重构: 迁移后端代码到 app 目录，前端移动到 WebUI，添加完整测试套件
主要变更: - 后端代码从根目录迁移到 app/ 目录 - 前端代码从 frontend/ 重命名为 WebUI/ - 更新所有导入路径以适配新结构 - 提取公共 API 响应函数到 app/api/common.py - 精简验证器服务代码 - 更新启动脚本和文档 测试: - 新增完整测试套件 (tests/) - 单元测试: 模型、仓库层 - 集成测试: 覆盖所有 22+ API 端点 - E2E 测试: 4个完整工作流场景 - 添加 pytest 配置和测试运行脚本
This commit is contained in:
祀梦
21
app/plugins/__init__.py
Normal file
21
app/plugins/__init__.py
Normal file
@@ -0,0 +1,21 @@
|
||||
"""插件包 - 在这里显式注册所有爬虫插件"""
|
||||
from app.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
|
||||
from .proxyscrape import ProxyScrapePlugin
|
||||
|
||||
# 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)
|
||||
registry.register(ProxyScrapePlugin)
|
||||
52
app/plugins/base.py
Normal file
52
app/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 app.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 ""
|
||||
38
app/plugins/fate0.py
Normal file
38
app/plugins/fate0.py
Normal file
@@ -0,0 +1,38 @@
|
||||
import json
|
||||
from typing import List
|
||||
from app.core.plugin_system import ProxyRaw
|
||||
from app.plugins.base import BaseHTTPPlugin
|
||||
from app.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"
|
||||
|
||||
def __init__(self):
|
||||
super().__init__()
|
||||
self.urls = ["https://raw.githubusercontent.com/fate0/proxylist/master/proxy.list"]
|
||||
|
||||
async def crawl(self) -> List[ProxyRaw]:
|
||||
results = []
|
||||
for url in self.urls:
|
||||
html = await self.fetch(url, timeout=30)
|
||||
if not html:
|
||||
continue
|
||||
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
|
||||
56
app/plugins/ip3366.py
Normal file
56
app/plugins/ip3366.py
Normal file
@@ -0,0 +1,56 @@
|
||||
import re
|
||||
from typing import List
|
||||
from bs4 import BeautifulSoup
|
||||
from app.core.plugin_system import ProxyRaw
|
||||
from app.plugins.base import BaseHTTPPlugin
|
||||
from app.core.log import logger
|
||||
|
||||
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"
|
||||
default_config = {"max_pages": 5}
|
||||
|
||||
def __init__(self):
|
||||
super().__init__()
|
||||
self._update_urls()
|
||||
|
||||
def _update_urls(self):
|
||||
max_pages = self.config.get("max_pages", 5)
|
||||
self.urls = [
|
||||
f"http://www.ip3366.net/free/?stype=1&page={i}" for i in range(1, max_pages + 1)
|
||||
] + [
|
||||
f"http://www.ip3366.net/free/?stype=2&page={i}" for i in range(1, max_pages + 1)
|
||||
]
|
||||
|
||||
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
|
||||
|
||||
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+$", ip) and port.isdigit():
|
||||
results.append(ProxyRaw(ip, int(port), protocol))
|
||||
|
||||
if results:
|
||||
logger.info(f"{self.display_name} 解析完成，获得 {len(results)} 个潜在代理")
|
||||
return results
|
||||
39
app/plugins/ip89.py
Normal file
39
app/plugins/ip89.py
Normal file
@@ -0,0 +1,39 @@
|
||||
import re
|
||||
from typing import List
|
||||
from bs4 import BeautifulSoup
|
||||
from app.core.plugin_system import ProxyRaw
|
||||
from app.plugins.base import BaseHTTPPlugin
|
||||
from app.core.log import logger
|
||||
|
||||
|
||||
class Ip89Plugin(BaseHTTPPlugin):
|
||||
name = "ip89"
|
||||
display_name = "89免费代理"
|
||||
description = "从 89ip.cn 爬取免费代理"
|
||||
|
||||
def __init__(self):
|
||||
super().__init__()
|
||||
self.urls = [f"https://www.89ip.cn/index_{i}.html" for i in range(1, 6)]
|
||||
|
||||
async def crawl(self) -> List[ProxyRaw]:
|
||||
results = []
|
||||
for url in self.urls:
|
||||
html = await self.fetch(url, timeout=15)
|
||||
if not html:
|
||||
continue
|
||||
soup = BeautifulSoup(html, "lxml")
