python爬虫之一---------豆瓣妹子图

Posted 2020-09-26

 1 #-*- coding:utf-8 -*-
 2 __author__ = "carry"
 3 import urllib
 4 import urllib2
 5 from bs4 import BeautifulSoup
 6 
 7 
 8 url = ‘http://www.dbmeinv.com/?pager_offset=1‘
 9 x = 1
10 def crawl(url):
11     headers = {‘User-Agent‘:‘Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/50.0.2661.102 Safari/537.36‘}
12     req = urllib2.Request(url,headers=headers)
13     page = urllib2.urlopen(req,timeout=20)
14     contents = page.read()
15     #print (contents.decode(‘utf-8‘))
16     soup = BeautifulSoup(contents,‘html.parser‘)
17     my_girl = soup.find_all(‘img‘)
18     #print my_girl
19     for girl in my_girl:
20         link = girl.get(‘src‘)
21         print link
22         global x
23         urllib.urlretrieve(link,‘image\%s.jpg‘%x)
24         print("正在下载第%s张"%x)
25         x +=1
26 
27 for page in range(1,20):
28     url = ‘http://www.dbmeinv.com/?pager_offset=%d‘%page
29     crawl(url)
30 print("图片下载完毕")