first commit
This commit is contained in:
祀梦
61
plugins/fate0.py
Normal file
61
plugins/fate0.py
Normal file
@@ -0,0 +1,61 @@
|
||||
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
|
||||
|
||||
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():
|
||||
continue
|
||||
try:
|
||||
data = json.loads(line)
|
||||
ip = data.get('host')
|
||||
port = data.get('port')
|
||||
protocol = data.get('type', '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())
|
||||
74
plugins/ip3366.py
Normal file
74
plugins/ip3366.py
Normal file
@@ -0,0 +1,74 @@
|
||||
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
|
||||
|
||||
VALID_PROTOCOLS = ['http', 'https', 'socks4', 'socks5']
|
||||
|
||||
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
|
||||
|
||||
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")
|
||||
|
||||
|
||||
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())
|
||||
69
plugins/ip89.py
Normal file
69
plugins/ip89.py
Normal file
@@ -0,0 +1,69 @@
|
||||
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
|
||||
|
||||
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)
|
||||
]
|
||||
|
||||
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
|
||||
|
||||
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")
|
||||
|
||||
|
||||
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())
|
||||
79
plugins/kuaidaili.py
Normal file
79
plugins/kuaidaili.py
Normal file
@@ -0,0 +1,79 @@
|
||||
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
|
||||
|
||||
VALID_PROTOCOLS = ['http', 'https', 'socks4', 'socks5']
|
||||
|
||||
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
|
||||
|
||||
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")
|
||||
|
||||
|
||||
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())
|
||||
64
plugins/proxylist_download.py
Normal file
64
plugins/proxylist_download.py
Normal file
@@ -0,0 +1,64 @@
|
||||
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 asyncio
|
||||
|
||||
class ProxyListDownloadPlugin(BasePlugin):
|
||||
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"
|
||||
]
|
||||
|
||||
async def parse(self, html):
|
||||
if not html:
|
||||
return
|
||||
|
||||
lines = html.split('\r\n')
|
||||
if len(lines) <= 1:
|
||||
lines = html.split('\n')
|
||||
|
||||
count = 0
|
||||
for line in lines:
|
||||
line = line.strip()
|
||||
if not line:
|
||||
continue
|
||||
|
||||
if ':' in line:
|
||||
parts = line.split(':')
|
||||
if len(parts) >= 2:
|
||||
ip = parts[0]
|
||||
port = parts[1]
|
||||
protocol = 'http' if 'type=http' in self.current_url else 'https'
|
||||
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 = 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())
|
||||
78
plugins/speedx.py
Normal file
78
plugins/speedx.py
Normal file
@@ -0,0 +1,78 @@
|
||||
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
|
||||
|
||||
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"
|
||||
]
|
||||
|
||||
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:
|
||||
continue
|
||||
|
||||
if ':' in line:
|
||||
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):
|
||||
continue
|
||||
|
||||
# 验证端口是数字
|
||||
if not port.isdigit() or not (1 <= int(port) <= 65535):
|
||||
continue
|
||||
|
||||
# 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())
|
||||
79
plugins/yundaili.py
Normal file
79
plugins/yundaili.py
Normal file
@@ -0,0 +1,79 @@
|
||||
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
|
||||
|
||||
VALID_PROTOCOLS = ['http', 'https', 'socks4', 'socks5']
|
||||
|
||||
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
|
||||
|
||||
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")
|
||||
|
||||
|
||||
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())
|
||||
Reference in New Issue
Block a user