Python 爬虫技巧：百度页面重定向的自动跟踪与处理

python
import urllib.request

def fetch_url(url):
    try:
        response = urllib.request.urlopen(url)
        return response.read().decode('utf-8')
    except urllib.error.URLError as e:
        print(f"Failed to reach a server: {e.reason}")
        return None

# 使用示例
content = fetch_url('http://www.baidu.com')

python
from urllib import request, error

class RedirectHandler(request.HTTPRedirectHandler):
    def __init__(self, max_redirects=10):
        super().__init__()
        self.max_redirects = max_redirects
        self.redirect_count = 0

    def http_error_302(self, req, fp, code, msg, headers):
        self.redirect_count += 1
        if self.redirect_count >= self.max_redirects:
            raise error.HTTPError(req.full_url, code, msg, headers, fp)
        return super().http_error_302(req, fp, code, msg, headers)

def fetch_url_with_redirect_handling(url):
    opener = request.build_opener(RedirectHandler())
    request.install_opener(opener)
    try:
        with request.urlopen(url) as response:
            return response.read().decode('utf-8')
    except error.HTTPError as e:
        print(f"HTTP error: {e.code}")
        return None
    except error.URLError as e:
        print(f"URL error: {e.reason}")
        return None

# 使用示例
content = fetch_url_with_redirect_handling('http://www.baidu.com')

import http.client
from urllib.parse import urlparse
from http.client import HTTPResponse

# 代理服务器设置
proxyHost = "dfefefr"
proxyPort = "5445"
proxyUser = "16QMSOML"
proxyPass = "280651"

class PersistentHTTPConnection(http.client.HTTPConnection):
    def __init__(self, host, port=None, timeout=socket._GLOBAL_DEFAULT_TIMEOUT, 
                 proxy_info=None):
        super().__init__(host, port, timeout)
        self.proxy_info = proxy_info

    def connect(self):
        # 连接到代理服务器
        super().connect()
        if self.proxy_info:
            # 使用 Basic Auth 认证
            username, password = self.proxy_info
            credentials = f"{username}:{password}"
            credentials = "Basic " + credentials.encode('utf-8').base64().decode('utf-8')
            self.sock.sendall(b"Proxy-Authorization: " + credentials.encode('utf-8'))

class PersistentHTTPConnectionWithProxy(PersistentHTTPConnection):
    def __enter__(self):
        return self

    def __exit__(self, exc_type, exc_val, exc_tb):
        self.close()

def fetch_with_persistent_connection(url, proxy_info=None):
    parsed_url = urlparse(url)
    conn = PersistentHTTPConnectionWithProxy(parsed_url.netloc, proxy_info=proxy_info)
    conn.connect()  # 连接到代理服务器
    conn.request("GET", parsed_url.path)
    response = conn.getresponse()
    if response.status == 200:
        return response.read().decode('utf-8')
    else:
        print(f"HTTP error: {response.status}")
        return None

# 使用示例
content = fetch_with_persistent_connection('http://www.baidu.com', (proxyUser, proxyPass))