def __iter__(self):
for token in Filter.__iter__(self):
if token["type"] in ["StartTag", "EmptyTag"] and token["data"]:
for attr, value in token["data"].items():
token["data"][attr] = "moo"
yield token
def __iter__(self):
for token in Filter.__iter__(self):
if token['type'] in ['StartTag', 'EmptyTag'] and token['data']:
for attr, value in token['data'].items():
token['data'][attr] = 'moo'
yield token
def __iter__(self):
for token in Filter.__iter__(self):
if token['type'] in ['StartTag', 'EmptyTag'] and token['data']:
for attr, value in token['data'].items():
token['data'][attr] = 'moo'
yield token
def __iter__(self):
for token in Filter.__iter__(self):
if token['type'] in ['StartTag', 'EmptyTag'] and token['data']:
if (None, 'href') in token['data']:
# This means a href attribute with no namespace
if ':' not in token['data'][(None, 'href')]:
# Relative link!
del token['data'][(None, 'href')]
yield token
def __iter__(self):
for token in Filter.__iter__(self):
if token['type'] in ['StartTag', 'EmptyTag'] and token['data']:
for attr, value in token['data'].items():
if attr[1] == 'src':
src = '/safeImage?url=' + urllib.parse.quote_plus(
token['data'][attr])
token['data'][attr] = src
yield token
def __iter__(self):
for token in Filter.__iter__(self):
if token['type'] in ['StartTag', 'EmptyTag'] and token['data']:
for attr, value in token['data'].items():
if attr[1] == 'href':
href = token['data'][attr]
if href.startswith('//'):
href = 'https:' + href
href = urllib.parse.unquote(href)
href = re.sub('"', '%22', href)
token['data'][attr] = href
yield token
def __iter__(self):
remove_end_tag = False
for token in Filter.__iter__(self):
# only check anchor tags
if 'name' in token and token['name'] == 'a' and token['type'] in ['StartTag', 'EndTag']:
if token['type'] == 'StartTag':
remove_end_tag = True
for attr, value in token['data'].items():
if attr == (None, 'href') and value != '' and is_valid_url(value):
remove_end_tag = False
if remove_end_tag:
continue
elif token['type'] == 'EndTag' and remove_end_tag:
remove_end_tag = False
continue
yield token
def __iter__(self):
remove_end_tag = False
for token in Filter.__iter__(self):
# only check anchor tags
if 'name' in token and token['name'] == 'a' and token['type'] in [
'StartTag', 'EndTag'
]:
if token['type'] == 'StartTag':
remove_end_tag = True
for attr, value in token['data'].items():
if attr == (None, 'href'
) and value != '' and is_valid_url(value):
remove_end_tag = False
if remove_end_tag:
continue
elif token['type'] == 'EndTag' and remove_end_tag:
remove_end_tag = False
continue
yield token