Add 'body' and 'head' properties on document

kata198 · kata198 · commit b488388b3fdf · 2017-05-21T02:51:53.000-04:00
diff --git a/README.md b/README.md
@@ -38,11 +38,14 @@ Short Doc
 ---------
 
 
-The AdvancedHTMLParser can read in a file (or string) of HTML, and will create a modifiable DOM tree from it. It can also be constructed manually from AdvancedHTMLParser.AdvancedTag objects.
+**AdvancedHTMLParser**
 
 Think of this like "document" in a browser.
 
 
+The AdvancedHTMLParser can read in a file (or string) of HTML, and will create a modifiable DOM tree from it. It can also be constructed manually from AdvancedHTMLParser.AdvancedTag objects.
+
+
 To populate an AdvancedHTMLParser from existing HTML:
 
 	parser = AdvancedHTMLParser.AdvancedHTMLParser()
@@ -83,6 +86,14 @@ The parser then exposes many "standard" functions as you'd find on the web for a
 The results of all of these getElement\* functions are TagCollection objects. These objects can be modified, and will be reflected in the parent DOM.
 
 
+The parser also contains some expected properties, like
+
+
+	head                    - The "head" tag associated with this document, or None
+
+	body                    - The "body" tag associated with this document, or None
+
+
 **General Attributes**
 
 In general, attributes can be accessed with dot-syntax, i.e.
diff --git a/README.rst b/README.rst
@@ -35,10 +35,14 @@ Various examples can be found in the "tests" directory.
 Short Doc
 ---------
 
-The AdvancedHTMLParser can read in a file (or string) of HTML, and will create a modifiable DOM tree from it. It can also be constructed manually from AdvancedHTMLParser.AdvancedTag objects.
+
+**AdvancedHTMLParser**
+
 
 Think of this like "document" in a browser.
 
+The AdvancedHTMLParser can read in a file (or string) of HTML, and will create a modifiable DOM tree from it. It can also be constructed manually from AdvancedHTMLParser.AdvancedTag objects.
+
 
 To populate an AdvancedHTMLParser from existing HTML:
 
@@ -84,6 +88,14 @@ The parser then exposes many "standard" functions as you'd find on the web for a
 The results of all of these getElement\* functions are TagCollection objects. These objects can be modified, and will be reflected in the parent DOM.
 
 
+The parser also contains some expected properties, like
+
+
+	head                    - The "head" tag associated with this document, or None
+
+	body                    - The "body" tag associated with this document, or None
+
+
 **General Attributes**
 
 In general, attributes can be accessed with dot-syntax, i.e.
diff --git a/tests/AdvancedHTMLParserTests/test_General.py b/tests/AdvancedHTMLParserTests/test_General.py
@@ -187,6 +187,21 @@ def test_getBody(self):
         assert bodyEm , 'Expected ".body" property to fetch an element'
         assert bodyEm.tagName == 'body' , 'Got wrong body element'
 
+        parser = AdvancedHTMLParser.AdvancedHTMLParser()
+        parser.parseStr('<div id="hello"> <span> One </span> </div>')
+        
+        bodyEm = parser.body
+        
+        assert not bodyEm , 'Expected to find no "body" when no <body> tag is present.'
+        
+        parser = AdvancedHTMLParser.AdvancedHTMLParser()
+        parser.parseStr('<div id="hello"> <span> One </span> </div> <div id="other">Cheese</div>')
+
+        bodyEm = parser.body
+
+        assert not bodyEm , 'Expected to find no "body" when no <body> tag is present.'
+
+
     def test_getHead(self):
         parser = AdvancedHTMLParser.AdvancedHTMLParser()
         parser.parseStr(self.testHTML)
@@ -196,6 +211,19 @@ def test_getHead(self):
         assert headEm , 'Expected ".head" property to fetch an element'
         assert headEm.tagName == 'head' , 'Got wrong head element'
 
+        parser = AdvancedHTMLParser.AdvancedHTMLParser()
+        parser.parseStr('<div id="hello"> <span> One </span> </div>')
+        
+        headEm = parser.head
+        
+        assert not headEm , 'Expected to find no "head" when no <head> tag is present.'
+        
+        parser = AdvancedHTMLParser.AdvancedHTMLParser()
+        parser.parseStr('<div id="hello"> <span> One </span> </div> <div id="other">Cheese</div>')
+
+        headEm = parser.head
+
+        assert not headEm , 'Expected to find no "head" when no <head> tag is present.'
 
 if __name__ == '__main__':
     subprocess.Popen('GoodTests.py "%s"' %(sys.argv[0],), shell=True).wait()
