Python中处理嵌套文件迭代器的策略与实践：避免迭代器耗尽

import requests

# 假设 hosts.txt 和 strings1.txt 存在
# hosts.txt:
# google.com
# target.com
# bing.com

# strings1.txt:
# x
# y
# z

with open('hosts.txt','r') as file:
    with open('strings1.txt','r') as strings:
        for line in file:
            host = line.strip()
            print(f"Processing host: {host}") # 调试输出
            for string in strings:
                param = string.strip()
                url = f"https://{host}/?test={param}"
                try:
                    resp = requests.get(url, timeout=5) # 增加超时设置
                    print(f'Results for {url} -> Status: {resp.status_code}')
                except requests.exceptions.RequestException as e:
                    print(f'Error requesting {url}: {e}')

import requests

# 1. 预加载 hosts.txt 内容到列表
try:
    with open("hosts.txt", "r") as f_hosts:
        hosts = list(map(str.strip, f_hosts))
except FileNotFoundError:
    print("Error: hosts.txt not found.")
    exit()

# 2. 预加载 strings1.txt 内容到列表
try:
    with open("strings1.txt", "r") as f_strings:
        strings = list(map(str.strip, f_strings))
except FileNotFoundError:
    print("Error: strings1.txt not found.")
    exit()

print("Hosts loaded:", hosts)
print("Strings loaded:", strings)

# 3. 嵌套遍历列表，构建URL并发送请求
for host in hosts:
    for param in strings:
        url = f"https://{host}/?test={param}"
        print(f"Attempting to request: {url}")
        try:
            # 发送GET请求，并设置超时，处理可能的网络错误
            response = requests.get(url, timeout=10)
            print(f"Results for {url} -> Status: {response.status_code}")
            # 你可以在这里进一步处理 response.text 或 response.json()
        except requests.exceptions.Timeout:
            print(f"Request to {url} timed out.")
        except requests.exceptions.ConnectionError as e:
            print(f"Connection error for {url}: {e}")
        except requests.exceptions.RequestException as e:
            print(f"An unexpected error occurred for {url}: {e}")

print("\nProcessing complete.")

Hosts loaded: ['google.com', 'target.com', 'bing.com']
Strings loaded: ['x', 'y', 'z']
Attempting to request: https://google.com/?test=x
Results for https://google.com/?test=x -> Status: 302
Attempting to request: https://google.com/?test=y
Results for https://google.com/?test=y -> Status: 302
Attempting to request: https://google.com/?test=z
Results for https://google.com/?test=z -> Status: 302
Attempting to request: https://target.com/?test=x
Results for https://target.com/?test=x -> Status: 200
Attempting to request: https://target.com/?test=y
Results for https://target.com/?test=y -> Status: 200
Attempting to request: https://target.com/?test=z
Results for https://target.com/?test=z -> Status: 200
Attempting to request: https://bing.com/?test=x
Results for https://bing.com/?test=x -> Status: 200
Attempting to request: https://bing.com/?test=y
Results for https://bing.com/?test=y -> Status: 200
Attempting to request: https://bing.com/?test=z
Results for https://bing.com/?test=z -> Status: 200

Processing complete.