fix #44

zhegexiaohuozi · Sep 25, 2020 · 4ad42a4 · 4ad42a4
1 parent e637b49
commit 4ad42a4
Show file tree

Hide file tree

Showing 2 changed files with 31 additions and 1 deletion.
diff --git a/src/main/java/org/seimicrawler/xpath/core/node/Text.java b/src/main/java/org/seimicrawler/xpath/core/node/Text.java
@@ -12,6 +12,8 @@
 import org.jsoup.nodes.Element;
 import org.jsoup.select.Elements;
 
+import java.lang.reflect.Field;
+import java.lang.reflect.Method;
 import java.util.HashMap;
 import java.util.List;
 import java.util.Map;
@@ -59,6 +61,13 @@ public void head(Node node, int depth) {
                                 }
                                 Element data = new Element(Constants.DEF_TEXT_TAG_NAME);
                                 data.text(textNode.getWholeText());
+                                try {
+                                    Method parent = Node.class.getDeclaredMethod("setParentNode",Node.class);
+                                    parent.setAccessible(true);
+                                    parent.invoke(data,textNode.parent());
+                                } catch (Exception e) {
+                                    //ignore
+                                }
                                 CommonUtil.setSameTagIndexInSiblings(data,index);
                                 res.add(data);
                             }

diff --git a/src/test/java/org/seimicrawler/xpath/JXDocumentTest.java b/src/test/java/org/seimicrawler/xpath/JXDocumentTest.java
@@ -222,8 +222,11 @@ public void testA(){
         }
     }
 
+    /**
+     * fix https://github.com/zhegexiaohuozi/JsoupXpath/issues/52
+     */
     @Test
-    public void FixTextBehaviorTest(){
+    public void fixTextBehaviorTest(){
         String html = "<p><span class=\"text-muted\">分类：</span>动漫<span class=\"split-line\"></span><span class=\"text-muted hidden-xs\">地区：</span>日本<span class=\"split-line\"></span><span class=\"text-muted hidden-xs\">年份：</span>2010</p>";
         JXDocument jxDocument = JXDocument.create(html);
         List<JXNode> jxNodes = jxDocument.selN("//text()[3]");
@@ -235,4 +238,22 @@ public void FixTextBehaviorTest(){
         logger.info("all = {}",allText);
     }
 
+    /**
+     * fix https://github.com/zhegexiaohuozi/JsoupXpath/issues/44
+     */
+    @Test
+    public void fixTextElNoParentTest(){
+        String test="<div class='a'> a <div>need</div> <div class='e'> not need</div> c </div>";
+        JXDocument j = JXDocument.create(test);
+        List<JXNode> l = j.selN("//div[@class='a']//text()[not(ancestor::div[@class='e'])]");
+        Set<String> finalRes = new HashSet<>();
+        for (JXNode i : l){
+            logger.info("{}",i.toString());
+            finalRes.add(i.asString());
+        }
+        Assert.assertFalse(finalRes.contains("not need"));
+        Assert.assertTrue(finalRes.contains("need"));
+        Assert.assertEquals(4, finalRes.size());
+    }
+
 }