Fork me on Github

爬取 pic 

 1 import time
 2 import requests
 3 from bs4 import BeautifulSoup
 4 
 5 index = 1
 6 num = 1
 7 while index <= 27:
 8     header = {
 9         "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) "
10                       "Chrome/60.0.3100.0 Safari/537.36 "
11     }
12     url = 'https://desk.3gbizhi.com/deskDM/index_{}.html'.format(index)
13     resp = requests.get(url, headers=header)
14     # bs4解析页面
15     page = BeautifulSoup(resp.text, 'html.parser')
16     pageList = page.find_all('a', style="display: block;", target="_blank")
17     armUrl = set([])
18     for i in pageList:
19         armUrl.add(i.get('href'))
20 
21     # 最终页面发起请求
22     hrefList = set([])
23     for url in armUrl:
24         resp = requests.get(url, headers=header)
25         time.sleep(0.001)
26         # bs4解析页面
27         page = BeautifulSoup(resp.text, 'html.parser')
28         src = page.find('div', class_="morew").find('a').get('href')
29         # 下载图片
30         imgResp = requests.get(src)
31         imgName = src.split("/")[-1]
32         with open("cartoonImg/" + imgName, mode="wb") as f:
33             f.write(imgResp.content)
34             print("图片下载中------------------" + str(num))
35             num = num+1
36             f.close()
37     index = index + 1
38 print('\n下载完成！')

 

posted @ 2022-05-29 22:42  昂昂呀  阅读(33)  评论(0)    收藏  举报