dinislage/CouchPotatoServer
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

BeautifulSoup4 python 3

Browse Source
This commit is contained in:
Ruud
2014-10-06 11:12:35 +02:00
parent 5b7e814166
commit 6b4e6857de
9 changed files with 138 additions and 138 deletions
Download Patch File Download Diff File Expand all files Collapse all files
libs/bs4/builder/_lxml.py
+11 -11
View File
@@ -4,7 +4,7 @@ __all__ = [
]
from io import BytesIO
from StringIO import StringIO
from io import StringIO
import collections
from lxml import etree
from bs4.element import Comment, Doctype, NamespacedAttribute
@@ -78,12 +78,12 @@ class LXMLTreeBuilderForXML(TreeBuilder):
Each 4-tuple represents a strategy for parsing the document.
"""
if isinstance(markup, unicode):
if isinstance(markup, str):
# We were given Unicode. Maybe lxml can parse Unicode on
# this system?
yield markup, None, document_declared_encoding, False
if isinstance(markup, unicode):
if isinstance(markup, str):
# No, apparently not. Convert the Unicode to UTF-8 and
# tell lxml to parse it as UTF-8.
yield (markup.encode("utf8"), "utf8",
@@ -102,7 +102,7 @@ class LXMLTreeBuilderForXML(TreeBuilder):
def feed(self, markup):
if isinstance(markup, bytes):
markup = BytesIO(markup)
elif isinstance(markup, unicode):
elif isinstance(markup, str):
markup = StringIO(markup)
# Call feed() at least once, even if the markup is empty,
@@ -117,7 +117,7 @@ class LXMLTreeBuilderForXML(TreeBuilder):
if len(data) != 0:
self.parser.feed(data)
self.parser.close()
except (UnicodeDecodeError, LookupError, etree.ParserError), e:
except (UnicodeDecodeError, LookupError, etree.ParserError) as e:
raise ParserRejectedMarkup(str(e))
def close(self):
@@ -135,12 +135,12 @@ class LXMLTreeBuilderForXML(TreeBuilder):
self.nsmaps.append(None)
elif len(nsmap) > 0:
# A new namespace mapping has come into play.
inverted_nsmap = dict((value, key) for key, value in nsmap.items())
inverted_nsmap = dict((value, key) for key, value in list(nsmap.items()))
self.nsmaps.append(inverted_nsmap)
# Also treat the namespace mapping as a set of attributes on the
# tag, so we can recreate it later.
attrs = attrs.copy()
for prefix, namespace in nsmap.items():
for prefix, namespace in list(nsmap.items()):
attribute = NamespacedAttribute(
"xmlns", prefix, "http://www.w3.org/2000/xmlns/")
attrs[attribute] = namespace
@@ -149,7 +149,7 @@ class LXMLTreeBuilderForXML(TreeBuilder):
# from lxml with namespaces attached to their names, and
# turn then into NamespacedAttribute objects.
new_attrs = {}
for attr, value in attrs.items():
for attr, value in list(attrs.items()):
namespace, attr = self._getNsTag(attr)
if namespace is None:
new_attrs[attr] = value
@@ -207,7 +207,7 @@ class LXMLTreeBuilderForXML(TreeBuilder):
def test_fragment_to_document(self, fragment):
"""See `TreeBuilder`."""
return u'<?xml version="1.0" encoding="utf-8"?>\n%s' % fragment
return '<?xml version="1.0" encoding="utf-8"?>\n%s' % fragment
class LXMLTreeBuilder(HTMLTreeBuilder, LXMLTreeBuilderForXML):
@@ -224,10 +224,10 @@ class LXMLTreeBuilder(HTMLTreeBuilder, LXMLTreeBuilderForXML):
self.parser = self.parser_for(encoding)
self.parser.feed(markup)
self.parser.close()
except (UnicodeDecodeError, LookupError, etree.ParserError), e:
except (UnicodeDecodeError, LookupError, etree.ParserError) as e:
raise ParserRejectedMarkup(str(e))
def test_fragment_to_document(self, fragment):
"""See `TreeBuilder`."""
return u'<html><body>%s</body></html>' % fragment
return '<html><body>%s</body></html>' % fragment