def __call__(self, data, **metadata):
if strutils.is_xml(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 render_priority(self, data: bytes, *, content_type: Optional[str] = None, **metadata) -> float:
if not data:
return 0
if content_type in self.__content_types:
return 1
elif strutils.is_xml(data):
return 0.4
return 0
def __call__(self, data, **metadata):
if strutils.is_xml(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.is_xml(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 = src.split()
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.is_xml(data):
return get("XML")(data, **metadata)
if metadata.get("query"):
return get("Query")(data, **metadata)
if data and strutils.is_mostly_bin(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.is_xml(data):
return get("XML")(data, **metadata)
if metadata.get("query"):
return get("Query")(data, **metadata)
if data and strutils.is_mostly_bin(data):
return get("Hex")(data)
if not data:
return "No content", []
return get("Raw")(data)
def __call__(self, data, **metadata):
if strutils.is_xml(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 = src.split()
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 = "{}/{}".format(ct[0], ct[1])
if ct in contentviews.content_types_map:
return contentviews.content_types_map[ct][0](data, **metadata)
elif strutils.is_xml(data):
return contentviews.get("XML/HTML")(data, **metadata)
elif ct.startswith("image/"):
return contentviews.get("Image")(data, **metadata)
if metadata.get("query"):
return contentviews.get("Query")(data, **metadata)
if data and strutils.is_mostly_bin(data):
return contentviews.get("Hex")(data)
if not data:
return "No content", []
return contentviews.get("Raw")(data)
def test_is_xml():
assert not strutils.is_xml(b"foo")
assert strutils.is_xml(b"<foo")
assert strutils.is_xml(b" \n<foo")
def test_is_xml():
assert not strutils.is_xml(b"foo")
assert strutils.is_xml(b"<foo")
assert strutils.is_xml(b" \n<foo")
