Mobai
/
magic-Dependency
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

update jsoup to 1.10.3 #608

master
yihua.huang 2017-06-24 11:29:35 +08:00
parent faca38d4ec
commit eb376fca74
3 changed files with 2 additions and 19 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
pom.xml
View File

@ -146,7 +146,7 @@
<dependency> <dependency>
<groupId>org.jsoup</groupId> <groupId>org.jsoup</groupId>
<artifactId>jsoup</artifactId> <artifactId>jsoup</artifactId>
<version>1.8.3</version> <version>1.10.3</version>
</dependency> </dependency>
<dependency> <dependency>
<groupId>org.mockito</groupId> <groupId>org.mockito</groupId>

18
webmagic-core/src/main/java/us/codecraft/webmagic/selector/Html.java
View File

@ -3,7 +3,6 @@ package us.codecraft.webmagic.selector;
import org.jsoup.Jsoup; import org.jsoup.Jsoup;
import org.jsoup.nodes.Document; import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element; import org.jsoup.nodes.Element;
import org.jsoup.nodes.Entities;
import org.slf4j.Logger; import org.slf4j.Logger;
import org.slf4j.LoggerFactory; import org.slf4j.LoggerFactory;
@ -20,25 +19,12 @@ public class Html extends HtmlNode {
private Logger logger = LoggerFactory.getLogger(getClass()); private Logger logger = LoggerFactory.getLogger(getClass());
private static volatile boolean INITED = false;
/** /**
* Disable jsoup html entity escape. It can be set just before any Html instance is created. * Disable jsoup html entity escape. It can be set just before any Html instance is created.
* @deprecated
*/ */
public static boolean DISABLE_HTML_ENTITY_ESCAPE = false; public static boolean DISABLE_HTML_ENTITY_ESCAPE = false;
/**
* Disable jsoup html entity escape. It is a hack way only for jsoup 1.7.2.
*/
private void disableJsoupHtmlEntityEscape() {
if (DISABLE_HTML_ENTITY_ESCAPE && !INITED) {
Entities.EscapeMode.base.getMap().clear();
Entities.EscapeMode.extended.getMap().clear();
Entities.EscapeMode.xhtml.getMap().clear();
INITED = true;
}
}
/** /**
* Store parsed document for better performance when only one text exist. * Store parsed document for better performance when only one text exist.
*/ */
@ -46,7 +32,6 @@ public class Html extends HtmlNode {
public Html(String text, String url) { public Html(String text, String url) {
try { try {
disableJsoupHtmlEntityEscape();
this.document = Jsoup.parse(text, url); this.document = Jsoup.parse(text, url);
} catch (Exception e) { } catch (Exception e) {
this.document = null; this.document = null;
@ -56,7 +41,6 @@ public class Html extends HtmlNode {
public Html(String text) { public Html(String text) {
try { try {
disableJsoupHtmlEntityEscape();
this.document = Jsoup.parse(text); this.document = Jsoup.parse(text);
} catch (Exception e) { } catch (Exception e) {
this.document = null; this.document = null;

1
webmagic-core/src/test/java/us/codecraft/webmagic/HtmlTest.java
View File

@ -30,7 +30,6 @@ public class HtmlTest {
@Test @Test
public void testEnableJsoupHtmlEntityEscape() throws Exception { public void testEnableJsoupHtmlEntityEscape() throws Exception {
Html.DISABLE_HTML_ENTITY_ESCAPE = false;
Html html = new Html("aaaaaaa&b"); Html html = new Html("aaaaaaa&b");
assertThat(html.regex("(aaaaaaa&amp;b)").toString()).isEqualTo("aaaaaaa&amp;b"); assertThat(html.regex("(aaaaaaa&amp;b)").toString()).isEqualTo("aaaaaaa&amp;b");
} }