Python genshi.core.DOCTYPE Examples
The following are 30
code examples of genshi.core.DOCTYPE().
You can vote up the ones you like or vote down the ones you don't like,
and go to the original project or source file by following the links above each example.
You may also want to check out all available functions/classes of the module
genshi.core
, or try the search function
.
.
Example #1
| Source File: genshi.py From python with Apache License 2.0 | 5 votes |
|
def to_genshi(walker):
text = []
for token in walker:
type = token["type"]
if type in ("Characters", "SpaceCharacters"):
text.append(token["data"])
elif text:
yield TEXT, "".join(text), (None, -1, -1)
text = []
if type in ("StartTag", "EmptyTag"):
if token["namespace"]:
name = "{%s}%s" % (token["namespace"], token["name"])
else:
name = token["name"]
attrs = Attrs([(QName("{%s}%s" % attr if attr[0] is not None else attr[1]), value)
for attr, value in token["data"].items()])
yield (START, (QName(name), attrs), (None, -1, -1))
if type == "EmptyTag":
type = "EndTag"
if type == "EndTag":
if token["namespace"]:
name = "{%s}%s" % (token["namespace"], token["name"])
else:
name = token["name"]
yield END, QName(name), (None, -1, -1)
elif type == "Comment":
yield COMMENT, token["data"], (None, -1, -1)
elif type == "Doctype":
yield DOCTYPE, (token["name"], token["publicId"],
token["systemId"]), (None, -1, -1)
else:
pass # FIXME: What to do?
if text:
yield TEXT, "".join(text), (None, -1, -1)
Example #2
| Source File: genshi.py From CTFCrackTools-V2 with GNU General Public License v3.0 | 5 votes |
|
def to_genshi(walker):
text = []
for token in walker:
type = token["type"]
if type in ("Characters", "SpaceCharacters"):
text.append(token["data"])
elif text:
yield TEXT, "".join(text), (None, -1, -1)
text = []
if type in ("StartTag", "EmptyTag"):
if token["namespace"]:
name = "{%s}%s" % (token["namespace"], token["name"])
else:
name = token["name"]
attrs = Attrs([(QName("{%s}%s" % attr if attr[0] is not None else attr[1]), value)
for attr, value in token["data"].items()])
yield (START, (QName(name), attrs), (None, -1, -1))
if type == "EmptyTag":
type = "EndTag"
if type == "EndTag":
if token["namespace"]:
name = "{%s}%s" % (token["namespace"], token["name"])
else:
name = token["name"]
yield END, QName(name), (None, -1, -1)
elif type == "Comment":
yield COMMENT, token["data"], (None, -1, -1)
elif type == "Doctype":
yield DOCTYPE, (token["name"], token["publicId"],
token["systemId"]), (None, -1, -1)
else:
pass # FIXME: What to do?
if text:
yield TEXT, "".join(text), (None, -1, -1)
Example #3
| Source File: genshi.py From vnpy_crypto with MIT License | 5 votes |
|
def to_genshi(walker):
text = []
for token in walker:
type = token["type"]
if type in ("Characters", "SpaceCharacters"):
text.append(token["data"])
elif text:
yield TEXT, "".join(text), (None, -1, -1)
text = []
if type in ("StartTag", "EmptyTag"):
if token["namespace"]:
name = "{%s}%s" % (token["namespace"], token["name"])
else:
name = token["name"]
attrs = Attrs([(QName("{%s}%s" % attr if attr[0] is not None else attr[1]), value)
for attr, value in token["data"].items()])
yield (START, (QName(name), attrs), (None, -1, -1))
if type == "EmptyTag":
type = "EndTag"
if type == "EndTag":
if token["namespace"]:
name = "{%s}%s" % (token["namespace"], token["name"])
else:
name = token["name"]
yield END, QName(name), (None, -1, -1)
elif type == "Comment":
yield COMMENT, token["data"], (None, -1, -1)
elif type == "Doctype":
yield DOCTYPE, (token["name"], token["publicId"],
token["systemId"]), (None, -1, -1)
else:
pass # FIXME: What to do?
if text:
yield TEXT, "".join(text), (None, -1, -1)
Example #4
| Source File: genshi.py From PhonePi_SampleServer with MIT License | 5 votes |
|
def to_genshi(walker):
text = []
for token in walker:
type = token["type"]
if type in ("Characters", "SpaceCharacters"):
text.append(token["data"])
elif text:
yield TEXT, "".join(text), (None, -1, -1)
text = []
if type in ("StartTag", "EmptyTag"):
if token["namespace"]:
name = "{%s}%s" % (token["namespace"], token["name"])
else:
name = token["name"]
attrs = Attrs([(QName("{%s}%s" % attr if attr[0] is not None else attr[1]), value)
for attr, value in token["data"].items()])
yield (START, (QName(name), attrs), (None, -1, -1))
if type == "EmptyTag":
type = "EndTag"
if type == "EndTag":
if token["namespace"]:
name = "{%s}%s" % (token["namespace"], token["name"])
else:
name = token["name"]
yield END, QName(name), (None, -1, -1)
elif type == "Comment":
yield COMMENT, token["data"], (None, -1, -1)
elif type == "Doctype":
yield DOCTYPE, (token["name"], token["publicId"],
token["systemId"]), (None, -1, -1)
else:
pass # FIXME: What to do?
