这次给大家带来Python爬虫浏览器标识库,使用Python爬虫浏览器标识库的注意事项有哪些,下面就是实战案例,一起来看一下。

   UserAgent.pyclass toObj(object):def init(self, d):for a, b in d.items():            if isinstance(b, (list, tuple)):setattr(self, a, [toObj(x) if isinstance(x, dict) else x for x in b])            else:setattr(self, a, toObj(b) if isinstance(b, dict) else b)             '''
Android 设备
''' Android = toObj({    "Xiaomi": {        "Id": "Xiaomi",        "Name": "小米手机",        "UserAgent": "Mozilla/5.0 (Linux; U; Android 4.1.1; zh-cn;  MI2 Build/JRO03L) AppleWebKit/534.30 (KHTML, like Gecko) Version/4.0 Mobile Safari/534.30 XiaoMi/MiuiBrowser/1.0"},    "Meizu": {        "Id": "Meizu",        "Name": "魅族手机",        "UserAgent": "JUC (Linux; U; 2.3.5; zh-cn; MEIZU MX; 640*960) UCWEB8.5.1.179/145/33232"},    "Nexus7": {        "Id": "Nexus7",        "Name": "Nexus 7 (Tablet)",        "UserAgent": "Mozilla/5.0 (Linux; Android 4.1.1; Nexus 7 Build/JRO03D) AppleWebKit/535.19 (KHTML, like Gecko) Chrome/18.0.1025.166  Safari/535.19"},    "AndroidGalaxyS3": {        "Id": "AndroidGalaxyS3",        "Name": "Samsung Galaxy S3 (Handset)",        "UserAgent": "Mozilla/5.0 (Linux; U; Android 4.0.4; en-gb; GT-I9300 Build/IMM76D) AppleWebKit/534.30 (KHTML, like Gecko) Version/4.0 Mobile Safari/534.30"},    "AndroidGalaxyTab": {        "Id": "AndroidGalaxyTab",        "Name": "Samsung Galaxy Tab (Tablet)",        "UserAgent": "Mozilla/5.0 (Linux; U; Android 2.2; en-gb; GT-P1000 Build/FROYO) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0 Mobile Safari/533.1"}
})'''
国产浏览器
'''China = toObj({    "360se": {        "Id": "360se",        "Name": "360安全浏览器",        "UserAgent": "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; 360SE)"},    "360chrome": {        "Id": "360chrome",        "Name": "360极速浏览器",        "UserAgent": "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; 360Chrome)"},    "liebao": {        "Id": "liebao",        "Name": "猎豹浏览器",        "UserAgent": "Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/39.0.2171.99 Safari/537.36 LBBROWSER"},    "ucpc": {        "Id": "ucpc",        "Name": "UC浏览器电脑版",        "UserAgent": "Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/41.0.2272.118 UBrowser/5.1.2238.18 Safari/537.36"},    "uc": {        "Id": "uc",        "Name": "UC浏览器手机版",        "UserAgent": "UCWEB/2.0 (iOS; U; iPh OS 4_3_2; zh-CN; iPh4) U2/1.0.0 UCBrowser/8.6.0.199 U2/1.0.0 Mobile"}, "sougou": {        "Id": "sougou",        "Name": "搜狗浏览器",        "UserAgent": "Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/35.0.1916.153 Safari/537.36 SE 2.X MetaSr 1.0"}, "baidu": {        "Id": "baidu",        "Name": "百度浏览器",        "UserAgent": "Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/38.0.2125.122 BIDUBrowser/7.5 Safari/537.36"}, "maxthon": {        "Id": "maxthon",        "Name": "遨游浏览器",        "UserAgent": "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Maxthon 2.0)"}, "qq": {        "Id": "qq",        "Name": "QQ浏览器",        "UserAgent": "Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/43.0.2357.124 Safari/537.36 QQBrowser/9.0.2229.400"}, "mqq": {        "Id": "mqq",        "Name": "QQ浏览器手机版",        "UserAgent": "MQQBrowser/3.6/Adr (Linux; U; 4.0.3; zh-cn; HUAWEI U8818 Build/U8818V100R001C17B926;480*800)"}, "wechat": {        "Id": "wechat",        "Name": "微信内置浏览器",        "UserAgent": "Mozilla/5.0 (iPhone; CPU iPhone OS 6_1_3 like Mac OS X) AppleWebKit/536.26 (KHTML, like Gecko) Mobile/10B329 MicroMessenger/5.0.1"}
})'''
搜索引擎浏览器
