分享个自己Python爬虫时的浏览器标识库

简介: 本人使用的Python3版本,python2未做测试如有问题很可能出在 toObj函数上toObj函数具体参考:https://stackoverflow.

本人使用的Python3版本,python2未做测试
如有问题很可能出在 toObj函数上
toObj函数具体参考:
https://stackoverflow.com/questions/1305532/convert-Python-dict-to-object

UserAgent.py

class 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 ua
import 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) 
相关文章
|
27天前
|
机器学习/深度学习 存储 数据挖掘
Python图像处理实用指南:PIL库的多样化应用
本文介绍Python中PIL库在图像处理中的多样化应用,涵盖裁剪、调整大小、旋转、模糊、锐化、亮度和对比度调整、翻转、压缩及添加滤镜等操作。通过具体代码示例,展示如何轻松实现这些功能,帮助读者掌握高效图像处理技术,适用于图片美化、数据分析及机器学习等领域。
59 20
|
2月前
|
数据采集 存储 XML
Python爬虫:深入探索1688关键词接口获取之道
在数字化经济中,数据尤其在电商领域的价值日益凸显。1688作为中国领先的B2B平台,其关键词接口对商家至关重要。本文介绍如何通过Python爬虫技术,合法合规地获取1688关键词接口,助力商家洞察市场趋势,优化营销策略。
|
17天前
|
测试技术 Python
【03】做一个精美的打飞机小游戏,规划游戏项目目录-分门别类所有的资源-库-类-逻辑-打包为可玩的exe-练习python打包为可执行exe-优雅草卓伊凡-持续更新-分享源代码和游戏包供游玩-1.0.2版本
【03】做一个精美的打飞机小游戏,规划游戏项目目录-分门别类所有的资源-库-类-逻辑-打包为可玩的exe-练习python打包为可执行exe-优雅草卓伊凡-持续更新-分享源代码和游戏包供游玩-1.0.2版本
72 31
【03】做一个精美的打飞机小游戏,规划游戏项目目录-分门别类所有的资源-库-类-逻辑-打包为可玩的exe-练习python打包为可执行exe-优雅草卓伊凡-持续更新-分享源代码和游戏包供游玩-1.0.2版本
|
2月前
|
XML JSON 数据库
Python的标准库
Python的标准库
182 77
|
19天前
|
数据采集 JSON 数据格式
Python爬虫:京东商品评论内容
京东商品评论接口为商家和消费者提供了重要工具。商家可分析评论优化产品,消费者则依赖评论做出购买决策。该接口通过HTTP请求获取评论内容、时间、点赞数等数据,支持分页和筛选好评、中评、差评。Python示例代码展示了如何调用接口并处理返回的JSON数据。应用场景包括产品优化、消费者决策辅助、市场竞争分析及舆情监测。
|
1月前
|
数据采集 供应链 API
Python爬虫与1688图片搜索API接口:深度解析与显著收益
在电子商务领域,数据是驱动业务决策的核心。阿里巴巴旗下的1688平台作为全球领先的B2B市场,提供了丰富的API接口,特别是图片搜索API(`item_search_img`),允许开发者通过上传图片搜索相似商品。本文介绍如何结合Python爬虫技术高效利用该接口,提升搜索效率和用户体验,助力企业实现自动化商品搜索、库存管理优化、竞品监控与定价策略调整等,显著提高运营效率和市场竞争力。
70 3
|
2月前
|
数据采集 存储 缓存
如何使用缓存技术提升Python爬虫效率
如何使用缓存技术提升Python爬虫效率
|
2月前
|
数据采集 Web App开发 监控
Python爬虫:爱奇艺榜单数据的实时监控
Python爬虫:爱奇艺榜单数据的实时监控
|
2月前
|
数据采集 JSON API
如何利用Python爬虫淘宝商品详情高级版(item_get_pro)API接口及返回值解析说明
本文介绍了如何利用Python爬虫技术调用淘宝商品详情高级版API接口(item_get_pro),获取商品的详细信息,包括标题、价格、销量等。文章涵盖了环境准备、API权限申请、请求构建和返回值解析等内容,强调了数据获取的合规性和安全性。
|
3月前
|
机器学习/深度学习 算法 数据挖掘
数据分析的 10 个最佳 Python 库
数据分析的 10 个最佳 Python 库
169 4
数据分析的 10 个最佳 Python 库

热门文章

最新文章