webMagic-Mobai
/
magic-Dependency
mirror of https://gitea.qinmian.online/Mobai/magic-Dependency.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

fix GithubRepoPageProcessor in example

master
yihua.huang 2016-11-24 08:18:06 +08:00
parent cfed860fb9
commit dafd2b77ff
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
webmagic-core/src/main/java/us/codecraft/webmagic/processor/example/GithubRepoPageProcessor.java
View File

@ -11,11 +11,11 @@ import us.codecraft.webmagic.processor.PageProcessor;
*/ */
public class GithubRepoPageProcessor implements PageProcessor { public class GithubRepoPageProcessor implements PageProcessor {
private Site site = Site.me().setRetryTimes(3).setSleepTime(0); private Site site = Site.me().setRetryTimes(3).setSleepTime(1000);
@Override @Override
public void process(Page page) { public void process(Page page) {
page.addTargetRequests(page.getHtml().links().regex("(https://github\\.com/[\\w\\-]+/[\\w\\-])").all()); page.addTargetRequests(page.getHtml().links().regex("(https://github\\.com/[\\w\\-]+/[\\w\\-]+)").all());
page.addTargetRequests(page.getHtml().links().regex("(https://github\\.com/[\\w\\-])").all()); page.addTargetRequests(page.getHtml().links().regex("(https://github\\.com/[\\w\\-])").all());
page.putField("author", page.getUrl().regex("https://github\\.com/(\\w+)/.*").toString()); page.putField("author", page.getUrl().regex("https://github\\.com/(\\w+)/.*").toString());
page.putField("name", page.getHtml().xpath("//h1[@class='entry-title public']/strong/a/text()").toString()); page.putField("name", page.getHtml().xpath("//h1[@class='entry-title public']/strong/a/text()").toString());