3.启动nginx
[root@node03 sbin]# nginx #不显示任何东西一般是成功啦
4.查看nginx是否启动成功
[root@node03 sbin]# ps -ef | grep nginx root 3730 1 0 09:24 ? 00:00:00 nginx: master process nginx nobody 3731 3730 0 09:24 ? 00:00:20 nginx: worker process is shutting down nobody 5766 3730 0 12:17 ? 00:00:00 nginx: worker process root 5824 3708 0 12:24 pts/1 00:00:00 grep nginx #看到有两个nginx进程，表示成功le
5.浏览器访问nginx
在浏览器输入：node03/kafkalua
说明：如何么有配置hosts则输入openresty所在设备的地址如：192.168.52.120/kafkalua
在浏览器输入：node03/或者 192.168.52.120/
再在浏览器输入：node03:80/kafkalua 和 node03:80/试试 搬来nginx.conf来看看：
node03:80/kafkalua 这里的nide03是服务器的别名或者之间写文服务器地址，80是【listen 80;】配置的监听端口，80端口可以省略不写，如果这写成【listen 8088;】那么浏览器需输入 node03:8088/kafkalua （这里不能省略8088），kafkalua是工程名。
server {
listen 80;
server_name localhost;
#charset koi8-r;
#access_log logs/host.access.log main;
location / {
root html;
index index.html index.htm;
}
#------------------添加的代码---------------------------------------
location /kafkalua { #这里的kafkalua就是工程名字，不加默认为空
#开启nginx监控
stub_status on;
#加载lua文件
default_type text/html;
#指定kafka的lua文件位置，就是我们刚才创建的kafkalua.lua（前面已经强调要记住的！！！！）
content_by_lua_file /export/servers/openresty/testlua/kafkalua.lua;
}
第五步：创建测试爬虫程序
1.创建maven工程导入依赖
<dependencies>
<dependency>
<groupId>org.jsoup</groupId>
<artifactId>jsoup</artifactId>
<version>1.11.3</version>
</dependency>
<dependency>
<groupId>org.apache.httpcomponents</groupId>
<artifactId>httpclient</artifactId>
<version>4.5.4</version>
</dependency>
</dependencies>
2.伪爬虫程序
public class SpiderGoAirCN {
private static String basePath = "http://node03/kafkalua";
public static void main(String[] args) throws Exception {
for (int i = 0; i < 50000; i++) {
// 请求查询信息
spiderQueryao();
// 请求html
spiderHtml();
// 请求js
spiderJs();
// 请求css
spiderCss();
// 请求png
spiderPng();
// 请求jpg
spiderJpg();
Thread.sleep(100);
}
}
/**
*
* @throws Exception
*/
public static void spiderQueryao() throws Exception {
// 1.指定目标网站 ^.*/B2C40/query/jaxb/direct/query.ao.*$
String url = basePath + "/B2C40/query/jaxb/direct/query.ao";
// 2.发起请求
HttpPost httpPost = new HttpPost(url);
// 3. 设置请求参数
httpPost.setHeader("Time-Local", getLocalDateTime());
httpPost.setHeader("Requst",
"POST /B2C40/query/jaxb/direct/query.ao HTTP/1.1");
httpPost.setHeader("Request Method", "POST");
httpPost.setHeader("Content-Type",
"application/x-www-form-urlencoded; charset=UTF-8");
httpPost.setHeader(
"Referer",
"http://b2c.csair.com/B2C40/modules/bookingnew/main/flightSelectDirect.html?t=S&c1=CAN&c2=WUH&d1="
+ getGoTime() + "&at=1&ct=0&it=0");
httpPost.setHeader("Remote Address", "192.168.56.80");
httpPost.setHeader(
"User-Agent",
"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36");
httpPost.setHeader("Time-Iso8601", getISO8601Timestamp());
httpPost.setHeader("Server Address", "243.45.78.132");
httpPost.setHeader(
"Cookie",
