def test_get_href_from_tags(self):
tag_filter = {
'name': 'div',
'attrs': {
'id': 'href_test'
}
}
links = htmlparser.get_href_from_tags(open('test/test.html').read(), tag_filter)
self.assertTrue(links == ['test1.com', 'test2.com'])
def apply_filter(html_string, filter):
if 'type' in filter and filter['type'] == 'a_href':
content = htmlparser.get_href_from_tags(html_string, {'name': filter['tag'],
'attrs': {filter['attribute']: filter['value']}})[0]
elif 'type' in filter and filter['type'] == 'text':
content = htmlparser.get_formatted_text_from_tags(html_string, {'name': filter['tag'],
'attrs': {
filter['attribute']: filter['value']}})[0]
elif 'type' in filter and filter['type'] == 'list':
content = htmlparser.get_content_list_from_tags(html_string, {'name': filter['tag'],
'attrs': {
filter['attribute']: filter['value']}})[0]
elif 'type' in filter:
content = htmlparser.get_attr_from_tags(html_string, {'name': filter['tag'],
'attrs': {filter['attribute']: filter['value']},
'type': filter['type']})[0]
else:
content = htmlparser.get_content_from_tags(html_string, {'name': filter['tag'],
'attrs': {filter['attribute']: filter['value']}})[0]
return content