if text:
yield TEXT, "".join(text), (None, -1, -1)
Example #5
| Source File: genshi.py From Ansible with MIT License | 5 votes |
|
def to_genshi(walker):
text = []
for token in walker:
type = token["type"]
if type in ("Characters", "SpaceCharacters"):
text.append(token["data"])
elif text:
yield TEXT, "".join(text), (None, -1, -1)
text = []
if type in ("StartTag", "EmptyTag"):
if token["namespace"]:
name = "{%s}%s" % (token["namespace"], token["name"])
else:
name = token["name"]
attrs = Attrs([(QName("{%s}%s" % attr if attr[0] is not None else attr[1]), value)
for attr, value in token["data"].items()])
yield (START, (QName(name), attrs), (None, -1, -1))
if type == "EmptyTag":
type = "EndTag"
if type == "EndTag":
if token["namespace"]:
name = "{%s}%s" % (token["namespace"], token["name"])
else:
name = token["name"]
yield END, QName(name), (None, -1, -1)
elif type == "Comment":
yield COMMENT, token["data"], (None, -1, -1)
elif type == "Doctype":
yield DOCTYPE, (token["name"], token["publicId"],
token["systemId"]), (None, -1, -1)
else:
pass # FIXME: What to do?
if text:
yield TEXT, "".join(text), (None, -1, -1)
Example #6
| Source File: genshi.py From python2017 with MIT License | 5 votes |
|
def to_genshi(walker):
text = []
for token in walker:
type = token["type"]
if type in ("Characters", "SpaceCharacters"):
text.append(token["data"])
elif text:
yield TEXT, "".join(text), (None, -1, -1)
text = []
if type in ("StartTag", "EmptyTag"):
if token["namespace"]:
name = "{%s}%s" % (token["namespace"], token["name"])
else:
name = token["name"]
attrs = Attrs([(QName("{%s}%s" % attr if attr[0] is not None else attr[1]), value)
for attr, value in token["data"].items()])
yield (START, (QName(name), attrs), (None, -1, -1))
if type == "EmptyTag":
type = "EndTag"
if type == "EndTag":
if token["namespace"]:
name = "{%s}%s" % (token["namespace"], token["name"])
else:
name = token["name"]
yield END, QName(name), (None, -1, -1)
elif type == "Comment":
yield COMMENT, token["data"], (None, -1, -1)
elif type == "Doctype":
yield DOCTYPE, (token["name"], token["publicId"],
token["systemId"]), (None, -1, -1)
else:
pass # FIXME: What to do?
if text:
yield TEXT, "".join(text), (None, -1, -1)
Example #7
| Source File: genshi.py From Safejumper-for-Desktop with GNU General Public License v2.0 | 5 votes |
|
def to_genshi(walker):
text = []
for token in walker:
type = token["type"]
if type in ("Characters", "SpaceCharacters"):
text.append(token["data"])
elif text:
yield TEXT, "".join(text), (None, -1, -1)
text = []
if type in ("StartTag", "EmptyTag"):
if token["namespace"]:
name = "{%s}%s" % (token["namespace"], token["name"])
else:
name = token["name"]
attrs = Attrs([(QName("{%s}%s" % attr if attr[0] is not None else attr[1]), value)
for attr, value in token["data"].items()])
yield (START, (QName(name), attrs), (None, -1, -1))
if type == "EmptyTag":
type = "EndTag"
if type == "EndTag":
if token["namespace"]:
name = "{%s}%s" % (token["namespace"], token["name"])
else:
name = token["name"]
yield END, QName(name), (None, -1, -1)
elif type == "Comment":
yield COMMENT, token["data"], (None, -1, -1)
elif type == "Doctype":
yield DOCTYPE, (token["name"], token["publicId"],
token["systemId"]), (None, -1, -1)
else:
pass # FIXME: What to do?