'''Spider = toObj({    "Baidu": {        "Id": "Baidu",        "Name": "百度PC",        "UserAgent": "Mozilla/5.0 (compatible; Baiduspider/2.0; +http://www.baidu.com/search/spider.html)"},    "Baidum": {        "Id": "Baidum",        "Name": "百度移动端",        "UserAgent": "Mozilla/5.0 (Linux;u;Android 4.2.2;zh-cn;) AppleWebKit/534.46 (KHTML,like Gecko) Version/5.1 Mobile Safari/10600.6.3 (compatible; Baiduspider/2.0; +http://www.baidu.com/search/spider.html)"},    "BingBot": {        "Id": "BingBot",        "Name": "BingBot (Bing's spider)",        "UserAgent": "Mozilla/5.0 (compatible; bingbot/2.0; +http://www.bing.com/bingbot.htm)"},    "Googlebot": {        "Id": "Googlebot",        "Name": "Googlebot (Google's spider)",        "UserAgent": "Googlebot/2.1 (+http://www.googlebot.com/bot.html)"},    "Slurp": {        "Id": "Slurp",        "Name": "Slurp! (Yahoo's spider)",        "UserAgent": "Mozilla/5.0 (compatible; Yahoo! Slurp; http://help.yahoo.com/help/us/ysearch/slurp)"}
})'''
Mac OS
'''Safari = toObj({    "SafariMac": {        "Id": "SafariMac",        "Name": "Safari on Mac",        "UserAgent": "Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_6; en-US) AppleWebKit/533.20.25 (KHTML, like Gecko) Version/5.0.4 Safari/533.20.27"},    "SafariWin": {        "Id": "SafariWin",        "Name": "Safari on Windows",        "UserAgent": "Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/533.20.25 (KHTML, like Gecko) Version/5.0.4 Safari/533.20.27"},    "SafariiPad": {        "Id": "SafariiPad",        "Name": "Safari on iPad",        "UserAgent": "Mozilla/5.0 (iPad; CPU OS 5_0 like Mac OS X) AppleWebKit/534.46 (KHTML, like Gecko) Version/5.1 Mobile/9A334 Safari/7534.48.3"},    "SafariiPhone": {        "Id": "SafariiPhone",        "Name": "Safari on iPhone",        "UserAgent": "Mozilla/5.0 (iPhone; CPU iPhone OS 5_0 like Mac OS X) AppleWebKit/534.46 (KHTML, like Gecko) Version/5.1 Mobile/9A334 Safari/7534.48.3"}
})'''
Opera 欧朋
'''Opera = toObj({    "OperaMac": {        "Id": "OperaMac",        "Name": "Opera on Mac",        "UserAgent": "Opera/9.80 (Macintosh; Intel Mac OS X 10.6.8; U; en) Presto/2.9.168 Version/11.52"},    "OperaWin": {        "Id": "OperaWin",        "Name": "Opera on Windows",        "UserAgent": "Opera/9.80 (Windows NT 6.1; WOW64; U; en) Presto/2.10.229 Version/11.62"}
})'''
Chrome
'''Chrome = toObj({    "ChromeAndroidMobile": {        "Id": "ChromeAndroidMobile",        "Name": "Chrome on Android Mobile",        "UserAgent": "Mozilla/5.0 (Linux; Android 4.0.4; Galaxy Nexus Build/IMM76B) AppleWebKit/535.19 (KHTML, like Gecko) Chrome/18.0.1025.133 Mobile Safari/535.19"},    "ChromeAndroidTablet": {        "Id": "ChromeAndroidTablet",        "Name": "Chrome on Android Tablet",        "UserAgent": "Mozilla/5.0 (Linux; Android 4.1.2; Nexus 7 Build/JZ054K) AppleWebKit/535.19 (KHTML, like Gecko) Chrome/18.0.1025.166 Safari/535.19"},    "ChromeMac": {        "Id": "ChromeMac",        "Name": "Chrome on Mac",        "UserAgent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_2) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/27.0.1453.93 Safari/537.36"},    "ChromeUbuntu": {        "Id": "ChromeUbuntu",        "Name": "Chrome on Ubuntu",        "UserAgent": "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/535.11 (KHTML, like Gecko) Ubuntu/11.10 Chromium/27.0.1453.93 Chrome/27.0.1453.93 Safari/537.36"},    "ChromeWin": {        "Id": "ChromeWin",        "Name": "Chrome on Windows",        "UserAgent": "Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/27.0.1453.94 Safari/537.36"},    "ChromeiPhone": {        "Id": "ChromeiPhone",        "Name": "Chrome on iPhone",        "UserAgent": "Mozilla/5.0 (iPhone; CPU iPhone OS 6_1_4 like Mac OS X) AppleWebKit/536.26 (KHTML, like Gecko) CriOS/27.0.1453.10 Mobile/10B350 Safari/8536.25"}
