From fc68c0f7d86fbfb7188b7dff6d812e269e48ddcb Mon Sep 17 00:00:00 2001
From: "yihua.huang" <code4crafter@gmail.com>
Date: Fri, 16 Aug 2013 12:22:00 +0800
Subject: [PATCH] add docs in en

---
 en_docs/README.md | 98 +++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 98 insertions(+)
 create mode 100644 en_docs/README.md

diff --git a/en_docs/README.md b/en_docs/README.md
new file mode 100644
index 00000000..c420f499
--- /dev/null
+++ b/en_docs/README.md
@@ -0,0 +1,98 @@
+webmagic
+---
+[![Build Status](https://travis-ci.org/code4craft/webmagic.png?branch=master)](https://travis-ci.org/code4craft/webmagic)
+
+>A crawler framework.
+
+## Features:
+
+* Simple core with high flexibility.
+* Simple API for html extracting.
+* Multi-thread and Distributed support.
+* Easy to be integrated.
+
+## Install:
+
+Clone the repo and build:
+
+	git clone https://github.com/code4craft/webmagic.git
+	cd webmagic
+	mvn clean install	  
+
+Add dependencies to your project:
+
+		<dependency>
+            <groupId>us.codecraft</groupId>
+            <artifactId>webmagic-core</artifactId>
+            <version>0.2.0</version>
+        </dependency>
+		<dependency>
+            <groupId>us.codecraft</groupId>
+            <artifactId>webmagic-extension</artifactId>
+            <version>0.2.0</version>
+        </dependency>
+
+## Get Started:
+
+### First crawler:
+
+Write a class implements PageProcessor：
+
+    public class OschinaBlogPageProcesser implements PageProcessor {
+
+        private Site site = Site.me().setDomain("my.oschina.net")
+           .addStartUrl("http://my.oschina.net/flashsword/blog");
+
+        @Override
+        public void process(Page page) {
+            List<String> links = page.getHtml().links().regex("http://my\\.oschina\\.net/flashsword/blog/\\d+").all();
+            page.addTargetRequests(links);
+            page.putField("title", page.getHtml().xpath("//div[@class='BlogEntity']/div[@class='BlogTitle']/h1").toString());
+            page.putField("content", page.getHtml().$("div.content").toString());
+            page.putField("tags",page.getHtml().xpath("//div[@class='BlogTags']/a/text()").all());
+        }
+
+        @Override
+        public Site getSite() {
+            return site;
+
+        }
+
+        public static void main(String[] args) {
+            Spider.create(new OschinaBlogPageProcesser())
+                 .pipeline(new ConsolePipeline()).run();
+        }
+    }
+
+* `page.addTargetRequests(links)`
+	
+	Add urls for crawling.
+    
+You can also use annotation way:
+
+	@TargetUrl("http://my.oschina.net/flashsword/blog/\\d+")
+	public class OschinaBlog {
+
+	    @ExtractBy("//title")
+	    private String title;
+
+	    @ExtractBy(value = "div.BlogContent",type = ExtractBy.Type.Css)
+	    private String content;
+
+	    @ExtractBy(value = "//div[@class='BlogTags']/a/text()", multi = true)
+	    private List<String> tags;
+
+	    public static void main(String[] args) {
+	        OOSpider.create(
+	        	Site.me().addStartUrl("http://my.oschina.net/flashsword/blog"),
+				new ConsolePageModelPipeline(), OschinaBlog.class).run();
+	    }
+	}
+	
+### Samples:
+
+There are some samples in `webmagic-samples` package.
+
+### Lisence:
+
+Lisenced under [Apache 2.0 lisence](http://opensource.org/licenses/Apache-2.0)
\ No newline at end of file