if text:
yield TEXT, "".join(text), (None, -1, -1)
Example #8
| Source File: test_treewalkers.py From MARA_Framework with GNU Lesser General Public License v3.0 | 5 votes |
|
def PullDOMAdapter(node):
from xml.dom import Node
from xml.dom.pulldom import START_ELEMENT, END_ELEMENT, COMMENT, CHARACTERS
if node.nodeType in (Node.DOCUMENT_NODE, Node.DOCUMENT_FRAGMENT_NODE):
for childNode in node.childNodes:
for event in PullDOMAdapter(childNode):
yield event
elif node.nodeType == Node.DOCUMENT_TYPE_NODE:
raise NotImplementedError("DOCTYPE nodes are not supported by PullDOM")
elif node.nodeType == Node.COMMENT_NODE:
yield COMMENT, node
elif node.nodeType in (Node.TEXT_NODE, Node.CDATA_SECTION_NODE):
yield CHARACTERS, node
elif node.nodeType == Node.ELEMENT_NODE:
yield START_ELEMENT, node
for childNode in node.childNodes:
for event in PullDOMAdapter(childNode):
yield event
yield END_ELEMENT, node
else:
raise NotImplementedError("Node type not supported: " + str(node.nodeType))
Example #9
| Source File: genshistream.py From nzb-subliminal with GNU General Public License v3.0 | 5 votes |
|
def tokens(self, event, next):
kind, data, pos = event
if kind == START:
tag, attrib = data
name = tag.localname
namespace = tag.namespace
if tag in voidElements:
for token in self.emptyTag(namespace, name, list(attrib),
not next or next[0] != END
or next[1] != tag):
yield token
else:
yield self.startTag(namespace, name, list(attrib))
elif kind == END:
name = data.localname
namespace = data.namespace
if name not in voidElements:
yield self.endTag(namespace, name)
elif kind == COMMENT:
yield self.comment(data)
elif kind == TEXT:
for token in self.text(data):
yield token
elif kind == DOCTYPE:
yield self.doctype(*data)
elif kind in (XML_NAMESPACE, DOCTYPE, START_NS, END_NS, \
START_CDATA, END_CDATA, PI):
pass
else:
yield self.unknown(kind)
Example #10
| Source File: genshi.py From anpr with Creative Commons Attribution 4.0 International | 5 votes |
|
def to_genshi(walker):
text = []
for token in walker:
type = token["type"]
if type in ("Characters", "SpaceCharacters"):
text.append(token["data"])
elif text:
yield TEXT, "".join(text), (None, -1, -1)
text = []
if type in ("StartTag", "EmptyTag"):
if token["namespace"]:
name = "{%s}%s" % (token["namespace"], token["name"])
else:
name = token["name"]
attrs = Attrs([(QName("{%s}%s" % attr if attr[0] is not None else attr[1]), value)
for attr, value in token["data"].items()])
yield (START, (QName(name), attrs), (None, -1, -1))
if type == "EmptyTag":
type = "EndTag"
if type == "EndTag":
if token["namespace"]:
name = "{%s}%s" % (token["namespace"], token["name"])
else:
name = token["name"]
yield END, QName(name), (None, -1, -1)
elif type == "Comment":
yield COMMENT, token["data"], (None, -1, -1)
elif type == "Doctype":
yield DOCTYPE, (token["name"], token["publicId"],
token["systemId"]), (None, -1, -1)
else:
pass # FIXME: What to do?
if text:
yield TEXT, "".join(text), (None, -1, -1)
Example #11
| Source File: genshi.py From planespotter with MIT License | 5 votes |
|
def to_genshi(walker):
text = []
for token in walker:
type = token["type"]
if type in ("Characters", "SpaceCharacters"):
text.append(token["data"])
elif text:
yield TEXT, "".join(text), (None, -1, -1)
text = []
if type in ("StartTag", "EmptyTag"):
if token["namespace"]:
name = "{%s}%s" % (token["namespace"], token["name"])
else:
name = token["name"]
attrs = Attrs([(QName("{%s}%s" % attr if attr[0] is not None else attr[1]), value)
for attr, value in token["data"].items()])
yield (START, (QName(name), attrs), (None, -1, -1))
if type == "EmptyTag":
type = "EndTag"
if type == "EndTag":
if token["namespace"]:
name = "{%s}%s" % (token["namespace"], token["name"])
else:
name = token["name"]
yield END, QName(name), (None, -1, -1)
elif type == "Comment":
yield COMMENT, token["data"], (None, -1, -1)
elif type == "Doctype":
yield DOCTYPE, (token["name"], token["publicId"],
token["systemId"]), (None, -1, -1)
else:
pass # FIXME: What to do?