})'''
IE
'''IE = toObj({    "IE10": {        "Id": "IE10",        "Name": "Internet Explorer 10",        "UserAgent": "Mozilla/5.0 (compatible; WOW64; MSIE 10.0; Windows NT 6.2)"},    "IE6": {        "Id": "IE6",        "Name": "Internet Explorer 6",        "UserAgent": "Mozilla/4.0 (Windows; MSIE 6.0; Windows NT 5.2)"},    "IE7": {        "Id": "IE7",        "Name": "Internet Explorer 7",        "UserAgent": "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.0)"},    "IE8": {        "Id": "IE8",        "Name": "Internet Explorer 8",        "UserAgent": "Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.0; Trident/4.0)"},    "IE9": {        "Id": "IE9",        "Name": "Internet Explorer 9",        "UserAgent": "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Trident/5.0)"}
})'''
Firefox
'''Firefox = toObj({    "FFAndroidHandset": {        "Id": "FFAndroidHandset",        "Name": "Firefox on Android Mobile",        "UserAgent": "Mozilla/5.0 (Android; Mobile; rv:14.0) Gecko/14.0 Firefox/14.0"},    "FFAndroidTablet": {        "Id": "FFAndroidTablet",        "Name": "Firefox on Android Tablet",        "UserAgent": "Mozilla/5.0 (Android; Tablet; rv:14.0) Gecko/14.0 Firefox/14.0"},    "FFMac": {        "Id": "FFMac",        "Name": "Firefox on Mac",        "UserAgent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10.8; rv:21.0) Gecko/20100101 Firefox/21.0"},    "FFUbuntu": {        "Id": "FFUbuntu",        "Name": "Firefox on Ubuntu",        "UserAgent": "Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:21.0) Gecko/20130331 Firefox/21.0"},    "FFWin": {        "Id": "FFWin",        "Name": "Firefox on Windows",        "UserAgent": "Mozilla/5.0 (Windows NT 6.2; WOW64; rv:21.0) Gecko/20100101 Firefox/21.0"}
})'''
Windows Phone
'''WinPhone = toObj({    "Win7Phone": {        "Id": "Win7Phone",        "Name": "Windows Phone 7",        "UserAgent": "Mozilla/4.0 (compatible; MSIE 7.0; Windows Phone OS 7.0; Trident/3.1; IEMobile/7.0; LG; GW910)"},    "Win75Phone": {        "Id": "Win75Phone",        "Name": "Windows Phone 7.5",        "UserAgent": "Mozilla/5.0 (compatible; MSIE 9.0; Windows Phone OS 7.5; Trident/5.0; IEMobile/9.0; SAMSUNG; SGH-i917)"},    "Win8Phone": {        "Id": "Win8Phone",        "Name": "Windows Phone 8",        "UserAgent": "Mozilla/5.0 (compatible; MSIE 10.0; Windows Phone 8.0; Trident/6.0; IEMobile/10.0; ARM; Touch; NOKIA; Lumia 920)"}
})'''
iOS
'''iOS = toObj({    "iPad": {        "Id": "iPad",        "Name": "iPad",        "UserAgent": "Mozilla/5.0 (iPad; CPU OS 5_0 like Mac OS X) AppleWebKit/534.46 (KHTML, like Gecko) Version/5.1 Mobile/9A334 Safari/7534.48.3"},    "iPhone": {        "Id": "iPhone",        "Name": "iPhone",        "UserAgent": "Mozilla/5.0 (iPhone; CPU iPhone OS 5_0 like Mac OS X) AppleWebKit/534.46 (KHTML, like Gecko) Version/5.1 Mobile/9A334 Safari/7534.48.3"},    "iPod": {        "Id": "iPod",        "Name": "iPod",        "UserAgent": "Mozilla/5.0 (iPod; U; CPU like Mac OS X; en) AppleWebKit/420.1 (KHTML, like Gecko) Version/3.0 Mobile/3A101a Safari/419.3"}
})
Other = toObj({    "BlackBerry": {        "Id": "BlackBerry",        "Name": "BlackBerry - Playbook 2.1",        "UserAgent": "Mozilla/5.0 (PlayBook; U; RIM Tablet OS 2.1.0; en-US) AppleWebKit/536.2+ (KHTML, like Gecko) Version/7.2.1.0 Safari/536.2+"},    "MeeGo": {        "Id": "MeeGo",        "Name": "MeeGo - Nokia N9",        "UserAgent": "Mozilla/5.0 (MeeGo; NokiaN9) AppleWebKit/534.13 (KHTML, like Gecko) NokiaBrowser/8.5.0 Mobile Safari/534.13"}
})

