get text from title and remove useless tag

README.txt

@@ -8,3 +8,27 @@ Pour installer lxml il faut installer paquets :
 - libxml2-dev
 - python2.7-dev
 - libxslt1-dev
+
+Il faudra fournir un fichier de style guide-style.protoxml à la racine du dossier traduit, par exemple :
+<?xml version="1.0" encoding="UTF-8"?>
+
+<package name="com.daysofwonder.dowml">
+    
+    <message class="DOWMLStyle">
+        
+        <text_attributes>
+            <size>22</size>
+            <font>TimesNewRomanPSMT</font>
+            <alignment>NEAR</alignment>
+            <vertical_alignment>CENTER</vertical_alignment>
+        </text_attributes>
+        
+        <layout>
+            <!--<size relative_width="1" relative_height="1"/>-->
+            <secondary_alignment>CENTER</secondary_alignment>
+            <weight>1</weight>
+        </layout>
+        
+    </message>
+
+</package>
\ No newline at end of file

formatter.py

@@ -55,7 +55,8 @@ class Formatter:
 		self.format_body()
 
 	def format_extra(self):
-		assert(self._data._title)
+		if not self._data._title:
+			self._data._title = ""
 
 		title = etree.Element("property")
 		title.attrib["key"] = "Title"

html_parser.py

@@ -34,8 +34,19 @@ class Parser:
 
 	def parse_title(self):
 		title = self._soup.h1
-		if title:
-			self._data._title = title.string
+		title_string = self.get_string_from_content(title)
+		self._data._title = title_string
+
+	def get_string_from_content(self, content):
+		result = ""
+		for c in content:
+			name = c.name
+			if not name:
+				result += c.string
+			else:
+				result += self.get_string_from_content(c)
+		return result
+
 
 	def parse_content(self, content, lvl = 0):
 		try:

main.py

@@ -55,6 +55,7 @@ def parse_format_and_write_file(filename, dest, level):
 			formatter.write_to_file(dest)
 		except Exception as e:
 			print "Error with file while fomatting: " + str(filename)
+			print "Error message: " + str(e)
 
 
 if __name__=="__main__":