Python爬取王者荣耀高清原画壁纸


张登友,张登友的博客,张登友的网站——

代码如下

import requests
import re
import json
import urllib.parse
from tqdm import tqdm
import time
 
 
headers ={
    'user-agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.79 Safari/537.36'
}
def get_picSrc(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&jsoncallback=jQuery17108079906974233315_1576410038567&iAMSActivityId=51991&_everyRead=true&iTypeId=2&iFlowId=267733&iActId=2735&iModuleId=2735&_=1576410754875'.format(str(page))
    response = requests.get(url,headers=headers)
    if response.status_code ==200:
        # print(response.text)
        temp = re.search('jQuery\d+_\d+\((.*?)\)',response.text,re.S)
        if temp:
            data = json.loads(temp.group(1))
            data_list = data['List']
            for item in data_list:
                sProdName = urllib.parse.unquote(item['sProdName'])
                sProdImgNo_8 = urllib.parse.unquote(item['sProdImgNo_8'])
                pic_src = sProdImgNo_8[:-3]+'0'
                pic_info ={
                    'sProdName':sProdName,
                    'pic_src':pic_src
                }
                yield pic_info
 
def downloadFILE(url,name):
    headers={
        'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/77.0.3865.90 Safari/537.36'
    }
    resp = requests.get(url=url,stream=True,headers=headers)
    content_size = int(int(resp.headers['Content-Length'])/1024)
    with open(name, "wb") as f:
        print("Pkg total size is:",content_size,'k,start...')
        for data in tqdm(iterable=resp.iter_content(1024),total=content_size,unit='k',desc=name):
            f.write(data)
        print(name , "download finished!")                
                 
 
if __name__ == "__main__":
    for page in range(0,20):
        print('[info] page:',page)
        pic_infos = get_picSrc(page)
        for pic_info in pic_infos:
            print(pic_info)
            try:
                downloadFILE(pic_info['pic_src'],pic_info['sProdName']+'.jpg')
            except:
                continue
        time.sleep(3)

在这个路径下打开终端运行 ,记得在文件夹中运行 ( 否则被图片铺满桌面 ) 代码中sProdImgNo_8的部分改成sProdImgNo_6就可以下载1920*1080格式的了, 1到8分别是不同尺寸的,但左上还是有王者荣耀的水印,没有水印的是爬取英雄资料的背景图片是1920*822格式了。

终端运行脚本

查看结果

查看结果

转载自一个论坛的大佬。当时下载完,过了几天才测试,忘了链接。。。。


文章作者: 张登友
版权声明: 本博客所有文章除特別声明外,均采用 CC BY 4.0 许可协议。转载请注明来源 张登友 !
评论
  目录