def extract_regex(regex, text, replace_entities=True, flags=0):
"""Extract a list of unicode strings from the given text/encoding using the following policies:
* if the regex contains a named group called "extract" that will be returned
* if the regex contains multiple numbered groups, all those will be returned (flattened)
* if the regex doesn't contain any group the entire regex matching is returned
"""
if isinstance(regex, six.string_types):
regex = re.compile(regex, flags=flags)
if 'extract' in regex.groupindex:
# named group
try:
extracted = regex.search(text).group('extract')
except AttributeError:
strings = []
else:
strings = [extracted] if extracted is not None else []
else:
# full regex or numbered groups
strings = regex.findall(text)
# strings = flatten(strings) # 这东西会把多维列表铺平
if not replace_entities:
return strings
values = []
for value in strings:
if isinstance(value, (list, tuple)): # w3lib_replace_entities 不能接收list tuple
values.append([w3lib_replace_entities(v, keep=['lt', 'amp']) for v in value])
else:
values.append(w3lib_replace_entities(value, keep=['lt', 'amp']))
return values
def extract_regex(regex, text, replace_entities=True):
"""Extract a list of unicode strings from the given text/encoding using the following policies:
* if the regex contains a named group called "extract" that will be returned
* if the regex contains multiple numbered groups, all those will be returned (flattened)
* if the regex doesn't contain any group the entire regex matching is returned
"""
if isinstance(regex, six.string_types):
regex = re.compile(regex, re.UNICODE)
if 'extract' in regex.groupindex:
# named group
try:
extracted = regex.search(text).group('extract')
except AttributeError:
strings = []
else:
strings = [extracted] if extracted is not None else []
else:
# full regex or numbered groups
strings = regex.findall(text)
strings = flatten(strings)
if not replace_entities:
return strings
return [w3lib_replace_entities(s, keep=['lt', 'amp']) for s in strings]