if text:
yield TEXT, "".join(text), (None, -1, -1)
Example #12
| Source File: genshi.py From recruit with Apache License 2.0 | 5 votes |
|
def to_genshi(walker):
text = []
for token in walker:
type = token["type"]
if type in ("Characters", "SpaceCharacters"):
text.append(token["data"])
elif text:
yield TEXT, "".join(text), (None, -1, -1)
text = []
if type in ("StartTag", "EmptyTag"):
if token["namespace"]:
name = "{%s}%s" % (token["namespace"], token["name"])
else:
name = token["name"]
attrs = Attrs([(QName("{%s}%s" % attr if attr[0] is not None else attr[1]), value)
for attr, value in token["data"].items()])
yield (START, (QName(name), attrs), (None, -1, -1))
if type == "EmptyTag":
type = "EndTag"
if type == "EndTag":
if token["namespace"]:
name = "{%s}%s" % (token["namespace"], token["name"])
else:
name = token["name"]
yield END, QName(name), (None, -1, -1)
elif type == "Comment":
yield COMMENT, token["data"], (None, -1, -1)
elif type == "Doctype":
yield DOCTYPE, (token["name"], token["publicId"],
token["systemId"]), (None, -1, -1)
else:
pass # FIXME: What to do?
if text:
yield TEXT, "".join(text), (None, -1, -1)
Example #13
| Source File: genshi.py From Ansible with MIT License | 4 votes |
|
def tokens(self, event, next):
kind, data, _ = event
if kind == START:
tag, attribs = data
name = tag.localname
namespace = tag.namespace
converted_attribs = {}
for k, v in attribs:
if isinstance(k, QName):
converted_attribs[(k.namespace, k.localname)] = v
else:
converted_attribs[(None, k)] = v
if namespace == namespaces["html"] and name in voidElements:
for token in self.emptyTag(namespace, name, converted_attribs,
not next or next[0] != END or
next[1] != tag):
yield token
else:
yield self.startTag(namespace, name, converted_attribs)
elif kind == END:
name = data.localname
namespace = data.namespace
if namespace != namespaces["html"] or name not in voidElements:
yield self.endTag(namespace, name)
elif kind == COMMENT:
yield self.comment(data)
elif kind == TEXT:
for token in self.text(data):
yield token
elif kind == DOCTYPE:
yield self.doctype(*data)
elif kind in (XML_NAMESPACE, DOCTYPE, START_NS, END_NS,
START_CDATA, END_CDATA, PI):
pass
else:
yield self.unknown(kind)
Example #14
| Source File: genshi.py From CTFCrackTools-V2 with GNU General Public License v3.0 | 4 votes |
|
def tokens(self, event, next):
kind, data, _ = event
if kind == START:
tag, attribs = data
name = tag.localname
namespace = tag.namespace
converted_attribs = {}
for k, v in attribs:
if isinstance(k, QName):
converted_attribs[(k.namespace, k.localname)] = v
else:
converted_attribs[(None, k)] = v
if namespace == namespaces["html"] and name in voidElements:
for token in self.emptyTag(namespace, name, converted_attribs,
not next or next[0] != END or
next[1] != tag):
yield token
else:
yield self.startTag(namespace, name, converted_attribs)
elif kind == END:
name = data.localname
namespace = data.namespace
if namespace != namespaces["html"] or name not in voidElements:
yield self.endTag(namespace, name)
elif kind == COMMENT:
yield self.comment(data)
elif kind == TEXT:
for token in self.text(data):
yield token
elif kind == DOCTYPE:
yield self.doctype(*data)
elif kind in (XML_NAMESPACE, DOCTYPE, START_NS, END_NS,
START_CDATA, END_CDATA, PI):
pass
else:
yield self.unknown(kind)
Example #15
| Source File: genshi.py From bazarr with GNU General Public License v3.0 | 4 votes |
|
def tokens(self, event, next):
kind, data, _ = event
if kind == START:
tag, attribs = data
name = tag.localname
namespace = tag.namespace
converted_attribs = {}
for k, v in attribs:
if isinstance(k, QName):
converted_attribs[(k.namespace, k.localname)] = v
else:
converted_attribs[(None, k)] = v
if namespace == namespaces["html"] and name in voidElements:
for token in self.emptyTag(namespace, name, converted_attribs,
not next or next[0] != END or
next[1] != tag):
