test_sitemap_view.py 文件源码

def parse_sitemap(content):
    if not isinstance(content, six.text_type):
        content = content.decode('utf-8')
    urlset_match = re.search(
        r'<urlset[^>]*>(?P<urls>[\s\S]*)</urlset>', content
    )
    if urlset_match:
        results = []
        urlset_content = urlset_match.groupdict()['urls']
        for url_content in re.findall(r'<url>([\s\S]+)</url>', urlset_content):
            results.append(
                dict(
                    re.findall(r'<([^>]+)>([^<]*)</[^>]+>', url_content)
                )
            )
    else:
        results = None
    return results