def convertToText(self):
txts = []
node = self.getTopNode()
txt = node.text
if txt and re.search('[^ \t\r\n]',txt):
txt = HTMLParser().unescape(txt)
txts.append(innerTrim(txt))
for node in list(self.getTopNode()):
txt = Parser.getText(node)
if txt:
txt = HTMLParser().unescape(txt)
txts.append(innerTrim(txt))
return '\n\n'.join(txts)
def getTextAndWriteToFile(self, node):
txts = [i for i in node.itertext()]
f = codecs.open("log.txt",'wb','utf-8')
for line in txts:
f.write(line)
f.close()
return innerTrim(u' '.join(txts).strip())
def convertToText(self):
txts = []
for node in list(self.getTopNode()):
txt = Parser.getText(node)
if txt:
txt = HTMLParser().unescape(txt)
txts.append(innerTrim(txt))
return '\n\n'.join(txts)
def convertToText(self):
txts = []
for node in list(self.getTopNode()):
txt = Parser.getText(node)
if txt:
txt = HTMLParser().unescape(txt)
txts.append(innerTrim(txt))
return '\n\n'.join(txts)
def convert_to_text(self):
txts = []
for node in list(self.get_top_node()):
txt = self.parser.getText(node)
if txt:
txt = HTMLParser().unescape(txt)
txt_lis = innerTrim(txt).split(r'\n')
txts.extend(txt_lis)
return '\n\n'.join(txts)
def convert_to_text(self):
txts = []
for node in list(self.get_top_node()):
txt = self.parser.getText(node)
if txt:
txt = HTMLParser().unescape(txt)
txt_lis = innerTrim(txt).split(r'\n')
txts.extend(txt_lis)
return '<br/>'.join(txts)
def convertToText(self,article):
txts = []
for node in list(self.getTopNode()):
txt = Parser.getFormattedText(node)
if txt:
txt = HTMLParser().unescape(txt)
txts.append(innerTrim(txt))
text = '\n'.join(txts)
text = re.sub(u'[\ufffc]','\n',text)
lines = text.split('\n')
text = ''
# cutting title from article text if found in first 4 rows
if len(lines) > 4:
for i in range(0,4):
if lines[i] == article.h1 or lines[i] == article.title:
del lines[i]
break
for line in lines:
if re.search('[^ \t\r]',line): text += line + '\n'
return text
def getText(self, node):
txts = [i for i in node.itertext()]
return innerTrim(u' '.join(txts).strip())
def getText(self, node):
txts = [i for i in node.itertext()]
return innerTrim(u' '.join(txts).strip())
def clean(self, node):
html_string = self.parser.nodeToString(node, method='html')
clean_html_string = self.clean_html(html_string)
return innerTrim(clean_html_string)
def getTextAndShowInConsole(self, node):
txts = [i for i in node.itertext()]
print txts
return innerTrim(u' '.join(txts).strip())
def getText(self, node):
txts = [i for i in node.itertext()]
return innerTrim(u" ".join(txts))
