49 lines
1.0 KiB
Python
49 lines
1.0 KiB
Python
import json
|
|
import re
|
|
|
|
all_data = []
|
|
|
|
# 制造新的url
|
|
def makeNewUrl(url):
|
|
url_1 = re.findall('com/(.*)/m',url)
|
|
url_2 = re.findall('/m/(.*)null',url)
|
|
if len(url_1) == 0 or len(url_2) == 0:
|
|
return False
|
|
new_url = "http://r.photo.store.qq.com/"
|
|
new_url += url_1[0]
|
|
new_url += "/r/"
|
|
new_url += url_2[0]
|
|
return new_url
|
|
|
|
# 处理文件
|
|
def manageJson(i):
|
|
map_url = './imgs'+str(i)+'.json'
|
|
row_map_url = './row/rowImgs'+str(i)+'.json'
|
|
fp = open(map_url)
|
|
data_row = json.load(fp)
|
|
fp.close()
|
|
data = []
|
|
for url in data_row:
|
|
if not url:
|
|
continue
|
|
new_url = makeNewUrl(url)
|
|
if not new_url:
|
|
continue
|
|
data.append(new_url)
|
|
fp = open(row_map_url, mode='w')
|
|
fp.write(json.dumps(data))
|
|
fp.close()
|
|
all_data.extend(data)
|
|
print('第%s个文件处理完成'%(i))
|
|
print('第%s个文件有效长度为%s'%(i, len(data)))
|
|
|
|
# 合成全部数据
|
|
def composeAllData():
|
|
fp = open('./row/allData.json', mode='w')
|
|
fp.write(json.dumps(all_data))
|
|
fp.close()
|
|
|
|
for i in range(1,33):
|
|
manageJson(i)
|
|
composeAllData()
|