爬虫案例爬取游民星空壁纸代码

最新推荐文章于 2020-02-28 17:08:00 发布

YangCaine

最新推荐文章于 2020-02-28 17:08:00 发布

阅读量350

点赞数 3

分类专栏： python爬虫文章标签： python 爬虫

本文链接：https://blog.csdn.net/qq_39071593/article/details/97797446

版权

python爬虫专栏收录该内容

2 篇文章 0 订阅

订阅专栏

import requests
import json
import time
import os
import re
path = "./壁纸/"

headers = {'cookie':'', # 传入你的cookies
           'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.181 Safari/537.36'}

def get_page():
    r = requests.get('http://pic.gamersky.com/home/getimagesindex?sort=time_desc&pageIndex=1&pageSize=50&nodeId=21089',
                headers = headers)
    d = r.json()
    d = json.loads(d)
    # print(d)
    # 总页数
    totalPages = d["totalPages"]
    for page in range(1,totalPages+1):
        r = requests.get(
            'http://pic.gamersky.com/home/getimagesindex?sort=time_desc&pageIndex='+ str(page) +'&pageSize=50&nodeId=21089',
            headers=headers)
        d = r.json()
        d = json.loads(d)
        for item in d["body"]:
            img_name = str(item["id"]) + item["title"]
            img_name = re.sub(r"高清壁纸|/|:","",img_name)
            # img_name = str(item["id"])+item["title"]
            # img_name = img_name.replace("高清壁纸","")
            # img_name = img_name.replace("/", " ")
            img = item["originImg"]
            img_name = path + img_name + ".jpg"
            print(img_name)
            with open(img_name, 'wb') as file:  # 以byte形式将图片数据写入
                img = requests.get(
                    img,
                    headers=headers)
                file.write(img.content)
                file.flush()
            file.close()  # 关闭文件

if __name__ == "__main__":
    #判断是否存在文件夹
    if not os.path.exists("壁纸"):
        # 创建文件夹
        os.makedirs(path)
    get_page()
    print("finish")