img_crawler/cache1.py
2020-12-02 22:31:54 +08:00

34 lines
723 B
Python

import urllib.request
import re
import os
import urllib
import json
def createFileFolder(i):
# 获取当前绝对地址
path = os.path.abspath('.')
# 拼接新地址
path = os.path.join(path,str(i))
# 创建文件夹
os.mkdir(path)
return path
def getImg(index):
# 读取json文件
fp = open('./allData.json')
data = json.load(fp)
folder_url = ''
for url in data:
print('当前index%s'%(index))
if index < 5000:
index += 1
continue
if index%500 == 0:
folder_url = createFileFolder(int(index/500))
img_url = os.path.join(folder_url,str(index%500)+'.jpg')
urllib.request.urlretrieve(url, img_url)
print('%s下载完成'%(img_url))
index += 1
getImg(0)