Scrapy配置之：user-agent

1. 單一user-agent

# settings.py 文件

# Chrome版
USER_AGENT = "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.97 Safari/537.36"

# Firefox版
USER_AGENT = "Mozilla/5.0 (Windows NT 6.2; Win64; x64; rv:16.0.1) Gecko/20121011 Firefox/21.0.1"

2. 隨機user-agent

2.1 fake-useragent安裝

# 獲取user-agent地址：
http://fake-useragent.herokuapp.com/browsers/0.1.11
    
# GitHub地址：
https://github.com/hellysmile/fake-useragent
    
# 安裝：
pip install fake-useragent

from fake_useragent import UserAgent
ua = UserAgent()

ua.ie
# Mozilla/5.0 (Windows; U; MSIE 9.0; Windows NT 9.0; en-US);
ua.msie
# Mozilla/5.0 (compatible; MSIE 10.0; Macintosh; Intel Mac OS X 10_7_3; Trident/6.0)'
ua['Internet Explorer']
# Mozilla/5.0 (compatible; MSIE 8.0; Windows NT 6.1; Trident/4.0; GTB7.4; InfoPath.2; SV1; .NET CLR 3.3.69573; WOW64; en-US)
ua.opera
# Opera/9.80 (X11; Linux i686; U; ru) Presto/2.8.131 Version/11.11
ua.chrome
# Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.2 (KHTML, like Gecko) Chrome/22.0.1216.0 Safari/537.2'
ua.google
# Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_4) AppleWebKit/537.13 (KHTML, like Gecko) Chrome/24.0.1290.1 Safari/537.13
ua['google chrome']
# Mozilla/5.0 (X11; CrOS i686 2268.111.0) AppleWebKit/536.11 (KHTML, like Gecko) Chrome/20.0.1132.57 Safari/536.11
ua.firefox
# Mozilla/5.0 (Windows NT 6.2; Win64; x64; rv:16.0.1) Gecko/20121011 Firefox/16.0.1
ua.ff
# Mozilla/5.0 (X11; Ubuntu; Linux i686; rv:15.0) Gecko/20100101 Firefox/15.0.1
ua.safari
# Mozilla/5.0 (iPad; CPU OS 6_0 like Mac OS X) AppleWebKit/536.26 (KHTML, like Gecko) Version/6.0 Mobile/10A5355d Safari/8536.25

# and the best one, random via real world browser usage statistic
ua.random

2.2 在Scrapy中配置

# setting.py 文件

DOWNLOADER_MIDDLEWARES = {
   'ArticleSpider.middlewares.ArticlespiderDownloaderMiddleware': 543,
   'scrapy.downloadermiddlewares.useragent.UserAgentMiddleware': None
}

RANDOM_UA_TYPE = "random"

# middlewares.py文件
from fake_useragent import UserAgent


class RandomUserAgentMiddleware(object):
    
    #隨機更換user-agent
    def __init__(self, crawler):
        super(RandomUserAgentMiddleware, self).__init__()
        self.ua = UserAgent()
        self.ua_type = crawler.settings.get("RANDOM_UA_TYPE", "random")

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

    def process_request(self, request, spider):
        def get_ua():
            return getattr(self.ua, self.ua_type)

        request.headers.setdefault('User-Agent', get_ua())