"JSESSIONID=782121159357B98CA6112554CF44321E; sid=b5cc11e02e154ac5b0f3609332f86803; aid=8ae8768760927e280160bb348bef3e12; identifyStatus=N; userType4logCookie=M; userId4logCookie=13818791413; useridCookie=13818791413; userCodeCookie=13818791413; temp_zh=cou%3D0%3Bsegt%3D%E5%8D%95%E7%A8%8B%3Btime%3D2018-01-13%3B%E5%B9%BF%E5%B7%9E-%E5%8C%97%E4%BA%AC%3B1%2C0%2C0%3B%26cou%3D1%3Bsegt%3D%E5%8D%95%E7%A8%8B%3Btime%3D"
+ getGoTime()
+ "%3B%E5%B9%BF%E5%B7%9E-%E6%88%90%E9%83%BD%3B1%2C0%2C0%3B%26; JSESSIONID=782121159357B98CA6112554CF44321E; WT-FPC=id=211.103.142.26-608782688.30635197:lv=1516170718655:ss=1516170709449:fs=1513243317440:pn=2:vn=10; language=zh_CN; WT.al_flight=WT.al_hctype(S)%3AWT.al_adultnum(1)%3AWT.al_childnum(0)%3AWT.al_infantnum(0)%3AWT.al_orgcity1(CAN)%3AWT.al_dstcity1(CTU)%3AWT.al_orgdate1("
+ getGoTime() + ")");
// 4.设置请求参数
ArrayList<BasicNameValuePair> parameters = new ArrayList<BasicNameValuePair>();
parameters
.add(new BasicNameValuePair(
"json",
"{"depcity":"CAN", "arrcity":"WUH", "flightdate":"20180220", "adultnum":"1", "childnum":"0", "infantnum":"0", "cabinorder":"0", "airline":"1", "flytype":"0", "international":"0", "action":"0", "segtype":"1", "cache":"0", "preUrl":"", "isMember":""}"));
httpPost.setEntity(new UrlEncodedFormEntity(parameters));
// 5. 发起请求
CloseableHttpClient httpClient = HttpClients.createDefault();
CloseableHttpResponse response = httpClient.execute(httpPost);
// 6.获取返回值
System.out.println(response != null);
}
public static void spiderHtml() throws Exception {
// 1.指定目标网站 ^.*html.*$
String url = basePath + "/B2C40/modules/bookingnew/main/flightSelectDirect.html?t=S&c1=CAN&c2=CTU&d1=2018-01-17&at=1&ct=0&it=0";
// 2.发起请求
HttpPost httpPost = new HttpPost(url);
// 3. 设置请求参数
httpPost.setHeader("Time-Local", getLocalDateTime());
httpPost.setHeader("Requst",
"POST /B2C40/query/jaxb/direct/query.ao HTTP/1.1");
httpPost.setHeader("Request Method", "POST");
httpPost.setHeader("Content-Type",
"application/x-www-form-urlencoded; charset=UTF-8");
httpPost.setHeader(
"Referer",
"http://b2c.csair.com/B2C40/modules/bookingnew/main/flightSelectDirect.html?t=S&c1=CAN&c2=WUH&d1=2018-02-20&at=1&ct=0&it=0");
httpPost.setHeader("Remote Address", "192.168.56.1");
httpPost.setHeader(
"User-Agent",
"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36");
httpPost.setHeader("Time-Iso8601", getISO8601Timestamp());
httpPost.setHeader("Server Address", "192.168.56.80");
httpPost.setHeader(
"Cookie",
"JSESSIONID=782121159357B98CA6112554CF44321E; sid=b5cc11e02e154ac5b0f3609332f86803; aid=8ae8768760927e280160bb348bef3e12; identifyStatus=N; userType4logCookie=M; userId4logCookie=13818791413; useridCookie=13818791413; userCodeCookie=13818791413; temp_zh=cou%3D0%3Bsegt%3D%E5%8D%95%E7%A8%8B%3Btime%3D2018-01-13%3B%E5%B9%BF%E5%B7%9E-%E5%8C%97%E4%BA%AC%3B1%2C0%2C0%3B%26cou%3D1%3Bsegt%3D%E5%8D%95%E7%A8%8B%3Btime%3D2018-01-17%3B%E5%B9%BF%E5%B7%9E-%E6%88%90%E9%83%BD%3B1%2C0%2C0%3B%26; JSESSIONID=782121159357B98CA6112554CF44321E; WT-FPC=id=211.103.142.26-608782688.30635197:lv=1516170718655:ss=1516170709449:fs=1513243317440:pn=2:vn=10; language=zh_CN; WT.al_flight=WT.al_hctype(S)%3AWT.al_adultnum(1)%3AWT.al_childnum(0)%3AWT.al_infantnum(0)%3AWT.al_orgcity1(CAN)%3AWT.al_dstcity1(CTU)%3AWT.al_orgdate1(2018-01-17)");