yield token
else:
yield self.startTag(namespace, name, converted_attribs)
elif kind == END:
name = data.localname
namespace = data.namespace
if namespace != namespaces["html"] or name not in voidElements:
yield self.endTag(namespace, name)
elif kind == COMMENT:
yield self.comment(data)
elif kind == TEXT:
for token in self.text(data):
yield token
elif kind == DOCTYPE:
yield self.doctype(*data)
elif kind in (XML_NAMESPACE, DOCTYPE, START_NS, END_NS,
START_CDATA, END_CDATA, PI):
pass
else:
yield self.unknown(kind)
Example #16
| Source File: genshi.py From recruit with Apache License 2.0 | 4 votes |
|
def tokens(self, event, next):
kind, data, _ = event
if kind == START:
tag, attribs = data
name = tag.localname
namespace = tag.namespace
converted_attribs = {}
for k, v in attribs:
if isinstance(k, QName):
converted_attribs[(k.namespace, k.localname)] = v
else:
converted_attribs[(None, k)] = v
if namespace == namespaces["html"] and name in voidElements:
for token in self.emptyTag(namespace, name, converted_attribs,
not next or next[0] != END or
next[1] != tag):
yield token
else:
yield self.startTag(namespace, name, converted_attribs)
elif kind == END:
name = data.localname
namespace = data.namespace
if namespace != namespaces["html"] or name not in voidElements:
yield self.endTag(namespace, name)
elif kind == COMMENT:
yield self.comment(data)
elif kind == TEXT:
for token in self.text(data):
yield token
elif kind == DOCTYPE:
yield self.doctype(*data)
elif kind in (XML_NAMESPACE, DOCTYPE, START_NS, END_NS,
START_CDATA, END_CDATA, PI):
pass
else:
yield self.unknown(kind)
Example #17
| Source File: genshi.py From planespotter with MIT License | 4 votes |
|
def tokens(self, event, next):
kind, data, _ = event
if kind == START:
tag, attribs = data
name = tag.localname
namespace = tag.namespace
converted_attribs = {}
for k, v in attribs:
if isinstance(k, QName):
converted_attribs[(k.namespace, k.localname)] = v
else:
converted_attribs[(None, k)] = v
if namespace == namespaces["html"] and name in voidElements:
for token in self.emptyTag(namespace, name, converted_attribs,
not next or next[0] != END or
next[1] != tag):
yield token
else:
yield self.startTag(namespace, name, converted_attribs)
elif kind == END:
name = data.localname
namespace = data.namespace
if namespace != namespaces["html"] or name not in voidElements:
yield self.endTag(namespace, name)
elif kind == COMMENT:
yield self.comment(data)
elif kind == TEXT:
for token in self.text(data):
yield token
elif kind == DOCTYPE:
yield self.doctype(*data)
elif kind in (XML_NAMESPACE, DOCTYPE, START_NS, END_NS,
START_CDATA, END_CDATA, PI):
pass
else:
yield self.unknown(kind)
Example #18
| Source File: genshi.py From Weapon-Detection-And-Classification with MIT License | 4 votes |
|
def to_genshi(walker):
"""Convert a tree to a genshi tree
:arg walker: the treewalker to use to walk the tree to convert it
:returns: generator of genshi nodes
"""
text = []
for token in walker:
type = token["type"]
if type in ("Characters", "SpaceCharacters"):
text.append(token["data"])
elif text:
yield TEXT, "".join(text), (None, -1, -1)
text = []
if type in ("StartTag", "EmptyTag"):
if token["namespace"]:
name = "{%s}%s" % (token["namespace"], token["name"])
else:
name = token["name"]
attrs = Attrs([(QName("{%s}%s" % attr if attr[0] is not None else attr[1]), value)
for attr, value in token["data"].items()])
yield (START, (QName(name), attrs), (None, -1, -1))
if type == "EmptyTag":
type = "EndTag"
if type == "EndTag":
if token["namespace"]:
name = "{%s}%s" % (token["namespace"], token["name"])
else:
name = token["name"]
yield END, QName(name), (None, -1, -1)
elif type == "Comment":
yield COMMENT, token["data"], (None, -1, -1)
elif type == "Doctype":
yield DOCTYPE, (token["name"], token["publicId"],
token["systemId"]), (None, -1, -1)
else:
pass # FIXME: What to do?
