• 编写爬虫获取英雄联盟所有英雄的全部皮肤
  • 需要库：
    • requests
    • re
    • json
    • os
  • 效果：在该代码文件目录下生成n个Hero文件夹保存皮肤图片。
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
"""
Date: 2019.11.7
Author: Justlovesmile
Language: python3
"""
import requests
import re
import json
import os

def getHtml(url):
    try:
        r=requests.get(url)
        r.raise_for_status()
        r.encoding=r.apparent_encoding
    except:
        print(url+"爬取失败！")
    else:
        response = r.text
        getInfo(response)

def getInfo(res):
    lists=re.findall(r'"keys":(.*?),"data"',res)
    #print(lists)
    hero_id=json.loads(lists[0])
    #print(hero_id)
    for hero in hero_id.values():
        getSkin(hero)

def getSkin(hero):
    url='https://lol.qq.com/biz/hero/'+hero+'.js'
    try:
        r=requests.get(url)
        r.raise_for_status()
        r.encoding=r.apparent_encoding
    except:
        print(url+"爬取失败！")
    else:
        html=r.text
        num=re.findall(r'"id":"(\d{4,6})","num"',html)
        for i in range(len(num)):
            img_url='https://game.gtimg.cn/images/lol/act/img/skin/big' + num[i] + '.jpg'
            save_img(hero,img_url)

def save_img(hero,img_url):
    root=hero+"\\"
    path=root+img_url.split('/')[-1]
    try:
        if not os.path.exists(root):
            os.mkdir(root)
        if not os.path.exists(path):
            r=requests.get(img_url)
            with open(path,'wb') as f:
                f.write(r.content)
                f.close()
                print("文件保存成功！")
        else:
            print("文件已存在！")
    except:
        print("爬取失败！")
    print(img_url+"已下载")

def main():
    url="https://lol.qq.com/biz/hero/champion.js"
    getHtml(url)

if __name__ == "__main__":
    main()