class HTMLSequenceWrapperRecord(object):
def __init__(self, element, url, mintextlen=10):
self.cleaner = SimpleHTMLCleaner()
self.mintextlen = mintextlen
self.elem = element
self.url = url
# the whole text
self.text = self.elem.text_content()
self.text = self.cleaner.clean(self.text)
self.chunks = []
self.__extract_chunks(self.elem)
def has_value(self):
if self.cleaner.contains_text(self.text) == False:
return False
return len(self.text) > self.mintextlen
def get_chunks(self):
return self.chunks
def get_text(self):
return self.text
def _handle_elem(self, elem):
if elem.text == None: return None
if not self.cleaner.contains_text(elem): return None
# new chunk
chunk = TextChunk()
## extracting links
if elem.get('href') != None:
chunk.set_link(elem.get('href'))
# extracting 'title' atribute in anchor
if elem.tag == 'a' and elem.get('title') != None:
chunk.set_comment(elem.get('title'))
# extracting text
txt = elem.text_content()
chunk.set_text(self.cleaner.clean(txt))
# setting style
fs = elem.style
chunk.set_style(fs)
chunk.set_tag(elem.tag)
return chunk
def __extract_chunks(self, elem):
thischunk = self._handle_elem(elem)
if thischunk != None:
self.chunks.append(thischunk)
for child in elem.iterchildren():
self.__extract_chunks(child)
def __str__(self):
return "<" + __modulename__ + ".HTMLSequenceWrapperRecord instance " + self.text + " >"
class HTMLSequenceWrapperRecord(object):
def __init__(self, element, url, mintextlen=10):
self.cleaner = SimpleHTMLCleaner()
self.mintextlen = mintextlen
self.elem = element
self.url = url
# the whole text
self.text = self.elem.text_content()
self.text = self.cleaner.clean(self.text)
self.chunks = []
self.__extract_chunks(self.elem)
def has_value(self):
if self.cleaner.contains_text(self.text) == False:
return False
return len(self.text) > self.mintextlen
def get_chunks(self):
return self.chunks
def get_text(self):
return self.text
def _handle_elem(self, elem):
if elem.text == None: return None
if not self.cleaner.contains_text(elem): return None
# new chunk
chunk = TextChunk()
## extracting links
if elem.get('href') != None:
chunk.set_link(elem.get('href'))
# extracting 'title' atribute in anchor
if elem.tag == 'a' and elem.get('title') != None:
chunk.set_comment(elem.get('title'))
# extracting text
txt = elem.text_content()
chunk.set_text(self.cleaner.clean(txt))
# setting style
fs = elem.style
chunk.set_style(fs)
chunk.set_tag(elem.tag)
return chunk
def __extract_chunks(self, elem):
thischunk = self._handle_elem(elem)
if thischunk != None:
self.chunks.append(thischunk)
for child in elem.iterchildren():
self.__extract_chunks(child)
def __str__(self):
return "<"+__modulename__+".HTMLSequenceWrapperRecord instance " + self.text + " >"
