Preserve IDs & class names of unwrapped DIVs

parser.go

@@ -890,8 +890,16 @@ func (ps *Parser) grabArticle() *html.Node {
 				// the scoring algorithm with DIVs with are, in
 				// practice, paragraphs.
 				if ps.hasSingleTagInsideElement(node, "p") && ps.getLinkDensity(node) < 0.25 {
+					divID := dom.ID(node)
+					divClassName := dom.ClassName(node)
 					newNode := dom.Children(node)[0]
 					node, _ = dom.ReplaceChild(node.Parent, newNode, node)
+					if divID != "" && dom.ID(node) == "" {
+						dom.SetAttribute(node, "id", divID)
+					}
+					if divClassName != "" && dom.ClassName(node) == "" {
+						dom.SetAttribute(node, "class", divClassName)
+					}
 					elementsToScore = append(elementsToScore, node)
 				} else if !ps.hasChildBlockElement(node) {
 					ps.setNodeTag(node, "p")

test-pages/gmw/expected.html

@@ -51,7 +51,7 @@
                     <a href="http://www.gmw.cn" target="_blank"><img src="https://img.gmw.cn/pic/content_logo.png" title="返回光明网首页"/></a>
                 </p>
 
-                <p>[责任编辑:肖春芳]</p>
+                <p id="contentLiability">[责任编辑:肖春芳]</p>
 
 
             </div></div>

test-pages/lazy-image-1/expected.html

@@ -38,7 +38,7 @@ <h2 id="292e">
                                         (for more details about V8 and its garbage collector you can read my previous article <a target="_blank" rel="noopener" href="http://fakehost/voodoo-engineering/nodejs-internals-v8-garbage-collector-a6eca82540ec">here</a>)
                                     </p>
                                     <blockquote>
-                                        <p>
+                                        <p id="6f9a">
                                                 Stay focused on the CPU!
                                             </p>
                                     </blockquote>
@@ -61,7 +61,7 @@ <h2 id="8d00">
                                         CPU profiling: what’s the difference with CPU monitoring?
                                     </h2>
                                     <blockquote>
-                                        <p>
+                                        <p id="19fb">
                                                 “Most commonly, profiling information serves to aid program optimization. Profiling is achieved by instrumenting either the program source code or its binary executable form using a tool called a profiler”
                                             </p>
                                     </blockquote>