Home       Trees       Indices       Help   
lxml
Package lxml :: Package tests :: Module test_htmlparser
[hide private]
[frames] | no frames]

Source Code for Module lxml.tests.test_htmlparser

  1  # -*- coding: utf-8 -*- 
  2   
  3  """ 
  4  HTML parser test cases for etree 
  5  """ 
  6   
  7  import unittest 
  8  import tempfile, os 
  9   
 10  from common_imports import StringIO, etree, fileInTestDir 
 11  from common_imports import SillyFileLike, HelperTestCase 
 12   

 13 -class HtmlParserTestCase(HelperTestCase): 

 14      """HTML parser test cases 
 15      """ 
 16      etree = etree 
 17   
 18      html_str = "<html><head><title>test</title></head><body><h1>page title</h1></body></html>" 
 19      broken_html_str = "<html><head><title>test<body><h1>page title</h3></p></html>" 
 20      uhtml_str = u"<html><head><title>test á\uF8D2</title></head><body><h1>page á\uF8D2 title</h1></body></html>" 
 21   

 22 -    def tearDown(self): 

 23          self.etree.setDefaultParser() 
 24          super(HtmlParserTestCase, self).tearDown() 

 25   

 26 -    def test_module_HTML(self): 

 27          element = self.etree.HTML(self.html_str) 
 28          self.assertEqual(self.etree.tostring(element), 
 29                           self.html_str) 

 30   

 31 -    def test_module_HTML_unicode(self): 

 32          element = self.etree.HTML(self.uhtml_str) 
 33          self.assertEqual(unicode(self.etree.tostring(element, 'UTF8'), 'UTF8'), 
 34                           unicode(self.uhtml_str.encode('UTF8'), 'UTF8')) 

 35   

 37          parser = self.etree.HTMLParser(recover=False) 
 38          parse = self.etree.parse 
 39          f = StringIO("<html></body>") 
 40          self.assertRaises(self.etree.XMLSyntaxError, 
 41                            parse, f, parser) 

 42   

 44          parser = self.etree.HTMLParser(recover=False) 
 45          parse = self.etree.parse 
 46          f = StringIO(self.broken_html_str) 
 47          self.assertRaises(self.etree.XMLSyntaxError, 
 48                            parse, f, parser) 

 49   

 50 -    def test_module_HTML_broken(self): 

 51          element = self.etree.HTML(self.broken_html_str) 
 52          self.assertEqual(self.etree.tostring(element), 
 53                           self.html_str) 

 54   

 55 -    def test_module_HTML_cdata(self): 

 56          # by default, libxml2 generates CDATA nodes for <script> content 
 57          html = '<html><head><style>foo</style></head></html>' 
 58          element = self.etree.HTML(html) 
 59          self.assertEquals(element[0][0].text, "foo") 

 60   

 61 -    def test_module_HTML_access(self): 

 62          element = self.etree.HTML(self.html_str) 
 63          self.assertEqual(element[0][0].tag, 'title') 

 64   

 65 -    def test_module_parse_html(self): 

 66          parser = self.etree.HTMLParser() 
 67          filename = tempfile.mktemp(suffix=".html") 
 68          open(filename, 'wb').write(self.html_str) 
 69          try: 
 70              f = open(filename, 'r') 
 71              tree = self.etree.parse(f, parser) 
 72              f.close() 
 73              self.assertEqual(self.etree.tostring(tree.getroot()), self.html_str) 
 74          finally: 
 75              os.remove(filename) 

 76   

 78          parser = self.etree.HTMLParser() 
 79          f = SillyFileLike(self.html_str) 
 80          tree = self.etree.parse(f, parser) 
 81          html = self.etree.tostring(tree.getroot(), 'UTF-8') 
 82          self.assertEqual(html, self.html_str) 

 83   
 84  ##     def test_module_parse_html_filelike_unicode(self): 
 85  ##         parser = self.etree.HTMLParser() 
 86  ##         f = SillyFileLike(self.uhtml_str) 
 87  ##         tree = self.etree.parse(f, parser) 
 88  ##         html = self.etree.tostring(tree.getroot(), 'UTF-8') 
 89  ##         self.assertEqual(unicode(html, 'UTF-8'), self.uhtml_str) 
 90   

 91 -    def test_html_file_error(self): 

 92          parser = self.etree.HTMLParser() 
 93          parse = self.etree.parse 
 94          self.assertRaises(IOError, 
 95                            parse, "__some_hopefully_nonexisting_file__.html", 
 96                            parser) 

 97   

 99          self.assertRaises(self.etree.XMLSyntaxError, 
100                            self.etree.parse, StringIO(self.broken_html_str)) 
101   
102          self.etree.setDefaultParser( self.etree.HTMLParser() ) 
103   
104          tree = self.etree.parse(StringIO(self.broken_html_str)) 
105          self.assertEqual(self.etree.tostring(tree.getroot()), 
106                           self.html_str) 
107   
108          self.etree.setDefaultParser() 
109   
110          self.assertRaises(self.etree.XMLSyntaxError, 
111                            self.etree.parse, StringIO(self.broken_html_str)) 

112   

113 -def test_suite(): 

114      suite = unittest.TestSuite() 
115      suite.addTests([unittest.makeSuite(HtmlParserTestCase)]) 
116      return suite 

117   
118  if __name__ == '__main__': 
119      unittest.main() 
120

   Home       Trees       Indices       Help   
lxml
Generated by Epydoc 3.0 on Mon Feb 11 15:49:35 2008 http://epydoc.sourceforge.net