Merge pull request #11162 from pymedusa/release/release-1.0.12

Release/release 1.0.12

CHANGELOG.md

@@ -1,3 +1,18 @@
+## 1.0.12 (03-03-2023)
+
+#### New Features
+- Add RSS Feed Client (Thanks to @sawyersteven)
+
+#### Improvements
+- Update many Python dependencies
+
+#### Fixes
+- Ensure that git_path is a valid file (Thanks to @pizza-power)
+- Avoid exception when the filepart doesn't match a season
+- Encode NZBGet username, password and host
+
+-----
+
 ## 1.0.11 (14-01-2023)
 
 #### Improvements

Dockerfile

@@ -19,7 +19,7 @@ RUN \
     mkdir /tmp/unrar-install && \
     tar xf /tmp/unrar-pkg/unrar-*.apk -C /tmp/unrar-install
 
-FROM python:3.10.4-alpine3.15
+FROM python:3.10.8-alpine3.15
 LABEL maintainer="pymedusa"
 
 ARG GIT_BRANCH

ext3/bs4/__init__.py → ext/bs4/__init__.py

@@ -7,16 +7,16 @@
 provides methods and Pythonic idioms that make it easy to navigate,
 search, and modify the parse tree.
 
-Beautiful Soup works with Python 2.7 and up. It works better if lxml
+Beautiful Soup works with Python 3.6 and up. It works better if lxml
 and/or html5lib is installed.
 
 For more than you ever wanted to know about Beautiful Soup, see the
 documentation: http://www.crummy.com/software/BeautifulSoup/bs4/doc/
 """
 
 __author__ = "Leonard Richardson (leonardr@segfault.org)"
-__version__ = "4.9.3"
-__copyright__ = "Copyright (c) 2004-2020 Leonard Richardson"
+__version__ = "4.11.2"
+__copyright__ = "Copyright (c) 2004-2023 Leonard Richardson"
 # Use of this source code is governed by the MIT license.
 __license__ = "MIT"
 
@@ -29,7 +29,16 @@
 import traceback
 import warnings
 
-from .builder import builder_registry, ParserRejectedMarkup
+# The very first thing we do is give a useful error if someone is
+# running this code under Python 2.
+if sys.version_info.major < 3:
+    raise ImportError('You are trying to use a Python 3-specific version of Beautiful Soup under Python 2. This will not work. The final version of Beautiful Soup to support Python 2 was 4.9.3.')
+
+from .builder import (
+    builder_registry,
+    ParserRejectedMarkup,
+    XMLParsedAsHTMLWarning,
+)
 from .dammit import UnicodeDammit
 from .element import (
     CData,
@@ -49,10 +58,6 @@
     TemplateString,
     )
 
-# The very first thing we do is give a useful error if someone is
-# running this code under Python 3 without converting it.
-'You are trying to run the Python 2 version of Beautiful Soup under Python 3. This will not work.'!='You need to convert the code, either by installing it (`python setup.py install`) or by running 2to3 (`2to3 -w bs4`).'
-
 # Define some custom warnings.
 class GuessedAtParserWarning(UserWarning):
     """The warning issued when BeautifulSoup has to guess what parser to
@@ -65,7 +70,7 @@ class MarkupResemblesLocatorWarning(UserWarning):
     on disk.
     """
 
-
+   
 class BeautifulSoup(Tag):
     """A data structure representing a parsed HTML or XML document.
 
@@ -205,10 +210,10 @@ def deprecated_argument(old_name, new_name):
             if old_name in kwargs:
                 warnings.warn(
                     'The "%s" argument to the BeautifulSoup constructor '
-                    'has been renamed to "%s."' % (old_name, new_name))
-                value = kwargs[old_name]
-                del kwargs[old_name]
-                return value
+                    'has been renamed to "%s."' % (old_name, new_name),
+                    DeprecationWarning, stacklevel=3
+                )
+                return kwargs.pop(old_name)
             return None
 
         parse_only = parse_only or deprecated_argument(
@@ -303,39 +308,18 @@ def deprecated_argument(old_name, new_name):
         self._namespaces = dict()
         self.parse_only = parse_only
 
