def __call__(self, data, **metadata):
if strutils.isXML(data.decode()):
parser = lxml.etree.HTMLParser(strip_cdata=True, remove_blank_text=True)
d = lxml.html.fromstring(data, parser=parser)
docinfo = d.getroottree().docinfo
s = lxml.etree.tostring(d, pretty_print=True, doctype=docinfo.doctype, encoding="utf8")
return "HTML", format_text(s)
def __call__(self, data, **metadata):
if strutils.isXML(data):
parser = lxml.etree.HTMLParser(strip_cdata=True,
remove_blank_text=True)
d = lxml.html.fromstring(data, parser=parser)
docinfo = d.getroottree().docinfo
s = lxml.etree.tostring(d,
pretty_print=True,
doctype=docinfo.doctype,
encoding='utf8')
return "HTML", format_text(s)
def __call__(self, data, **metadata):
if strutils.isXML(data):
parser = lxml.etree.HTMLParser(
strip_cdata=True,
remove_blank_text=True
)
d = lxml.html.fromstring(data, parser=parser)
docinfo = d.getroottree().docinfo
def piglify(src):
words = string.split(src)
ret = ''
for word in words:
idx = -1
while word[idx] in string.punctuation and (idx * -1) != len(word):
idx -= 1
if word[0].lower() in 'aeiou':
if idx == -1:
ret += word[0:] + "hay"
else:
ret += word[0:len(word) + idx + 1] + "hay" + word[idx + 1:]
else:
if idx == -1:
ret += word[1:] + word[0] + "ay"
else:
ret += word[1:len(word) + idx + 1] + word[0] + "ay" + word[idx + 1:]
ret += ' '
return ret.strip()
def recurse(root):
if hasattr(root, 'text') and root.text:
root.text = piglify(root.text)
if hasattr(root, 'tail') and root.tail:
root.tail = piglify(root.tail)
if len(root):
for child in root:
recurse(child)
recurse(d)
s = lxml.etree.tostring(
d,
pretty_print=True,
doctype=docinfo.doctype
)
return "HTML", contentviews.format_text(s)
def __call__(self, data, **metadata):
headers = metadata.get("headers", {})
ctype = headers.get("content-type")
if data and ctype:
ct = http.parse_content_type(ctype) if ctype else None
ct = "%s/%s" % (ct[0], ct[1])
if ct in content_types_map:
return content_types_map[ct][0](data, **metadata)
elif strutils.isXML(data):
return get("XML")(data, **metadata)
if metadata.get("query"):
return get("Query")(data, **metadata)
if data and strutils.isMostlyBin(data):
return get("Hex")(data)
if not data:
return "No content", []
return get("Raw")(data)
def __call__(self, data, **metadata):
headers = metadata.get("headers", {})
ctype = headers.get("content-type")
if data and ctype:
ct = http.parse_content_type(ctype) if ctype else None
ct = "%s/%s" % (ct[0], ct[1])
if ct in content_types_map:
return content_types_map[ct][0](data, **metadata)
elif strutils.isXML(data):
return get("XML")(data, **metadata)
if metadata.get("query"):
return get("Query")(data, **metadata)
if data and strutils.isMostlyBin(data):
return get("Hex")(data)
if not data:
return "No content", []
return get("Raw")(data)
def test_isXml():
assert not strutils.isXML("foo")
assert strutils.isXML("<foo")
assert strutils.isXML(" \n<foo")