import YunDaiLiPlugin
|
||||
|
||||
# 显式注册所有插件
|
||||
registry.register(Fate0Plugin)
|
||||
registry.register(ProxyListDownloadPlugin)
|
||||
registry.register(Ip3366Plugin)
|
||||
registry.register(Ip89Plugin)
|
||||
registry.register(KuaiDaiLiPlugin)
|
||||
registry.register(SpeedXPlugin)
|
||||
registry.register(YunDaiLiPlugin)
|
||||
52
plugins/base.py
Normal file
52
plugins/base.py
Normal file
@@ -0,0 +1,52 @@
|
||||
"""通用 HTTP 爬虫基类 - 为基于 HTTP 请求的插件提供封装"""
|
||||
import random
|
||||
import asyncio
|
||||
import aiohttp
|
||||
from typing import List
|
||||
from core.plugin_system import BaseCrawlerPlugin
|
||||
|
||||
|
||||
class BaseHTTPPlugin(BaseCrawlerPlugin):
|
||||
"""基于 HTTP 的爬虫插件基类"""
|
||||
|
||||
def __init__(self):
|
||||
super().__init__()
|
||||
self.user_agents = [
|
||||
"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36",
|
||||
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/119.0.0.0 Safari/537.36",
|
||||
"Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/118.0.0.0 Safari/537.36",
|
||||
"Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:109.0) Gecko/20100101 Firefox/121.0",
|
||||
]
|
||||
self.urls: List[str] = []
|
||||
self.current_url: str = ""
|
||||
|
||||
def get_headers(self) -> dict:
|
||||
return {
|
||||
"User-Agent": random.choice(self.user_agents),
|
||||
"Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8",
|
||||
"Accept-Language": "zh-CN,zh;q=0.8,zh-TW;q=0.7,zh-HK;q=0.5,en-US;q=0.3,en;q=0.2",
|
||||
"Connection": "keep-alive",
|
||||
}
|
||||
|
||||
async def fetch(self, url: str, timeout: float = 10.0, retries: int = 3) -> str:
|
||||
"""异步抓取指定 URL 的 HTML 内容"""
|
||||
headers = self.get_headers()
|
||||
async with aiohttp.ClientSession(headers=headers) as session:
|
||||
for attempt in range(retries):
|
||||
try:
|
||||
async with session.get(
|
||||
url, timeout=aiohttp.ClientTimeout(total=timeout)
|
||||
) as response:
|
||||
if response.status == 200:
|
||||
content = await response.read()
|
||||
encoding = response.get_encoding()
|
||||
if encoding == "utf-8" or not encoding:
|
||||
try:
|
||||
return content.decode("utf-8")
|
||||
except UnicodeDecodeError:
|
||||
return content.decode("gbk", errors="ignore")
|
||||
return content.decode(encoding, errors="ignore")
|
||||
except Exception:
|
||||
pass
|
||||
await asyncio.sleep(random.uniform(1, 3))
|
||||
return ""
|
||||
@@ -1,66 +1,38 @@
|
||||
import sys
|
||||
import os
|
||||
sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
|
||||
|
||||
from core.crawler import BasePlugin
|
||||
from core.log import logger
|
||||
import json
|
||||
import asyncio
|
||||
from typing import List
|
||||
from core.plugin_system import ProxyRaw
|
||||
from plugins.base import BaseHTTPPlugin
|
||||
from core.log import logger
|
||||
|
||||
|
||||
class Fate0Plugin(BaseHTTPPlugin):
|
||||
name = "fate0"
|
||||
display_name = "Fate0聚合源"
|
||||
description = "从 GitHub 持续更新的高质量代理聚合列表"
|
||||
|
||||
class Fate0Plugin(BasePlugin):
|
||||
def __init__(self):
|
||||
super().__init__()
|
||||
self.name = "Fate0聚合源"
|
||||
# 这是一个持续更新的高质量代理聚合列表
|
||||
self.urls = ["https://raw.githubusercontent.com/fate0/proxylist/master/proxy.list"]
|
||||
|
||||
async def parse(self, html):
|
||||
if not html:
|
||||
return
|
