pull/79/merge
yihua.huang 11 years ago
parent 6252042ed2
commit 7038c00a9a

@ -22,27 +22,27 @@
Add dependencies to your pom.xml: Add dependencies to your pom.xml:
```xml ```xml
<dependency> <dependency>
<groupId>us.codecraft</groupId> <groupId>us.codecraft</groupId>
<artifactId>webmagic-core</artifactId> <artifactId>webmagic-core</artifactId>
<version>0.4.3</version> <version>0.4.3</version>
</dependency> </dependency>
<dependency> <dependency>
<groupId>us.codecraft</groupId> <groupId>us.codecraft</groupId>
<artifactId>webmagic-extension</artifactId> <artifactId>webmagic-extension</artifactId>
<version>0.4.3</version> <version>0.4.3</version>
</dependency> </dependency>
``` ```
WebMagic use slf4j with slf4j-log4j12 implementation. If you customized your slf4j implementation, please exclude slf4j-log4j12. WebMagic use slf4j with slf4j-log4j12 implementation. If you customized your slf4j implementation, please exclude slf4j-log4j12.
```xml ```xml
<exclusions> <exclusions>
<exclusion> <exclusion>
<groupId>org.slf4j</groupId> <groupId>org.slf4j</groupId>
<artifactId>slf4j-log4j12</artifactId> <artifactId>slf4j-log4j12</artifactId>
</exclusion> </exclusion>
</exclusions> </exclusions>
``` ```
@ -53,30 +53,30 @@ WebMagic use slf4j with slf4j-log4j12 implementation. If you customized your slf
Write a class implements PageProcessor Write a class implements PageProcessor
```java ```java
public class OschinaBlogPageProcesser implements PageProcessor { public class OschinaBlogPageProcesser implements PageProcessor {
private Site site = Site.me().setDomain("my.oschina.net"); private Site site = Site.me().setDomain("my.oschina.net");
@Override @Override
public void process(Page page) { public void process(Page page) {
List<String> links = page.getHtml().links().regex("http://my\\.oschina\\.net/flashsword/blog/\\d+").all(); List<String> links = page.getHtml().links().regex("http://my\\.oschina\\.net/flashsword/blog/\\d+").all();
page.addTargetRequests(links); page.addTargetRequests(links);
page.putField("title", page.getHtml().xpath("//div[@class='BlogEntity']/div[@class='BlogTitle']/h1").toString()); page.putField("title", page.getHtml().xpath("//div[@class='BlogEntity']/div[@class='BlogTitle']/h1").toString());
page.putField("content", page.getHtml().$("div.content").toString()); page.putField("content", page.getHtml().$("div.content").toString());
page.putField("tags",page.getHtml().xpath("//div[@class='BlogTags']/a/text()").all()); page.putField("tags",page.getHtml().xpath("//div[@class='BlogTags']/a/text()").all());
} }
@Override @Override
public Site getSite() { public Site getSite() {
return site; return site;
} }
public static void main(String[] args) { public static void main(String[] args) {
Spider.create(new OschinaBlogPageProcesser()).addUrl("http://my.oschina.net/flashsword/blog") Spider.create(new OschinaBlogPageProcesser()).addUrl("http://my.oschina.net/flashsword/blog")
.addPipeline(new ConsolePipeline()).run(); .addPipeline(new ConsolePipeline()).run();
}
} }
}
``` ```
* `page.addTargetRequests(links)` * `page.addTargetRequests(links)`
@ -86,24 +86,24 @@ Write a class implements PageProcessor
You can also use annotation way: You can also use annotation way:
```java ```java
@TargetUrl("http://my.oschina.net/flashsword/blog/\\d+") @TargetUrl("http://my.oschina.net/flashsword/blog/\\d+")
public class OschinaBlog { public class OschinaBlog {
@ExtractBy("//title") @ExtractBy("//title")
private String title; private String title;
@ExtractBy(value = "div.BlogContent",type = ExtractBy.Type.Css) @ExtractBy(value = "div.BlogContent",type = ExtractBy.Type.Css)
private String content; private String content;
@ExtractBy(value = "//div[@class='BlogTags']/a/text()", multi = true) @ExtractBy(value = "//div[@class='BlogTags']/a/text()", multi = true)
private List<String> tags; private List<String> tags;
public static void main(String[] args) { public static void main(String[] args) {
OOSpider.create( OOSpider.create(
Site.me(), Site.me(),
new ConsolePageModelPipeline(), OschinaBlog.class).addUrl("http://my.oschina.net/flashsword/blog").run(); new ConsolePageModelPipeline(), OschinaBlog.class).addUrl("http://my.oschina.net/flashsword/blog").run();
} }
} }
``` ```
### Docs and samples: ### Docs and samples:

Loading…
Cancel
Save