import concurrent.futures
import requests

def fetch_url(url):
    try:
        response = requests.get(url)
        response.raise_for_status()
        return response.text
    except requests.exceptions.HTTPError as e:
        if e.response.status_code == 503:
            print(f"503 error occurred for {url}")
            # Handle 503 error
        else:
            raise

def main():
    urls = ["http://example.com/page1", "http://example.com/page2", ...]
    max_workers = 10  # 控制并發(fā)線程數(shù)量
    with concurrent.futures.ThreadPoolExecutor(max_workers=max_workers) as executor:
        futures = [executor.submit(fetch_url, url) for url in urls]
        for future in concurrent.futures.as_completed(futures):
            try:
                data = future.result()
                # Process data
            except Exception as e:
                print(f"Error: {e}")

if __name__ == "__main__":
    main()

import time
import requests

def fetch_url(url):
    try:
        response = requests.get(url)
        response.raise_for_status()
        return response.text
    except requests.exceptions.HTTPError as e:
        if e.response.status_code == 503:
            print(f"503 error occurred for {url}")
            # Handle 503 error
        else:
            raise

def main():
    urls = ["http://example.com/page1", "http://example.com/page2", ...]
    for url in urls:
        fetch_url(url)
        time.sleep(1)  # 設(shè)置請(qǐng)求間隔為 1 秒

if __name__ == "__main__":
    main()

import requests
import time
from requests.adapters import HTTPAdapter
from urllib3.util.retry import Retry

# 代理配置
proxyHost = "www.16yun.cn"
proxyPort = "5445"
proxyUser = "16QMSOML"
proxyPass = "280651"

# 用戶(hù)代理池
user_agents = [
    "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.3",
    "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/51.0.2704.103 Safari/537.36",
    "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/14.0.3 Safari/605.1.15",
    "Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:88.0) Gecko/20100101 Firefox/88.0"
]

def get_proxy():
    """獲取認(rèn)證代理"""
    return f"http://{proxyUser}:{proxyPass}@{proxyHost}:{proxyPort}"

def create_session():
    """創(chuàng)建帶有重試機(jī)制的會(huì)話"""
    session = requests.Session()
    retry_strategy = Retry(
        total=3,
        backoff_factor=1,
        status_forcelist=[500, 502, 503, 504]
    )
    adapter = HTTPAdapter(max_retries=retry_strategy)
    session.mount("http://", adapter)
    session.mount("https://", adapter)
    return session

def fetch_url(url):
    """獲取URL內(nèi)容"""
    session = create_session()
    proxy = get_proxy()
    headers = {"User-Agent": random.choice(user_agents)}
    
    try:
        response = session.get(
            url,
            proxies={"http": proxy, "https": proxy},
            headers=headers,
            timeout=10
        )
        response.raise_for_status()
        print(f"成功獲取: {url} [狀態(tài)碼: {response.status_code}]")
        return response.text
    except requests.exceptions.HTTPError as e:
        if e.response.status_code == 503:
            print(f"503錯(cuò)誤: {url} - 服務(wù)器暫時(shí)不可用")
            # 可以在這里添加重試邏輯或記錄到日志
        else:
            print(f"HTTP錯(cuò)誤 {e.response.status_code}: {url}")
        raise
    except Exception as e:
        print(f"請(qǐng)求異常: {url} - {str(e)}")
        raise

def main():
    """主函數(shù)"""
    urls = [
        "http://example.com/page1",
        "http://example.com/page2",
        "http://example.com/page3"
    ]
    
    for url in urls:
        try:
            fetch_url(url)
            time.sleep(1)  # 請(qǐng)求間隔
        except Exception as e:
            print(f"處理 {url} 時(shí)出錯(cuò): {e}")
            continue

if __name__ == "__main__":
    import random  # 為user_agents隨機(jī)選擇
    main()

import requests
from requests.adapters import HTTPAdapter
from requests.packages.urllib3.util.retry import Retry

def fetch_url(url):
    session = requests.Session()
    retries = Retry(total=5, backoff_factor=1, status_forcelist=[503])
    session.mount("http://", HTTPAdapter(max_retries=retries))
    try:
        response = session.get(url)
        response.raise_for_status()
        return response.text
    except requests.exceptions.HTTPError as e:
        if e.response.status_code == 503:
            print(f"503 error occurred for {url}")
            # Handle 503 error
        else:
            raise

def main():
    urls = ["http://example.com/page1", "http://example.com/page2", ...]
    for url in urls:
        fetch_url(url)

if __name__ == "__main__":
    main()

import concurrent.futures
import requests
import time
import random
from requests.adapters import HTTPAdapter
from requests.packages.urllib3.util.retry import Retry

user_agents = [
    "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.3",
    "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/51.0.2704.103 Safari/537.36",
    # 添加更多用戶(hù)代理
]

proxies = ["http://proxy1.example.com:8080", "http://proxy2.example.com:8080", ...]

def fetch_url(url):
    headers = {"User-Agent": random.choice(user_agents)}
    session = requests.Session()
    retries = Retry(total=5, backoff_factor=1, status_forcelist=[503])
    session.mount("http://", HTTPAdapter(max_retries=retries))
    try:
        response = session.get(url, headers=headers, proxies=random.choice(proxies))
        response.raise_for_status()
        return response.text
    except requests.exceptions.HTTPError as e:
        if e.response.status_code == 503:
            print(f"503 error occurred for {url}")
            # Handle 503 error
        else:
            raise

def main():
    urls = ["http://example.com/page1", "http://example.com/page2", ...]
    max_workers = 10  # 控制并發(fā)線程數(shù)量
    with concurrent.futures.ThreadPoolExecutor(max_workers=max_workers) as executor:
        futures = [executor.submit(fetch_url, url) for url in urls]
        for future in concurrent.futures.as_completed(futures):
            try:
                data = future.result()
                # Process data
            except Exception as e:
                print(f"Error: {e}")
            time.sleep(1)  # 設(shè)置請(qǐng)求間隔為 1 秒

if __name__ == "__main__":
    main()