||||
|
||||
count = 0
|
||||
# fate0 的数据格式是每行一个 JSON 对象
|
||||
for line in html.split('\n'):
|
||||
if not line.strip():
|
||||
async def crawl(self) -> List[ProxyRaw]:
|
||||
results = []
|
||||
for url in self.urls:
|
||||
html = await self.fetch(url, timeout=30)
|
||||
if not html:
|
||||
continue
|
||||
try:
|
||||
data = json.loads(line)
|
||||
ip = data.get('host')
|
||||
port = data.get('port')
|
||||
protocol = data.get('type', 'http')
|
||||
|
||||
# 协议标准化
|
||||
protocol = protocol.lower().strip()
|
||||
if protocol not in ('http', 'https', 'socks4', 'socks5'):
|
||||
protocol = 'http'
|
||||
|
||||
if ip and port:
|
||||
yield ip, int(port), protocol
|
||||
count += 1
|
||||
except Exception:
|
||||
continue
|
||||
|
||||
if count > 0:
|
||||
logger.info(f"{self.name} 解析完成，获得 {count} 个潜在代理")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
async def test_plugin():
|
||||
plugin = Fate0Plugin()
|
||||
print(f"========== 测试 {plugin.name} ==========")
|
||||
print(f"目标URL数量: {len(plugin.urls)}")
|
||||
print(f"开始抓取...\n")
|
||||
|
||||
proxies = await plugin.run()
|
||||
|
||||
print(f"\n========== 抓取结果 ==========")
|
||||
print(f"总计获取 {len(proxies)} 个代理:")
|
||||
print("-" * 60)
|
||||
|
||||
for idx, (ip, port, protocol) in enumerate(proxies, 1):
|
||||
print(f"{idx:3d}. {ip:15s} : {str(port):5s} | {protocol}")
|
||||
|
||||
print("-" * 60)
|
||||
print(f"完成！共 {len(proxies)} 个代理~")
|
||||
|
||||
asyncio.run(test_plugin())
|
||||
for line in html.split("\n"):
|
||||
line = line.strip()
|
||||
if not line:
|
||||
continue
|
||||
try:
|
||||
data = json.loads(line)
|
||||
ip = data.get("host")
|
||||
port = data.get("port")
|
||||
protocol = data.get("type", "http")
|
||||
if ip and port:
|
||||
results.append(ProxyRaw(ip, int(port), protocol))
|
||||
except Exception:
|
||||
continue
|
||||
if results:
|
||||
logger.info(f"{self.display_name} 解析完成，获得 {len(results)} 个潜在代理")
|
||||
return results
|
||||
|
||||
@@ -1,74 +1,51 @@
|
||||
import sys
|
||||
import os
|
||||
sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
|
||||
|
||||
from core.crawler import BasePlugin
|
||||
from core.log import logger
|
||||
from bs4 import BeautifulSoup
|
||||
import re
|
||||
import asyncio
|
||||
from typing import List
|
||||
from bs4 import BeautifulSoup
|
||||
from core.plugin_system import ProxyRaw
|
||||
from plugins.base import BaseHTTPPlugin
|
||||
from core.log import logger
|
||||
|
||||
VALID_PROTOCOLS = ['http', 'https', 'socks4', 'socks5']
|
||||
VALID_PROTOCOLS = ("http", "https", "socks4", "socks5")
|
||||
|
||||
|
||||
class Ip3366Plugin(BaseHTTPPlugin):
|
||||
name = "ip3366"
|
||||
display_name = "IP3366"
|
||||
description = "从 IP3366 网站爬取免费代理"
|
||||
|
||||
class Ip3366Plugin(BasePlugin):
|
||||
def __init__(self):
|
||||
super().__init__()
|
||||
self.name = "IP3366"
|
||||
# 抓取高匿和普通代理的前 5 页
|
||||
self.urls = [
|
||||
f"http://www.ip3366.net/free/?stype=1&page={i}" for i in range(1, 6)
|
||||
] + [
|
||||
f"http://www.ip3366.net/free/?stype=2&page={i}" for i in range(1, 6)
|
||||
]
|
||||
|
||||
async def parse(self, html):
|
||||
if not html:
|
||||
return
|
||||
|
||||
soup = BeautifulSoup(html, 'lxml')
|
||||
list_div = soup.find('div', id='list')
|
||||
if not list_div: return
|
||||
|
