|
马上注册,结交更多好友,享用更多功能^_^
您需要 登录 才可以下载或查看,没有账号?立即注册
x
- #coding:utf-8
- import urllib.request
- import re
- import os
- num = int(input('请输入您需要爬的页数:\n'))
- for page_num in range(0,num):
-
- url = 'http://www.budejie.com/pic/' + str(page_num)
- headers = {'User-Agent':'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.181 Safari/537.36'}
- req = urllib.request.Request(url,headers=headers)
- response = urllib.request.urlopen(req)
- html = response.read().decode('utf-8')
- # print(html)
- target_url = re.findall(r'data-original="(.+?)" title=*',html)
- file_path = '存放图片的path'
- os.chdir(file_path)
- os.mkdir(str(page_num))
- os.chdir(str(page_num))
- # print(os.getcwd())
- for img_url in target_url:
- img_name = img_url.split('.')[-2].split('/')[-1]
- img_type = img_url.split('.')[-1]
- img_finall = img_name + '.' + img_type
- urllib.request.urlretrieve(img_url,img_finall)
- print('%s\t已下载完成'%img_url)
复制代码 |
|