BackTrackZ/scrapy
BackTrackZ/scrapy
1
0
Fork 0
mirror of https://github.com/scrapy/scrapy.git synced 2025-02-26 10:43:43 +00:00
Code Releases Wiki Activity

scarpy.xpath: added __weakref__ to __slots__, removed unused XPathSelector.response attribute, moved deprecated methods to the bottom

Browse Source
This commit is contained in:
Pablo Hoffman 2009-08-18 20:00:54 -03:00
parent 00527fc93c
commit 240e06813d
2 changed files with 18 additions and 20 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
scrapy/xpath/document.py
View File

@ -10,7 +10,7 @@ from scrapy.xpath.factories import xmlDoc_from_html
class Libxml2Document(object):
cache = weakref.WeakKeyDictionary()
__slots__ = ['xmlDoc', 'xpathContext']
__slots__ = ['xmlDoc', 'xpathContext', '__weakref__']
def __new__(cls, response, factory=xmlDoc_from_html):
cache = cls.cache.setdefault(response, {})

36
scrapy/xpath/selector.py
View File

@ -16,7 +16,7 @@ from scrapy.utils.decorator import deprecated
class XPathSelector(object_ref):
__slots__ = ['doc', 'xmlNode', 'response', 'expr']
__slots__ = ['doc', 'xmlNode', 'expr', '__weakref__']
def __init__(self, response=None, text=None, node=None, parent=None, expr=None):
if parent:
@ -31,7 +31,6 @@ class XPathSelector(object_ref):
self.doc = Libxml2Document(response, factory=self._get_libxml2_doc)
self.xmlNode = self.doc.xmlDoc
self.expr = expr
self.response = response
def select(self, xpath):
"""Perform the given XPath query on the current XPathSelector and
@ -42,24 +41,15 @@ class XPathSelector(object_ref):
xpath_result = self.doc.xpathContext.xpathEval(xpath)
except libxml2.xpathError:
raise ValueError("Invalid XPath: %s" % xpath)
cls = type(self)
if hasattr(xpath_result, '__iter__'):
return XPathSelectorList([cls(node=node, parent=self, expr=xpath, \
response=self.response) for node in xpath_result])
return XPathSelectorList([self.__class__(node=node, parent=self, \
expr=xpath) for node in xpath_result])
else:
return XPathSelectorList([cls(node=xpath_result, parent=self, \
expr=xpath, response=self.response)])
return XPathSelectorList([self.__class__(node=xpath_result, \
parent=self, expr=xpath)])
else:
return XPathSelectorList([])
@deprecated(use_instead='XPathSelector.select')
def __call__(self, xpath):
return self.select(xpath)
@deprecated(use_instead='XPathSelector.select')
def x(self, xpath):
return self.select(xpath)
def re(self, regex):
"""Return a list of unicode strings by applying the regex over all
current XPath selections, and flattening the results"""
@ -110,6 +100,14 @@ class XPathSelector(object_ref):
__repr__ = __str__
@deprecated(use_instead='XPathSelector.select')
def __call__(self, xpath):
return self.select(xpath)
@deprecated(use_instead='XPathSelector.select')
def x(self, xpath):
return self.select(xpath)
class XPathSelectorList(list):
"""List of XPathSelector objects"""
@ -122,10 +120,6 @@ class XPathSelectorList(list):
return a new (flattened) XPathSelectorList of the results"""
return XPathSelectorList(flatten([x.select(xpath) for x in self]))
@deprecated(use_instead='XPathSelectorList.select')
def x(self, xpath):
return self.select(xpath)
def re(self, regex):
"""Perform the re() method on each XPathSelector of the list, and
return the result as a flattened list of unicode strings"""
@ -139,6 +133,10 @@ class XPathSelectorList(list):
def extract_unquoted(self):
return [x.extract_unquoted() if isinstance(x, XPathSelector) else x for x in self]
@deprecated(use_instead='XPathSelectorList.select')
def x(self, xpath):
return self.select(xpath)
class XmlXPathSelector(XPathSelector):
"""XPathSelector for XML content"""