||||
table = list_div.find('table')
|
||||
if not table: return
|
||||
async def crawl(self) -> List[ProxyRaw]:
|
||||
results = []
|
||||
for url in self.urls:
|
||||
html = await self.fetch(url, timeout=15)
|
||||
if not html:
|
||||
continue
|
||||
soup = BeautifulSoup(html, "lxml")
|
||||
list_div = soup.find("div", id="list")
|
||||
if not list_div:
|
||||
continue
|
||||
table = list_div.find("table")
|
||||
if not table:
|
||||
continue
|
||||
|
||||
rows = table.find_all('tr')
|
||||
count = 0
|
||||
for row in rows:
|
||||
tds = row.find_all('td')
|
||||
if len(tds) >= 5:
|
||||
ip = tds[0].get_text(strip=True)
|
||||
port = tds[1].get_text(strip=True)
|
||||
protocol = tds[4].get_text(strip=True).lower() if len(tds) > 4 else 'http'
|
||||
|
||||
if protocol not in VALID_PROTOCOLS:
|
||||
protocol = 'http'
|
||||
|
||||
if re.match(r'^\d+\.\d+\.\d+\.\d+$', ip) and port.isdigit():
|
||||
yield ip, int(port), protocol
|
||||
count += 1
|
||||
|
||||
if count > 0:
|
||||
logger.info(f"{self.name} 解析完成，获得 {count} 个潜在代理")
|
||||
for row in table.find_all("tr"):
|
||||
tds = row.find_all("td")
|
||||
if len(tds) >= 5:
|
||||
ip = tds[0].get_text(strip=True)
|
||||
port = tds[1].get_text(strip=True)
|
||||
protocol = tds[4].get_text(strip=True).lower() if len(tds) > 4 else "http"
|
||||
if protocol not in VALID_PROTOCOLS:
|
||||
protocol = "http"
|
||||
if re.match(r"^\d+\.\d+\.\d+\.\d+$", ip) and port.isdigit():
|
||||
results.append(ProxyRaw(ip, int(port), protocol))
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
async def test_plugin():
|
||||
plugin = Ip3366Plugin()
|
||||
print(f"========== 测试 {plugin.name} ==========")
|
||||
print(f"目标URL数量: {len(plugin.urls)}")
|
||||
print(f"开始抓取...\n")
|
||||
|
||||
proxies = await plugin.run()
|
||||
|
||||
print(f"\n========== 抓取结果 ==========")
|
||||
print(f"总计获取 {len(proxies)} 个代理:")
|
||||
print("-" * 60)
|
||||
|
||||
for idx, (ip, port, protocol) in enumerate(proxies, 1):
|
||||
print(f"{idx:3d}. {ip:15s} : {str(port):5s} | {protocol}")
|
||||
|
||||
print("-" * 60)
|
||||
print(f"完成！共 {len(proxies)} 个代理~")
|
||||
|
||||
asyncio.run(test_plugin())
|
||||
if results:
|
||||
logger.info(f"{self.display_name} 解析完成，获得 {len(results)} 个潜在代理")
|
||||
return results
|
||||
|
||||
@@ -1,69 +1,39 @@
|
||||
import sys
|
||||
import os
|
||||
sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
|
||||
|
||||
from core.crawler import BasePlugin
|
||||
from core.log import logger
|
||||
from bs4 import BeautifulSoup
|
||||
import re
|
||||
import asyncio
|
||||
from typing import List
|
||||
from bs4 import BeautifulSoup
|
||||
from core.plugin_system import ProxyRaw
|
||||
from plugins.base import BaseHTTPPlugin
|
||||
from core.log import logger
|
||||
|
||||
|
||||
class Ip89Plugin(BaseHTTPPlugin):
|
||||
name = "ip89"
|
||||
display_name = "89免费代理"
|
||||
description = "从 89ip.cn 爬取免费代理"
|
||||
|
||||
class Ip89Plugin(BasePlugin):
|
||||
def __init__(self):
|
||||
super().__init__()
|
||||
self.name = "89免费代理"
|
||||
# 抓取前 5 页
|
||||
self.urls = [
|
||||
f"https://www.89ip.cn/index_{i}.html" for i in range(1, 6)
|
||||
]
|
||||
self.urls = [f"https://www.89ip.cn/index_{i}.html" for i in range(1, 6)]
|
||||
|
||||
async def parse(self, html):
|
||||
"""
|
||||
