import json,re
d=json.load(open('/data/www/files/ggzy_raw.json'))
recs=d["records"]
cand=[v for v in recs.values() if v["cat"] in ("002002001","002002003")]
cand.sort(key=lambda x:(x["cat"],x["date"]),reverse=True)

sel=[0,21,22,40,56,57,60,64,72,82,83,110,128,129,139,143,144,145,149,158,136,137,117,148,153,59,65,30,69,152,161,51,146,154,13,96,31,118,125,126,122,123,124,152,155,162,163,164,165,166,157,159,160,155]
sel=sorted(set(sel))
for i in sel[:20]:
    v=cand[i]
    c=v["content"]
    print("="*100)
    print(i,v["cat"],v["date"],v["title"])
    print("URL:",v["url"])
    print("CONTENT:",re.sub(r'\s+',' ',c)[:900])