songboran

  日志模块:

    为什么要实现日志模块

      能够方便的对程序进行测试

      能够方便记录程序的运行状态

      能够方便记录错误信息

    日志的实现

      代码:

# utils/log.py
import sys
import logging
from settings import LOG_FMT,LOG_LEVEL,LOG_FILENAME,LOG_DATEFMT


class Logger(object):

    def __init__(self):
        # 1. 获取一个logger对象
        self._logger = logging.getLogger()
        # 2. 设置format对象
        self.formatter = logging.Formatter(fmt=LOG_FMT,datefmt=LOG_DATEFMT)
        # 3. 设置日志输出
        # 3.1 设置文件日志模式
        self._logger.addHandler(self._get_file_handler(LOG_FILENAME))
        # 3.2 设置终端日志模式
        self._logger.addHandler(self._get_console_handler())
        # 4. 设置日志等级
        self._logger.setLevel(LOG_LEVEL)

    def _get_file_handler(self, filename):
        \'\'\'返回一个文件日志handler\'\'\'
        # 1. 获取一个文件日志handler
        filehandler = logging.FileHandler(filename=filename,encoding="utf-8")
        # 2. 设置日志格式
        filehandler.setFormatter(self.formatter)
        # 3. 返回
        return filehandler

    def _get_console_handler(self):
        \'\'\'返回一个输出到终端日志handler\'\'\'
        # 1. 获取一个输出到终端日志handler
        console_handler = logging.StreamHandler(sys.stdout)
        # 2. 设置日志格式
        console_handler.setFormatter(self.formatter)
        # 3. 返回handler
        return console_handler

    @property
    def logger(self):
        return self._logger

# 初始化并配一个logger对象,达到单例的
# 使用时,直接导入logger就可以使用
logger = Logger().logger

if __name__ == \'__main__\':
    logger.debug("调试信息")
    logger.info("状态信息")
    logger.warning("警告信息")
    logger.error("错误信息")
    logger.critical("严重错误信息")

配置文件settings.py

# 日志的配置信息
import logging
# 默认的配置 LOG_LEVEL=logging.INFO # 日志的默认等级 LOG_FMT=\'%(asctime)s %(filename)s [line:%(lineno)d] %(levelname)s: %(message)s\' LOG_DATEFMT=\'%Y-%m-%d %H:%M:%S\' # 默认时间格式 LOG_FILENAME=\'log.log\' # 默认日志文件名称

测试结果:

 

 

 

    http模块:

    目的:获取随机的User-Agent请求头

      步骤:

        1.准备User-Agent的列表

        2.写一个方法获取随机User-Agent的请求头

      代码:

import random

"""
5.2 http模块
我在从代理IP网站上抓取代理IP 和 检验代理IP时候, 为了不容易不服务器识别为是一个爬虫, 我们最好提供随机的User-Agent请求头.

目标: 获取随机User-Agent的请求头
步骤:
   1. 准备User-Agent的列表
   2. 实现一个方法, 获取随机User-Agent的请求头
"""