解析 89ip 页面
|
||||
"""
|
||||
if not html:
|
||||
return
|
||||
|
||||
soup = BeautifulSoup(html, 'lxml')
|
||||
table = soup.find('table', class_='layui-table')
|
||||
if not table:
|
||||
return
|
||||
async def crawl(self) -> List[ProxyRaw]:
|
||||
results = []
|
||||
for url in self.urls:
|
||||
html = await self.fetch(url, timeout=15)
|
||||
if not html:
|
||||
continue
|
||||
soup = BeautifulSoup(html, "lxml")
|
||||
table = soup.find("table", class_="layui-table")
|
||||
if not table:
|
||||
continue
|
||||
|
||||
rows = table.find_all('tr')
|
||||
count = 0
|
||||
for row in rows:
|
||||
tds = row.find_all('td')
|
||||
if len(tds) >= 2:
|
||||
ip = tds[0].get_text(strip=True)
|
||||
port = tds[1].get_text(strip=True)
|
||||
# 89ip 通常不直接写协议，默认尝试 http
|
||||
protocol = 'http'
|
||||
|
||||
if re.match(r'^\d+\.\d+\.\d+\.\d+$', ip) and port.isdigit():
|
||||
yield ip, int(port), protocol
|
||||
count += 1
|
||||
|
||||
if count > 0:
|
||||
logger.info(f"{self.name} 解析完成，获得 {count} 个潜在代理")
|
||||
for row in table.find_all("tr"):
|
||||
tds = row.find_all("td")
|
||||
if len(tds) >= 2:
|
||||
ip = tds[0].get_text(strip=True)
|
||||
port = tds[1].get_text(strip=True)
|
||||
if re.match(r"^\d+\.\d+\.\d+\.\d+$", ip) and port.isdigit():
|
||||
results.append(ProxyRaw(ip, int(port), "http"))
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
async def test_plugin():
|
||||
plugin = Ip89Plugin()
|
||||
print(f"========== 测试 {plugin.name} ==========")
|
||||
print(f"目标URL数量: {len(plugin.urls)}")
|
||||
print(f"开始抓取...\n")
|
||||
|
||||
proxies = await plugin.run()
|
||||
|
||||
print(f"\n========== 抓取结果 ==========")
|
||||
print(f"总计获取 {len(proxies)} 个代理:")
|
||||
print("-" * 60)
|
||||
|
||||
for idx, (ip, port, protocol) in enumerate(proxies, 1):
|
||||
print(f"{idx:3d}. {ip:15s} : {str(port):5s} | {protocol}")
|
||||
|
||||
print("-" * 60)
|
||||
print(f"完成！共 {len(proxies)} 个代理~")
|
||||
|
||||
asyncio.run(test_plugin())
|
||||
if results:
|
||||
logger.info(f"{self.display_name} 解析完成，获得 {len(results)} 个潜在代理")
|
||||
return results
|
||||
|
||||
@@ -1,79 +1,49 @@
|
||||
import sys
|
||||
import os
|
||||
sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
|
||||
|
||||
from core.crawler import BasePlugin
|
||||
from core.log import logger
|
||||
from bs4 import BeautifulSoup
|
||||
import re
|
||||
import asyncio
|
||||
from typing import List
|
||||
from bs4 import BeautifulSoup
|
||||
from core.plugin_system import ProxyRaw
|
||||
from plugins.base import BaseHTTPPlugin
|
||||
from core.log import logger
|
||||
|
||||
VALID_PROTOCOLS = ['http', 'https', 'socks4', 'socks5']
|
||||
VALID_PROTOCOLS = ("http", "https", "socks4", "socks5")
|
||||
|
||||
|
||||
class KuaiDaiLiPlugin(BaseHTTPPlugin):
|
||||
name = "kuaidaili"
|
||||
display_name = "快代理"
|
||||
description = "从快代理网站爬取免费代理"
|
||||
|
||||
class KuaiDaiLiPlugin(BasePlugin):
|
||||
def __init__(self):
|
||||
super().__init__()
|
||||
self.name = "快代理"
|
||||
# 抓取国内高匿和国内普通代理的前 10 页
|
||||
self.urls = [
|
||||
f"https://www.kuaidaili.com/free/inha/{i}/" for i in range(1, 11)
|
||||
] + [
|
||||
f"https://www.kuaidaili.com/free/intr/{i}/" for i in range(1, 11)
|
||||
]
|
||||
|
||||
async def parse(self, html):
|
||||
"""
|
||||
解析快代理页面
|
||||
"""
|
||||