// 4.设置请求参数
// httpPost.setEntity(new StringEntity(
// "depcity=CAN&arrcity=WUH&flightdate=20180220&adultnum=1&childnum=0&infantnum=0&cabinorder=0&airline=1&flytype=0&international=0&action=0&segtype=1&cache=0&preUrl=&isMember="));
ArrayList<BasicNameValuePair> parameters = new ArrayList<BasicNameValuePair>();
parameters
.add(new BasicNameValuePair(
"json",
"{"depcity":"CAN", "arrcity":"WUH", "flightdate":"20180220", "adultnum":"1", "childnum":"0", "infantnum":"0", "cabinorder":"0", "airline":"1", "flytype":"0", "international":"0", "action":"0", "segtype":"1", "cache":"0", "preUrl":"", "isMember":""}"));
httpPost.setEntity(new UrlEncodedFormEntity(parameters));
// 5. 发起请求
CloseableHttpClient httpClient = HttpClients.createDefault();
CloseableHttpResponse response = httpClient.execute(httpPost);
// 6.获取返回值
System.out.println(response != null);
}
public static void spiderJs() throws Exception {
// 1.指定目标网站
String url = basePath +"/B2C40/dist/main/modules/common/requireConfig.js";
// 2.发起请求
HttpPost httpPost = new HttpPost(url);
// 3. 设置请求参数
httpPost.setHeader("Time-Local", getLocalDateTime());
httpPost.setHeader("Requst",
"POST /B2C40/query/jaxb/direct/query.ao HTTP/1.1");
httpPost.setHeader("Request Method", "POST");
httpPost.setHeader("Content-Type",
"application/x-www-form-urlencoded; charset=UTF-8");
httpPost.setHeader(
"Referer",
"http://b2c.csair.com/B2C40/modules/bookingnew/main/flightSelectDirect.html?t=S&c1=CAN&c2=WUH&d1=2018-02-20&at=1&ct=0&it=0");
httpPost.setHeader("Remote Address", "192.168.56.1");
httpPost.setHeader(
"User-Agent",
"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36");
httpPost.setHeader("Time-Iso8601", getISO8601Timestamp());
httpPost.setHeader("Server Address", "192.168.56.80");
httpPost.setHeader(
"Cookie",
"JSESSIONID=782121159357B98CA6112554CF44321E; sid=b5cc11e02e154ac5b0f3609332f86803; aid=8ae8768760927e280160bb348bef3e12; identifyStatus=N; userType4logCookie=M; userId4logCookie=13818791413; useridCookie=13818791413; userCodeCookie=13818791413; temp_zh=cou%3D0%3Bsegt%3D%E5%8D%95%E7%A8%8B%3Btime%3D2018-01-13%3B%E5%B9%BF%E5%B7%9E-%E5%8C%97%E4%BA%AC%3B1%2C0%2C0%3B%26cou%3D1%3Bsegt%3D%E5%8D%95%E7%A8%8B%3Btime%3D2018-01-17%3B%E5%B9%BF%E5%B7%9E-%E6%88%90%E9%83%BD%3B1%2C0%2C0%3B%26; JSESSIONID=782121159357B98CA6112554CF44321E; WT-FPC=id=211.103.142.26-608782688.30635197:lv=1516170718655:ss=1516170709449:fs=1513243317440:pn=2:vn=10; language=zh_CN; WT.al_flight=WT.al_hctype(S)%3AWT.al_adultnum(1)%3AWT.al_childnum(0)%3AWT.al_infantnum(0)%3AWT.al_orgcity1(CAN)%3AWT.al_dstcity1(CTU)%3AWT.al_orgdate1(2018-01-17)");