Default = Chrome.ChromeWin.UserAgent

使用

import  UserAgent as uaimport requests
print("默认标识",ua.Default)
print("小米标识",ua.Android.Xiaomi.UserAgent)
_headers={    'Accept-Language': 'zh-CN,zh;q=0.8',    'Content-Type': 'text/html;Charset=utf-8',    "User-Agent":ua.Android.Xiaomi.UserAgent
}
rd = requests.get("http://www.jianshu.com/", params=None, headers=_headers)
rd.encoding = 'utf-8'print(rd.text)

Python爬虫浏览器标识库相关推荐

  1. python爬虫基础-requests库

    python爬虫基础-requests库 python爬虫 1.什么是爬虫? 通过编写程序,模拟浏览器上网,然后让其去互联网上抓取数据的过程. 注意:浏览器抓取的数据对应的页面是一个完整的页面. 为什 ...

  2. Python爬虫之selenium库使用详解

    Python爬虫之selenium库使用详解 本章内容如下: 什么是Selenium selenium基本使用 声明浏览器对象 访问页面 查找元素 多个元素查找 元素交互操作 交互动作 执行JavaS ...

  3. python爬虫之urllib库详解

    python爬虫之urllib库详解 前言 一.urllib库是什么? 二.urllib库的使用 urllib.request模块 urllib.parse模块 利用try-except,进行超时处理 ...

  4. Python爬虫环境常用库安装

    Python爬虫环境常用库安装 1:urllib urllib.request 这两个库是python自带的库,不需要重新安装,在python中输入如下代码: import urllib import ...

