python壁纸推荐_python爬虫项目-一见倾心壁纸

方法1

1 import re

2 import urllib

3 import urllib.request

4

5 def gethtml(url):

6 page = urllib.request.urlopen(url)

7 html = page.read()

8 return html

9

10 def getimage(html,x):

11 #https://mmbiz.qpic.cn/mmbiz_jpg/ib55rg6wzuc3b16kiy3uu53nkcttdic8uea4wwbpahj8lpibvankps2fztyjrv7w7dbeenrhfvpuuyrenaxsldgja/640?wx_fmt=jpeg

12 #https://mmbiz.qpic.cn/mmbiz_jpg/ib55rg6wzuc3b16kiy3uu53nkcttdic8uehqoci7r86nehl2neforaqvctiaeaiuwjtwpknxnnxipuuuqnujefkyw/640?wx_fmt=jpeg

13 #此处正则为重点

14 reg = 'data-src="(.*?)"'

15 image = re.compile(reg)

16 imlist = re.findall(reg,html.decode('utf-8'))

17

18 print(imlist)

19 for i in imlist:

20 print(i)

21 print(x)

22 urllib.request.urlretrieve(i,'%s.jpg' % x)

23 x +=1

24 return x

25 x=1

26 url = 'https://mp.weixin.qq.com/s/mvdcn0o3093olihmykqbia'

27 html = gethtml(url)

28 x = getimage(html,x)

29 print('下载完成')

30 #下载结果与此.py文件在同一目录

方法2：beautifulsoup 避免写正则表达式(因为不会)

import requests

import urllib.request

from bs4 import beautifulsoup

url = "https://mp.weixin.qq.com/s/cm3bua0um1jbznr2de7twg"

r = requests.get(url)

demo = r.text

soup = beautifulsoup(demo,"html.parser")

piclist=[]

for link in soup.find_all('img'):

link_list = link.get('data-src')

if link_list != none:

piclist.append(link_list)

#print(piclist)

#print(type(link_list))

x = 0

for http in piclist:

print(http)

#f:\桌面\pa 是存储路径，需要先建立文件夹

filesavepath = r'f:\桌面\pa\%s.jpg' % x

urllib.request.urlretrieve(http,filesavepath)

x +=1

print('正在保存第{:.0f}张图片'.format(x))

print('下载完成')

希望与广大网友互动？？

点此进行留言吧！