github-forks
/
webmagic
mirror of https://github.com/code4craft/webmagic.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity

try invite selenium

Browse Source
pull/17/head
yihua.huang 12 years ago
parent c2142f872b
commit d3e527fd6b
6 changed files with 165 additions and 223 deletions
Show Stats Download Patch File Download Diff File

110
pom.xml
Unescape Escape View File

@ -3,17 +3,64 @@
xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
<groupId>us.codecraft</groupId>
<version>0.0.1-SNAPSHOT</version>
<version>0.1.0</version>
<modelVersion>4.0.0</modelVersion>
<packaging>pom</packaging>
<artifactId>webmagic</artifactId>
<modules>
<module>./webmagic-core</module>
<module>./webmagic-plugin/</module>
<module>./webmagic-samples/</module>
<module>webmagic-core</module>
<module>webmagic-plugin/</module>
<module>webmagic-samples/</module>
<module>webmagic-selenium</module>
</modules>
<dependencyManagement>
<dependencies>
<dependency>
<groupId>junit</groupId>
<artifactId>junit</artifactId>
<version>4.7</version>
<scope>test</scope>
</dependency>
<dependency>
<groupId>org.apache.httpcomponents</groupId>
<artifactId>httpclient</artifactId>
<version>4.2.4</version>
</dependency>
<dependency>
<groupId>log4j</groupId>
<artifactId>log4j</artifactId>
<version>1.2.17</version>
</dependency>
<dependency>
<groupId>org.apache.commons</groupId>
<artifactId>commons-lang3</artifactId>
<version>3.1</version>
</dependency>
<dependency>
<groupId>commons-collections</groupId>
<artifactId>commons-collections</artifactId>
<version>3.2.1</version>
</dependency>
<dependency>
<groupId>net.sourceforge.htmlcleaner</groupId>
<artifactId>htmlcleaner</artifactId>
<version>2.4</version>
</dependency>
<dependency>
<groupId>org.apache.commons</groupId>
<artifactId>commons-io</artifactId>
<version>1.3.2</version>
</dependency>
<dependency>
<groupId>org.jsoup</groupId>
<artifactId>jsoup</artifactId>
<version>1.7.2</version>
</dependency>
</dependencies>
</dependencyManagement>
<build>
<plugins>
<plugin>
@ -25,6 +72,61 @@
<target>1.6</target>
</configuration>
</plugin>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-dependency-plugin</artifactId>
<executions>
<execution>
<id>copy-dependencies</id>
<phase>package</phase>
<goals>
<goal>copy-dependencies</goal>
</goals>
<configuration>
<outputDirectory>${project.build.directory}/lib</outputDirectory>
<overWriteReleases>false</overWriteReleases>
<overWriteSnapshots>false</overWriteSnapshots>
<overWriteIfNewer>true</overWriteIfNewer>
</configuration>
</execution>
</executions>
</plugin>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-resources-plugin</artifactId>
<configuration>
<encoding>UTF-8</encoding>
</configuration>
</plugin>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-source-plugin</artifactId>
<executions>
<execution>
<id>attach-sources</id>
<goals>
<goal>jar</goal>
</goals>
</execution>
</executions>
</plugin>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-javadoc-plugin</artifactId>
<executions>
<execution>
<id>attach-javadocs</id>
<goals>
<goal>jar</goal>
</goals>
</execution>
</executions>
</plugin>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-release-plugin</artifactId>
<version>2.0-beta-7</version>
</plugin>
</plugins>
</build>

