简单几步爬取王者高清壁纸

王者作为当今热门的游戏，深受各类人群的喜爱，有些人喜欢收集王者高清壁纸放在桌面，那么怎么才能从网络海量图库中收集可用的高清壁纸呢？下面就看看我是怎么样通过爬虫的手段实现高清壁纸收集的。

1. # coding=utf-8
   
2. 
   
3. import requests
   
4. import os
   
5. import re
   
6. 
   
7. 
   
8. url = 'https://pvp.qq.com/web201605/js/herolist.json'
   
9. headers = {
   
10.     'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/99.0.4844.74 Safari/537.36 Edg/99.0.1150.55'
    
11. }
    
12. rsp = requests.get(url, headers=headers)
    
13. # print(rsp.text)
    
14. print(rsp.status_code)
    
15. # print(rsp.json())
    
16. for index in rsp.json():
    
17.     # 获取英雄名字和id
    
18.     hero_name = index['cname']
    
19.     hero_id = index['ename']
    
20. 
    
21.     # filename = f'{hero_name}\\'
    
22.     # if not os.path.exists(filename):
    
23.     #     os.mkdir(filename)
    
24. 
    
25.     index_url = f'https://pvp.qq.com/web201605/herodetail/{hero_id}.shtml'
    
26.     # print(hero_name, hero_id, index_url)
    
27.     rsp1 = requests.get(url=index_url, headers=headers)
    
28.     # rsp1.encoding = 'gbk'
    
29.     rsp1.encoding = rsp1.apparent_encoding#自动识别编码
    
30.     # print(rsp1.text)
    
31.     temp = '
    
32. '
    
33.     title_list = re.findall('
    
34. ', rsp1.text)[0]
    
35.     title_list = re.sub('&\d+', '', title_list).split('|')
    
36. 
    
37.     for num in range(1, len(title_list) + 1):
    
38. 
    
39.         img_url = f'https://game.gtimg.cn/images/yxzj/img201606/skin/hero-info/{hero_id}/{hero_id}-bigskin-{num}.jpg'
    
40.         img_title = title_list[num - 1]
    
41. 
    
42.         img_data = requests.get(url=img_url, headers=headers).content
    
43.         with open('photo/' + img_title + '.jpg', 'wb') as f:
    
44.             print(f'=====================正在爬取{hero_name}的皮肤========================')
    
45.             f.write(img_data)
    
46.         # print(img_title, img_url)

复制代码