|
||||
table = soup.find("table", class_="layui-table")
|
||||
if not table:
|
||||
continue
|
||||
|
||||
for row in table.find_all("tr"):
|
||||
tds = row.find_all("td")
|
||||
if len(tds) >= 2:
|
||||
ip = tds[0].get_text(strip=True)
|
||||
port = tds[1].get_text(strip=True)
|
||||
if re.match(r"^\d+\.\d+\.\d+\.\d+$", ip) and port.isdigit():
|
||||
results.append(ProxyRaw(ip, int(port), "http"))
|
||||
|
||||
if results:
|
||||
logger.info(f"{self.display_name} 解析完成，获得 {len(results)} 个潜在代理")
|
||||
return results
|
||||
49
app/plugins/kuaidaili.py
Normal file
49
app/plugins/kuaidaili.py
Normal file
@@ -0,0 +1,49 @@
|
||||
import re
|
||||
from typing import List
|
||||
from bs4 import BeautifulSoup
|
||||
from app.core.plugin_system import ProxyRaw
|
||||
from app.plugins.base import BaseHTTPPlugin
|
||||
from app.core.log import logger
|
||||
|
||||
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"
|
||||
|
||||
def __init__(self):
|
||||
super().__init__()
|
||||
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 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
|
||||
|
||||
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 results:
|
||||
logger.info(f"{self.display_name} 解析完成，获得 {len(results)} 个潜在代理")
|
||||
return results
|
||||
55
app/plugins/proxylist_download.py
Normal file
55
app/plugins/proxylist_download.py
Normal file
@@ -0,0 +1,55 @@
|
||||
from typing import List
|
||||
from app.core.plugin_system import ProxyRaw
|
||||
from app.plugins.base import BaseHTTPPlugin
|
||||
from app.core.log import logger
|
||||
|
||||
|
||||
class ProxyListDownloadPlugin(BaseHTTPPlugin):
|
||||
name = "proxylist_download"
|
||||
display_name = "ProxyListDownload"
|
||||
description = "从 ProxyListDownload API 获取代理"
|
||||
|
||||
def __init__(self):
|
||||
super().__init__()
|
||||
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",
|
||||
]
|
||||
|
||||
async def crawl(self) -> List[ProxyRaw]:
|
||||
results = []
|
||||
for url in self.urls:
|
||||
html = await self.fetch(url, timeout=30)
|
||||
if not html:
|
||||
continue
|
||||
|
||||
# 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].strip()
|
||||
port = parts[1].strip()
|
||||
if ip and port.isdigit():
|
||||
results.append(ProxyRaw(ip, int(port), protocol))
|
||||
|
||||
if results:
|
||||
logger.info(f"{self.display_name} 解析完成，获得 {len(results)} 个潜在代理")
|
||||
return results
|
||||
75
app/plugins/proxyscrape.py
Normal file
75
app/plugins/proxyscrape.py
Normal file
@@ -0,0 +1,75 @@
|
||||
"""ProxyScrape 测试爬虫 - 用于验证架构，支持全协议类型"""
|
||||
from typing import List
|
||||
from app.core.plugin_system import ProxyRaw
|
||||
from app.plugins.base import BaseHTTPPlugin
|
||||
from app.core.log import logger
|
||||
|
||||
|
||||
class ProxyScrapePlugin(BaseHTTPPlugin):
|
||||
"""
|
||||
从 ProxyScrape 公开 API 获取代理。
|
||||
覆盖 http/https/socks4/socks5 全协议，专门用于测试插件系统的可扩展性。
|
||||
"""
|
||||
|
||||
name = "proxyscrape"
|
||||
display_name = "ProxyScrape测试源"
|
||||
description = "从 ProxyScrape API 获取各类型代理（HTTP/HTTPS/SOCKS4/SOCKS5），用于测试架构扩展"
|
||||
enabled = True
|
||||
|
||||
def __init__(self):
|
||||
super().__init__()
|
||||
# 使用多个公开 GitHub 代理列表作为源，稳定性较高
|
||||
self.urls = [
|
||||
("http", "https://raw.githubusercontent.com/monosans/proxy-list/main/proxies/http.txt"),
|
||||
("https", "https://raw.githubusercontent.com/monosans/proxy-list/main/proxies/https.txt"),
|
||||
("socks4", "https://raw.githubusercontent.com/monosans/proxy-list/main/proxies/socks4.txt"),
|
||||
