Python爬取 | 王者荣耀英雄皮肤海报

这里只展示代码，具体介绍请点击下方链接。

Python爬取 | 王者荣耀英雄皮肤海报

import requests
import re
import os
import time
import winreg

count = 0  # 计数用

# 获取第一次页面所以英雄的id以及名字
def first_url(url):
    response = requests.get(url)
    response.encoding = 'gbk'
    response = response.text
    id_name = re.findall('<li><a href=.*?/(\d{3}).*?alt=.*?>(.*?)</a></li>', response, re.S)
    return id_name

# 获取英雄皮肤昵称以及获取皮肤数目
def second_url(url, name):
    response = requests.get(url)
    response.encoding = 'gbk'
    response = response.text
    # 第66行
    # <ul class="pic-pf-list pic-pf-list3" data-imgname="月光之女&0|哥特玫瑰&1|绯红之刃&0|紫霞仙子&12|一生所爱&44|瓷语鉴心&1">
    response = re.findall('<ul class=.*?data-imgname="(.*?)">', response)
    response = response[0].split('|')
    skin_names = []
    for i in response:
        names = re.sub('[^\u4e00-\u9fa5]', '', i) + ' ' + name
        skin_names.append(names)
    return skin_names

def download(url, skin_names, path):
    num = len(skin_names)  # 获取英雄皮肤数目，以控制循环次数
    times = str(num)  # 将皮肤个数字符化，用于文件名称显示皮肤个数
    name = skin_names[0].split(' ')[-1]  # 这里是获取英雄名字，如露娜，用于后面皮肤全称的拼接
    path = path + '/' + name + ' ' + times + '张'  # 皮肤存储路径
    if not os.path.exists(path):  # 如果路径不存在，则自动创建
        os.mkdir(path)
    for n in range(0, num):  # 循环
        skin_url = url + str(n + 1) + '.jpg'  # 皮肤图片的链接
        image_path = path + '/' + skin_names[n] + '.jpg'  # 每张皮肤的命名
        global count  # 定义全局变量，用于统计皮肤下载张数
        count = count + 1
        print(f'   第{count}张  正在下载>>{name}<<的第{str(n + 1)}张皮肤，共{times}张')
        with open(image_path, 'wb') as f:  # 皮肤图片下载并保存
            f.write(requests.get(skin_url).content)
        time.sleep(0.3)

def get_desktop():
    key = winreg.OpenKey(winreg.HKEY_CURRENT_USER,
                         r'Software\Microsoft\Windows\CurrentVersion\Explorer\Shell Folders')  # 利用系统的链表
    zm = winreg.QueryValueEx(key, "Desktop")[0]  # 获取的是Unicode类型数据
    return str(zm)  # Unicode转化为str并返回

def main():
    path = f'{get_desktop()}\\王者荣耀角色皮肤图片'
    print(path)
    if not os.path.exists(path):
        os.mkdir(path)
    url = 'https://pvp.qq.com/web201605/herolist.shtml'
    id_name = first_url(url)
    # 拼接链接
    for i in id_name:
        hero_url = f'http://pvp.qq.com/web201605/herodetail/{i[0]}.shtml'
        skin_names = second_url(hero_url, i[1])  # i[1]是英雄的名字，比如露娜，云中君等
        skin_url = f'http://game.gtimg.cn/images/yxzj/img201606/skin/hero-info/{i[0]}/{i[0]}-bigskin-'
        download(skin_url, skin_names, path)

if __name__ == '__main__':
    main()