Upgrade BeautifulSoup to v4.13

pyproject.toml

@@ -38,7 +38,7 @@ classifiers = [
 ]
 dependencies = [
     "appdirs==1.4.4",
-    "beautifulsoup4==4.12.3",
+    "beautifulsoup4==4.13.3",
     "charset-normalizer==3.4.1",
     "cssutils==2.11.1",
     "dhash==1.4",

thug/DOM/DFT.py

@@ -1574,7 +1574,7 @@ def check_small_element(self, element, tagname):
 
             try:
                 value = int(attrs[key].split("px")[0])
-            except Exception:  # pylint:disable=broad-except
+            except Exception:  # pragma: no cover,pylint:disable=broad-except
                 value = None
 
             if not value:

thug/DOM/W3C/Core/Document.py

@@ -224,7 +224,7 @@ def getElementsByTagName(self, tagname):
         from .NodeList import NodeList
 
         if tagname in ("*",):
-            return NodeList(self.doc, self.doc.find_all(string=False))
+            return NodeList(self.doc, self.doc.find_all())
 
         return NodeList(self.doc, self.doc.find_all(tagname.lower()))
 

thug/DOM/W3C/Core/Node.py

@@ -114,7 +114,7 @@ def setNodeValue(self, value):  # pragma: no cover
     nodeValue = property(getNodeValue, setNodeValue)
 
     def getTextContent(self):
-        return self.tag.string
+        return str(self.tag.string)
 
     def setTextContent(self, value):
         self.tag.string = str(value)
@@ -429,7 +429,7 @@ def normalize(self):
                 index += 1
                 continue
 
-            child.tag.string = child.innerText + sibling.innerText
+            child.tag.string.replace_with(child.innerText + sibling.innerText)
             self.removeChild(sibling)
 
     # Introduced in DOM Level 2

thug/DOM/W3C/HTML/HTMLBodyElement.py

@@ -31,7 +31,7 @@ def getInnerHTML(self):
         for tag in self.tag.contents:
             try:
                 html.write(str(tag))
-            except Exception as e:  # pylint:disable=broad-except
+            except Exception as e:  # pragma: no cover,pylint:disable=broad-except
                 log.warning("[HTMLBodyElement] innerHTML warning: %s", str(e))
 
         return html.getvalue()

thug/DOM/W3C/HTML/HTMLDocument.py

@@ -481,7 +481,7 @@ def getElementsByName(self, elementName):
     def _all(self):
         from .HTMLAllCollection import HTMLAllCollection
 
-        s = list(self.doc.find_all(string=False))
+        s = list(self.doc.find_all())
         return HTMLAllCollection(self.doc, s)
 
     @property