import sys, os
from html.parser import HTMLParser

CACHE = r"D:\code\crm-需求梳理\lanhu-mcp\data\axure_extract_bade4454"

class T(HTMLParser):
    def __init__(self):
        super().__init__(); self.out=[]; self.skip=0
    def handle_starttag(self,t,a):
        if t in ('script','style'): self.skip+=1
    def handle_endtag(self,t):
        if t in ('script','style') and self.skip>0: self.skip-=1
    def handle_data(self,d):
        if self.skip: return
        d=d.strip()
        if d: self.out.append(d)

def extract(fn):
    p=T()
    with open(os.path.join(CACHE,fn),encoding='utf-8',errors='replace') as f:
        p.feed(f.read())
    lines=[l for l in ('\n'.join(p.out)).splitlines() if l.strip()]
    # dedupe consecutive
    res=[]
    for l in lines:
        if not res or res[-1]!=l:
            res.append(l)
    return res

if __name__=='__main__':
    files=sys.argv[1:]
    for fn in files:
        lines=extract(fn)
        out=os.path.join(r"D:\code\crm-backend-matt\.scratch\lanhu-text", fn.replace('.html','.txt'))
        os.makedirs(os.path.dirname(out),exist_ok=True)
        with open(out,'w',encoding='utf-8') as f:
            f.write('\n'.join(lines))
        print(f"{fn}: {len(lines)} lines -> {out}")