Scrapy 设置代理IP | 设置随机USER-AGENT #防止对方发现我们
设置代理IP:
# middleware.py class my_proxy(object): def process_request(self,request,spider): #代理服务器的ip 与端口号 #注册一个 阿布云 request.meta['proxy']='http-pro.abuyun.com:9010' #设置通行用户的用户名和密码 #要购买 pro_name_pass=b'H211EAT5905745KC:F8FFBC929EB7D5A7' #加密 encode_pass_name=base64.b64encode(pro_name_pass) #设置http头 request.headers['proxy-Authorization'] = 'Basic ' + encode_pass_name.decode() # settings.py DOWNLOADER_MIDDLEWARES = { # 'douban.middlewares.DoubanDownloaderMiddleware': 543, 'douban.middlewares.my_proxy': 543, }
随机USER_AGENT(一)
# middlewares.py import random 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)) # settings.py 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", ] DOWNLOADER_MIDDLEWARES = { # 'yqin.middlewares.YqinDownloaderMiddleware': 543, 'yqin.middlewares.RandomUserAgentMiddleware': 10, }
随机USER_AGENT(一)
# middlewares.py 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) # settings.py DOWNLOADER_MIDDLEWARES = { # 'yqin.middlewares.YqinDownloaderMiddleware': 543, 'yqin.middlewares.RandomUserAgentMiddleware': 10, }