def handle_starttag(self, tag: str, attrs: List[Tuple[str, str]]) -> None:
attr_d = dict(attrs)
title = attr_d.get('title', '').strip()
if tag in self.link_types:
url_attr, rels = self.link_types[tag]
if not rels or attr_d.get("rel", None) in rels:
target = attr_d.get(url_attr, "")
if target:
if "#" in target:
target = target[:target.index('#')]
for proc in self.link_procs:
proc(self.message.base_uri, target, tag, title)
elif tag == 'base':
self.message.base_uri = attr_d.get('href', self.message.base_uri)
elif tag == 'meta' and attr_d.get('http-equiv',
'').lower() == 'content-type':
ct = attr_d.get('content', None)
if ct:
try:
media_type, params = ct.split(";", 1)
except ValueError:
media_type, params = ct, ''
media_type = media_type.lower()
param_dict = {}
for param in headers.split_string(params, rfc7231.parameter,
r"\s*;\s*"):
try:
a, v = param.split("=", 1)
param_dict[a.lower()] = headers.unquote_string(v)
except ValueError:
param_dict[param.lower()] = None
self.message.character_encoding = param_dict.get(
'charset', self.message.character_encoding)
def handle_starttag(self, tag: str, attrs: List[Tuple[str, str]]) -> None:
attr_d = dict(attrs)
title = attr_d.get('title', '').strip()
if tag in self.link_types:
url_attr, rels = self.link_types[tag]
if not rels or attr_d.get("rel", None) in rels:
target = attr_d.get(url_attr, "")
if target:
if "#" in target:
target = target[:target.index('#')]
for proc in self.link_procs:
proc(self.message.base_uri, target, tag, title)
elif tag == 'base':
self.message.base_uri = attr_d.get('href', self.message.base_uri)
elif tag == 'meta' and attr_d.get('http-equiv', '').lower() == 'content-type':
ct = attr_d.get('content', None)
if ct:
try:
media_type, params = ct.split(";", 1)
except ValueError:
media_type, params = ct, ''
media_type = media_type.lower()
param_dict = {}
for param in headers.split_string(params, rfc7231.parameter, r"\s*;\s*"):
try:
a, v = param.split("=", 1)
param_dict[a.lower()] = headers.unquote_string(v)
except ValueError:
param_dict[param.lower()] = None
self.message.character_encoding = param_dict.get('charset',
self.message.character_encoding)
def handle_starttag(self, tag, attrs):
attr_d = dict(attrs)
title = attr_d.get('title', '').strip()
if tag in self.link_types.keys():
url_attr, rels = self.link_types[tag]
if not rels or attr_d.get("rel", None) in rels:
target = attr_d.get(url_attr, "")
if target:
if "#" in target:
target = target[:target.index('#')]
for proc in self.link_procs:
proc(self.base, target, tag, title)
elif tag == 'base':
self.base = attr_d.get('href', self.base)
elif tag == 'meta' and \
attr_d.get('http-equiv', '').lower() == 'content-type':
ct = attr_d.get('content', None)
if ct:
try:
media_type, params = ct.split(";", 1)
except ValueError:
media_type, params = ct, ''
media_type = media_type.lower()
param_dict = {}
for param in rh.split_string(
params, syntax.PARAMETER, "\s*;\s*"
):
try:
a, v = param.split("=", 1)
param_dict[a.lower()] = rh.unquote_string(v)
except ValueError:
param_dict[param.lower()] = None
self.doc_enc = param_dict.get('charset', self.doc_enc)
def test_split_string(self):
i = 0
for (instr, expected_outlist, item, split) in [
('"abc", "def"', ['"abc"',
'"def"'], rfc7230.quoted_string, r"\s*,\s*"),
(r'"\"ab", "c\d"', [r'"\"ab"',
r'"c\d"'], rfc7230.quoted_string, r"\s*,\s*")
]:
self.red.__init__()
outlist = headers.split_string(str(instr), item, split)
self.assertEqual(
expected_outlist, outlist,
"[%s] %s != %s" % (i, str(expected_outlist), str(outlist)))
i += 1
def test_split_string(self):
i = 0
for (instr, expected_outlist, item, split) in [
('"abc", "def"',
['"abc"', '"def"'],
syntax.QUOTED_STRING,
r"\s*,\s*"
),
(r'"\"ab", "c\d"',
[r'"\"ab"', r'"c\d"'],
syntax.QUOTED_STRING,
r"\s*,\s*"
)
]:
self.red.__init__()
outlist = headers.split_string(unicode(instr), item, split)
self.assertEqual(expected_outlist, outlist,
"[%s] %s != %s" % (i, str(expected_outlist), str(outlist)))
i += 1