You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
39 lines
1.2 KiB
39 lines
1.2 KiB
4 weeks ago
|
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}")
|