if not html:
|
||||
return
|
||||
|
||||
soup = BeautifulSoup(html, 'lxml')
|
||||
# 快代理的表格在 tbody 中
|
||||
table = soup.find('table')
|
||||
if not table:
|
||||
# 尝试通过正则表达式匹配可能被加密或特殊处理的数据
|
||||
logger.warning(f"{self.name} 未能找到表格，可能是触发了反爬或结构变化")
|
||||
return
|
||||
async def crawl(self) -> List[ProxyRaw]:
|
||||
results = []
|
||||
for url in self.urls:
|
||||
html = await self.fetch(url, timeout=15)
|
||||
if not html:
|
||||
continue
|
||||
soup = BeautifulSoup(html, "lxml")
|
||||
table = soup.find("table")
|
||||
if not table:
|
||||
logger.warning(f"{self.display_name} 未能找到表格，可能是触发了反爬")
|
||||
continue
|
||||
|
||||
rows = table.find_all('tr')
|
||||
count = 0
|
||||
for row in rows:
|
||||
tds = row.find_all('td')
|
||||
if len(tds) >= 5:
|
||||
ip = tds[0].get_text(strip=True)
|
||||
port = tds[1].get_text(strip=True)
|
||||
protocol = tds[4].get_text(strip=True).lower() if len(tds) > 4 else 'http'
|
||||
|
||||
if protocol not in VALID_PROTOCOLS:
|
||||
protocol = 'http'
|
||||
|
||||
# 简单校验格式
|
||||
if re.match(r'^\d+\.\d+\.\d+\.\d+$', ip) and port.isdigit():
|
||||
yield ip, int(port), protocol
|
||||
count += 1
|
||||
|
||||
if count > 0:
|
||||
logger.info(f"{self.name} 解析完成，获得 {count} 个潜在代理")
|
||||
for row in table.find_all("tr"):
|
||||
tds = row.find_all("td")
|
||||
if len(tds) >= 5:
|
||||
ip = tds[0].get_text(strip=True)
|
||||
port = tds[1].get_text(strip=True)
|
||||
protocol = tds[4].get_text(strip=True).lower() if len(tds) > 4 else "http"
|
||||
if protocol not in VALID_PROTOCOLS:
|
||||
protocol = "http"
|
||||
if re.match(r"^\d+\.\d+\.\d+\.\d+$", ip) and port.isdigit():
|
||||
results.append(ProxyRaw(ip, int(port), protocol))
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
async def test_plugin():
|
||||
plugin = KuaiDaiLiPlugin()
|
||||
print(f"========== 测试 {plugin.name} ==========")
|
||||
print(f"目标URL数量: {len(plugin.urls)}")
|
||||
print(f"开始抓取...\n")
|
||||
|
||||
proxies = await plugin.run()
|
||||
|
||||
print(f"\n========== 抓取结果 ==========")
|
||||
print(f"总计获取 {len(proxies)} 个代理:")
|
||||
print("-" * 60)
|
||||
|
||||
for idx, (ip, port, protocol) in enumerate(proxies, 1):
|
||||
print(f"{idx:3d}. {ip:15s} : {str(port):5s} | {protocol}")
|
||||
|
||||
print("-" * 60)
|
||||
print(f"完成！共 {len(proxies)} 个代理~")
|
||||
|
||||
asyncio.run(test_plugin())
|
||||
if results:
|
||||
logger.info(f"{self.display_name} 解析完成，获得 {len(results)} 个潜在代理")
|
||||
return results
|
||||
|
||||
@@ -1,75 +1,55 @@
|
||||
import sys
|
||||
import os
|
||||
sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
|
||||
|
||||
from core.crawler import BasePlugin
|
||||
from typing import List
|
||||
from core.plugin_system import ProxyRaw
|
||||
from plugins.base import BaseHTTPPlugin
|
||||
from core.log import logger
|
||||
import asyncio
|
||||
|
||||
class ProxyListDownloadPlugin(BasePlugin):
|
||||
|
||||
class ProxyListDownloadPlugin(BaseHTTPPlugin):
|
||||
name = "proxylist_download"
|
||||
display_name = "ProxyListDownload"
|
||||
description = "从 ProxyListDownload API 获取代理"
|
||||
|
||||
def __init__(self):
|
||||
super().__init__()
|
||||
self.name = "ProxyListDownload"
|
||||
self.urls = [
|
||||
"https://www.proxy-list.download/api/v1/get?type=http",
|
||||
