0
這可能是一件非常簡單的事情,但我一直在失敗。使用lxml/XPath獲得第n個元素失敗
當root
包含一個或多個「<鏈接/ >」時,root.xpath('(// link)')將它們全部返回。但root.xpath('(// link)[0]')返回一個空列表。哪裏不對?
from unittest import TestCase, TestProgram
class T(TestCase):
base_path = r'(//_:link)'
def test0ok(self):
self._test(2, self.base_path)
def test1ng(self):
self._test(1, self.base_path + r'[0]')
def _test(self, expected, path):
try:
from lxml.etree import fromstring as parse_xml_string
except ImportError:
raise
root = parse_xml_string(_xhtml)
nsmap = dict(_=root.nsmap[None])
gotten = root.xpath(path, namespaces=nsmap)
gotten = len(gotten)
self.assertEqual(expected, gotten)
_xhtml = br'''
<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE html PUBLIC
"-//W3C//DTD XHTML 1.1//EN"
"http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd"
>
<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en">
<head>
<link rev="made" href="./" />
<link rel="contents" href="./" />
<title>te</title>
</head>
<body>
<h1>st</h1>
</body>
</html>
'''[1:]
if __name__ == r'__main__':
TestProgram()