kangshifu-board/scripts/collect-five-topic-experiences-20261111.py

"""Focused discovery for actual dormitory, late-night and flavor experiences."""
from concurrent.futures import ThreadPoolExecutor, as_completed
import importlib.util
import json
from pathlib import Path

ROOT=Path(__file__).resolve().parents[1]
spec=importlib.util.spec_from_file_location('su',ROOT/'scripts/collect-five-topic-supplement.py')
m=importlib.util.module_from_spec(spec);spec.loader.exec_module(m)
WORK=ROOT/'work/five-topic-research-20261111'
m.WORK=WORK;m.PUBLIC=WORK/'sources';m.SEARCH=WORK/'search';m.base.PUBLIC=m.PUBLIC
JOBS=[('student','宿舍 泡面 体验 site:post.smzdm.com'),
      ('student','夜宵 拌面 试吃 site:post.smzdm.com'),
      ('novelty','冬阴功 方便面 试吃 site:post.smzdm.com'),
      ('novelty','香菜 拌面 试吃 site:post.smzdm.com')]

def main():
 state={'status':'running','sources':[],'rejected':[]};candidates=[]
 for i,(topic,q) in enumerate(JOBS,110):
  try:candidates.extend(m.search(i,topic,q))
  except Exception as e:
   state['rejected'].append({'query':q,'reason':str(e)})
   if 'VERIFICATION' in str(e):break
 with ThreadPoolExecutor(max_workers=2) as pool:
  tasks={pool.submit(m.collect,r):r for r in candidates}
  for f in as_completed(tasks):
   try:
    r=f.result();r['collectionDirectory']='sources';state['sources'].append(r)
   except Exception as e:state['rejected'].append({'url':tasks[f]['url'],'reason':str(e)})
   m.base.save(WORK/'experience-collection-result.json',state)
   print(json.dumps({'readable':len(state['sources']),'rejected':len(state['rejected'])}),flush=True)
 state.update(status='awaiting-semantic-review',candidates=len(candidates));m.base.save(WORK/'experience-collection-result.json',state)

if __name__=='__main__':main()