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/__init__.py
+2 -2
View File
@@ -153,13 +153,13 @@ class TreeBuilder(object):
universal = self.cdata_list_attributes.get('*', [])
tag_specific = self.cdata_list_attributes.get(
tag_name.lower(), None)
for attr in attrs.keys():
for attr in list(attrs.keys()):
if attr in universal or (tag_specific and attr in tag_specific):
# We have a "class"-type attribute whose string
# value is a whitespace-separated list of
# values. Split it into a list.
value = attrs[attr]
if isinstance(value, basestring):
if isinstance(value, str):
values = whitespace_re.split(value)
else:
# html5lib sometimes calls setAttributes twice
libs/bs4/builder/_html5lib.py
+6 -6
View File
@@ -37,7 +37,7 @@ class HTML5TreeBuilder(HTMLTreeBuilder):
doc = parser.parse(markup, encoding=self.user_specified_encoding)
# Set the character encoding detected by the tokenizer.
if isinstance(markup, unicode):
if isinstance(markup, str):
# We need to special-case this because html5lib sets
# charEncoding to UTF-8 if it gets Unicode input.
doc.original_encoding = None
@@ -51,7 +51,7 @@ class HTML5TreeBuilder(HTMLTreeBuilder):
def test_fragment_to_document(self, fragment):
"""See `TreeBuilder`."""
return u'<html><head></head><body>%s</body></html>' % fragment
return '<html><head></head><body>%s</body></html>' % fragment
class TreeBuilderForHtml5lib(html5lib.treebuilders._base.TreeBuilder):
@@ -124,7 +124,7 @@ class Element(html5lib.treebuilders._base.Node):
def appendChild(self, node):
string_child = child = None
if isinstance(node, basestring):
if isinstance(node, str):
# Some other piece of code decided to pass in a string
# instead of creating a TextElement object to contain the
# string.
@@ -139,7 +139,7 @@ class Element(html5lib.treebuilders._base.Node):
else:
child = node.element
if not isinstance(child, basestring) and child.parent is not None:
if not isinstance(child, str) and child.parent is not None:
node.element.extract()
if (string_child and self.element.contents
@@ -152,7 +152,7 @@ class Element(html5lib.treebuilders._base.Node):
old_element.replace_with(new_element)
self.soup._most_recent_element = new_element
else:
if isinstance(node, basestring):
if isinstance(node, str):
# Create a brand new NavigableString from this string.
child = self.soup.new_string(node)
@@ -183,7 +183,7 @@ class Element(html5lib.treebuilders._base.Node):
self.soup.builder._replace_cdata_list_attribute_values(
self.name, attributes)
for name, value in attributes.items():
for name, value in list(attributes.items()):
self.element[name] = value
# The attributes may contain variables that need substitution.
libs/bs4/builder/_htmlparser.py
+6 -6
View File
@@ -4,7 +4,7 @@ __all__ = [
'HTMLParserTreeBuilder',
]
from HTMLParser import (
from html.parser import (
HTMLParser,
HTMLParseError,
)
@@ -72,9 +72,9 @@ class BeautifulSoupHTMLParser(HTMLParser):
real_name = int(name)
try:
data = unichr(real_name)
except (ValueError, OverflowError), e:
data = u"\N{REPLACEMENT CHARACTER}"
data = chr(real_name)
except (ValueError, OverflowError) as e:
data = "\N{REPLACEMENT CHARACTER}"
self.handle_data(data)
@@ -142,7 +142,7 @@ class HTMLParserTreeBuilder(HTMLTreeBuilder):
declared within markup, whether any characters had to be
replaced with REPLACEMENT CHARACTER).
"""
if isinstance(markup, unicode):
if isinstance(markup, str):
yield (markup, None, None, False)
return
@@ -158,7 +158,7 @@ class HTMLParserTreeBuilder(HTMLTreeBuilder):
parser.soup = self.soup
try:
parser.feed(markup)
except HTMLParseError, e:
except HTMLParseError as e:
warnings.warn(RuntimeWarning(
"Python's built-in HTMLParser cannot parse the given document. This is not a bug in Beautiful Soup. The best solution is to install an external parser (lxml or html5lib), and use Beautiful Soup with that parser. See http://www.crummy.com/software/BeautifulSoup/bs4/doc/#installing-a-parser for help."))
raise e
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