学习札记之python：王者荣耀皮肤壁纸小爬虫

当初闲来无聊，一时兴起学python的目的就是爬一下皮肤的壁纸，如今小目标已经达成了，下一步就是2d小游戏了，加油！

（用了一点正则表达式的知识）

import urllib.request as ureq
import os
import re
from urllib import error

def url_open(url):
    req = ureq.Request(url)
    req.add_header('User-Agent', 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:77.0) Gecko/20100101 Firefox/77.0')
    req.add_header('Referer', url)
    response = ureq.urlopen(req)
    html = response.read()
    return html


def get_pages(url):
    html = url_open(url).decode("gbk")
    hero_nums = re.findall(r'<a href="herodetail/(\d\d\d)\.shtml"', html)
    # 正则表达式和查找不同，注意网页源代码的空白符，尽量避免空白符
    hero_names = re.findall('height="91" alt="(\S+)">\S+</a></li>', html)
    heros = dict(zip(hero_names, hero_nums))
    return heros


def download_wz():
    folder = input("请输入一个文件名:")
    try:
        os.mkdir(folder)
    except OSError:
        pass
    os.chdir(folder)
    url = "https://pvp.qq.com/web201605/herolist.shtml"
    heros = get_pages(url)
    for each in heros:
        print(each)
        os.mkdir(each)
        os.chdir(each)
        # 这里采用了尝试的方法
        for i in range(10):
            skin_pages = 'http://game.gtimg.cn/images/yxzj/img201606/skin/hero-info/' + heros[each] + \
                         '/' + heros[each] + '-bigskin-' + str(i + 1) + '.jpg'
            try:
                ureq.urlopen(skin_pages).getcode()
                filename = skin_pages.split('/')[-1]
                with open(filename, 'wb') as f:
                    img = url_open(skin_pages)
                    f.write(img)  # 写入文件
            except error.HTTPError:
                break

        os.chdir("..")


if __name__ == "__main__":
    download_wz()