Add HTML parser, properly remove img tags

BirdyNet.py

@@ -26,6 +26,7 @@ from qtpy.QtCore import *
 from qtpy.QtMultimedia import QSound
 import configparser
 import json
+import time
 
 os.chdir(sp)
 distro = os.path.splitext(s.rsplit(os.path.sep)[-1])[0]
@@ -97,6 +98,8 @@ class browserWindow(QMainWindow):
 		
 		self.cDoc = browserDoc(self)
 		
+		self.cStatusBar = QStatusBar(self)
+		
 		self.cResizeElements()
 		self.show()
 		self.cNavigate()
@@ -110,7 +113,11 @@ class browserWindow(QMainWindow):
 		self.cButtonGo.resize(barSize,barSize)
 		
 		self.cDoc.move(0,mb + barSize)
-		self.cDoc.resize(self.cWidth,self.cHeight - barSize - mb)
+		self.cDoc.resize(self.cWidth,self.cHeight - barSize - mb - mb)
+		
+		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()
@@ -119,12 +126,20 @@ class browserWindow(QMainWindow):
 	
 	def cNavigate(self,event = None):
 		try:
-			print(prettyJson(parseUrl(self.cUrlBar.text())))
+			#print(prettyJson(parseUrl(self.cUrlBar.text())))
+			start = time.time()
 			response = downloadPage(self.cUrlBar.text(),{"User-Agent": self.cUserAgent})
+			end = time.time()
+			print("Downloading page: " +str(end - start))
+			
 			infoFetcher(response)
 			self.cDocumentInfo = response
+			
+			start = time.time()
 			self.cDoc.cRenderHtml(response["body"].decode("utf-8",errors="ignore"))
-			print(prettyJson(response["headers"]))
+			end = time.time()
+			print("Rendering page: " +str(end - start))
+			#print(prettyJson(response["headers"]))
 		except Exception as e:
 			self.cDoc.cRenderHtml(str(e))
 			raise

addons/0.documentViewer.QTextBrowser.py

@@ -1,3 +1,9 @@
+global HTMLParser
+from html.parser import HTMLParser
+
+global html
+import html
+
 global browserDoc
 class browserDoc(QTextBrowser):
 	def __init__(self,*args,**kwargs):
@@ -13,9 +19,46 @@ class browserDoc(QTextBrowser):
 		self.setStyleSheet("QTextBrowser { " +style+ " }")
 		self.anchorClicked.connect(self.cAnchorClicked)
 	
-	def cRenderHtml(self,html):
+	class cHtmlParser(HTMLParser):
+		def __init__(self):
+			HTMLParser.__init__(self)
+			self.output = ""
+		
+		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 += '<a href="' +html.escape(url)+ '">image: ' +html.escape(altText)+ '</a>'
+						return
+				
+				return
+			
+			self.output += "<" +tag
+			for attr in attrs:
+				self.output += ' ' +html.escape(attr[0])+ '="' +html.escape(attr[1])+ '"'
+			self.output += ">"
+		
+		def handle_endtag(self,tag):
+			if tag in ["img"]: return
+			self.output += "</" +html.escape(tag)+ ">"
+		
+		def handle_data(self,data):
+			self.output += data
+	
+	def cRenderHtml(self,htm):
+		parser = self.cHtmlParser()
+		parser.feed(htm)
+		
 		self.clear()
-		self.insertHtml(html.replace("<img","<dummy")) # half-assed slowdown fix
+		self.insertHtml(parser.output)
 		self.update()
 	
 	def cAnchorClicked(self,url):
@@ -24,8 +67,9 @@ class browserDoc(QTextBrowser):
 		curUrl = browserWindow.cDocumentInfo["url"]
 		curUrlParsed = parseUrl(curUrl)
 		urlParsed = parseUrl(url)
-		#print("navigating from: " +curUrl)
-		#print("to: " +url)
+		print("---")
+		print("navigating from: " +curUrl)
+		print("to: " +url)
 		if urlParsed["protocol"] == "": # is relative
 			if url[0] == "#":
 				curUrlParsed["anchor"] = url[1:]