Gecco爬虫代码分析
程序员文章站
2022-05-05 12:29:28
...
###配置需要渲染的SpiderBean
@Gecco(matchUrl="https://github.com/{user}/{project}", pipelines="consolePipeline")
public class MyGithub implements HtmlBean {
private static final long serialVersionUID = -7127412585200687225L;
@RequestParameter("user")
private String user;
@RequestParameter("project")
private String project;
@HtmlField(cssPath=".repository-meta-content")
private String title;
@Text
@HtmlField(cssPath=".pagehead-actions li:nth-child(2) .social-count")
private int star;
@Text
@HtmlField(cssPath=".pagehead-actions li:nth-child(3) .social-count")
private int fork;
@HtmlField(cssPath=".entry-content")
private String readme;
public String getReadme() {
return readme;
}
public void setReadme(String readme) {
this.readme = readme;
}
public String getUser() {
return user;
}
public void setUser(String user) {
this.user = user;
}
public String getProject() {
return project;
}
public void setProject(String project) {
this.project = project;
}
public String getTitle() {
return title;
}
public void setTitle(String title) {
this.title = title;
}
public int getStar() {
return star;
}
public void setStar(int star) {
this.star = star;
}
public int getFork() {
return fork;
}
public void setFork(int fork) {
this.fork = fork;
}
}
###启动爬虫引擎
public static void main(String[] args) {
GeccoEngine.create()
.classpath("com.geccocrawler.gecco.demo")
//爬虫userAgent设置
.userAgent("Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/45.0.2454.85 Safari/537.36")
//开始抓取的页面地址
.start("https://github.com/xtuhcy/gecco")
//开启几个爬虫线程
.thread(1)
//单个爬虫每次抓取完一个请求后的间隔时间
.interval(2000)
.run();
}
##公共注解说明 ###@Gecco
定义一个SpiderBean必须有的注解,告诉爬虫引擎什么样的url转换成该java bean,使用什么渲染器渲染,java bean渲染完成后传递给哪些管道过滤器继续处理