Commit 84b897f8 authored by yihua.huang's avatar yihua.huang

update AngularJSProcessor

parent 03c25123
package us.codecraft.webmagic.selector;
import com.jayway.jsonpath.JsonPath;
import us.codecraft.webmagic.utils.Experimental;
import java.util.ArrayList;
import java.util.List;
......@@ -13,7 +12,6 @@ import java.util.List;
* @author code4crafter@gmail.com <br>
* @since 0.2.1
*/
@Experimental
public class JsonPathSelector implements Selector {
private String jsonPathStr;
......
package us.codecraft.webmagic.selector;
import org.junit.Test;
import us.codecraft.webmagic.Page;
import static org.assertj.core.api.Assertions.assertThat;
......@@ -16,5 +17,9 @@ public class JsonTest {
public void testRemovePadding() throws Exception {
String name = new Json(text).removePadding("callback").jsonPath("$.name").get();
assertThat(name).isEqualTo("json");
Page page = null;
page.getJson().jsonPath("$.name").get();
page.getJson().removePadding("callback").jsonPath("$.name").get();
}
}
package us.codecraft.webmagic.samples;
import org.apache.commons.collections.CollectionUtils;
import us.codecraft.webmagic.Page;
import us.codecraft.webmagic.Site;
import us.codecraft.webmagic.processor.PageProcessor;
import us.codecraft.webmagic.selector.JsonPathSelector;
import java.util.List;
/**
* @author yihua.huang@dianping.com
* @author code4crafter@gmail.com
* @since 0.5.0
*/
public class AngularJSProcessor implements PageProcessor{
public class AngularJSProcessor implements PageProcessor {
private Site site = Site.me();
private static final String ARITICALE_URL = "http://angularjs\\.cn/api/article/\\w+";
private static final String LIST_URL = "http://angularjs\\.cn/api/article/latest.*";
@Override
public void process(Page page) {
if (page.getUrl().regex(LIST_URL).match()) {
List<String> ids = new JsonPathSelector("$.data._id").selectList(page.getRawText());
if (CollectionUtils.isNotEmpty(ids)) {
for (String id : ids) {
page.addTargetRequest("http://angularjs\\.cn/api/article/" + id);
}
}
} else {
page.putField("title", new JsonPathSelector("$.title").select(page.getRawText()));
page.putField("content", new JsonPathSelector("$.content").select(page.getRawText()));
}
}
@Override
public Site getSite() {
return null;
return site;
}
}
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment