爬取lol皮肤

#!/usr/bin/python
# -*- coding: utf-8 -*-
# data:2018-11-23
# user:fei
import re
import requests
import json,random

def path_js(url_js):
    res_js = requests.get(url=url_js).content
    html_js = res_js.decode("gbk")
    req = '"keys":(.*?),"data"'
    req = re.compile(req)
    list_js = re.findall(req,html_js)
    # print(list_js)
    dict_js = json.loads(list_js[0])
    return dict_js

def path_url(dict_js):
    for key in dict_js:
        for item in range(20):
            nums = str(item)
            if len(nums) == 1:
                names_str = "big" + key + "00" + nums + ".jpg"
            elif len(nums) == 2:
                names_str = "big" + key + "0" + nums + ".jpg"
            url = "http://ossweb-img.qq.com/images/lol/web201310/skin/%s" %names_str
            # header = {'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:23.0) Gecko/20100101 Firefox/23.0'}
            path = "F:/360downloads/boot/photo/%s" %names_str

            head_list = [
                'MSIE (MSIE 6.0; X11; Linux; i686) Opera 7.23',
                'Opera/9.20 (Macintosh; Intel Mac OS X; U; en)',
                'Opera/9.0 (Macintosh; PPC Mac OS X; U; en)',
                'iTunes/9.0.3 (Macintosh; U; Intel Mac OS X 10_6_2; en-ca)',
                'Mozilla/4.76 [en_jp] (X11; U; SunOS 5.8 sun4u)',
                'iTunes/4.2 (Macintosh; U; PPC Mac OS X 10.2)',
                'Mozilla/5.0 (Macintosh; Intel Mac OS X 10.6; rv:5.0) Gecko/20100101 Firefox/5.0',
                'Mozilla/5.0 (Macintosh; Intel Mac OS X 10.6; rv:9.0) Gecko/20100101 Firefox/9.0',
                'Mozilla/5.0 (Macintosh; Intel Mac OS X 10.8; rv:16.0) Gecko/20120813 Firefox/16.0',
                'Mozilla/4.77 [en] (X11; I; IRIX;64 6.5 IP30)',
                'Mozilla/4.8 [en] (X11; U; SunOS; 5.7 sun4u)'
            ]
            # heade = random.choice(head_list)
            header = {'User-Agent': random.choice(head_list)}
            # print(heade)
            img_file = requests.get(url, headers=header)
            if img_file.status_code == 404:
                pass
            else:
                print("正在存储图片" + url)
                with open(path,"wb") as f:
                    f.write(img_file.content)
#
if __name__ == '__main__':
    url_js = "https://lol.qq.com/biz/hero/champion.js"
    dict_js = path_js(url_js)
    url = path_url(dict_js)

 

转载于:https://www.cnblogs.com/tengfei520/p/10095091.html