if text:
yield TEXT, "".join(text), (None, -1, -1)
Example #19
| Source File: genshi.py From Weapon-Detection-And-Classification with MIT License | 4 votes |
|
def tokens(self, event, next):
kind, data, _ = event
if kind == START:
tag, attribs = data
name = tag.localname
namespace = tag.namespace
converted_attribs = {}
for k, v in attribs:
if isinstance(k, QName):
converted_attribs[(k.namespace, k.localname)] = v
else:
converted_attribs[(None, k)] = v
if namespace == namespaces["html"] and name in voidElements:
for token in self.emptyTag(namespace, name, converted_attribs,
not next or next[0] != END or
next[1] != tag):
yield token
else:
yield self.startTag(namespace, name, converted_attribs)
elif kind == END:
name = data.localname
namespace = data.namespace
if namespace != namespaces["html"] or name not in voidElements:
yield self.endTag(namespace, name)
elif kind == COMMENT:
yield self.comment(data)
elif kind == TEXT:
for token in self.text(data):
yield token
elif kind == DOCTYPE:
yield self.doctype(*data)
elif kind in (XML_NAMESPACE, DOCTYPE, START_NS, END_NS,
START_CDATA, END_CDATA, PI):
pass
else:
yield self.unknown(kind)
Example #20
| Source File: genshistream.py From Flask-P2P with MIT License | 4 votes |
|
def tokens(self, event, next):
kind, data, pos = event
if kind == START:
tag, attribs = data
name = tag.localname
namespace = tag.namespace
converted_attribs = {}
for k, v in attribs:
if isinstance(k, QName):
converted_attribs[(k.namespace, k.localname)] = v
else:
converted_attribs[(None, k)] = v
if namespace == namespaces["html"] and name in voidElements:
for token in self.emptyTag(namespace, name, converted_attribs,
not next or next[0] != END
or next[1] != tag):
yield token
else:
yield self.startTag(namespace, name, converted_attribs)
elif kind == END:
name = data.localname
namespace = data.namespace
if name not in voidElements:
yield self.endTag(namespace, name)
elif kind == COMMENT:
yield self.comment(data)
elif kind == TEXT:
for token in self.text(data):
yield token
elif kind == DOCTYPE:
yield self.doctype(*data)
elif kind in (XML_NAMESPACE, DOCTYPE, START_NS, END_NS,
START_CDATA, END_CDATA, PI):
pass
else:
yield self.unknown(kind)
Example #21
| Source File: genshi.py From bazarr with GNU General Public License v3.0 | 4 votes |
|
def to_genshi(walker):
"""Convert a tree to a genshi tree
:arg walker: the treewalker to use to walk the tree to convert it
:returns: generator of genshi nodes
"""
text = []
for token in walker:
type = token["type"]
if type in ("Characters", "SpaceCharacters"):
text.append(token["data"])
elif text:
yield TEXT, "".join(text), (None, -1, -1)
text = []
if type in ("StartTag", "EmptyTag"):
if token["namespace"]:
name = "{%s}%s" % (token["namespace"], token["name"])
else:
name = token["name"]
attrs = Attrs([(QName("{%s}%s" % attr if attr[0] is not None else attr[1]), value)
for attr, value in token["data"].items()])
yield (START, (QName(name), attrs), (None, -1, -1))
if type == "EmptyTag":
type = "EndTag"
if type == "EndTag":
if token["namespace"]:
name = "{%s}%s" % (token["namespace"], token["name"])
else:
name = token["name"]
yield END, QName(name), (None, -1, -1)
elif type == "Comment":
yield COMMENT, token["data"], (None, -1, -1)
elif type == "Doctype":
yield DOCTYPE, (token["name"], token["publicId"],
token["systemId"]), (None, -1, -1)
else:
pass # FIXME: What to do?
if text:
yield TEXT, "".join(text), (None, -1, -1)
Example #22
| Source File: genshi.py From python with Apache License 2.0 | 4 votes |
|
def tokens(self, event, next):
kind, data, _ = event
if kind == START:
tag, attribs = data
name = tag.localname
namespace = tag.namespace
converted_attribs = {}
for k, v in attribs:
if isinstance(k, QName):
converted_attribs[(k.namespace, k.localname)] = v
else:
converted_attribs[(None, k)] = v
if namespace == namespaces["html"] and name in voidElements:
for token in self.emptyTag(namespace, name, converted_attribs,
not next or next[0] != END or
next[1] != tag):
yield token
else:
yield self.startTag(namespace, name, converted_attribs)
elif kind == END:
name = data.localname
namespace = data.namespace
if namespace != namespaces["html"] or name not in voidElements:
yield self.endTag(namespace, name)
elif kind == COMMENT:
yield self.comment(data)
elif kind == TEXT:
for token in self.text(data):
yield token
elif kind == DOCTYPE:
yield self.doctype(*data)
elif kind in (XML_NAMESPACE, DOCTYPE, START_NS, END_NS,
START_CDATA, END_CDATA, PI):
pass
else:
yield self.unknown(kind)
Example #23
