user-agent大全頁面:
https://fake-useragent.herokuapp.com/browsers/0.1.6
使用fake-useragent模塊
模塊github地址:https://github.com/hellysmile/fake-useragent
安裝方法:
pip install fake-useragent
使用方法:

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
scrapy 自動切換方法:
編輯middlewares.py文件
from fake_useragent import UserAgent # 新增一個類 class RandomUserAgentMidddlware(object): # 隨機更換user-agent def __init__(self, crawler): super(RandomUserAgentMidddlware, self).__init__() self.ua = UserAgent() # 從配置文件讀取隨機類型 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): # 通過配置文件的隨機類型進行調用 def get_ua(): return getattr(self.ua, self.ua_type) request.headers.setdefault('User-Agent', get_ua())
settings文件
DOWNLOADER_MIDDLEWARES = { # 將自己編寫的類導入 'ArticleSpider.middlewares.RandomUserAgentMidddlware': 543, # 導入系統自帶的useragent類,並將優先級設置為none 'scrapy.downloadermiddlewares.useragent.UserAgentMiddleware': None, } # 設置自定義的random的屬性 RANDOM_UA_TYPE = "random"