"""Inspect local initial HTML and a saved post-render DOM; executes no JavaScript."""
from html.parser import HTMLParser
import json
class Visible(HTMLParser):
def __init__(self):super().__init__();self.skip=0;self.parts=[]
def handle_starttag(self,tag,attrs):
if tag in ('script','style'):self.skip+=1
def handle_endtag(self,tag):
if tag in ('script','style'):self.skip=max(0,self.skip-1)
def handle_data(self,data):
if not self.skip:self.parts.append(data)
def text(self):return ''.join(self.parts)
html={
'server_rendered':'团队知识库
支持私有部署与按项目权限。
',
'javascript_shell':'正在加载
',
'saved_rendered_dom':''}
rows=[]
for name,body in html.items():
parser=Visible();parser.feed(body);text=parser.text()
rows.append({'fixture':name,'http_status':200,'extracted_text':text,'fact_present':'私有部署' in text})
assert [x['fact_present'] for x in rows]==[True,False,True]
print(json.dumps({'label':'本地教学HTML；非Googlebot或商业AI实测','results':rows},ensure_ascii=False,indent=2))