"https://www.proxy-list.download/api/v1/get?type=https",
|
||||
"https://www.proxy-list.download/api/v1/get?type=socks4",
|
||||
"https://www.proxy-list.download/api/v1/get?type=socks5"
|
||||
"https://www.proxy-list.download/api/v1/get?type=socks5",
|
||||
]
|
||||
|
||||
async def parse(self, html):
|
||||
if not html:
|
||||
return
|
||||
|
||||
lines = html.split('\r\n')
|
||||
if len(lines) <= 1:
|
||||
lines = html.split('\n')
|
||||
|
||||
count = 0
|
||||
# 根据 URL 判断协议类型
|
||||
if 'type=socks4' in self.current_url:
|
||||
protocol = 'socks4'
|
||||
elif 'type=socks5' in self.current_url:
|
||||
protocol = 'socks5'
|
||||
elif 'type=https' in self.current_url:
|
||||
protocol = 'https'
|
||||
else:
|
||||
protocol = 'http'
|
||||
|
||||
for line in lines:
|
||||
line = line.strip()
|
||||
if not line:
|
||||
async def crawl(self) -> List[ProxyRaw]:
|
||||
results = []
|
||||
for url in self.urls:
|
||||
html = await self.fetch(url, timeout=30)
|
||||
if not html:
|
||||
continue
|
||||
|
||||
if ':' in line:
|
||||
parts = line.split(':')
|
||||
|
||||
# 根据 URL 判断协议
|
||||
if "type=socks4" in url:
|
||||
protocol = "socks4"
|
||||
elif "type=socks5" in url:
|
||||
protocol = "socks5"
|
||||
elif "type=https" in url:
|
||||
protocol = "https"
|
||||
else:
|
||||
protocol = "http"
|
||||
|
||||
lines = html.split("\r\n")
|
||||
if len(lines) <= 1:
|
||||
lines = html.split("\n")
|
||||
|
||||
for line in lines:
|
||||
line = line.strip()
|
||||
if not line or ":" not in line:
|
||||
continue
|
||||
parts = line.split(":")
|
||||
if len(parts) >= 2:
|
||||
ip = parts[0]
|
||||
port = parts[1]
|
||||
yield ip, int(port), protocol
|
||||
count += 1
|
||||
|
||||
if count > 0:
|
||||
logger.info(f"{self.name} 解析完成，从 {self.current_url} 获得 {count} 个潜在代理")
|
||||
ip = parts[0].strip()
|
||||
port = parts[1].strip()
|
||||
if ip and port.isdigit():
|
||||
results.append(ProxyRaw(ip, int(port), protocol))
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
async def test_plugin():
|
||||
plugin = ProxyListDownloadPlugin()
|
||||
print(f"========== 测试 {plugin.name} ==========")
|
||||
print(f"目标URL数量: {len(plugin.urls)}")
|
||||
print(f"开始抓取...\n")
|
||||
|
||||
proxies = await plugin.run()
|
||||
|
||||
print(f"\n========== 抓取结果 ==========")
|
||||
print(f"总计获取 {len(proxies)} 个代理:")
|
||||
print("-" * 60)
|
||||
|
||||
for idx, (ip, port, protocol) in enumerate(proxies, 1):
|
||||
print(f"{idx:3d}. {ip:15s} : {str(port):5s} | {protocol}")
|
||||
|
||||
print("-" * 60)
|
||||
print(f"完成！共 {len(proxies)} 个代理~")
|
||||
|
||||
asyncio.run(test_plugin())
|
||||
if results:
|
||||
logger.info(f"{self.display_name} 解析完成，获得 {len(results)} 个潜在代理")
|
||||
return results
|
||||
|
||||
@@ -1,78 +1,51 @@
|
||||
import sys
|
||||
import os
|
||||
sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
|
||||
|
||||
from core.crawler import BasePlugin
|
||||
from core.log import logger
|
||||
import re
|
||||
import asyncio
|
||||
from typing import List
|
||||
from core.plugin_system import ProxyRaw
|
||||
from plugins.base import BaseHTTPPlugin
|
||||
from core.log import logger
|
||||
|
||||
|
||||
class SpeedXPlugin(BaseHTTPPlugin):
|
||||
name = "speedx"
|
||||
display_name = "SpeedX代理源"
|
||||
description = "从 SpeedX GitHub 仓库获取 SOCKS 代理列表"
|
||||
|
