X-Git-Url: https://git.llucax.com/software/subdivxget.git/blobdiff_plain/44c70b16fa26aad38244f816c2b0ad3c3a170ecc..f274666ba6db3400c33faf64aa40c3d2ba2d5156:/subdivxget?ds=sidebyside

diff --git a/subdivxget b/subdivxget
index 1aecc66..bd6fc6e 100755
--- a/subdivxget
+++ b/subdivxget
@@ -43,6 +43,8 @@ class SubDivXHTMLParser(HTMLParser.HTMLParser):
 		self.parsing = False
 		self.subs = []
 		self.attr = None
+		self.cur = None
+		self.in_script_style = False
 
 	def handle_starttag(self, tag, attrs):
 		attrs = dict(attrs)
@@ -52,6 +54,9 @@ class SubDivXHTMLParser(HTMLParser.HTMLParser):
 			self.parsing = True
 		if not self.parsing:
 			return
+		if tag == 'script' or tag == 'style':
+			self.in_script_style = True
+			return
 		if tag == 'div':
 			if attrs.get('id') == 'buscador_detalle':
 				self.parsing = True
@@ -67,6 +72,9 @@ class SubDivXHTMLParser(HTMLParser.HTMLParser):
 
 	def handle_endtag(self, tag):
 		if self.parsing:
+			if tag == 'script' or tag == 'style':
+				self.in_script_style = False
+				return
 			self.depth -= 1
 		if self.depth == 0:
 			self.parsing = False
@@ -75,6 +83,10 @@ class SubDivXHTMLParser(HTMLParser.HTMLParser):
 		if not self.parsing:
 			return
 		data = data.strip()
+		# Hack to handle comments in <script> <style> which don't end
+		# up in handle_comment(), so we just ignore the whole tags
+		if self.in_script_style:
+			return
 		if self.attr is not None and data:
 			self.cur[self.attr] = data
 			self.attr = None