我们可以遍历URL,将它们扔到列表中,然后将它们写到文件中:
from xml.etree import ElementTree as ET
tree = ET.parse('test.xml')
root = tree.getroot()
name_space = '{http://www.sitemaps.org/schemas/sitemap/0.9}'
urls = []
for child in root.iter():
for block in child.findall('{}url'.format(name_space)):
for url in block.findall('{}loc'.format(name_space)):
urls.append('{}\n'.format(url.text))
with open('sample_urls.txt', 'w+') as f:
f.writelines(urls)