Skip to content

W
webmagic
Commit dafd2b77 authored by yihua.huang's avatar yihua.huang
Browse files
Options

fix GithubRepoPageProcessor in example

parent cfed860f
Hide whitespace changes
Inline Side-by-side
Showing with 2 additions and 2 deletions
webmagic-core/src/main/java/us/codecraft/webmagic/processor/example/GithubRepoPageProcessor.java
View file @ dafd2b77
...@@ -11,11 +11,11 @@ import us.codecraft.webmagic.processor.PageProcessor; ...@@ -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());
......
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