Files
digital-psychology/scrape_batch2.py
T

71 lines
3.3 KiB
Python

import json, subprocess, os
BASE='https://minke8.cn'
scales=[
("jlz","贝克焦虑测试量表(BAI)","焦虑症测试"),
("jl2","汉密尔顿焦虑量表(HAMA)","焦虑症测试"),
("jl3","状态-特质焦虑问卷(STAI)","焦虑症测试"),
("jl5","焦虑症筛查量表(GAD-7)","焦虑症测试"),
("jl6","考试焦虑量表(TAS)","焦虑症测试"),
("jl8","中学生焦虑自评量表","焦虑症测试"),
("qp1","耶鲁布朗强迫标准量表(YBOCS)","强迫症测试"),
("qp3","强迫信念问卷(OBQ-44)","强迫症测试"),
("qp4","强迫量表修订版(OCI-R)","强迫症测试"),
("zk1","贝克-拉范森躁狂量表(BRMS)","躁狂症测试"),
("zk2","轻躁狂自评量表(HCL-32)","躁狂症测试"),
("zk3","杨氏躁狂评定量表(YMRS)","躁狂症测试"),
("sx1","心境障碍问卷(MDQ)","双向情感障碍"),
("sx2","双相情感障碍自评量表(BSQ)","双向情感障碍"),
("sk3","交往焦虑量表(IAS)","恐惧症测试"),
("sk4","社交回避及苦恼量表(SAD)","恐惧症测试"),
("sk5","社交焦虑量表(SIAS)","恐惧症测试"),
("sk6","社交恐惧量表(SPS)","恐惧症测试"),
("iq2","瑞文智商测试(60题)","智商测试"),
("iq3","智力测试(增强版)","智商测试"),
("eq1","情商测试量表(BARON)","情商测试"),
("eq2","情绪智力量表(EIS)","情商测试"),
("sm2","匹兹堡睡眠质量指数(PSQI)","其它测试"),
("sm1","阿森斯失眠量表(AIS)","其它测试"),
("qt1","躯体化症状自评量表(SSS)","其它测试"),
("gd6","创伤后应激障碍量表(PCL-C)","其它测试"),
("xl13","防御方式自评量表(DSQ)","其它测试"),
("gd4","家庭环境量表(FES)","其它测试"),
("gd1","婚姻质量问卷(ENRICH)","其它测试"),
("gd2","爱情态度测试(LAS)","其它测试"),
("gd3","心理压力测试(PSTR)","其它测试"),
]
results=[]
for idx,(slug,name,cat) in enumerate(scales):
url=f'{BASE}/{slug}.html'
print(f'[{idx+1}/{len(scales)}] {name}', flush=True)
try:
r=subprocess.run(f'curl -sL -X POST {url} -d action=process\&index=0', shell=True, capture_output=True, text=True, timeout=15)
d=json.loads(r.stdout)
qc=d.get('length',0)
if qc==0: print(f' SKIP (0 q)'); continue
except: print(f' FAIL init'); continue
qs=[]; os_=[]
for i in range(qc):
try:
r=subprocess.run(f'curl -sL -X POST {url} -d action=process\&index={i}', shell=True, capture_output=True, text=True, timeout=10)
d=json.loads(r.stdout)
qs.append(d.get('tm',''))
os_.append(d.get('xx',[]))
except: qs.append(''); os_.append([])
if i%30==29: print('.', end='', flush=True)
results.append({'slug':slug,'name':name,'category':cat,'url':url,'description':'','question_count':qc,'questions':qs,'options':os_})
print(f' OK({qc})')
existing=[]
if os.path.exists('scales_data.json'):
with open('scales_data.json') as f: existing=json.load(f)
existing_slugs={s['slug'] for s in existing}
for r in results:
if r['slug'] not in existing_slugs:
existing.append(r)
with open('scales_data.json','w') as f: json.dump(existing, f, ensure_ascii=False, indent=2)
total_q=sum(s['question_count'] for s in existing)
print(f'Saved: {len(existing)} scales, {total_q} questions')