mirror of
https://github.com/clinton-hall/nzbToMedia.git
synced 2025-08-14 02:26:53 -07:00
Update subliminal to 2.0.5
Also updates: - appdirs-1.4.3 - babelfish-0.5.5 - beautifulsoup4-4.6.3 - certifi-2018.11.29 - chardet-3.0.4 - click-7.0 - decorator-4.3.0 - dogpile.cache-0.7.1 - enzyme-0.4.1 - guessit-3.0.3 - idna-2.8 - pbr-5.1.1 - pysrt-1.1.1 - python-dateutil-2.7.5 - pytz-2018.7 - rarfile-3.0 - rebulk-1.0.0 - requests-2.21.0 - six-1.12.0 - stevedore-1.30.0 - urllib3-1.24.1
This commit is contained in:
Labrys of Knossos
parent
2eb9d9dc7c
commit
f3fcb47427
761 changed files with 29015 additions and 1843 deletions
|
|
@ -6,6 +6,7 @@ __all__ = [
|
|||
]
|
||||
|
||||
import warnings
|
||||
import re
|
||||
from bs4.builder import (
|
||||
PERMISSIVE,
|
||||
HTML,
|
||||
|
|
@ -17,7 +18,10 @@ from bs4.element import (
|
|||
whitespace_re,
|
||||
)
|
||||
import html5lib
|
||||
from html5lib.constants import namespaces
|
||||
from html5lib.constants import (
|
||||
namespaces,
|
||||
prefixes,
|
||||
)
|
||||
from bs4.element import (
|
||||
Comment,
|
||||
Doctype,
|
||||
|
|
@ -29,7 +33,7 @@ try:
|
|||
# Pre-0.99999999
|
||||
from html5lib.treebuilders import _base as treebuilder_base
|
||||
new_html5lib = False
|
||||
except ImportError, e:
|
||||
except ImportError as e:
|
||||
# 0.99999999 and up
|
||||
from html5lib.treebuilders import base as treebuilder_base
|
||||
new_html5lib = True
|
||||
|
|
@ -60,7 +64,7 @@ class HTML5TreeBuilder(HTMLTreeBuilder):
|
|||
parser = html5lib.HTMLParser(tree=self.create_treebuilder)
|
||||
|
||||
extra_kwargs = dict()
|
||||
if not isinstance(markup, unicode):
|
||||
if not isinstance(markup, str):
|
||||
if new_html5lib:
|
||||
extra_kwargs['override_encoding'] = self.user_specified_encoding
|
||||
else:
|
||||
|
|
@ -68,13 +72,13 @@ class HTML5TreeBuilder(HTMLTreeBuilder):
|
|||
doc = parser.parse(markup, **extra_kwargs)
|
||||
|
||||
# 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
|
||||
else:
|
||||
original_encoding = parser.tokenizer.stream.charEncoding[0]
|
||||
if not isinstance(original_encoding, basestring):
|
||||
if not isinstance(original_encoding, str):
|
||||
# In 0.99999999 and up, the encoding is an html5lib
|
||||
# Encoding object. We want to use a string for compatibility
|
||||
# with other tree builders.
|
||||
|
|
@ -83,18 +87,22 @@ class HTML5TreeBuilder(HTMLTreeBuilder):
|
|||
|
||||
def create_treebuilder(self, namespaceHTMLElements):
|
||||
self.underlying_builder = TreeBuilderForHtml5lib(
|
||||
self.soup, namespaceHTMLElements)
|
||||
namespaceHTMLElements, self.soup)
|
||||
return self.underlying_builder
|
||||
|
||||
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(treebuilder_base.TreeBuilder):
|
||||
|
||||
def __init__(self, soup, namespaceHTMLElements):
|
||||
self.soup = soup
|
||||
def __init__(self, namespaceHTMLElements, soup=None):
|
||||
if soup:
|
||||
self.soup = soup
|
||||
else:
|
||||
from bs4 import BeautifulSoup
|
||||
self.soup = BeautifulSoup("", "html.parser")
|
||||
super(TreeBuilderForHtml5lib, self).__init__(namespaceHTMLElements)
|
||||
|
||||
def documentClass(self):
|
||||
|
|
@ -117,7 +125,8 @@ class TreeBuilderForHtml5lib(treebuilder_base.TreeBuilder):
|
|||
return TextNode(Comment(data), self.soup)
|
||||
|
||||
def fragmentClass(self):
|
||||
self.soup = BeautifulSoup("")
|
||||
from bs4 import BeautifulSoup
|
||||
self.soup = BeautifulSoup("", "html.parser")
|
||||
self.soup.name = "[document_fragment]"
|
||||
return Element(self.soup, self.soup, None)
|
||||
|
||||
|
|
@ -131,6 +140,56 @@ class TreeBuilderForHtml5lib(treebuilder_base.TreeBuilder):
|
|||
def getFragment(self):
|
||||
return treebuilder_base.TreeBuilder.getFragment(self).element
|
||||
|
||||
def testSerializer(self, element):
|
||||
from bs4 import BeautifulSoup
|
||||
rv = []
|
||||
doctype_re = re.compile(r'^(.*?)(?: PUBLIC "(.*?)"(?: "(.*?)")?| SYSTEM "(.*?)")?$')
|
||||
|
||||
def serializeElement(element, indent=0):
|
||||
if isinstance(element, BeautifulSoup):
|
||||
pass
|
||||
if isinstance(element, Doctype):
|
||||
m = doctype_re.match(element)
|
||||
if m:
|
||||
name = m.group(1)
|
||||
if m.lastindex > 1:
|
||||
publicId = m.group(2) or ""
|
||||
systemId = m.group(3) or m.group(4) or ""
|
||||
rv.append("""|%s<!DOCTYPE %s "%s" "%s">""" %
|
||||
(' ' * indent, name, publicId, systemId))
|
||||
else:
|
||||
rv.append("|%s<!DOCTYPE %s>" % (' ' * indent, name))
|
||||
else:
|
||||
rv.append("|%s<!DOCTYPE >" % (' ' * indent,))
|
||||
elif isinstance(element, Comment):
|
||||
rv.append("|%s<!-- %s -->" % (' ' * indent, element))
|
||||
elif isinstance(element, NavigableString):
|
