def html():
html_parser = HTMLParser()
html_parser.parse(r'files/Test2.html')
print('html parser', html_parser.get_processed_stems(),
len(html_parser.get_processed_stems()))
print('html parser link result', html_parser.get_links(),
len(html_parser.get_links()))
def test_parseHTMLParser(self):
html = HTMLParser()
html.parse('files/Test.html')
text = [
'page', 'margin', '2cm', 'p', 'margin', '0', '25cm', 'direct',
'ltr', 'color', '00000a', 'line', 'height', '115', 'text', 'align',
'left', 'orphan', '2', 'widow', '2', 'p', 'western', 'font',
'famili', 'liber', 'serif', 'serif', 'font', 'size', '12pt',
'languag', 'ru', 'ru', 'p', 'cjk', 'font', 'famili', 'noto', 'san',
'cjk', 'sc', 'regular', 'font', 'size', '12pt', 'languag', 'zh',
'cn', 'p', 'ctl', 'font', 'famili', 'lohit', 'devanagari', 'font',
'size', '12pt', 'languag', 'hi', 'in', 'link', 'languag', 'zxx',
'i', 'test', 'poop', 'test', 'anim', 'test', 'anim', 'googl',
'link'
]
assert html.get_processed_stems() == text
def html_test():
html_parser = HTMLParser()
html_parser.parse(r'D:\Test2.html')
print(html_parser.get_processed_stems())
print(html_parser.get_links())
def test_get_linksHTMLParser(self):
html = HTMLParser()
html.parse('files/Test.html')
text = [('google\nlink', 'http://google.com/'),
('google\nlink', 'http://google.com/')]
assert html.get_links() == text
def html(link):
html_parser = HTMLParser()
html_parser.parse(link)
word_list = html_parser.get_processed_stems()
return word_list