def parse_full_10K(cls, doc): text = "" for child in doc.getchildren(): if child.tag == 'sec-header': continue html, properties = TXTML.get_HTML_from_document(child) if properties['type'] == '10-K': text = text + html.text_content() return text
def a_droped_text(self): droped = drop_tree(drop_tree(self.body, 'a'), '\s') if len(droped) > 0: return text_content(droped) return u''
def text(self): # return tags removed text return text_content(self.body)
def text(self): content = self.content if type(content) == unicode and len(content) > 0: return text_content(content) return False