69
webmagic-core/pom.xml
Unescape Escape View File

@ -2,8 +2,11 @@
<project xmlns="http://maven.apache.org/POM/4.0.0"
xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
<parent>
<groupId>us.codecraft</groupId>
<artifactId>webmagic</artifactId>
<version>0.1.0</version>
</parent>
<modelVersion>4.0.0</modelVersion>
<artifactId>webmagic-core</artifactId>
@ -12,109 +15,43 @@
<dependency>
<groupId>org.apache.httpcomponents</groupId>
<artifactId>httpclient</artifactId>
<version>4.2.4</version>
</dependency>
<dependency>
<groupId>junit</groupId>
<artifactId>junit</artifactId>
<version>4.7</version>
<scope>test</scope>
</dependency>
<dependency>
<groupId>com.google.guava</groupId>
<artifactId>guava</artifactId>
<version>13.0.1</version>
</dependency>
<dependency>
<groupId>org.apache.commons</groupId>
<artifactId>commons-lang3</artifactId>
<version>3.1</version>
</dependency>
<dependency>
<groupId>log4j</groupId>
<artifactId>log4j</artifactId>
<version>1.2.17</version>
</dependency>
<dependency>
<groupId>commons-collections</groupId>
<artifactId>commons-collections</artifactId>
<version>3.2.1</version>
</dependency>
<dependency>
<groupId>net.sourceforge.htmlcleaner</groupId>
<artifactId>htmlcleaner</artifactId>
<version>2.4</version>
</dependency>
<dependency>
<groupId>org.jsoup</groupId>
<artifactId>jsoup</artifactId>
<version>1.7.2</version>
</dependency>
<dependency>
<groupId>org.apache.commons</groupId>
<artifactId>commons-io</artifactId>
<version>1.3.2</version>
</dependency>
</dependencies>
<build>
<plugins>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-compiler-plugin</artifactId>
<version>3.1</version>
<configuration>
<source>1.6</source>
<target>1.6</target>
</configuration>
</plugin>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-resources-plugin</artifactId>
<configuration>
<encoding>UTF-8</encoding>
</configuration>
</plugin>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-source-plugin</artifactId>
<executions>
<execution>
<id>attach-sources</id>
<goals>
<goal>jar</goal>
</goals>
</execution>
</executions>
</plugin>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-javadoc-plugin</artifactId>
<executions>
<execution>
<id>attach-javadocs</id>
<goals>
<goal>jar</goal>
</goals>
</execution>
</executions>
</plugin>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-release-plugin</artifactId>
<version>2.0-beta-7</version>
</plugin>
</plugins>
</build>
</project>

58
webmagic-plugin/pom.xml
Unescape Escape View File

@ -2,8 +2,11 @@
<project xmlns="http://maven.apache.org/POM/4.0.0"
xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
<parent>
<groupId>us.codecraft</groupId>
<artifactId>webmagic</artifactId>
<version>0.1.0</version>
</parent>
<modelVersion>4.0.0</modelVersion>
<artifactId>webmagic-plugin</artifactId>
@ -12,13 +15,11 @@
<dependency>
<groupId>us.codecraft</groupId>
<artifactId>webmagic-core</artifactId>
<version>0.1.0</version>
<version>${project.version}</version>
</dependency>
<dependency>
<groupId>junit</groupId>
<artifactId>junit</artifactId>
<version>4.7</version>
<scope>test</scope>
</dependency>
<dependency>
<groupId>org.freemarker</groupId>
@ -32,55 +33,4 @@
</dependency>
</dependencies>
<build>
<plugins>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-compiler-plugin</artifactId>
<version>3.1</version>
<configuration>
<source>1.6</source>
<target>1.6</target>
</configuration>
</plugin>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-resources-plugin</artifactId>
<configuration>
<encoding>UTF-8</encoding>
</configuration>
</plugin>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-source-plugin</artifactId>
<executions>
<execution>
<id>attach-sources</id>
<goals>
<goal>jar</goal>
</goals>
</execution>
</executions>
</plugin>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-javadoc-plugin</artifactId>
<executions>
<execution>
<id>attach-javadocs</id>
<goals>
<goal>jar</goal>
</goals>
</execution>
</executions>
</plugin>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-release-plugin</artifactId>
<version>2.0-beta-7</version>
</plugin>
</plugins>
</build>
</project>