| Source File: genshistream.py From Financial-Portfolio-Flask with MIT License | 4 votes |
|
def tokens(self, event, next):
kind, data, pos = event
if kind == START:
tag, attribs = data
name = tag.localname
namespace = tag.namespace
converted_attribs = {}
for k, v in attribs:
if isinstance(k, QName):
converted_attribs[(k.namespace, k.localname)] = v
else:
converted_attribs[(None, k)] = v
if namespace == namespaces["html"] and name in voidElements:
for token in self.emptyTag(namespace, name, converted_attribs,
not next or next[0] != END
or next[1] != tag):
yield token
else:
yield self.startTag(namespace, name, converted_attribs)
elif kind == END:
name = data.localname
namespace = data.namespace
if name not in voidElements:
yield self.endTag(namespace, name)
elif kind == COMMENT:
yield self.comment(data)
elif kind == TEXT:
for token in self.text(data):
yield token
elif kind == DOCTYPE:
yield self.doctype(*data)
elif kind in (XML_NAMESPACE, DOCTYPE, START_NS, END_NS,
START_CDATA, END_CDATA, PI):
pass
else:
yield self.unknown(kind)
Example #24
| Source File: genshi.py From Hands-On-Application-Development-with-PyCharm with MIT License | 4 votes |
|
def to_genshi(walker):
"""Convert a tree to a genshi tree
:arg walker: the treewalker to use to walk the tree to convert it
:returns: generator of genshi nodes
"""
text = []
for token in walker:
type = token["type"]
if type in ("Characters", "SpaceCharacters"):
text.append(token["data"])
elif text:
yield TEXT, "".join(text), (None, -1, -1)
text = []
if type in ("StartTag", "EmptyTag"):
if token["namespace"]:
name = "{%s}%s" % (token["namespace"], token["name"])
else:
name = token["name"]
attrs = Attrs([(QName("{%s}%s" % attr if attr[0] is not None else attr[1]), value)
for attr, value in token["data"].items()])
yield (START, (QName(name), attrs), (None, -1, -1))
if type == "EmptyTag":
type = "EndTag"
if type == "EndTag":
if token["namespace"]:
name = "{%s}%s" % (token["namespace"], token["name"])
else:
name = token["name"]
yield END, QName(name), (None, -1, -1)
elif type == "Comment":
yield COMMENT, token["data"], (None, -1, -1)
elif type == "Doctype":
yield DOCTYPE, (token["name"], token["publicId"],
token["systemId"]), (None, -1, -1)
else:
pass # FIXME: What to do?
if text:
yield TEXT, "".join(text), (None, -1, -1)
Example #25
| Source File: genshi.py From Hands-On-Application-Development-with-PyCharm with MIT License | 4 votes |
|
def tokens(self, event, next):
kind, data, _ = event
if kind == START:
tag, attribs = data
name = tag.localname
namespace = tag.namespace
converted_attribs = {}
for k, v in attribs:
if isinstance(k, QName):
converted_attribs[(k.namespace, k.localname)] = v
else:
converted_attribs[(None, k)] = v
if namespace == namespaces["html"] and name in voidElements:
for token in self.emptyTag(namespace, name, converted_attribs,
not next or next[0] != END or
next[1] != tag):
yield token
else:
yield self.startTag(namespace, name, converted_attribs)
elif kind == END:
name = data.localname
namespace = data.namespace
if namespace != namespaces["html"] or name not in voidElements:
yield self.endTag(namespace, name)
elif kind == COMMENT:
yield self.comment(data)
elif kind == TEXT:
for token in self.text(data):
yield token
elif kind == DOCTYPE:
yield self.doctype(*data)
elif kind in (XML_NAMESPACE, DOCTYPE, START_NS, END_NS,
START_CDATA, END_CDATA, PI):
pass
else:
yield self.unknown(kind)
Example #26
| Source File: genshi.py From stopstalk-deployment with MIT License | 4 votes |
|
def to_genshi(walker):
"""Convert a tree to a genshi tree
:arg walker: the treewalker to use to walk the tree to convert it
:returns: generator of genshi nodes
"""
text = []
for token in walker:
type = token["type"]
if type in ("Characters", "SpaceCharacters"):
text.append(token["data"])
elif text:
yield TEXT, "".join(text), (None, -1, -1)
text = []
if type in ("StartTag", "EmptyTag"):
if token["namespace"]:
name = "{%s}%s" % (token["namespace"], token["name"])
else:
name = token["name"]
attrs = Attrs([(QName("{%s}%s" % attr if attr[0] is not None else attr[1]), value)
for attr, value in token["data"].items()])
yield (START, (QName(name), attrs), (None, -1, -1))
if type == "EmptyTag":
type = "EndTag"
if type == "EndTag":
if token["namespace"]:
name = "{%s}%s" % (token["namespace"], token["name"])
else:
name = token["name"]
yield END, QName(name), (None, -1, -1)
elif type == "Comment":
yield COMMENT, token["data"], (None, -1, -1)
elif type == "Doctype":
yield DOCTYPE, (token["name"], token["publicId"],
token["systemId"]), (None, -1, -1)
else:
pass # FIXME: What to do?
