|
小的最近一直在准备比赛,不断地在各大招聘网站上薅羊毛,然而现在爬虫很不受待见啊,想爬得快一点就会被封。(+_+)?
最尴尬的是,我在爬赶集网上的招聘信息的时候,爬上150条一定会把我封掉,每次都是这个数字
真是丧心病狂的设定(╯‵□′)╯︵┻━┻
被逼无奈,只能临时先搭建一个简陋的ip池这样子,才能维持的了生活。ε=ε=ε=(~ ̄▽ ̄)~
首先我们找一家ip代理网站来薅羊毛(注意不要爬太多了,大家都是要吃饭的嘛,做人留一面,日♂后好相见(・∀・(・∀・(・∀・*),这是俺最近被别人告♂诫的)
国内高匿免费HTTP代理IP__第1页国内高匿www.xicidaili.com
爬取ip地址,端口和类型三个就行了
用selenium比较方便和直观U•ェ•*U
思路
1.我们先把爬取到的ip保存下来,然后在挨个验证是否可用
2.把验证完可用的IP存入数据库
3.在scrapy 中使用代理ip
上代码
from selenium import webdriverimport timefrom ip_test.__init__ import *import pymysqlimport randomimport requestsfrom multiprocessing import Poolclass Getips: def __init__(self): self.connect = pymysql.connect(MYSQL_HOST, MYSQL_ROOT, MYSQL_PASSWORD, MYSQL_DATABASE) self.cursor = self.connect.cursor() # 选定数据库 def GetUserAgent(self): user_agents = [ "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"] "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.11 (KHTML, like Gecko) Chrome/20.0.1132.11 TaoBrowser/2.0 Safari/536.11"] "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/21.0.1180.71 Safari/537.1 LBBROWSER"] "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; WOW64; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; .NET4.0E; LBBROWSER)"] "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; QQDownload 732; .NET4.0C; .NET4.0E; LBBROWSER)"] "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.84 Safari/535.11 LBBROWSER"] "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.1; WOW64; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; .NET4.0E)"] "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; WOW64; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; .NET4.0E; QQBrowser/7.0.3698.400)"] "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; QQDownload 732; .NET4.0C; .NET4.0E)"] "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Trident/4.0; SV1; QQDownload 732; .NET4.0C; .NET4.0E; 360SE)"] "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; QQDownload 732; .NET4.0C; .NET4.0E)"] "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.1; WOW64; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; .NET4.0E)"] "Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/21.0.1180.89 Safari/537.1"] "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/21.0.1180.89 Safari/537.1"] "Mozilla/5.0 (iPad; U; CPU OS 4_2_1 like Mac OS X; zh-cn) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8C148 Safari/6533.18.5"] "Mozilla/5.0 (Windows NT 6.1; Win64; x64; rv:2.0b13pre) Gecko/20110307 Firefox/4.0b13pre"] "Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:16.0) Gecko/20100101 Firefox/16.0"] "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.11 (KHTML, like Gecko) Chrome/23.0.1271.64 Safari/537.11"] "Mozilla/5.0 (X11; U; Linux x86_64; zh-CN; rv:1.9.2.10) Gecko/20100922 Ubuntu/10.10 (maverick) Firefox/3.6.10" , user_agent = random.choice(user_agents) return user_agent def crawl(self): self.cursor.execute(USE) self.cursor.execute(DROP) self.cursor.execute(CREATE) self.browser=webdriver.Chrome() self.browser.get('http://www.xicidaili.com/nn/') current=time.time() time.sleep(2) while True: time_difference=time.time()-current print(time_difference) if time_difference>TIME_DIFFERENCE: break else: time.sleep(1) ip_addrs = self.browser.find_elements_by_xpath('//*[@id="ip_list"]/tbody/tr/td[2,') ports = self.browser.find_elements_by_xpath('//*[@id="ip_list"]/tbody/tr/td[3,') categorys=self.browser.find_elements_by_xpath('//*[@id="ip_list"]/tbody/tr/td[6,') for ip_addr,port,category_ in zip(ip_addrs,ports,categorys): category=category_.text.lower() ip=ip_addr.text+":"+port.text try: self.cursor.execute(SAVEIN, (category,ip)) self.connect.commit() except Exception as error: print(error) next_page=self.browser.find_elements_by_class_name('next_page') for n in next_page: time.sleep(1) next_page_url=n.get_attribute("href") self.browser.get(next_page_url) self.browser.close() def select_data(self,sql): self.cursor.execute(sql) alldata=self.cursor.fetchall() return alldata def test(self,data): self.cursor.execute(USE) self.cursor.execute(DROP1) self.cursor.execute(CREATE1) categorys=[, ips=[, for curr_ip in data: user_agent = self.GetUserAgent() headers = {"User-Agent": user_agent} proxies = { curr_ip[0]: curr_ip[0]+'://' + curr_ip[1,, } try: res = requests.get(tarURL, headers=headers, proxies=proxies, timeout=2).text if len(res) != 0: print(curr_ip[1,+" is corrected") try: self.cursor.execute(SAVEIN1, (curr_ip[0], curr_ip[1,)) self.connect.commit() categorys.append(curr_ip[0]) ips.append(curr_ip[1,) except Exception as error: print(error) except Exception as er: print("验证代理IP(" + curr_ip[1, + ")时发生如下错误):") print(er) time.sleep(0.5) def show(self,sql): self.cursor.execute(sql) alldata = self.cursor.fetchall() for data in alldata: print(data)if __name__=="__main__": g=Getips() g.crawl() g.test(g.select_data(SQL)) print("ok") g.show(SQL1)
相信你们能看懂,虽然写的乱了点╰( ̄ω ̄o)
数据库语句和俺以前用的一样
MYSQL_DATABASE='spider'MYSQL_ROOT='root'MYSQL_PASSWORD='123'USE='use spider'TABLE='ip_s1'TABLE1="tmp_ip_s1"DROP="drop table if exists %s"%TABLEDROP1="drop table if exists %s"%TABLE1CREATE='create table %s(category varchar(255) ,ip varchar(255)Not null)'%TABLECREATE1='create table %s(category varchar(255) ,ip varchar(255)Not null)'%TABLE1SAVEIN='insert into '+TABLE+' (category,ip) values(%s,%s)'SAVEIN1='insert into '+TABLE1+' (category,ip) values(%s,%s)'SQL="select * from %s"%TABLESQL1="select * from %s"%TABLE1tarURL = "http://www.baidu.com/"TIME_DIFFERENCE=5
看看效果
这是总共爬得的ip地址
这是能用的,其实也不少啦(●ˇ∀ˇ●)
经过我在赶集网上的实验,这些ip.......能用,就是效率太低啦d=====( ̄▽ ̄*)b
十几个url只能爬三条啊⊙﹏⊙∥
不过好歹能用啦,下回爬多一点试试
这是一个简陋版,其实还可以用多线程和其他的方法,等我有发现了就告诉大家(ง •_•)ง |
|