93
webmagic-samples/pom.xml
Unescape Escape View File

@ -2,9 +2,11 @@
<project xmlns="http://maven.apache.org/POM/4.0.0"
xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
<parent>
<groupId>us.codecraft</groupId>
<artifactId>webmagic</artifactId>
<version>0.1.0</version>
</parent>
<modelVersion>4.0.0</modelVersion>
<artifactId>webmagic-samples</artifactId>
@ -13,102 +15,17 @@
<dependency>
<groupId>us.codecraft</groupId>
<artifactId>webmagic-core</artifactId>
<version>0.1.0</version>
<version>${project.version}</version>
</dependency>
<dependency>
<groupId>us.codecraft</groupId>
<artifactId>webmagic-plugin</artifactId>
<version>0.1.0</version>
<version>${project.version}</version>
</dependency>
<dependency>
<groupId>junit</groupId>
<artifactId>junit</artifactId>
<version>4.7</version>
<scope>test</scope>
</dependency>
</dependencies>
<build>
<plugins>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-compiler-plugin</artifactId>
<version>3.1</version>
<configuration>
<source>1.6</source>
<target>1.6</target>
</configuration>
</plugin>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-dependency-plugin</artifactId>
<executions>
<execution>
<id>copy-dependencies</id>
<phase>package</phase>
<goals>
<goal>copy-dependencies</goal>
</goals>
<configuration>
<outputDirectory>${project.build.directory}/lib</outputDirectory>
<overWriteReleases>false</overWriteReleases>
<overWriteSnapshots>false</overWriteSnapshots>
<overWriteIfNewer>true</overWriteIfNewer>
</configuration>
</execution>
</executions>
</plugin>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-resources-plugin</artifactId>
<configuration>
<encoding>UTF-8</encoding>
</configuration>
</plugin>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-source-plugin</artifactId>
<executions>
<execution>
<id>attach-sources</id>
<goals>
<goal>jar</goal>
</goals>
</execution>
</executions>
</plugin>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-javadoc-plugin</artifactId>
<executions>
<execution>
<id>attach-javadocs</id>
<goals>
<goal>jar</goal>
</goals>
</execution>
</executions>
</plugin>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-jar-plugin</artifactId>
<configuration>
<archive>
<manifest>
<addClasspath>true</addClasspath>
<classpathPrefix>./lib/</classpathPrefix>
<mainClass>us.codecraft.webmagic.samples.DianpingIndexProcessor</mainClass>
</manifest>
</archive>
</configuration>
</plugin>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-release-plugin</artifactId>
<version>2.0-beta-7</version>
</plugin>
</plugins>
</build>
</project>

5
webmagic-samples/src/main/java/us/codecraft/webmagic/samples/IteyeBlogProcessor.java
Unescape Escape View File

@ -26,13 +26,12 @@ public class IteyeBlogProcessor implements PageProcessor {
public Site getSite() {
if (site == null) {
site = Site.me().setDomain("yanghaoli.iteye.com").addStartUrl("http://yanghaoli.iteye.com/").
setUserAgent("Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_2) AppleWebKit/537.31 (KHTML, like Gecko) Chrome/26.0.1410.65 Safari/537.31")
.setSleepTime(100).setRetryTimes(3);
setSleepTime(100).setRetryTimes(3);
}
return site;
}
public static void main(String[] args) {
Spider.create(new IteyeBlogProcessor()).thread(5).pipeline(new FilePipeline()).run();
Spider.create(new IteyeBlogProcessor()).thread(5).pipeline(new FilePipeline("/data/webmagic/")).run();
}
}

37
webmagic-selenium/pom.xml
Unescape Escape View File

@ -0,0 +1,37 @@
<?xml version="1.0" encoding="UTF-8"?>
<project xmlns="http://maven.apache.org/POM/4.0.0"
xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
<parent>
<groupId>us.codecraft</groupId>
<artifactId>webmagic</artifactId>
<version>0.1.0</version>
</parent>
<modelVersion>4.0.0</modelVersion>
<artifactId>webmagic-selenium</artifactId>
<dependencies>
<dependency>
<groupId>us.codecraft</groupId>
<artifactId>webmagic-core</artifactId>
<version>${project.version}</version>
</dependency>
<dependency>
<groupId>us.codecraft</groupId>
<artifactId>webmagic-plugin</artifactId>
<version>${project.version}</version>
</dependency>
<dependency>
<groupId>junit</groupId>
<artifactId>junit</artifactId>
</dependency>
<dependency>
<groupId>org.seleniumhq.selenium</groupId>
<artifactId>selenium-java</artifactId>
<version>2.33.0</version>
</dependency>
</dependencies>
</project>
Write Preview
Loading…
Cancel
Save