python爬蟲利用代理池更換IP的方法步驟

# 安裝python虛擬環境， python環境最好為python3.6，再往上的話，安裝依賴時會報錯
sudo apt update
sudo apt install python3.6
pip3 install virtualenv
virtualenv venv --python=python3.6
source venv/bin/activate

# 安裝redis
sudo apt install redis-server
# 啟動redis server
redis-server

git clone https://github.com/jhao104/proxy_pool.git
cd proxy_pool
pip install -r requirements.txt

# 修改setting.py 

# 配置API服務

HOST = "0.0.0.0"    # IP
PORT = 5010     # 監聽端口

# 配置數據庫

# 以下為三個示例，根據redis的配置，選擇其中一種即可
# 一般啟動redis時如果沒有配置文件，那麼選擇第一種即可
# 1. Redis IP: 127.0.0.1 Port: 6379
DB_CONN = 'redis://@127.0.0.1:6379'
# 2. Redis IP: 127.0.0.1 Port: 6379 Password: 123456
DB_CONN = 'redis://:[email protected]:6379'
# 3. Redis IP: 127.0.0.1 Port: 6379 Password: 123456 DB: 15
DB_CONN = 'redis://:[email protected]:6379/15'

 

# 配置 ProxyFetcher

PROXY_FETCHER = [
 "freeProxy01",  # 這裡是啟用的代理抓取方法名，所有fetch方法位於fetcher/proxyFetcher.py
 "freeProxy02",
 # ....
]

# 可以用tmux開三個窗口

# 啟動調度程序
python proxyPool.py schedule

# 啟動webApi服務
python proxyPool.py server

import requests

def get_proxy():
 return requests.get("http://127.0.0.1:5010/get/").json()

def delete_proxy(proxy):
 requests.get("http://127.0.0.1:5010/delete/?proxy={}".format(proxy))

# your spider code

def getHtml():
 # ....
 retry_count = 5
 proxy = get_proxy().get("proxy")
 while retry_count > 0:
  try:
   html = requests.get('http://www.example.com', proxies={"http": "http://{}".format(proxy)})
   # 使用代理訪問
   return html
  except Exception:
   retry_count -= 1
 # 刪除代理池中代理
 delete_proxy(proxy)
 return None