-        self.builder.initialize_soup(self)
-
         if hasattr(markup, 'read'):        # It's a file-type object.
             markup = markup.read()
         elif len(markup) <= 256 and (
                 (isinstance(markup, bytes) and not b'<' in markup)
                 or (isinstance(markup, str) and not '<' in markup)
         ):
-            # Print out warnings for a couple beginner problems
+            # Issue warnings for a couple beginner problems
             # involving passing non-markup to Beautiful Soup.
             # Beautiful Soup will still parse the input as markup,
-            # just in case that's what the user really wants.
-            if (isinstance(markup, str)
-                and not os.path.supports_unicode_filenames):
-                possible_filename = markup.encode("utf8")
-            else:
-                possible_filename = markup
-            is_file = False
-            try:
-                is_file = os.path.exists(possible_filename)
-            except Exception as e:
-                # This is almost certainly a problem involving
-                # characters not valid in filenames on this
-                # system. Just let it go.
-                pass
-            if is_file:
-                warnings.warn(
-                    '"%s" looks like a filename, not markup. You should'
-                    ' probably open this file and pass the filehandle into'
-                    ' Beautiful Soup.' % self._decode_markup(markup),
-                    MarkupResemblesLocatorWarning
-                )
-            self._check_markup_is_url(markup)
+            # since that is sometimes the intended behavior.
+            if not self._markup_is_url(markup):
+                self._markup_resembles_filename(markup)                
 
         rejections = []
         success = False
@@ -344,6 +328,7 @@ def deprecated_argument(old_name, new_name):
              self.builder.prepare_markup(
                  markup, from_encoding, exclude_encodings=exclude_encodings)):
             self.reset()
+            self.builder.initialize_soup(self)
             try:
                 self._feed()
                 success = True
@@ -379,10 +364,10 @@ def __copy__(self):
     def __getstate__(self):
         # Frequently a tree builder can't be pickled.
         d = dict(self.__dict__)
-        if 'builder' in d and not self.builder.picklable:
+        if 'builder' in d and d['builder'] is not None and not self.builder.picklable:
             d['builder'] = None
         return d
-
+    
     @classmethod
     def _decode_markup(cls, markup):
         """Ensure `markup` is bytes so it's safe to send into warnings.warn.
@@ -397,11 +382,13 @@ def _decode_markup(cls, markup):
         return decoded
 
     @classmethod
-    def _check_markup_is_url(cls, markup):
+    def _markup_is_url(cls, markup):
         """Error-handling method to raise a warning if incoming markup looks
         like a URL.
 
         :param markup: A string.
+        :return: Whether or not the markup resembles a URL
+            closely enough to justify a warning.
         """
         if isinstance(markup, bytes):
             space = b' '
@@ -410,20 +397,51 @@ def _check_markup_is_url(cls, markup):
             space = ' '
             cant_start_with = ("http:", "https:")
         else:
-            return
+            return False
 
         if any(markup.startswith(prefix) for prefix in cant_start_with):
             if not space in markup:
                 warnings.warn(
-                    '"%s" looks like a URL. Beautiful Soup is not an'
-                    ' HTTP client. You should probably use an HTTP client like'
-                    ' requests to get the document behind the URL, and feed'
-                    ' that document to Beautiful Soup.' % cls._decode_markup(
-                        markup
-                    ),
-                    MarkupResemblesLocatorWarning
+                    'The input looks more like a URL than markup. You may want to use'
+                    ' an HTTP client like requests to get the document behind'
+                    ' the URL, and feed that document to Beautiful Soup.',
+                    MarkupResemblesLocatorWarning,
+                    stacklevel=3
                 )
+                return True
+        return False
 