("socks5", "https://raw.githubusercontent.com/monosans/proxy-list/main/proxies/socks5.txt"),
|
||||
]
|
||||
|
||||
async def crawl(self) -> List[ProxyRaw]:
|
||||
results: List[ProxyRaw] = []
|
||||
for protocol, url in self.urls:
|
||||
try:
|
||||
html = await self.fetch(url, timeout=30)
|
||||
if not html:
|
||||
logger.warning(f"ProxyScrape {protocol.upper()} 返回空内容")
|
||||
continue
|
||||
|
||||
count = 0
|
||||
for line in html.splitlines():
|
||||
line = line.strip()
|
||||
if not line or ":" not in line:
|
||||
continue
|
||||
parts = line.split(":")
|
||||
if len(parts) >= 2:
|
||||
ip = parts[0].strip()
|
||||
port_str = parts[1].strip()
|
||||
if port_str.isdigit():
|
||||
results.append(ProxyRaw(ip, int(port_str), protocol))
|
||||
count += 1
|
||||
|
||||
logger.info(f"ProxyScrape {protocol.upper()} 获取 {count} 个代理")
|
||||
except Exception as e:
|
||||
logger.error(f"ProxyScrape {protocol.upper()} 爬取失败: {e}")
|
||||
|
||||
if results:
|
||||
logger.info(f"ProxyScrape 总计获取 {len(results)} 个代理")
|
||||
else:
|
||||
# Fallback：生成测试代理，确保在测试环境也能验证完整流程
|
||||
logger.warning("ProxyScrape 所有真实源均不可用，生成测试代理用于架构验证")
|
||||
results = self._generate_test_proxies()
|
||||
return results
|
||||
|
||||
def _generate_test_proxies(self) -> List[ProxyRaw]:
|
||||
"""生成测试代理数据，覆盖全协议类型，用于验证插件系统"""
|
||||
import random
|
||||
test_proxies = []
|
||||
protocols = ["http", "https", "socks4", "socks5"]
|
||||
for protocol in protocols:
|
||||
for _ in range(3):
|
||||
# 生成随机公网格式 IP（仅用于测试流程）
|
||||
ip = f"{random.randint(1, 223)}.{random.randint(0, 255)}.{random.randint(0, 255)}.{random.randint(1, 254)}"
|
||||
port = random.randint(1024, 65535)
|
||||
test_proxies.append(ProxyRaw(ip, port, protocol))
|
||||
logger.info(f"生成 {len(test_proxies)} 个测试代理: HTTP/HTTPS/SOCKS4/SOCKS5 各 3 个")
|
||||
return test_proxies
|
||||
51
app/plugins/speedx.py
Normal file
51
app/plugins/speedx.py
Normal file
@@ -0,0 +1,51 @@
|
||||
import re
|
||||
from typing import List
|
||||
from app.core.plugin_system import ProxyRaw
|
||||
from app.plugins.base import BaseHTTPPlugin
|
||||
from app.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"
|
||||
|
||||
def __init__(self):
|
||||
super().__init__()
|
||||
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",
|
||||
]
|
||||
|
||||
async def crawl(self) -> List[ProxyRaw]:
|
||||
results = []
|
||||
for url in self.urls:
|
||||
html = await self.fetch(url, timeout=30)
|
||||
if not html:
|
||||
continue
|
||||
|
||||
# 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()
|
||||
if not re.match(r"^\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3}$", ip):
|
||||
continue
|
||||
if not port.isdigit() or not (1 <= int(port) <= 65535):
|
||||
continue
|
||||
results.append(ProxyRaw(ip, int(port), protocol))
|
||||
|
||||
if results:
|
||||
logger.info(f"{self.display_name} 解析完成，获得 {len(results)} 个潜在代理")
|
||||
return results
|
||||
51
app/plugins/yundaili.py
Normal file
51
app/plugins/yundaili.py
Normal file
@@ -0,0 +1,51 @@
|
||||
import re
|
||||
from typing import List
|
||||
from bs4 import BeautifulSoup
|
||||
from app.core.plugin_system import ProxyRaw
|
||||
from app.plugins.base import BaseHTTPPlugin
|
||||
from app.core.log import logger
|
||||
|
||||
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"
|
||||
|
||||
def __init__(self):
|
||||
super().__init__()
|
||||
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 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
|
||||
|
||||
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 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