ExtractorError,
find_xpath_attr,
fix_xml_ampersands,
+ get_element_by_class,
InAdvancePagedList,
intlist_to_bytes,
is_html,
self.assertEqual(urshift(3, 1), 1)
self.assertEqual(urshift(-3, 1), 2147483646)
+ def test_get_element_by_class(self):
+ html = '''
+ <span class="foo bar">nice</span>
+ '''
+
+ self.assertEqual(get_element_by_class('foo', html), 'nice')
+ self.assertEqual(get_element_by_class('no-such-class', html), None)
+
if __name__ == '__main__':
unittest.main()
return get_element_by_attribute('id', id, html)
-def get_element_by_attribute(attribute, value, html):
+def get_element_by_class(class_name, html):
+ return get_element_by_attribute(
+ 'class', r'[^\'"]*\b%s\b[^\'"]*' % re.escape(class_name),
+ html, escape_value=False)
+
+
+def get_element_by_attribute(attribute, value, html, escape_value=True):
"""Return the content of the tag with the specified attribute in the passed HTML document"""
+ value = re.escape(value) if escape_value else value
+
m = re.search(r'''(?xs)
<([a-zA-Z0-9:._-]+)
(?:\s+[a-zA-Z0-9:._-]+(?:=[a-zA-Z0-9:._-]*|="[^"]*"|='[^']*'))*?
\s*>
(?P<content>.*?)
</\1>
- ''' % (re.escape(attribute), re.escape(value)), html)
+ ''' % (re.escape(attribute), value), html)
if not m:
return None