害虫图片爬取

 1 import requests
 2 from bs4 import BeautifulSoup
 3 
 4 r1 = requests.get(
 5     url = 'https://www.16pic.com/sucai/7597253.html',
 6     headers = {
 7         # '':'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.108 Safari/537.36',
 8         'User-Agent':'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/77.0.3865.120 Safari/537.36'
 9               }
10             )
11 
12 soup = BeautifulSoup(r1.text,'lxml')
13 #print(soup)
14 div = soup.find(name = 'div',attrs={'class':'flex_grid masonry'})
15 #print(div)
16 
17 li_list = div.find_all(name = 'a',attrs={'class':'image'})
18 print(li_list)
19 for li in li_list:
20     img = li.find(name = 'img')
21     print(img)
22     src = img.get('data-original')
23     src = 'http:'+src
24     print(src)
25 
26     #再次发起请求，下载图片
27     file_name = src.rsplit('/',maxsplit=1)[1]  # 设/后面的文字为文件名  分割完 取后面的
28     ret = requests.get(src)
29     with open(file_name,'wb') as f:
30         f.write(ret.content)   #.content  表示返回的是二进制   图片的内容是二进制

注意点：

这是一种反爬虫机制，如果选取属性 src 则获取的数据是空或者是乱码所以要选属性为 data-original

其次是图片的链接是没有 http: 故代码中要加上否则获取不到数据