def assert_exists(self):
"""
Return True if selector list is not empty.
"""
if not self.exists():
args = (self.origin_query, self.origin_selector_class.__name__)
raise DataNotFound(u'Node does not exists, query: %s, '
u'query type: %s' % args)
def node(self, default=NULL):
try:
return self.one().node()
except IndexError:
if default is NULL:
m = 'Could not get first item for %s query of class %s'\
% (self.origin_query, self.origin_selector_class.__name__)
raise DataNotFound(m)
else:
return default
def attr(self, key, default=NULL):
if self.is_text_node():
raise SelectionRuntimeError('Text node selectors do not '
'allow attr method')
if default is NULL:
if key in self.node().attrib:
return self.node().get(key)
else:
raise DataNotFound(u'No such attribute: %s' % key)
else:
return self.node().get(key, default)
def css_one(self, path, default=NULL):
"""
Get first element which matches the given css path
or raise DataNotFound.
"""
try:
return self.css_list(path)[0]
except IndexError:
if default is NULL:
raise DataNotFound('CSS path not found: %s' % path)
else:
return default
def rex_text(body, regexp, flags=0, default=NULL):
"""
Search `regexp` expression in `body` text and then strip tags in found result.
"""
match = rex(body, regexp, flags=flags, default=default)
try:
return normalize_space(decode_entities(match.group(1)))
except AttributeError:
if default is NULL:
raise DataNotFound('Regexp not found')
else:
return default
def rex(body, regexp, flags=0, byte=False, default=NULL):
"""
Search `regexp` expression in `body` text.
"""
regexp = normalize_regexp(regexp, flags)
match = regexp.search(body)
if match:
return match
else:
if default is NULL:
raise DataNotFound('Could not find regexp: %s' % regexp)
else:
return default