if text:
yield TEXT, "".join(text), (None, -1, -1)
Example #27
| Source File: genshi.py From stopstalk-deployment with MIT License | 4 votes |
|
def tokens(self, event, next):
kind, data, _ = event
if kind == START:
tag, attribs = data
name = tag.localname
namespace = tag.namespace
converted_attribs = {}
for k, v in attribs:
if isinstance(k, QName):
converted_attribs[(k.namespace, k.localname)] = v
else:
converted_attribs[(None, k)] = v
if namespace == namespaces["html"] and name in voidElements:
for token in self.emptyTag(namespace, name, converted_attribs,
not next or next[0] != END or
next[1] != tag):
yield token
else:
yield self.startTag(namespace, name, converted_attribs)
elif kind == END:
name = data.localname
namespace = data.namespace
if namespace != namespaces["html"] or name not in voidElements:
yield self.endTag(namespace, name)
elif kind == COMMENT:
yield self.comment(data)
elif kind == TEXT:
for token in self.text(data):
yield token
elif kind == DOCTYPE:
yield self.doctype(*data)
elif kind in (XML_NAMESPACE, DOCTYPE, START_NS, END_NS,
START_CDATA, END_CDATA, PI):
pass
else:
yield self.unknown(kind)
Example #28
| Source File: genshi.py From learn_python3_spider with MIT License | 4 votes |
|
def to_genshi(walker):
"""Convert a tree to a genshi tree
:arg walker: the treewalker to use to walk the tree to convert it
:returns: generator of genshi nodes
"""
text = []
for token in walker:
type = token["type"]
if type in ("Characters", "SpaceCharacters"):
text.append(token["data"])
elif text:
yield TEXT, "".join(text), (None, -1, -1)
text = []
if type in ("StartTag", "EmptyTag"):
if token["namespace"]:
name = "{%s}%s" % (token["namespace"], token["name"])
else:
name = token["name"]
attrs = Attrs([(QName("{%s}%s" % attr if attr[0] is not None else attr[1]), value)
for attr, value in token["data"].items()])
yield (START, (QName(name), attrs), (None, -1, -1))
if type == "EmptyTag":
type = "EndTag"
if type == "EndTag":
if token["namespace"]:
name = "{%s}%s" % (token["namespace"], token["name"])
else:
name = token["name"]
yield END, QName(name), (None, -1, -1)
elif type == "Comment":
yield COMMENT, token["data"], (None, -1, -1)
elif type == "Doctype":
yield DOCTYPE, (token["name"], token["publicId"],
token["systemId"]), (None, -1, -1)
else:
pass # FIXME: What to do?
if text:
yield TEXT, "".join(text), (None, -1, -1)
Example #29
| Source File: genshi.py From learn_python3_spider with MIT License | 4 votes |
|
def tokens(self, event, next):
kind, data, _ = event
if kind == START:
tag, attribs = data
name = tag.localname
namespace = tag.namespace
converted_attribs = {}
for k, v in attribs:
if isinstance(k, QName):
converted_attribs[(k.namespace, k.localname)] = v
else:
converted_attribs[(None, k)] = v
if namespace == namespaces["html"] and name in voidElements:
for token in self.emptyTag(namespace, name, converted_attribs,
not next or next[0] != END or
next[1] != tag):
yield token
else:
yield self.startTag(namespace, name, converted_attribs)
elif kind == END:
name = data.localname
namespace = data.namespace
if namespace != namespaces["html"] or name not in voidElements:
yield self.endTag(namespace, name)
elif kind == COMMENT:
yield self.comment(data)
elif kind == TEXT:
for token in self.text(data):
yield token
elif kind == DOCTYPE:
yield self.doctype(*data)
elif kind in (XML_NAMESPACE, DOCTYPE, START_NS, END_NS,
START_CDATA, END_CDATA, PI):
pass
else:
yield self.unknown(kind)
Example #30
| Source File: genshi.py From guildai with Apache License 2.0 | 4 votes |
|
def to_genshi(walker):
"""Convert a tree to a genshi tree
:arg walker: the treewalker to use to walk the tree to convert it
:returns: generator of genshi nodes
"""
text = []
for token in walker:
type = token["type"]
if type in ("Characters", "SpaceCharacters"):
text.append(token["data"])
elif text:
yield TEXT, "".join(text), (None, -1, -1)
text = []
if type in ("StartTag", "EmptyTag"):
if token["namespace"]:
name = "{%s}%s" % (token["namespace"], token["name"])
else:
name = token["name"]
attrs = Attrs([(QName("{%s}%s" % attr if attr[0] is not None else attr[1]), value)
for attr, value in token["data"].items()])
yield (START, (QName(name), attrs), (None, -1, -1))
if type == "EmptyTag":
type = "EndTag"
if type == "EndTag":
if token["namespace"]:
name = "{%s}%s" % (token["namespace"], token["name"])
else:
name = token["name"]
yield END, QName(name), (None, -1, -1)
elif type == "Comment":
yield COMMENT, token["data"], (None, -1, -1)
elif type == "Doctype":
yield DOCTYPE, (token["name"], token["publicId"],
token["systemId"]), (None, -1, -1)
else:
pass # FIXME: What to do?
if text:
yield TEXT, "".join(text), (None, -1, -1)