+    @classmethod
+    def _markup_resembles_filename(cls, markup):
+        """Error-handling method to raise a warning if incoming markup
+        resembles a filename.
+
+        :param markup: A bytestring or string.
+        :return: Whether or not the markup resembles a filename
+            closely enough to justify a warning.
+        """
+        path_characters = '/\\'
+        extensions = ['.html', '.htm', '.xml', '.xhtml', '.txt']
+        if isinstance(markup, bytes):
+            path_characters = path_characters.encode("utf8")
+            extensions = [x.encode('utf8') for x in extensions]
+        filelike = False
+        if any(x in markup for x in path_characters):
+            filelike = True
+        else:
+            lower = markup.lower()
+            if any(lower.endswith(ext) for ext in extensions):
+                filelike = True
+        if filelike:
+            warnings.warn(
+                'The input looks more like a filename than markup. You may'
+                ' want to open this file and pass the filehandle into'
+                ' Beautiful Soup.',
+                MarkupResemblesLocatorWarning, stacklevel=3
+            )
+            return True
+        return False
+
     def _feed(self):
         """Internal method that parses previously set markup, creating a large
         number of Tag and NavigableString objects.
@@ -485,7 +503,7 @@ def string_container(self, base_class=None):
 
         # On top of that, we may be inside a tag that needs a special
         # container class.
-        if self.string_container_stack:
+        if self.string_container_stack and container is NavigableString:
             container = self.builder.string_containers.get(
                 self.string_container_stack[-1].name, container
             )
@@ -541,9 +559,7 @@ def pushTag(self, tag):
     def endData(self, containerClass=None):
         """Method called by the TreeBuilder when the end of a data segment
         occurs.
-        """
-        containerClass = self.string_container(containerClass)
-
+        """       
         if self.current_data:
             current_data = ''.join(self.current_data)
             # If whitespace is not preserved, and this string contains
@@ -570,6 +586,7 @@ def endData(self, containerClass=None):
                     not self.parse_only.search(current_data)):
                 return
 
+            containerClass = self.string_container(containerClass)
             o = containerClass(current_data)
             self.object_was_parsed(o)
 
@@ -676,7 +693,7 @@ def _popToTag(self, name, nsprefix=None, inclusivePop=True):
         return most_recently_popped
 
     def handle_starttag(self, name, namespace, nsprefix, attrs, sourceline=None,
-                        sourcepos=None):
+                        sourcepos=None, namespaces=None):
         """Called by the tree builder when a new tag is encountered.
 
         :param name: Name of the tag.
@@ -686,6 +703,8 @@ def handle_starttag(self, name, namespace, nsprefix, attrs, sourceline=None,
             source document.
         :param sourcepos: The character position within `sourceline` where this
             tag was found.
+        :param namespaces: A dictionary of all namespace prefix mappings 
+            currently in scope in the document.
 
         If this method returns None, the tag was rejected by an active
         SoupStrainer. You should proceed as if the tag had not occurred
@@ -703,7 +722,8 @@ def handle_starttag(self, name, namespace, nsprefix, attrs, sourceline=None,
         tag = self.element_classes.get(Tag, Tag)(
             self, self.builder, name, namespace, nsprefix, attrs,
             self.currentTag, self._most_recent_element,
-            sourceline=sourceline, sourcepos=sourcepos
+            sourceline=sourceline, sourcepos=sourcepos,
+            namespaces=namespaces
         )
         if tag is None:
             return tag
@@ -722,7 +742,7 @@ def handle_endtag(self, name, nsprefix=None):
         #print("End tag: " + name)
         self.endData()
         self._popToTag(name, nsprefix)
-
+        
     def handle_data(self, data):
         """Called by the tree builder when a chunk of textual data is encountered."""
         self.current_data.append(data)
@@ -769,7 +789,9 @@ def __init__(self, *args, **kwargs):
         kwargs['features'] = 'xml'
         warnings.warn(
             'The BeautifulStoneSoup class is deprecated. Instead of using '
-            'it, pass features="xml" into the BeautifulSoup constructor.')
+            'it, pass features="xml" into the BeautifulSoup constructor.',
+            DeprecationWarning, stacklevel=2
+        )
         super(BeautifulStoneSoup, self).__init__(*args, **kwargs)