||||
class SpeedXPlugin(BasePlugin):
|
||||
def __init__(self):
|
||||
super().__init__()
|
||||
self.name = "SpeedX代理源"
|
||||
self.urls = [
|
||||
"https://raw.githubusercontent.com/TheSpeedX/SOCKS-List/master/http.txt",
|
||||
"https://raw.githubusercontent.com/TheSpeedX/SOCKS-List/master/socks4.txt",
|
||||
"https://raw.githubusercontent.com/TheSpeedX/SOCKS-List/master/socks5.txt"
|
||||
"https://raw.githubusercontent.com/TheSpeedX/SOCKS-List/master/socks5.txt",
|
||||
]
|
||||
|
||||
async def parse(self, html):
|
||||
if not html:
|
||||
return
|
||||
|
||||
lines = html.split('\n')
|
||||
count = 0
|
||||
for line in lines:
|
||||
line = line.strip()
|
||||
if not line:
|
||||
async def crawl(self) -> List[ProxyRaw]:
|
||||
results = []
|
||||
for url in self.urls:
|
||||
html = await self.fetch(url, timeout=30)
|
||||
if not html:
|
||||
continue
|
||||
|
||||
if ':' in line:
|
||||
parts = line.split(':')
|
||||
# 根据 URL 判断协议
|
||||
protocol = "http"
|
||||
if "socks5" in url:
|
||||
protocol = "socks5"
|
||||
elif "socks4" in url:
|
||||
protocol = "socks4"
|
||||
|
||||
for line in html.split("\n"):
|
||||
line = line.strip()
|
||||
if not line or ":" not in line:
|
||||
continue
|
||||
parts = line.split(":")
|
||||
if len(parts) >= 2:
|
||||
ip = parts[0].strip()
|
||||
port = parts[1].strip()
|
||||
|
||||
# 验证IP地址格式
|
||||
if not re.match(r'^\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3}$', ip):
|
||||
if not re.match(r"^\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3}$", ip):
|
||||
continue
|
||||
|
||||
# 验证端口是数字
|
||||
if not port.isdigit() or not (1 <= int(port) <= 65535):
|
||||
continue
|
||||
results.append(ProxyRaw(ip, int(port), protocol))
|
||||
|
||||
# 根据 URL 判断协议
|
||||
protocol = 'http'
|
||||
if 'socks5' in self.current_url:
|
||||
protocol = 'socks5'
|
||||
elif 'socks4' in self.current_url:
|
||||
protocol = 'socks4'
|
||||
|
||||
yield ip, int(port), protocol
|
||||
count += 1
|
||||
|
||||
if count > 0:
|
||||
logger.info(f"{self.name} 解析完成，从 {self.current_url} 获得 {count} 个潜在代理")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
async def test_plugin():
|
||||
plugin = SpeedXPlugin()
|
||||
print(f"========== 测试 {plugin.name} ==========")
|
||||
print(f"目标URL数量: {len(plugin.urls)}")
|
||||
print(f"开始抓取...\n")
|
||||
|
||||
proxies = await plugin.run()
|
||||
|
||||
print(f"\n========== 抓取结果 ==========")
|
||||
print(f"总计获取 {len(proxies)} 个代理:")
|
||||
print("-" * 60)
|
||||
|
||||
for idx, (ip, port, protocol) in enumerate(proxies, 1):
|
||||
print(f"{idx:3d}. {ip:15s} : {str(port):5s} | {protocol}")
|
||||
|
||||
print("-" * 60)
|
||||
print(f"完成！共 {len(proxies)} 个代理~")
|
||||
|
||||
asyncio.run(test_plugin())
|
||||
if results:
|
||||
logger.info(f"{self.display_name} 解析完成，获得 {len(results)} 个潜在代理")
|
||||
return results
|
||||
|
||||
@@ -1,79 +1,51 @@
|
||||
import sys
|
||||
import os
|
||||
sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
|
||||
|
||||
from core.crawler import BasePlugin
|
||||
from core.log import logger
|
||||
from bs4 import BeautifulSoup
|
||||
import re
|
||||
import asyncio
|
||||
from typing import List
|
||||
from bs4 import BeautifulSoup
|
||||
from core.plugin_system import ProxyRaw
|
||||
from plugins.base import BaseHTTPPlugin
