fix dep of slf4j-log4j12

master
yihua.huang 2014-04-03 23:04:31 +08:00
parent a34e92d11a
commit a1c7e826f7
3 changed files with 26 additions and 29 deletions

View File

@ -50,33 +50,35 @@ WebMagic use slf4j with slf4j-log4j12 implementation. If you customized your slf
### First crawler: ### First crawler:
Write a class implements PageProcessor Write a class implements PageProcessor. For example, I wrote a crawler of github repository infomation.
```java ```java
public class OschinaBlogPageProcesser implements PageProcessor { public class GithubRepoPageProcessor implements PageProcessor {
private Site site = Site.me().setDomain("my.oschina.net"); private Site site = Site.me().setRetryTimes(3).setSleepTime(1000);
@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(); page.addTargetRequests(page.getHtml().links().regex("(https://github\\.com/\\w+/\\w+)").all());
page.addTargetRequests(links); page.putField("author", page.getUrl().regex("https://github\\.com/(\\w+)/.*").toString());
page.putField("title", page.getHtml().xpath("//div[@class='BlogEntity']/div[@class='BlogTitle']/h1").toString()); page.putField("name", page.getHtml().xpath("//h1[@class='entry-title public']/strong/a/text()").toString());
page.putField("content", page.getHtml().$("div.content").toString()); if (page.getResultItems().get("name")==null){
page.putField("tags",page.getHtml().xpath("//div[@class='BlogTags']/a/text()").all()); //skip this page
page.setSkip(true);
}
page.putField("readme", page.getHtml().xpath("//div[@id='readme']/tidyText()"));
} }
@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 GithubRepoPageProcessor()).addUrl("https://github.com/code4craft").thread(5).run();
.addPipeline(new ConsolePipeline()).run();
} }
} }
``` ```
* `page.addTargetRequests(links)` * `page.addTargetRequests(links)`
@ -86,22 +88,23 @@ public class OschinaBlogPageProcesser 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("https://github.com/\\w+/\\w+")
public class OschinaBlog { @HelpUrl("https://github.com/\\w+")
public class GithubRepo {
@ExtractBy("//title") @ExtractBy(value = "//h1[@class='entry-title public']/strong/a/text()", notNull = true)
private String title; private String name;
@ExtractBy(value = "div.BlogContent",type = ExtractBy.Type.Css) @ExtractByUrl("https://github\\.com/(\\w+)/.*")
private String content; private String author;
@ExtractBy(value = "//div[@class='BlogTags']/a/text()", multi = true) @ExtractBy("//div[@id='readme']/tidyText()")
private List<String> tags; private String readme;
public static void main(String[] args) { public static void main(String[] args) {
OOSpider.create( OOSpider.create(Site.me().setSleepTime(1000)
Site.me(), , new ConsolePageModelPipeline(), GithubRepo.class)
new ConsolePageModelPipeline(), OschinaBlog.class).addUrl("http://my.oschina.net/flashsword/blog").run(); .addUrl("https://github.com/code4craft").thread(5).run();
} }
} }
``` ```

View File

@ -11,7 +11,7 @@ import us.codecraft.webmagic.processor.PageProcessor;
*/ */
public class GithubRepoPageProcessor implements PageProcessor { public class GithubRepoPageProcessor implements PageProcessor {
private Site site = Site.me().setRetryTimes(3).setSleepTime(100); private Site site = Site.me().setRetryTimes(3).setSleepTime(1000);
@Override @Override
public void process(Page page) { public void process(Page page) {

View File

@ -23,12 +23,6 @@
<groupId>us.codecraft</groupId> <groupId>us.codecraft</groupId>
<artifactId>webmagic-core</artifactId> <artifactId>webmagic-core</artifactId>
<version>${project.version}</version> <version>${project.version}</version>
<exclusions>
<exclusion>
<groupId>org.slf4j</groupId>
<artifactId>slf4j-log4j12</artifactId>
</exclusion>
</exclusions>
</dependency> </dependency>
<dependency> <dependency>
<groupId>junit</groupId> <groupId>junit</groupId>