"Proper" HTML parsing for whitelists and interpretation

BirdyNet.py

@@ -99,6 +99,7 @@ class browserWindow(QMainWindow):
 		self.cDoc = browserDoc(self)
 		
 		self.cStatusBar = QStatusBar(self)
+		self.cStatusBar.showMessage("Please wait...")
 		
 		self.cResizeElements()
 		self.show()
@@ -117,7 +118,6 @@ class browserWindow(QMainWindow):
 		
 		self.cStatusBar.move(0,self.cHeight - mb)
 		self.cStatusBar.resize(self.cWidth,mb)
-		self.cStatusBar.showMessage("Status")
 	
 	def resizeEvent(self,event):
 		self.cWidth = self.width()
@@ -127,6 +127,8 @@ class browserWindow(QMainWindow):
 	def cNavigate(self,event = None):
 		try:
 			#print(prettyJson(parseUrl(self.cUrlBar.text())))
+			self.cStatusBar.showMessage("Downloading...")
+			self.update()
 			start = time.time()
 			response = downloadPage(self.cUrlBar.text(),{"User-Agent": self.cUserAgent})
 			end = time.time()
@@ -135,10 +137,14 @@ class browserWindow(QMainWindow):
 			infoFetcher(response)
 			self.cDocumentInfo = response
 			
+			self.cStatusBar.showMessage("Rendering...")
+			self.update()
 			start = time.time()
 			self.cDoc.cRenderHtml(response["body"].decode("utf-8",errors="ignore"))
 			end = time.time()
 			print("Rendering page: " +str(end - start))
+			self.cStatusBar.showMessage("Ready")
+			self.update()
 			#print(prettyJson(response["headers"]))
 		except Exception as e:
 			self.cDoc.cRenderHtml(str(e))

addons/0.documentViewer.QTextBrowser.py

@@ -23,37 +23,38 @@ class browserDoc(QTextBrowser):
 		def __init__(self):
 			HTMLParser.__init__(self)
 			self.output = ""
+			self.voidElements = ["area","base","br","col","hr","img","input","link","meta","param","command","keygen","source"]
+			self.blackList = ["img","script","style"]
+			self.tagDir = []
 		
 		def handle_starttag(self,tag,attrs):
-			if tag == "img":
-				altText = False
-				for attr in attrs:
-					if attr[0] == "alt":
-						altText = html.escape(attr[1])
-						break
-				
-				for attr in attrs:
-					if attr[0] == "src":
-						url = attr[1]
-						if not altText: altText = url.rsplit("/")[-1]
-						self.output += 'img:<a href="' +html.escape(url)+ '">' +html.escape(altText)+ '</a>'
-						return
-				
-				return
+			if not tag in self.voidElements:
+				self.tagDir.append(tag)
 			
-			self.output += "<" +tag
+			if tag in self.blackList: return
+			
+			self.output += "<" +html.escape(tag)
 			for attr in attrs:
+				self.output += " " +html.escape(attr[0])
 				if attr[1] != None:
-					self.output += ' ' +html.escape(attr[0])+ '="' +html.escape(attr[1])+ '"'
-				else:
-					self.output += ' ' +html.escape(attr[0])
+					self.output += '="' +html.escape(attr[1])+ '"'
 			self.output += ">"
 		
 		def handle_endtag(self,tag):
-			if tag in ["img"]: return
+			if not tag in self.voidElements:
+				index = len(self.tagDir) - 1
+				while index >= 0:
+					if self.tagDir[index] == tag:
+						self.tagDir = self.tagDir[index + 1:]
+						break
+					index -= 1
 			self.output += "</" +html.escape(tag)+ ">"
 		
 		def handle_data(self,data):
+			curTag = ""
+			if len(self.tagDir) > 0:
+				curTag = self.tagDir[-1]
+			if curTag in self.blackList: return
 			self.output += data
 	
 	def cRenderHtml(self,htm):