python爬虫--王者荣耀高清壁纸下载

下面用的是普通的下载，因为图片过多，所以下载的速度可能会慢一点。

# 1、通过https://apps.game.qq.com/cgi-bin/ams/module/ishow/V1.0/query/workList_inc.cgi?activityId=2735&sVerifyCode=ABCD&sDataType=JSON&iListNum=20&totalpage=0&page=0&iOrder=0&iSortNumClose=1&jsoncallback=jQuery171015387338790761063_1587884222210&iAMSActivityId=51991&_everyRead=true&iTypeId=2&iFlowId=267733&iActId=2735&iModuleId=2735&_=1587884222349
# 可以获取到高清壁纸的url

# 2、获取高清壁纸的url后，通过parse.unqutoe可以进行解码，然后将最后的200改为0 ，就可以得到真实的高清壁纸的图片了

# 3.获取图片的url的地址中有一个参数page，通过修改page的值，可以进行翻页，默认page是从0开始的
import requests
from urllib import parse
from urllib import request
import os

# 用来存放无法下载的链接
un_download = []

# 设置请求头
headers = {
    'user-agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.88 Safari/537.36',
    'referer': 'https://pvp.qq.com/web201605/wallpaper.shtml'
}

# 收集打不开链接的图片信息（将200替换成0的链接）
def un_download_url(image_name,image_url):
    un_download_info = {}
    un_download_info['name'] = image_name
    original_url = image_url.replace('/0','/200')
    un_download_info['original_url'] = original_url
    un_download_info['curr_url'] = image_url

    return un_download_info


# 获取图片链接
def exact_image(data):

    image_urls = []
    for x in range(1,9):
        # 解析获取到的链接，高清的图片末尾是/0，所以要将200替换成0，防止url中间有200数值，所以用'/0'替换'/200'
        image_url = parse.unquote(data['sProdImgNo_%d'%x]).replace('/200', '/0')
        # image_url = parse.unquote(data['sProdImgNo_%d'%x])
        image_urls.append(image_url)
    return image_urls

# 下载图片
def download(image_urls,image_name,dirpath):
    for index, image_url in enumerate(image_urls):
        try:
            request.urlretrieve(image_url, os.path.join(dirpath, "%d.jpg" % (index + 1)))
            print("%s下载完成！" % (image_name + image_url))
        except Exception as e:
            # 收集打不开的链接信息
            un_download_info = un_download_url(image_name, image_url)
            un_download.append(un_download_info)

def main():
    page_url = 'https://apps.game.qq.com/cgi-bin/ams/module/ishow/V1.0/query/workList_inc.cgi?activityId=2735&sVerifyCode=ABCD&sDataType=JSON&iListNum=20&totalpage=0&page={}&iOrder=0&iSortNumClose=1&iAMSActivityId=51991&_everyRead=true&iTypeId=2&iFlowId=267733&iActId=2735&iModuleId=2735&_=1587884222349'
    file_num = 0
    # 从第1页到22页
    for i in range(0,22):
        print("第%d页"%(i+1))
        resp = requests.get(page_url.format(i),headers=headers)
        result = resp.json()

        datas = result['List']

        for data in datas:

            image_urls = exact_image(data)
            image_name = parse.unquote(data['sProdName']).replace("1:1","").strip()
            # 存放图片的文件夹名
            dirpath = os.path.join("image", image_name)
            try:
                # 创建对应的文件夹
                os.mkdir(dirpath)
                download(image_urls,image_name,dirpath)
            except FileExistsError as e:
                # 防止获取到的文件名有重复的，就在重复的文件名末尾加个2
                # 如果有三个以及三个以上重复的，重新写下面这一句代码
                os.mkdir(dirpath + '2')
                download(image_urls, image_name, dirpath+'2')
            file_num += 1
    return file_num
            # 2、只显示url
            # for image_url in image_urls:
            #     print('='*30)
            #     print(image_name)
            #     print(image_url)
            #     print('='*30)

if __name__ == '__main__':
    file_num = main()
    print(un_download)
    print('共下载%d种图片'%file_num)