python爬虫 王者荣耀某英雄皮肤下载器

实现：自己输入英雄名，下载皮肤在文件夹内
难点：

• ajax和网页路径分析
  英雄页面

#code是英雄对应的代码
hero_page_url = 'https://pvp.qq.com/web201605/herodetail/{0}.shtml'.format(code)

皮肤图片路径

'https://game.gtimg.cn/images/yxzj/img201606/skin/hero-info/{0}/{1}-bigskin-{2}.jpg'.format(code,code,i)

• 访问网页得到英雄列表json文件，并转为新的字典
  关键语法,从旧字典中提取值组成新字典

hero_dict.update([(hero['cname'] ,hero['ename'])])
#hero_dict[hero['cname']] =hero['ename']

下贴详细代码

import requests
from lxml import etree
import time
import json

headers={
    'referer': 'https://pvp.qq.com/web201605/herolist.shtml',
    'user-agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.25 Safari/537.36 Core/1.70.3754.400 QQBrowser/10.5.4034.400',
}
def hero_dict():
    hero_dict = {}
    hero_listurl = 'https://pvp.qq.com/web201605/js/herolist.json'
    hero_list =requests.get(hero_listurl,headers= headers).content.decode('utf-8')
    hero_list=json.loads(hero_list)
    # print(hero_list)
    for hero in hero_list:
        hero_dict.update([(hero['cname'] ,hero['ename'])])
    # print(hero_dict)
    return hero_dict

def pic_url(code,name):
    hero_page_url = 'https://pvp.qq.com/web201605/herodetail/{0}.shtml'.format(code)
    hero_Message = requests.get(hero_page_url, headers=headers).content.decode('gbk')
    hero_Html =etree.HTML(hero_Message)
    pic_num =hero_Html.xpath('//div[@class="pic-pf"]/ul/@data-imgname')[0]
    pic_names=pic_num.split('|')
    for i in range(1,len(pic_names)+1):
        pic_url ='https://game.gtimg.cn/images/yxzj/img201606/skin/hero-info/{0}/{1}-bigskin-{2}.jpg'.format(code,code,i)
        pic_cont = requests.get(pic_url, headers=headers).content
        with open('皮肤\\{0}-{1}-{2}.jpg'.format(name,i,pic_names[i-1]),'wb') as ff:
            ff.write(pic_cont)
        time.sleep(1)
if __name__ == '__main__':
    hero_dict()
    hero_name =input('请输入英雄名:\n')
    Hero_Dict = hero_dict()
    if hero_name in Hero_Dict.keys():
        hero_code = Hero_Dict[hero_name]
        pic_url(hero_code,hero_name)
    else:
        print('英雄不存在')

改成爬取所有英雄皮肤，只需要将输入英雄名改为所有英雄名，存储英雄代码和名字的列表循环遍历即可

import requests
from lxml import etree
import time
import json

headers={
    'referer': 'https://pvp.qq.com/web201605/herolist.shtml',
    'user-agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.25 Safari/537.36 Core/1.70.3754.400 QQBrowser/10.5.4034.400',
}
def hero_dict():
    hero_dict = {}
    hero_listurl = 'https://pvp.qq.com/web201605/js/herolist.json'
    hero_list =requests.get(hero_listurl,headers= headers).content.decode('utf-8')
    hero_list=json.loads(hero_list)
    # print(hero_list)
    for hero in hero_list:
        hero_dict.update([(hero['cname'] ,hero['ename'])])
    # print(hero_dict)
    return hero_dict

def pic_url(code,name):
    hero_page_url = 'https://pvp.qq.com/web201605/herodetail/{0}.shtml'.format(code)
    hero_Message = requests.get(hero_page_url, headers=headers).content.decode('gbk')
    hero_Html =etree.HTML(hero_Message)
    pic_num =hero_Html.xpath('//div[@class="pic-pf"]/ul/@data-imgname')[0]
    pic_names=pic_num.split('|')
    for i in range(1,len(pic_names)+1):
        pic_url ='https://game.gtimg.cn/images/yxzj/img201606/skin/hero-info/{0}/{1}-bigskin-{2}.jpg'.format(code,code,i)
        pic_cont = requests.get(pic_url, headers=headers).content
        with open('皮肤\\{0}-{1}-{2}.jpg'.format(name,i,pic_names[i-1]),'wb') as ff:
            ff.write(pic_cont)
            print('皮肤\\{0}-{1}-{2}.jpg下载完毕'.format(name,i,pic_names[i-1]))
        time.sleep(1)
if __name__ == '__main__':
    hero_dict()
    Hero_Dict = hero_dict()
    for key in Hero_Dict:
        hero_name = key
        hero_code = Hero_Dict[hero_name]
        pic_url(hero_code,hero_name)