python 爬虫 user-agent 生成

有些网站做了反爬技术，如：比较初级的通过判断请求头部中的user-agent字段来检测是否通过浏览器访问的。

在爬这类网站时需要模拟user-agent

import random
import re
from typing import dict, list


class useragent:

    '''
    代理
    '''
    __filepath = 'user-agent.txt'

    '''
    对象实例
    '''
    __instance = none

    '''
    代理浏览器
    '''
    __dict: dict[str, list] = {}

    '''
    代理浏览器
    '''
    __list: list[str] = []

    '''
    初始化
    '''

    def __init__(self):
        reg = re.compile(r'firefox|chrome|msie|opera', re.i)
        with open(self.__filepath, 'r', encoding='utf_8_sig') as f:
            for r in f:
                result = reg.search(r) and reg.search(r).group().lower()
                if result and (not result in self.__dict):
                    self.__dict[result] = []
                result and self.__dict[result].append(r.strip())
                self.__list.append(r.strip())

    '''
    单例 - 构造函数
    '''
    def __new__(cls):
        if not cls.__instance:
            cls.__instance = super(useragent, cls).__new__(cls)
        return cls.__instance

    '''
    谷歌
    '''
    @property
    def chrome(self) -> str:
        return random.choice(self.__dict['chrome'])

    '''
    火狐
    '''
    @property
    def firefox(self) -> str:
        return random.choice(self.__dict['firefox'])

    '''
    ie
    '''
    @property
    def ie(self) -> str:
        return random.choice(self.__dict['msie'])

    '''
    opera 浏览器
    '''
    @property
    def opera(self) -> str:
        return random.choice(self.__dict['opera'])

    '''
    随机
    '''

    def random(self) -> str:
        return random.choice(self.__list)


    '''
    迭代
    '''
    def __iter__(self):
        self.__iter = iter(self.__list)
        return self

    '''
    下一个
    '''
    def __next__(self):
        return next(self.__iter)

    '''
    索引
    '''
    def __getitem__(self, index) -> str or list(str):
        return self.__list[index]


useragent = useragent()
print(useragent.random())

'''
for n in useragent:
    print(n)
'''

 

user-agent.txt

mozilla/5.0 (windows nt 6.1) applewebkit/537.36 (khtml, like gecko) chrome/41.0.2228.0 safari/537.36
mozilla/5.0 (macintosh; intel mac os x 10_10_1) applewebkit/537.36 (khtml, like gecko) chrome/41.0.2227.1 safari/537.36
mozilla/5.0 (x11; linux x86_64) applewebkit/537.36 (khtml, like gecko) chrome/41.0.2227.0 safari/537.36
mozilla/5.0 (windows nt 6.1; wow64) applewebkit/537.36 (khtml, like gecko) chrome/41.0.2227.0 safari/537.36
mozilla/5.0 (windows nt 6.3; wow64) applewebkit/537.36 (khtml, like gecko) chrome/41.0.2226.0 safari/537.36
mozilla/5.0 (windows nt 6.4; wow64) applewebkit/537.36 (khtml, like gecko) chrome/41.0.2225.0 safari/537.36
mozilla/5.0 (windows nt 6.3; wow64) applewebkit/537.36 (khtml, like gecko) chrome/41.0.2225.0 safari/537.36
mozilla/5.0 (windows nt 5.1) applewebkit/537.36 (khtml, like gecko) chrome/41.0.2224.3 safari/537.36
mozilla/5.0 (windows nt 10.0) applewebkit/537.36 (khtml, like gecko) chrome/40.0.2214.93 safari/537.36
mozilla/5.0 (macintosh; intel mac os x 10_10_1) applewebkit/537.36 (khtml, like gecko) chrome/37.0.2062.124 safari/537.36
mozilla/5.0 (windows nt 6.3; win64; x64) applewebkit/537.36 (khtml, like gecko) chrome/37.0.2049.0 safari/537.36
mozilla/5.0 (windows nt 4.0; wow64) applewebkit/537.36 (khtml, like gecko) chrome/37.0.2049.0 safari/537.36
mozilla/5.0 (windows nt 6.1; wow64) applewebkit/537.36 (khtml, like gecko) chrome/36.0.1985.67 safari/537.36
mozilla/5.0 (windows nt 5.1) applewebkit/537.36 (khtml, like gecko) chrome/36.0.1985.67 safari/537.36
mozilla/5.0 (x11; openbsd i386) applewebkit/537.36 (khtml, like gecko) chrome/36.0.1985.125 safari/537.36
mozilla/5.0 (macintosh; intel mac os x 10_9_2) applewebkit/537.36 (khtml, like gecko) chrome/36.0.1944.0 safari/537.36
mozilla/5.0 (windows nt 5.1) applewebkit/537.36 (khtml, like gecko) chrome/35.0.3319.102 safari/537.36
mozilla/5.0 (windows nt 5.1) applewebkit/537.36 (khtml, like gecko) chrome/35.0.2309.372 safari/537.36
mozilla/5.0 (windows nt 5.1) applewebkit/537.36 (khtml, like gecko) chrome/35.0.2117.157 safari/537.36
mozilla/5.0 (macintosh; intel mac os x 10_9_3) applewebkit/537.36 (khtml, like gecko) chrome/35.0.1916.47 safari/537.36
mozilla/5.0 (windows nt 5.1) applewebkit/537.36 (khtml, like gecko) chrome/34.0.1866.237 safari/537.36
mozilla/5.0 (x11; linux x86_64) applewebkit/537.36 (khtml, like gecko) chrome/34.0.1847.137 safari/4e423f
mozilla/5.0 (windows nt 5.1) applewebkit/537.36 (khtml, like gecko) chrome/34.0.1847.116 safari/537.36 mozilla/5.0 (ipad; u; cpu os 3_2 like mac os x; en-us) applewebkit/531.21.10 (khtml, like gecko) version/4.0.4 mobile/7b334b safari/531.21.10
mozilla/5.0 (x11; linux x86_64) applewebkit/537.36 (khtml, like gecko) chrome/33.0.1750.517 safari/537.36
mozilla/5.0 (windows nt 6.2; win64; x64) applewebkit/537.36 (khtml, like gecko) chrome/32.0.1667.0 safari/537.36
mozilla/5.0 (macintosh; intel mac os x 10_9_0) applewebkit/537.36 (khtml, like gecko) chrome/32.0.1664.3 safari/537.36
mozilla/5.0 (macintosh; intel mac os x 10_8_0) applewebkit/537.36 (khtml, like gecko) chrome/32.0.1664.3 safari/537.36
mozilla/5.0 (windows nt 5.1) applewebkit/537.36 (khtml, like gecko) chrome/31.0.1650.16 safari/537.36
mozilla/5.0 (windows nt 6.1; wow64) applewebkit/537.36 (khtml, like gecko) chrome/31.0.1623.0 safari/537.36
......
mozilla/5.0 (macintosh; u; intel mac os x 10_5_8; zh-cn) applewebkit/533.18.1 (khtml, like gecko) version/5.0.2 safari/533.18.5

 

百度网盘

链接：https://pan.baidu.com/s/1ramkiyjvsi2_gxbxypj1dg
提取码：hak8