From 4738ae2d14a0d2419026cf5b2e9990cf3f3e06f1 Mon Sep 17 00:00:00 2001 From: "yihua.huang" Date: Fri, 25 Apr 2014 16:04:41 +0800 Subject: [PATCH] change url find to match #94 --- .../codecraft/webmagic/example/PatternProcessorExample.java | 6 +++--- .../codecraft/webmagic/handler/PatternRequestMatcher.java | 2 +- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/webmagic-extension/src/main/java/us/codecraft/webmagic/example/PatternProcessorExample.java b/webmagic-extension/src/main/java/us/codecraft/webmagic/example/PatternProcessorExample.java index 84b3164..f6b2e9b 100644 --- a/webmagic-extension/src/main/java/us/codecraft/webmagic/example/PatternProcessorExample.java +++ b/webmagic-extension/src/main/java/us/codecraft/webmagic/example/PatternProcessorExample.java @@ -31,7 +31,7 @@ public class PatternProcessorExample { @Override public RequestMatcher.MatchOther processResult(ResultItems resultItems, Task task) { log.info("Extracting from repo" + resultItems.getRequest()); - System.out.println(resultItems.get("reponame")); + System.out.println("Repo name: "+resultItems.get("reponame")); return RequestMatcher.MatchOther.YES; } }; @@ -49,12 +49,12 @@ public class PatternProcessorExample { @Override public RequestMatcher.MatchOther processResult(ResultItems resultItems, Task task) { - System.out.println(resultItems.get("username")); + System.out.println("User name: "+resultItems.get("username")); return RequestMatcher.MatchOther.YES; } }; - CompositePageProcessor pageProcessor = new CompositePageProcessor(Site.me().setDomain("github.com")); + CompositePageProcessor pageProcessor = new CompositePageProcessor(Site.me().setDomain("github.com").setRetryTimes(0).setSleepTime(0)); CompositePipeline pipeline = new CompositePipeline(); pageProcessor.setSubPageProcessors(githubRepoProcessor, githubUserProcessor); diff --git a/webmagic-extension/src/main/java/us/codecraft/webmagic/handler/PatternRequestMatcher.java b/webmagic-extension/src/main/java/us/codecraft/webmagic/handler/PatternRequestMatcher.java index 5c0f31a..9201a4c 100644 --- a/webmagic-extension/src/main/java/us/codecraft/webmagic/handler/PatternRequestMatcher.java +++ b/webmagic-extension/src/main/java/us/codecraft/webmagic/handler/PatternRequestMatcher.java @@ -32,6 +32,6 @@ public abstract class PatternRequestMatcher implements RequestMatcher { @Override public boolean match(Request request) { - return patternCompiled.matcher(request.getUrl()).find(); + return patternCompiled.matcher(request.getUrl()).matches(); } }