// 4.设置请求参数
ArrayList<BasicNameValuePair> parameters = new ArrayList<BasicNameValuePair>();
parameters
.add(new BasicNameValuePair(
"json",
"{"depcity":"CAN", "arrcity":"WUH", "flightdate":"20180220", "adultnum":"1", "childnum":"0", "infantnum":"0", "cabinorder":"0", "airline":"1", "flytype":"0", "international":"0", "action":"0", "segtype":"1", "cache":"0", "preUrl":"", "isMember":""}"));
httpPost.setEntity(new UrlEncodedFormEntity(parameters));
// 5. 发起请求
CloseableHttpClient httpClient = HttpClients.createDefault();
CloseableHttpResponse response = httpClient.execute(httpPost);
// 6.获取返回值
System.out.println(response != null);
}
public static void spiderCss() throws Exception {
// 1.指定目标网站
String url = basePath +"/B2C40/dist/main/css/flight.css";
// 2.发起请求
HttpPost httpPost = new HttpPost(url);
// 3. 设置请求参数
httpPost.setHeader("Time-Local", getLocalDateTime());
httpPost.setHeader("Requst",
"POST /B2C40/query/jaxb/direct/query.ao HTTP/1.1");
httpPost.setHeader("Request Method", "POST");
httpPost.setHeader("Content-Type",
"application/x-www-form-urlencoded; charset=UTF-8");
httpPost.setHeader("Referer",
"http://b2c.csair.com/B2C40/modules/bookingnew/main/flightSelectDirect.html");
httpPost.setHeader("Remote Address", "192.168.56.1");
httpPost.setHeader(
"User-Agent",
"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36");
httpPost.setHeader("Time-Iso8601", getISO8601Timestamp());
httpPost.setHeader("Server Address", "192.168.56.80");
httpPost.setHeader(
"Cookie",
"JSESSIONID=782121159357B98CA6112554CF44321E; sid=b5cc11e02e154ac5b0f3609332f86803; aid=8ae8768760927e280160bb348bef3e12; identifyStatus=N; userType4logCookie=M; userId4logCookie=13818791413; useridCookie=13818791413; userCodeCookie=13818791413; temp_zh=cou%3D0%3Bsegt%3D%E5%8D%95%E7%A8%8B%3Btime%3D2018-01-13%3B%E5%B9%BF%E5%B7%9E-%E5%8C%97%E4%BA%AC%3B1%2C0%2C0%3B%26cou%3D1%3Bsegt%3D%E5%8D%95%E7%A8%8B%3Btime%3D2018-01-17%3B%E5%B9%BF%E5%B7%9E-%E6%88%90%E9%83%BD%3B1%2C0%2C0%3B%26; JSESSIONID=782121159357B98CA6112554CF44321E; WT-FPC=id=211.103.142.26-608782688.30635197:lv=1516170718655:ss=1516170709449:fs=1513243317440:pn=2:vn=10; language=zh_CN; WT.al_flight=WT.al_hctype(S)%3AWT.al_adultnum(1)%3AWT.al_childnum(0)%3AWT.al_infantnum(0)%3AWT.al_orgcity1(CAN)%3AWT.al_dstcity1(CTU)%3AWT.al_orgdate1(2018-01-17)");
// 4.设置请求参数
ArrayList<BasicNameValuePair> parameters = new ArrayList<BasicNameValuePair>();
parameters
.add(new BasicNameValuePair(
"json",
"{"depcity":"CAN", "arrcity":"WUH", "flightdate":"20180220", "adultnum":"1", "childnum":"0", "infantnum":"0", "cabinorder":"0", "airline":"1", "flytype":"0", "international":"0", "action":"0", "segtype":"1", "cache":"0", "preUrl":"", "isMember":""}"));
httpPost.setEntity(new UrlEncodedFormEntity(parameters));
// 5. 发起请求
CloseableHttpClient httpClient = HttpClients.createDefault();