||||
rv.append("|%s\"%s\"" % (' ' * indent, element))
|
||||
else:
|
||||
if element.namespace:
|
||||
name = "%s %s" % (prefixes[element.namespace],
|
||||
element.name)
|
||||
else:
|
||||
name = element.name
|
||||
rv.append("|%s<%s>" % (' ' * indent, name))
|
||||
if element.attrs:
|
||||
attributes = []
|
||||
for name, value in list(element.attrs.items()):
|
||||
if isinstance(name, NamespacedAttribute):
|
||||
name = "%s %s" % (prefixes[name.namespace], name.name)
|
||||
if isinstance(value, list):
|
||||
value = " ".join(value)
|
||||
attributes.append((name, value))
|
||||
|
||||
for name, value in sorted(attributes):
|
||||
rv.append('|%s%s="%s"' % (' ' * (indent + 2), name, value))
|
||||
indent += 2
|
||||
for child in element.children:
|
||||
serializeElement(child, indent)
|
||||
serializeElement(element, 0)
|
||||
|
||||
return "\n".join(rv)
|
||||
|
||||
class AttrList(object):
|
||||
def __init__(self, element):
|
||||
self.element = element
|
||||
|
|
@ -170,7 +229,7 @@ class Element(treebuilder_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.
|
||||
|
|
@ -182,10 +241,12 @@ class Element(treebuilder_base.Node):
|
|||
child = node
|
||||
elif node.element.__class__ == NavigableString:
|
||||
string_child = child = node.element
|
||||
node.parent = self
|
||||
else:
|
||||
child = node.element
|
||||
node.parent = self
|
||||
|
||||
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
|
||||
|
|
@ -198,7 +259,7 @@ class Element(treebuilder_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)
|
||||
|
||||
|
|
@ -221,6 +282,8 @@ class Element(treebuilder_base.Node):
|
|||
most_recent_element=most_recent_element)
|
||||
|
||||
def getAttributes(self):
|
||||
if isinstance(self.element, Comment):
|
||||
return {}
|
||||
return AttrList(self.element)
|
||||
|
||||
def setAttributes(self, attributes):
|
||||
|
|
@ -236,7 +299,7 @@ class Element(treebuilder_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.
|
||||
|
|
@ -248,11 +311,11 @@ class Element(treebuilder_base.Node):
|
|||
attributes = property(getAttributes, setAttributes)
|
||||
|
||||
def insertText(self, data, insertBefore=None):
|
||||
text = TextNode(self.soup.new_string(data), self.soup)
|
||||
if insertBefore:
|
||||
text = TextNode(self.soup.new_string(data), self.soup)
|
||||
self.insertBefore(data, insertBefore)
|
||||
self.insertBefore(text, insertBefore)
|
||||
else:
|
||||
self.appendChild(data)
|
||||
self.appendChild(text)
|
||||
|
||||
def insertBefore(self, node, refNode):
|
||||
index = self.element.index(refNode.element)
|
||||
|
|
@ -274,6 +337,7 @@ class Element(treebuilder_base.Node):
|
|||
# print "MOVE", self.element.contents
|
||||
# print "FROM", self.element
|
||||
# print "TO", new_parent.element
|
||||
|
||||
element = self.element
|
||||
new_parent_element = new_parent.element
|
||||
# Determine what this tag's next_element will be once all the children
|
||||
|
|
@ -292,7 +356,6 @@ class Element(treebuilder_base.Node):
|
|||
new_parents_last_descendant_next_element = new_parent_element.next_element
|
||||
|
||||
to_append = element.contents
|
||||
append_after = new_parent_element.contents
|
||||
if len(to_append) > 0:
|
||||
# Set the first child's previous_element and previous_sibling
|
||||
# to elements within the new parent
|
||||
|
|
@ -309,12 +372,19 @@ class Element(treebuilder_base.Node):
|
|||
if new_parents_last_child:
|
||||
new_parents_last_child.next_sibling = first_child
|
||||
|
||||
# Fix the last child's next_element and next_sibling
|
||||
last_child = to_append[-1]
|
||||
last_child.next_element = new_parents_last_descendant_next_element
|
||||
# Find the very last element being moved. It is now the
|
||||
# parent's last descendant. It has no .next_sibling and
|
||||
# its .next_element is whatever the previous last
|
||||
# descendant had.
|
||||
last_childs_last_descendant = to_append[-1]._last_descendant(False, True)
|
||||
|
||||
last_childs_last_descendant.next_element = new_parents_last_descendant_next_element
|
||||
if new_parents_last_descendant_next_element:
|
||||
new_parents_last_descendant_next_element.previous_element = last_child
|
||||
last_child.next_sibling = None
|
||||
# TODO: This code has no test coverage and I'm not sure
|
||||
# how to get html5lib to go through this path, but it's
|
||||
# just the other side of the previous line.
|
||||
new_parents_last_descendant_next_element.previous_element = last_childs_last_descendant
|
||||
last_childs_last_descendant.next_sibling = None
|
||||
|
||||
for child in to_append:
|
||||
child.parent = new_parent_element
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue