def test_multipleRoot(self):
parser = AdvancedHTMLParser()
root1 = AdvancedTag('div')
root1.setAttribute('id', 'div1')
root2 = AdvancedTag('div')
root2.setAttribute('id', 'div2')
parser.parseStr(root1.outerHTML + root2.outerHTML)
assert len(
parser.getRootNodes()) == 2, 'Expected two root nodes on tree'
foundRoot1 = parser.getElementById('div1')
assert foundRoot1, 'Expected to find id=div1 in multi-root tree'
foundRoot2 = parser.getElementById('div2')
assert foundRoot2, 'Expected to find id=div1 in multi-root tree'
combinedHTML = (foundRoot1.outerHTML + foundRoot2.outerHTML).replace(
'\n', '').strip()
parsedHTML = parser.getHTML().replace('\n', '').strip()
assert combinedHTML == parsedHTML, 'Expected single element outerHTMLs to match parser HTML. """\n%s\n""" != """\n%s\n"""' % (
combinedHTML, parsedHTML)
def test_multipleRootsWithExternalTextSameReturn(self):
html = """<span>Hello</span>Outside<span>World</span>End"""
parser = AdvancedHTMLParser()
parser.parseStr(html)
strippedHTML = parser.getHTML().replace('\n', '').replace(' ','')
assert strippedHTML == html, "Expected multiple root nodes with text between the nodes to retain, '%s' == '%s'" %(html, strippedHTML)
def test_multipleRootsSameReturn(self):
html = """<span>Hello</span><span>World</span>"""
parser = AdvancedHTMLParser()
parser.parseStr(html)
strippedHTML = parser.getHTML().replace('\n', '').replace(' ','')
assert strippedHTML == html , "Expected multiple root nodes to retain, '%s' == '%s'" %(html, strippedHTML)
def test_multipleRootsWithExternalTextSameReturn(self):
html = """<span>Hello</span>Outside<span>World</span>End"""
parser = AdvancedHTMLParser()
parser.parseStr(html)
strippedHTML = parser.getHTML().replace('\n', '').replace(' ', '')
assert strippedHTML == html, "Expected multiple root nodes with text between the nodes to retain, '%s' == '%s'" % (
html, strippedHTML)
def test_multipleRootsSameReturn(self):
html = """<span>Hello</span><span>World</span>"""
parser = AdvancedHTMLParser()
parser.parseStr(html)
strippedHTML = parser.getHTML().replace('\n', '').replace(' ', '')
assert strippedHTML == html, "Expected multiple root nodes to retain, '%s' == '%s'" % (
html, strippedHTML)
def test_refTag(self):
html = """<html><body><p>This is <html></p></body></html>"""
parser = AdvancedHTMLParser()
parser.parseStr(html)
html = parser.getHTML().replace('\n', '').replace('html ', 'html')
assert 'This is <html>' not in html, 'Expected to retain < and >, got %s' %(html,)
assert 'This is <html>' in html, 'Expected to retain < and >, got %s' %(html,)
def test_untaggedText(self):
html = """ <span class="WebRupee">Rs.</span>\n29\n<br/><font style="font-size:smaller;font-weight:normal">\n3 days\n</font></td>, <td class="pricecell"><span class="WebRupee">Rs.</span>\n59\n<br/><font style="font-size:smaller;font-weight:normal">\n7 days\n</font></td>, <td class="pricecell"><span class="WebRupee">Rs.</span>\n99\n<br/><font style="font-size:smaller;font-weight:normal">\n12 days\n</font></td>"""
parser = AdvancedHTMLParser()
parser.parseStr(html)
html = parser.getHTML()
assert '\n29\n' in html , 'Expected to find item outside tags: \\n29\\n in ' + str(html)
def test_untaggedText(self):
html = """ <span class="WebRupee">Rs.</span>\n29\n<br/><font style="font-size:smaller;font-weight:normal">\n3 days\n</font></td>, <td class="pricecell"><span class="WebRupee">Rs.</span>\n59\n<br/><font style="font-size:smaller;font-weight:normal">\n7 days\n</font></td>, <td class="pricecell"><span class="WebRupee">Rs.</span>\n99\n<br/><font style="font-size:smaller;font-weight:normal">\n12 days\n</font></td>"""
parser = AdvancedHTMLParser()
parser.parseStr(html)
html = parser.getHTML()
assert '\n29\n' in html, 'Expected to find item outside tags: \\n29\\n in ' + str(
html)
def test_commentRetainedPriorRoot(self):
html = """<!-- CommentX --><html>
<body><span>Hello</span></body></html>"""
parser = AdvancedHTMLParser()
parser.parseStr(html)
retHTML = parser.getHTML()
assert 'CommentX' in retHTML, 'Expected to find comment, "CommentX" in returned HTML: "%s"' %(retHTML,)
def test_textPriorToRoot(self):
html = """Hello<html><span id="one">Cheese</span><div>Goodbye</div></html>"""
parser = AdvancedHTMLParser()
parser.parseStr(html)
strippedHTML = parser.getHTML().replace('\n', '')
# print ( strippedHTML )
assert strippedHTML.startswith('Hello') , 'Expected text before root tag to be retained, got "%s"' %(strippedHTML,)
def test_commentRetainedAfterRoot(self):
html = """<html>
<body><span>Hello</span></body></html><!-- CommentX -->"""
parser = AdvancedHTMLParser()
parser.parseStr(html)
retHTML = parser.getHTML()
assert 'CommentX' in retHTML, 'Expected to find comment, "CommentX" in returned HTML: "%s"' % (
retHTML, )
def test_refTag(self):
html = """<html><body><p>This is <html></p></body></html>"""
parser = AdvancedHTMLParser()
parser.parseStr(html)
html = parser.getHTML().replace('\n', '').replace('html ', 'html')
assert 'This is <html>' not in html, 'Expected to retain < and >, got %s' % (
html, )
assert 'This is <html>' in html, 'Expected to retain < and >, got %s' % (
html, )
def test_retainOriginalWhitespace(self):
'''
test_retainOriginalWhitespace - Test that we retain the original whitespacing
'''
parser = AdvancedHTMLParser()
parser.parseStr(TEST_HTML)
rawHtml = parser.getHTML()
# This will not equal the original HTML exactly because we fixup some tag issues, like ' >'
assert rawHtml == '<html ><head ><title >Hello World</title></head>\n <body >\n <div >Hello world <span >And welcome to the show.</span>\n </div>\n </body></html>' , 'Did not retain original whitespace like expected'
def test_retainOriginalWhitespace(self):
'''
test_retainOriginalWhitespace - Test that we retain the original whitespacing
'''
parser = AdvancedHTMLParser()
parser.parseStr(TEST_HTML)
rawHtml = parser.getHTML()
# This will not equal the original HTML exactly because we fixup some tag issues, like ' >'
assert rawHtml == '<html ><head ><title >Hello World</title></head>\n <body >\n <div >Hello world <span >And welcome to the show.</span>\n </div>\n </body></html>', 'Did not retain original whitespace like expected'
def test_nbsp(self):
html = """<html><body><p>Test One</p></body></html>"""
parser = AdvancedHTMLParser()
parser.parseStr(html)
html = parser.getHTML().replace('\n', '').replace('html ', 'html')
assert ' ' in html, '(Will fail in python2..) Expected to retain got %s' %(html,)
html = """<html><body><p>Test One</p></body></html>"""
parser = AdvancedHTMLParser()
parser.parseStr(html)
html = parser.getHTML().replace('\n', '').replace('html ', 'html')
assert ' ' not in html, '(Will fail in python2..) Expected not to insert got %s' %(html,)
html = """<html><body><p>Test One</p></body></html>"""
parser = AdvancedHTMLParser()
parser.parseStr(html)
html = parser.getHTML().replace('\n', '').replace('html ', 'html')
assert 'Test One' in html, '(Will fail in python2..) Expected to retain original data with two got %s' %(html,)
def test_textPriorToRoot(self):
html = """Hello<html><span id="one">Cheese</span><div>Goodbye</div></html>"""
parser = AdvancedHTMLParser()
parser.parseStr(html)
strippedHTML = parser.getHTML().replace('\n', '')
# print ( strippedHTML )
assert strippedHTML.startswith(
'Hello'
), 'Expected text before root tag to be retained, got "%s"' % (
strippedHTML, )
def test_nbsp(self):
html = """<html><body><p>Test One</p></body></html>"""
parser = AdvancedHTMLParser()
parser.parseStr(html)
html = parser.getHTML().replace('\n', '').replace('html ', 'html')
assert ' ' in html, '(Will fail in python2..) Expected to retain got %s' % (
html, )
html = """<html><body><p>Test One</p></body></html>"""
parser = AdvancedHTMLParser()
parser.parseStr(html)
html = parser.getHTML().replace('\n', '').replace('html ', 'html')
assert ' ' not in html, '(Will fail in python2..) Expected not to insert got %s' % (
html, )
html = """<html><body><p>Test One</p></body></html>"""
parser = AdvancedHTMLParser()
parser.parseStr(html)
html = parser.getHTML().replace('\n', '').replace('html ', 'html')
assert 'Test One' in html, '(Will fail in python2..) Expected to retain original data with two got %s' % (
html, )
def test_multipleRoot(self):
parser = AdvancedHTMLParser()
root1 = AdvancedTag('div')
root1.setAttribute('id', 'div1')
root2 = AdvancedTag('div')
root2.setAttribute('id', 'div2')
parser.parseStr(root1.outerHTML + root2.outerHTML)
assert len(parser.getRootNodes()) == 2, 'Expected two root nodes on tree'
foundRoot1 = parser.getElementById('div1')
assert foundRoot1, 'Expected to find id=div1 in multi-root tree'
foundRoot2 = parser.getElementById('div2')
assert foundRoot2, 'Expected to find id=div1 in multi-root tree'
combinedHTML = (foundRoot1.outerHTML + foundRoot2.outerHTML).replace('\n', '').strip()
parsedHTML = parser.getHTML().replace('\n', '').strip()
assert combinedHTML == parsedHTML, 'Expected single element outerHTMLs to match parser HTML. """\n%s\n""" != """\n%s\n"""' %(combinedHTML, parsedHTML)
