Scrapy 设置随机 User-Agent

Posted 2020-12-02 yuqiangli0616

方式一：在每个 Spider中设置（针对单个Spider）

class TencentSpider(scrapy.Spider):
    name = ‘tencent‘
    allowed_domains = [‘hr.tencent.com‘]

   
    headers = {
        ‘User-Agent‘: ‘Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (Khtml, like Gecko) Chrome/63.0.3239.132 Safari/537.36‘,
    }

    def parse(self, response):
        # 找到最后一页的页码
        page_num = response.xpath(‘//div[@class="pagenav"]/a[last()-1]/text()‘).extract()[0]
        # 生成每一页的请求
        for i in range(1, int(page_num) + 1):
            url = "https://hr.tencent.com/position.php?&start=%s#a" % (i * 10)
            yield Request(url=url, headers=TencentSpider.headers, callback=self.parse)

方式二： 在中间件中设置（全局）

在配置文件中设置User-Agent集合

# 请求头
CUSTOM_USER_AGENT = [
    "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",
]

View Code

编写中间件逻辑

# 请求头添加随机user-agent
class RandomUserAgentMiddleware(object):

    def __init__(self, agents):
        self.agent = agents

    @classmethod
    def from_crawler(cls, crawler):
        return cls(
            agents=crawler.settings.get(‘CUSTOM_USER_AGENT‘)
        )

    def process_request(self, request, spider):
        request.headers.setdefault(‘User-Agent‘, random.choice(self.agent))

View Code

激活中间件，并禁用默认的User-Agent中间件

DOWNLOADER_MIDDLEWARES = {
    ‘scrapy.downloadermiddleware.useragent.UserAgentMiddleware‘: None,
    ‘day1.middlewares.RandomUserAgentMiddleware‘: 10,
}

 查看请求头信息

响应 response 中封装了请求对应request，因此可以根据request中查看该响应请求时的请求头信息。

    def parse(self, response):
        print(response.request)
        print(response.request.headers[‘User-Agent‘])

使用 fake-useragent 模块随机生成 User-Agent

上面的user-agent是在配置文件中预先设定好的，我们也可以使用python模块 fake-useragent  生成user-agent

安装：

pip install fake-useragent

简单使用：

from fake_useragent import UserAgent
ua = UserAgent()
#ie浏览器的user agent
print(ua.ie)
Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Trident/5.0; chromeframe/13.0.782.215)


#opera浏览器
print(ua.opera)

#chrome浏览器
print(ua.chrome)

#firefox浏览器
print(ua.firefox)

#safri浏览器
print(ua.safari)

#最常用的方式
#写爬虫最实用的是可以随意变换headers，一定要有随机性。支持随机生成请求头
print(ua.random)

在中间件中使用

import random
from scrapy import signals
from fake_useragent import UserAgent

class RandomUserAgentMiddleware(object):

    def __init__(self):
        self.agent = UserAgent()

    @classmethod
    def from_crawler(cls, crawler):
        return cls()

    def process_request(self, request, spider):
        request.headers.setdefault(‘User-Agent‘, self.agent.random)