CloseableHttpResponse response = httpClient.execute(httpPost);
// 6.获取返回值
System.out.println(response != null);
}
public static void spiderPng() throws Exception {
// 1.指定目标网站
String url =basePath + "/B2C40/dist/main/images/common.png";
// 2.发起请求
HttpPost httpPost = new HttpPost(url);
// 3. 设置请求参数
httpPost.setHeader("Time-Local", getLocalDateTime());
httpPost.setHeader("Requst",
"POST /B2C40/query/jaxb/direct/query.ao HTTP/1.1");
httpPost.setHeader("Request Method", "POST");
httpPost.setHeader("Content-Type",
"application/x-www-form-urlencoded; charset=UTF-8");
httpPost.setHeader(
"Referer",
"http://b2c.csair.com/B2C40/modules/bookingnew/main/flightSelectDirect.html?t=S&c1=CAN&c2=WUH&d1=2018-02-20&at=1&ct=0&it=0");
httpPost.setHeader("Remote Address", "192.168.56.1");
httpPost.setHeader(
"User-Agent",
"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36");
httpPost.setHeader("Time-Iso8601", getISO8601Timestamp());
httpPost.setHeader("Server Address", "192.168.56.80");
httpPost.setHeader(
"Cookie",
"JSESSIONID=782121159357B98CA6112554CF44321E; sid=b5cc11e02e154ac5b0f3609332f86803; aid=8ae8768760927e280160bb348bef3e12; identifyStatus=N; userType4logCookie=M; userId4logCookie=13818791413; useridCookie=13818791413; userCodeCookie=13818791413; temp_zh=cou%3D0%3Bsegt%3D%E5%8D%95%E7%A8%8B%3Btime%3D2018-01-13%3B%E5%B9%BF%E5%B7%9E-%E5%8C%97%E4%BA%AC%3B1%2C0%2C0%3B%26cou%3D1%3Bsegt%3D%E5%8D%95%E7%A8%8B%3Btime%3D2018-01-17%3B%E5%B9%BF%E5%B7%9E-%E6%88%90%E9%83%BD%3B1%2C0%2C0%3B%26; JSESSIONID=782121159357B98CA6112554CF44321E; WT-FPC=id=211.103.142.26-608782688.30635197:lv=1516170718655:ss=1516170709449:fs=1513243317440:pn=2:vn=10; language=zh_CN; WT.al_flight=WT.al_hctype(S)%3AWT.al_adultnum(1)%3AWT.al_childnum(0)%3AWT.al_infantnum(0)%3AWT.al_orgcity1(CAN)%3AWT.al_dstcity1(CTU)%3AWT.al_orgdate1(2018-01-17)");
// 4.设置请求参数
ArrayList<BasicNameValuePair> parameters = new ArrayList<BasicNameValuePair>();
parameters
.add(new BasicNameValuePair(
"json",
"{"depcity":"CAN", "arrcity":"WUH", "flightdate":"20180220", "adultnum":"1", "childnum":"0", "infantnum":"0", "cabinorder":"0", "airline":"1", "flytype":"0", "international":"0", "action":"0", "segtype":"1", "cache":"0", "preUrl":"", "isMember":""}"));
httpPost.setEntity(new UrlEncodedFormEntity(parameters));
// 5. 发起请求
CloseableHttpClient httpClient = HttpClients.createDefault();
CloseableHttpResponse response = httpClient.execute(httpPost);
// 6.获取返回值
System.out.println(response != null);
}
public static void spiderJpg() throws Exception {
// 1.指定目标网站
String url = basePath +"/B2C40/dist/main/images/loadingimg.jpg";
// 2.发起请求
HttpPost httpPost = new HttpPost(url);
// 3. 设置请求参数
httpPost.setHeader("Time-Local", getLocalDateTime());
httpPost.setHeader("Requst",
"POST /B2C40/query/jaxb/direct/query.ao HTTP/1.1");
httpPost.setHeader("Request Method", "POST");
