GooglePoiCrawler/utility/json_preprocess.py

import codecs
import re
import json
fw=codecs.open('c:/tmp/result.json','w','utf-8')

content=""
fr=codecs.open('c:/tmp/ot.json','r','utf-8')
lines=fr.readlines()



for l in lines:
    newl=l.replace('\\"','"')
    content+=newl
result=re.search(r'\[\["',content)
content_begin=result.start()

result=re.search(r'\]\]"',content)
content_end=result.end()


#print(result.span(1))
#print(result.span(2))

#for r in result:
#   print(r)
#r=result[0]
#print(r)
#print(result)
fw.write(content[content_begin:content_end-1])
fw.close()

jscontent=content[content_begin:content_end-1]
jsobj=json.loads(jscontent)
print()
for x in jsobj[0][1][1:]:
#    print(x[14][0])
    print(x[14][11])
    print(x[14][10])
    print(x[14][2])
    print(x[14][78])

#    cnt=0
#    for xx in x[14]:
#        cnt+=1
#        if 'ChIJ' in str(xx):
#            print(xx)
#            print(cnt)

#    print(x[14][9])
#    try:
#        print(x[14][4][3])
#    except:
#        print(x[14][4])