首页 技术 正文
技术 2022年11月18日
0 收藏 339 点赞 5,066 浏览 4465 个字

自动

1、设置动态的user agent

 import urllib.request as ure
import urllib.parse as upa
import random
from bs4 import BeautifulSoup # 动态设置user agent:
def set_user_agent():
agent_list = [
"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"
] headers = {'User-Agent':random.choice(agent_list)} return headers

2、设置代理池

 def IPspider(numpage, headers):     url = 'http://www.xicidaili.com/nn/'
# 分页读取
ipdict = {} #IP端口保存在字典中
for num in range(1,numpage+1):
# 观察可以发现每个分页的url都是“url+页码”的格式。
ipurl=url+str(num)
print('Now downloading the Page %d ...'%num)
# 获取网页内容
request=ure.Request(ipurl,headers=headers)
content=ure.urlopen(request).read()
# 创建BeautifulSoup对象
bs=BeautifulSoup(content,'html.parser')
res=bs.find_all('tr')
for item in res:
try:
#temp=[]
#tds=item.find_all('td')
#temp.append(tds[1].text.encode('utf-8'))
#print(tds[1].text)
#temp.append(tds[2].text.encode('utf-8'))
#writer.writerow(temp)
tds = item.find_all('td')
ipdict[tds[1].text] = tds[2].text
except IndexError:
pass
return ipdict
相关推荐
python开发_常用的python模块及安装方法
adodb:我们领导推荐的数据库连接组件bsddb3:BerkeleyDB的连接组件Cheetah-1.0:我比较喜欢这个版本的cheeta…
日期:2022-11-24 点赞:878 阅读:9,084
Educational Codeforces Round 11 C. Hard Process 二分
C. Hard Process题目连接:http://www.codeforces.com/contest/660/problem/CDes…
日期:2022-11-24 点赞:807 阅读:5,559
下载Ubuntn 17.04 内核源代码
zengkefu@server1:/usr/src$ uname -aLinux server1 4.10.0-19-generic #21…
日期:2022-11-24 点赞:569 阅读:6,408
可用Active Desktop Calendar V7.86 注册码序列号
可用Active Desktop Calendar V7.86 注册码序列号Name: www.greendown.cn Code: &nb…
日期:2022-11-24 点赞:733 阅读:6,181
Android调用系统相机、自定义相机、处理大图片
Android调用系统相机和自定义相机实例本博文主要是介绍了android上使用相机进行拍照并显示的两种方式,并且由于涉及到要把拍到的照片显…
日期:2022-11-24 点赞:512 阅读:7,818
Struts的使用
一、Struts2的获取  Struts的官方网站为:http://struts.apache.org/  下载完Struts2的jar包,…
日期:2022-11-24 点赞:671 阅读:4,901