#   1. 准备User-Agent的列表
USER_AGENTS = [
    "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; AcooBrowser; .NET CLR 1.1.4322; .NET CLR 2.0.50727)",
    "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.0; Acoo Browser; SLCC1; .NET CLR 2.0.50727; Media Center PC 5.0; .NET CLR 3.0.04506)",
    "Mozilla/4.0 (compatible; MSIE 7.0; AOL 9.5; AOLBuild 4337.35; Windows NT 5.1; .NET CLR 1.1.4322; .NET CLR 2.0.50727)",
    "Mozilla/5.0 (Windows; U; MSIE 9.0; Windows NT 9.0; en-US)",
    "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Win64; x64; Trident/5.0; .NET CLR 3.5.30729; .NET CLR 3.0.30729; .NET CLR 2.0.50727; Media Center PC 6.0)",
    "Mozilla/5.0 (compatible; MSIE 8.0; Windows NT 6.0; Trident/4.0; WOW64; Trident/4.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; .NET CLR 1.0.3705; .NET CLR 1.1.4322)",
    "Mozilla/4.0 (compatible; MSIE 7.0b; Windows NT 5.2; .NET CLR 1.1.4322; .NET CLR 2.0.50727; InfoPath.2; .NET CLR 3.0.04506.30)",
    "Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN) AppleWebKit/523.15 (KHTML, like Gecko, Safari/419.3) Arora/0.3 (Change: 287 c9dfb30)",
    "Mozilla/5.0 (X11; U; Linux; en-US) AppleWebKit/527+ (KHTML, like Gecko, Safari/419.3) Arora/0.6",
    "Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.8.1.2pre) Gecko/20070215 K-Ninja/2.1.1",
    "Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN; rv:1.9) Gecko/20080705 Firefox/3.0 Kapiko/3.0",
    "Mozilla/5.0 (X11; Linux i686; U;) Gecko/20070322 Kazehakase/0.4.5",
    "Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.9.0.8) Gecko Fedora/1.9.0.8-1.fc10 Kazehakase/0.5.6",
    "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11",
    "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_3) AppleWebKit/535.20 (KHTML, like Gecko) Chrome/19.0.1036.7 Safari/535.20",
    "Opera/9.80 (Macintosh; Intel Mac OS X 10.6.8; U; fr) Presto/2.9.168 Version/11.52",
    "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.11 (KHTML, like Gecko) Chrome/20.0.1132.11 TaoBrowser/2.0 Safari/536.11",
    "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/21.0.1180.71 Safari/537.1 LBBROWSER",
    "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; WOW64; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; .NET4.0E; LBBROWSER)",
    "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; QQDownload 732; .NET4.0C; .NET4.0E; LBBROWSER)",
    "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.84 Safari/535.11 LBBROWSER",
    "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.1; WOW64; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; .NET4.0E)",
    "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; WOW64; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; .NET4.0E; QQBrowser/7.0.3698.400)",
    "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; QQDownload 732; .NET4.0C; .NET4.0E)",
    "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Trident/4.0; SV1; QQDownload 732; .NET4.0C; .NET4.0E; 360SE)",
    "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; QQDownload 732; .NET4.0C; .NET4.0E)",
    "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.1; WOW64; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; .NET4.0E)",
    "Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/21.0.1180.89 Safari/537.1",
    "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/21.0.1180.89 Safari/537.1",
    "Mozilla/5.0 (iPad; U; CPU OS 4_2_1 like Mac OS X; zh-cn) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8C148 Safari/6533.18.5",
    "Mozilla/5.0 (Windows NT 6.1; Win64; x64; rv:2.0b13pre) Gecko/20110307 Firefox/4.0b13pre",
    "Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:16.0) Gecko/20100101 Firefox/16.0",
    "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.11 (KHTML, like Gecko) Chrome/23.0.1271.64 Safari/537.11",
    "Mozilla/5.0 (X11; U; Linux x86_64; zh-CN; rv:1.9.2.10) Gecko/20100922 Ubuntu/10.10 (maverick) Firefox/3.6.10"
]

# 实现一个方法, 获取随机User-Agent的请求头
def get_request_headers():
    headers = {
        \'User-Agent\': random.choice(USER_AGENTS), #利用random模块的choice方法随机选取
        \'Accept\': \'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8\',# 接受类型
        \'Accept-Language\': \'en-US,en;q=0.5\',# 接收的语言
        \'Connection\': \'keep-alive\', #连接
        \'Accept-Encoding\': \'gzip, deflate\',# 压缩方式
    }

    return headers

if __name__ == \'__main__\':
    print(get_request_headers())
    print(get_request_headers())
    print(get_request_headers())

 

测试结果:

发现可以随机获取User-Agent

 

 

      

 

 

          

分类:

技术点:

相关文章: