python 微信推文图片提取,并打包压缩

from re import findall
from urllib.request import urlopen
import os,shutil
import zipfile
def makedir(path):
  os.chdir("/")
  isExists=os.path.exists(path)
  if isExists:
    shutil.rmtree(path)
  else:
    os.mkdir(path)

def getwechatimg(idx,url):
  path="/content/sample_data/wechat"+str(idx)
  makedir(path)
  os.chdir(path)
  # url = input()
  with urlopen(url) as fp:
    content = fp.read().decode()
  pattern = 'data-src="(.+?)"'
  result = findall(pattern, content)
  for index, item in enumerate(result):
    if item.endswith("jpeg"):
      with urlopen(str(item)) as fp:
        with open(str(index)+'.jpeg', 'wb') as fp1:
          fp1.write(fp.read())

  z = zipfile.ZipFile("/content/sample_data/download_"+str(idx)+".zip", 'w', zipfile.ZIP_DEFLATED)
  startdir = path
  for dirpath, dirnames, filenames in os.walk(startdir):
    fpath = path.replace(dirpath,'')
    for filename in filenames:
      z.write(os.path.join(fpath, filename))
  z.close()
  shutil.rmtree(path)

'''items 引号内添加文章链接'''
items=["",""]
for index,item in enumerate(items):
  getwechatimg(index,item)

 

  • 0
    点赞
  • 1
    收藏
    觉得还不错? 一键收藏
  • 0
    评论
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值