def handle_data(self, data):
if len(self.__tagStack) == 0:
return
currentTag = self.__tagStack[0].lower()
if currentTag == 'title':
self.__title = htmltools.htmlToText(data)
elif not currentTag in ('style', 'script', 'title'):
self.__text.write(" ")
data = texttools.stripWhiteSpaces(data) or ""
data = data.strip()
data = htmltools.htmlToText(data)
self.__text.write(data)
def handle_data(self, data):
if len(self.__tagStack) == 0:
return
currentTag = self.__tagStack[0].lower()
if currentTag == 'title':
self.__title = htmltools.htmlToText(data)
elif not currentTag in ('style', 'script', 'title'):
self.__text.write(" ")
data = texttools.stripWhiteSpaces(data) or ""
data = data.strip()
data = htmltools.htmlToText(data)
self.__text.write(data)
def htmlToText(data=None, input=None):
h = MyHTMLParser()
h.feed(data=data, input=input)
h.close()
text = texttools.stripWhiteSpaces(h.getText())
# print "title = %s" % h.getTitle()
# text = htmltools.htmlToText(texttools.stripWhiteSpaces(h.getText())) or ""
# text = texttools.stripWhiteSpaces(h.getText()) or ""
if not h.getTitle():
# we take the first 60 chars
if len(text) < 60:
title = text[0:60]
else:
end = 60
while end > 0 and data[end] != ' ':
end -= 1
break
title = text[0:end] + "..."
else:
title = h.getTitle()
# return (htmltools.htmlToText(title), htmltools.htmlToText(text), h.getLinks())
return (title, text, h.getLinks())
def htmlToText(data = None, input = None):
h = MyHTMLParser()
h.feed(data=data, input=input)
h.close()
text = texttools.stripWhiteSpaces(h.getText())
# print "title = %s" % h.getTitle()
# text = htmltools.htmlToText(texttools.stripWhiteSpaces(h.getText())) or ""
# text = texttools.stripWhiteSpaces(h.getText()) or ""
if not h.getTitle():
# we take the first 60 chars
if len(text) < 60:
title = text[0:60]
else:
end = 60
while end > 0 and data[end] != ' ':
end -= 1
break
title = text[0:end] + "..."
else:
title = h.getTitle()
# return (htmltools.htmlToText(title), htmltools.htmlToText(text), h.getLinks())
return (title, text, h.getLinks())