html5lib · gsnedders · Dec 3, 2015 · Dec 2, 2015
diff --git a/html5lib/filters/optionaltags.py b/html5lib/filters/optionaltags.py
@@ -58,7 +58,7 @@ def is_optional_start(self, tagname, previous, next):
         elif tagname == 'colgroup':
             # A colgroup element's start tag may be omitted if the first thing
             # inside the colgroup element is a col element, and if the element
-            # is not immediately preceeded by another colgroup element whose
+            # is not immediately preceded by another colgroup element whose
             # end tag has been omitted.
             if type in ("StartTag", "EmptyTag"):
                 # XXX: we do not look at the preceding event, so instead we never
@@ -70,7 +70,7 @@ def is_optional_start(self, tagname, previous, next):
         elif tagname == 'tbody':
             # A tbody element's start tag may be omitted if the first thing
             # inside the tbody element is a tr element, and if the element is
-            # not immediately preceeded by a tbody, thead, or tfoot element
+            # not immediately preceded by a tbody, thead, or tfoot element
             # whose end tag has been omitted.
             if type == "StartTag":
                 # omit the thead and tfoot elements' end tag when they are

diff --git a/html5lib/html5parser.py b/html5lib/html5parser.py
@@ -2564,7 +2564,7 @@ def endTagFrameset(self, token):
                 self.tree.openElements.pop()
             if (not self.parser.innerHTML and
                     self.tree.openElements[-1].name != "frameset"):
-                # If we're not in innerHTML mode and the the current node is not a
+                # If we're not in innerHTML mode and the current node is not a
                 # "frameset" element (anymore) then switch.
                 self.parser.phase = self.parser.phases["afterFrameset"]
 

diff --git a/html5lib/inputstream.py b/html5lib/inputstream.py
@@ -469,7 +469,7 @@ def detectEncoding(self, parseMeta=True, chardet=True):
         if encoding is None and parseMeta:
             encoding = self.detectEncodingMeta()
             confidence = "tentative"
-        # Guess with chardet, if avaliable
+        # Guess with chardet, if available
         if encoding is None and chardet:
             confidence = "tentative"
             try:

diff --git a/html5lib/tests/support.py b/html5lib/tests/support.py
@@ -16,10 +16,10 @@
 from html5lib import treebuilders
 del base_path
 
-# Build a dict of avaliable trees
+# Build a dict of available trees
 treeTypes = {"DOM": treebuilders.getTreeBuilder("dom")}
 
-# Try whatever etree implementations are avaliable from a list that are
+# Try whatever etree implementations are available from a list that are
 #"supposed" to work
 try:
     import xml.etree.ElementTree as ElementTree

diff --git a/html5lib/treebuilders/etree_lxml.py b/html5lib/treebuilders/etree_lxml.py
@@ -315,7 +315,7 @@ def insertRoot(self, token):
         """Create the document root"""
         # Because of the way libxml2 works, it doesn't seem to be possible to
         # alter information like the doctype after the tree has been parsed.
-        # Therefore we need to use the built-in parser to create our iniial
+        # Therefore we need to use the built-in parser to create our initial
         # tree, after which we can add elements like normal
         docStr = ""
         if self.doctype:

diff --git a/html5lib/utils.py b/html5lib/utils.py
@@ -64,7 +64,7 @@ def __getitem__(self, key):
         return dict.get(self, key, self.default)
 
 
-# Some utility functions to dal with weirdness around UCS2 vs UCS4
+# Some utility functions to deal with weirdness around UCS2 vs UCS4
 # python builds
 
 def isSurrogatePair(data):

diff --git a/utils/spider.py b/utils/spider.py
@@ -80,7 +80,7 @@ def updateURLs(self, tree):
                 except KeyError:
                     pass
 
-        #Remove all non-http URLs and a dd a sutiable base URL where that is
+        #Remove all non-http URLs and add a suitable base URL where that is
         #missing
         newUrls = set()
         for url in urls: