1.禁用Cookie
部分网站会通过用户的Cookie信息对用户进行识别与分析,所以要防止目标网站识别我们的会话信息。
在Scrapy中,默认是打开cookie的 (#COOKIES_ENABLED = False)
设置为:COOKIES_ENABLED = False (cookie启用:no),对于需要cookie的可以在请求头中headers加入cookie
class LagouspiderSpider(scrapy.Spider): name = "lagouspider" allowed_domains = ["www.lagou.com"] url = 'https://www.lagou.com/jobs/positionAjax.json?'#city=%E6%B7%B1%E5%9C%B3&needAddtionalResult=false' page = 1 allpage =0 cookie = 'JSESSIONID=ABAAABAAAFCAAEG34858C57541C1F9DF75AED18C3065736; Hm_lvt_4233e74dff0ae5bd0a3d81c6ccf756e6=1524281748; 04797acf-4515-11e8-90b5- LGSID=20180421130026-e7e614d7-4520-PRE_SITE=https%3A%2F%2Fwww.lagou.com%2Fjobs%2Flist_python%3Fcity%3D%25E6%25B7%25B1%25E5%259C%25B3%26cl%3Dfalse%26fromSearch%3Dtrue%26labelWords%3D%26suginput%3D; PRE_LAND=https%3A%2F%2Fwww.lagou.com%2Fjobs%2F4302345.html; LGRID=20180421130208-24b73966-4521-11e8-90f2-525400f775ce; Hm_lpvt_4233e74dff0ae5bd0a3d81c6ccf756e6=1524286956' headers = {'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8', 'Referer': 'https://www.lagou.com/jobs/list_python?city=%E6%B7%B1%E5%9C%B3&cl=false&fromSearch=true&labelWords=&suginput=', 'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.181 Safari/537.36', 'cookie': cookie } def start_requests(self): yield scrapy.FormRequest(self.url, headers=self.headers, formdata={ 'first': 'true','pn': str(self.page),'kd': 'python','city': '深圳'}, callback=self.parse)
2.设置下载延时
在Scrapy中,默认是关闭请求下载延时的(#DOWNLOAD_DELAY = 3)
去掉#,或者在spider的请求间中加入 time.sleep(random.randint(5, 10))
def parse(self, response): #print(response.text) item = LagouItem() data = json.loads(response.text) totalCount = data['content']['positionResult']['totalCount']#总共多少条信息 resultSize = data['content']['positionResult']['resultSize']#每页多少条信息 result = data['content']['positionResult']['result']#得到一个包含15个信息的列表 for each in result: for field in item.fields: if field in each.keys(): item[field] = each.get(field) yield item time.sleep(random.randint(5, 10)) if int(resultSize): self.allpage = int(totalCount) // int(resultSize) + 1 if self.page < self.allpage: self.page += 1 yield scrapy.FormRequest(self.url, headers=self.headers, formdata={ 'first': 'false','pn': str(self.page),'kd': 'python','city': '深圳'}, callback=self.parse)
3.设置USER-AGENT和代理ip
settings中:
DOWNLOADER_MIDDLEWARES = { 'doubanMongo.middlewares.RandomUserAgent': 300, 'doubanMongo.middlewares.RandomProxy':400 } USER_AGENTS = [ 'Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.0)', 'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.2)', 'Opera/9.27 (Windows NT 5.2; U; zh-cn)', 'Opera/8.0 (Macintosh; PPC Mac OS X; U; en)', 'Mozilla/5.0 (Macintosh; PPC Mac OS X; U; en) Opera 8.0', 'Mozilla/5.0 (Linux; U; Android 4.0.3; zh-cn; M032 Build/IML74K) AppleWebKit/534.30 (KHTML, like Gecko) Version/4.0 Mobile Safari/534.30', 'Mozilla/5.0 (Windows; U; Windows NT 5.2) AppleWebKit/525.13 (KHTML, like Gecko) Chrome/0.2.149.27 Safari/525.13' ] PROXIES=[{'ip_port':'117.48.214.249:16817','user_passwd':'632345244:4tf9pcpw'} #{'ip_port':'117.48.214.249:16817','user_passwd':''}, #{'ip_port':'117.48.214.249:16817','user_passwd':''}, #{'ip_port':'117.48.214.249:16817','user_passwd':''} ]
middlewares中:
from scrapy.conf import settings import base64 import random class RandomProxy(object): def process_request(self, request, spider): proxy = random.choice(settings["PROXIES"]) if proxy['user_passwd'] is None: request.meta['proxy'] = 'http://'+ proxy['ip_port'] else: # 对账户密码进行base64编码转换 b_pw = bytes(proxy['user_passwd'], encoding = "utf-8")#string转为bytes base64_userpasswd = base64.encodestring(b_pw)#需要的参数是bytes对象 # 对应到代理服务器的信令格式里 s_base64_userpasswd = str(base64_userpasswd, encoding="utf-8") #bytes转为string request.headers['Proxy-Authorization'] = 'Basic ' + s_base64_userpasswd request.meta['proxy'] = "http://" + proxy['ip_port'] class RandomUserAgent(object): def process_request(self, request, spider): useragent = random.choice(settings["USER_AGENTS"]) #print(useragent) request.headers.setdefault('User-Agent',useragent)