|
||||
from core.log import logger
|
||||
|
||||
VALID_PROTOCOLS = ['http', 'https', 'socks4', 'socks5']
|
||||
VALID_PROTOCOLS = ("http", "https", "socks4", "socks5")
|
||||
|
||||
|
||||
class YunDaiLiPlugin(BaseHTTPPlugin):
|
||||
name = "yundaili"
|
||||
display_name = "云代理"
|
||||
description = "从云代理网站爬取免费代理"
|
||||
|
||||
class YunDaiLiPlugin(BasePlugin):
|
||||
def __init__(self):
|
||||
super().__init__()
|
||||
self.name = "云代理"
|
||||
# 抓取高匿和普通代理的前 5 页
|
||||
self.urls = [
|
||||
f"http://www.ip3366.net/free/?stype=1&page={i}" for i in range(1, 6)
|
||||
] + [
|
||||
f"http://www.ip3366.net/free/?stype=2&page={i}" for i in range(1, 6)
|
||||
]
|
||||
|
||||
async def parse(self, html):
|
||||
"""
|
||||
解析云代理/IP3366 页面 (两者结构相似)
|
||||
"""
|
||||
if not html:
|
||||
return
|
||||
|
||||
soup = BeautifulSoup(html, 'lxml')
|
||||
list_table = soup.find('div', id='list')
|
||||
if not list_table:
|
||||
return
|
||||
|
||||
table = list_table.find('table')
|
||||
if not table:
|
||||
return
|
||||
async def crawl(self) -> List[ProxyRaw]:
|
||||
results = []
|
||||
for url in self.urls:
|
||||
html = await self.fetch(url, timeout=15)
|
||||
if not html:
|
||||
continue
|
||||
soup = BeautifulSoup(html, "lxml")
|
||||
list_table = soup.find("div", id="list")
|
||||
if not list_table:
|
||||
continue
|
||||
table = list_table.find("table")
|
||||
if not table:
|
||||
continue
|
||||
|
||||
rows = table.find_all('tr')
|
||||
count = 0
|
||||
for row in rows:
|
||||
tds = row.find_all('td')
|
||||
if len(tds) >= 5:
|
||||
ip = tds[0].get_text(strip=True)
|
||||
port = tds[1].get_text(strip=True)
|
||||
protocol = tds[4].get_text(strip=True).lower() if len(tds) > 4 else 'http'
|
||||
|
||||
if protocol not in VALID_PROTOCOLS:
|
||||
protocol = 'http'
|
||||
|
||||
if re.match(r'^\d+\.\d+\.\d+\.\d+$', ip) and port.isdigit():
|
||||
yield ip, int(port), protocol
|
||||
count += 1
|
||||
|
||||
if count > 0:
|
||||
logger.info(f"{self.name} 解析完成，获得 {count} 个潜在代理")
|
||||
for row in table.find_all("tr"):
|
||||
tds = row.find_all("td")
|
||||
if len(tds) >= 5:
|
||||
ip = tds[0].get_text(strip=True)
|
||||
port = tds[1].get_text(strip=True)
|
||||
protocol = tds[4].get_text(strip=True).lower() if len(tds) > 4 else "http"
|
||||
if protocol not in VALID_PROTOCOLS:
|
||||
protocol = "http"
|
||||
if re.match(r"^\d+\.\d+\.\d+\.\d+$", ip) and port.isdigit():
|
||||
results.append(ProxyRaw(ip, int(port), protocol))
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
async def test_plugin():
|
||||
plugin = YunDaiLiPlugin()
|
||||
print(f"========== 测试 {plugin.name} ==========")
|
||||
print(f"目标URL数量: {len(plugin.urls)}")
|
||||
print(f"开始抓取...\n")
|
||||
|
||||
proxies = await plugin.run()
|
||||
|
||||
print(f"\n========== 抓取结果 ==========")
|
||||
print(f"总计获取 {len(proxies)} 个代理:")
|
||||
print("-" * 60)
|
||||
|
||||
for idx, (ip, port, protocol) in enumerate(proxies, 1):
|
||||
print(f"{idx:3d}. {ip:15s} : {str(port):5s} | {protocol}")
|
||||
|
||||
print("-" * 60)
|
||||
print(f"完成！共 {len(proxies)} 个代理~")
|
||||
|
||||
asyncio.run(test_plugin())
|
||||
if results:
|
||||
logger.info(f"{self.display_name} 解析完成，获得 {len(results)} 个潜在代理")
|
||||
return results
|
||||
|
||||
Reference in New Issue
Block a user