添加反爬策略1-User-Agent
在“爬取熊猫主播人气排行”随笔的基础上,修改__fetch_content方法
1 import re 2 3 from urllib import request 4 from random import choice 5 # 断点调试 6 7 class Spider(): 8 ''' 9 This is a class 10 ''' 11 # 私有方法 12 # 匹配所有字符 [\s\S]*? 非贪婪 13 url='https://www.panda.tv/all?pdt=1.27.psbar-menu.0.1oj9bbkfjbh' 14 headers = { 15 'User-Agent':'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.92 Safari/537.36', 16 # 'connection':'keep-alive' 17 } 18 19 USER_AGENTS = [ 20 "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; AcooBrowser; .NET CLR 1.1.4322; .NET CLR 2.0.50727)", 21 "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)", 22 "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)", 23 "Mozilla/5.0 (Windows; U; MSIE 9.0; Windows NT 9.0; en-US)", 24 "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)", 25 "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)", 26 "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)", 27 "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)", 28 "Mozilla/5.0 (X11; U; Linux; en-US) AppleWebKit/527+ (KHTML, like Gecko, Safari/419.3) Arora/0.6", 29 "Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.8.1.2pre) Gecko/20070215 K-Ninja/2.1.1", 30 "Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN; rv:1.9) Gecko/20080705 Firefox/3.0 Kapiko/3.0", 31 "Mozilla/5.0 (X11; Linux i686; U;) Gecko/20070322 Kazehakase/0.4.5", 32 "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", 33 "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11", 34 "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", 35 "Opera/9.80 (Macintosh; Intel Mac OS X 10.6.8; U; fr) Presto/2.9.168 Version/11.52" 36 ] 37 user_agent = choice(USER_AGENTS) 38 root_pattern = '<div class="video-info">([\w\W]*?)</div>' 39 name_pattern = '</i>([\w\W]*?)</span>' 40 number_pattern = '<span class="video-number">([\w\W]*?)</span>' 41 def __fetch_content(self): 42 43 # This is a HTTP request 44 # 反爬虫策略 45 46 #格式一 47 # req = request.Request(Spider.url,headers = Spider.headers) 48 49 #格式二 50 req = request.Request(Spider.url) 51 req.add_header('User-Agent', Spider.user_agent) 52 request = request.urlopen(request)
# 构建一个HTTPHandler处理器对象,支持处理HTTP的请求
#http_handler = request.HTTPHandler()
# 调用buid_opener()方法构建一个自定义的opener对象,参数是构建的处理器对象
#opener = request.build_opener(http_handler)
#request = request.Request(Spider.url)
#request.add_header('User-Agent', Spider.user_agent)
#request = opener.open(request)
53
56 # 字节码 57 htmls = request.read() 58 htmls = str(htmls,encoding='utf-8') 59 60 return htmls