httpPost.setHeader("Content-Type",
"application/x-www-form-urlencoded; charset=UTF-8");
httpPost.setHeader(
"Referer",
"http://b2c.csair.com/B2C40/modules/bookingnew/main/flightSelectDirect.html?t=S&c1=CAN&c2=WUH&d1=2018-02-20&at=1&ct=0&it=0");
httpPost.setHeader("Remote Address", "192.168.56.1");
httpPost.setHeader(
"User-Agent",
"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36");
httpPost.setHeader("Time-Iso8601", getISO8601Timestamp());
httpPost.setHeader("Server Address", "192.168.56.80");
httpPost.setHeader(
"Cookie",
"JSESSIONID=782121159357B98CA6112554CF44321E; sid=b5cc11e02e154ac5b0f3609332f86803; aid=8ae8768760927e280160bb348bef3e12; identifyStatus=N; userType4logCookie=M; userId4logCookie=13818791413; useridCookie=13818791413; userCodeCookie=13818791413; temp_zh=cou%3D0%3Bsegt%3D%E5%8D%95%E7%A8%8B%3Btime%3D2018-01-13%3B%E5%B9%BF%E5%B7%9E-%E5%8C%97%E4%BA%AC%3B1%2C0%2C0%3B%26cou%3D1%3Bsegt%3D%E5%8D%95%E7%A8%8B%3Btime%3D2018-01-17%3B%E5%B9%BF%E5%B7%9E-%E6%88%90%E9%83%BD%3B1%2C0%2C0%3B%26; JSESSIONID=782121159357B98CA6112554CF44321E; WT-FPC=id=211.103.142.26-608782688.30635197:lv=1516170718655:ss=1516170709449:fs=1513243317440:pn=2:vn=10; language=zh_CN; WT.al_flight=WT.al_hctype(S)%3AWT.al_adultnum(1)%3AWT.al_childnum(0)%3AWT.al_infantnum(0)%3AWT.al_orgcity1(CAN)%3AWT.al_dstcity1(CTU)%3AWT.al_orgdate1(2018-01-17)");
// 4.设置请求参数
ArrayList<BasicNameValuePair> parameters = new ArrayList<BasicNameValuePair>();
parameters
.add(new BasicNameValuePair(
"json",
"{"depcity":"CAN", "arrcity":"WUH", "flightdate":"20180220", "adultnum":"1", "childnum":"0", "infantnum":"0", "cabinorder":"0", "airline":"1", "flytype":"0", "international":"0", "action":"0", "segtype":"1", "cache":"0", "preUrl":"", "isMember":""}"));
httpPost.setEntity(new UrlEncodedFormEntity(parameters));
// 5. 发起请求
CloseableHttpClient httpClient = HttpClients.createDefault();
CloseableHttpResponse response = httpClient.execute(httpPost);
// 6.获取返回值
System.out.println(response != null);
}
public static String getLocalDateTime() {
DateFormat df = new SimpleDateFormat("dd/MMM/yyyy'T'HH:mm:ss +08:00",
Locale.ENGLISH);
String nowAsISO = df.format(new Date());
return nowAsISO;
}
public static String getISO8601Timestamp() {
DateFormat df = new SimpleDateFormat("yyyy-MM-dd'T'HH:mm:ss+08:00");
String nowAsISO = df.format(new Date());
return nowAsISO;
}
public static String getGoTime() {
DateFormat df = new SimpleDateFormat("yyyy-MM-dd");
String nowAsISO = df.format(new Date());
return nowAsISO;
}
public static String getBackTime() {
Date date = new Date();// 取时间
Calendar calendar = new GregorianCalendar();
calendar.setTime(date);
calendar.add(calendar.DATE, +1);// 把日期往前减少一天，若想把日期向后推一天则将负数改为正数
date = calendar.getTime();
SimpleDateFormat formatter = new SimpleDateFormat("yyyy-MM-dd");
String dateString = formatter.format(date);
return dateString;
}
}