  5. python爬虫(四)_urllib2库的基本使用

    python爬虫(四)_urllib2库的基本使用 本篇我们将开始学习如何进行网页抓取,更多内容请参考:python学习指南 urllib2库的基本使用 所谓网页抓取,就是把URL地址中指定的网络资源 ...

  6. python爬虫浏览器伪装和设置代理ip

    1.python爬虫浏览器伪装 #导入urllib.request模块 import urllib.request#设置请求头 headers=("User-Agent",&quo ...

  7. Python爬虫之Scrapy库的下载和安装

    Python爬虫之Scrapy库的下载和安装 下载scrapy库 1.点击https://www.lfd.uci.edu/~gohlke/pythonlibs,进入该网页后Ctrl+F输入scrapy ...

  8. python request库_【Python爬虫】Request库入门

    什么是爬虫? 网络爬虫(又被称为网页蜘蛛,网络机器人,在FOAF社区中间,更经常的称为网页追逐者),是一种按照一定的规则,自动地抓取万维网信息的程序或者脚本.另外一些不常使用的名字还有蚂蚁.自动索引. ...

  9. 【Python爬虫】Request库入门

    什么是爬虫? 网络爬虫(又被称为网页蜘蛛,网络机器人,在FOAF社区中间,更经常的称为网页追逐者),是一种按照一定的规则,自动地抓取万维网信息的程序或者脚本.另外一些不常使用的名字还有蚂蚁.自动索引. ...

  10. python爬虫的常用库

    1.requests 这个库是爬虫最常用的一个库. 2.Selenium Selenium 这是一个自动化测试工具,利用它我们可以驱动浏览器执行特定的动作,如点击.下拉等操作 对于一些用JS做谊染的页 ...

最新文章

  1. Oracle学习笔记:a inner join b与from a,b where a.x=b.x的差异
  2. 数据库面试题【七、InnoDB索引和MyISAM索引的区别】
  3. 赌还是不赌 你应该辞职去创业吗?
  4. 总结-Linux基础指令
  5. 前景检测算法 (GMM)
  6. 谁有 CaliberRM.2005.Enterprise 版 或CaliberRM.2006 注册码?
  7. 百胜中国供应链管理中心正式开工落户上海嘉定;百度发布第六代量产无人车 | 美通企业日报...
  8. ItemCF的Python实现
  9. BUUCTF MISC刷题
  10. Graph U-Nets [gPool gUnpool] 图分类 节点分类 图池化 ICML 2019
  11. 职场四种人:打工者、职业人、企业人和社会人,你是那种人?
  12. B站JavaScript从入门到精通智能社Blue石川老师视频部分代码_轮播图
  13. 机器人合肥乐博_乐博机器人编程——让机器人陪伴全国儿童成长
  14. Vue3入门到精通--reactive以及reactive相关函数
  15. (改进GM(1,1)模型)灰色残差马尔科夫预测模型的matlab实现
  16. 不一般的Cover Letter
  17. BIGGAN代码以及训练参数,超级清晰版(CIFAR10数据集生成)
  18. WordPress自定义gravatar头像,缓存Gravatar头像为网站提速
  19. WAYOS版本OEM,替换WAYOS的LOGO,江边小鸟杰作啊
  20. R语言Logistic回归模型案例(绘制列线图、校正曲线):研究低出生体重婴儿的核心影像因素

热门文章

  1. 所以,网络工程师能从事什么工作?
  2. Filtered request failed
  3. unipp怎么打包微信公众号_uni-app微信小程序运行和打包
  4. 系统架构设计师考点全纪要(自己整理,本人一次稳过)
  5. 常规的几个API接口(也包括比价)
  6. 配置OpenLDAP使用TLS通信
  7. Windows 桌面应用开发入门
  8. 矩阵键盘——按下矩阵按键,数码管显示出位置对应的字符(0123 4567 89Ab CdEF)
  9. 高级架构师_Elasticsearch_第二章kibana+IK分词器安装+索引操作+ 映射操作
  10. 一个屌丝程序猿的人生(七)