使用python爬取壁纸(python爬取桌面应用软件数据)

代码实现

话不多说，直接上代码，拿走不谢！

手机壁纸爬取(国外)

import requests

import json

import time

def test():

list = []

for i in range(1,10):

if i == 1:

url = "https://unsplash.com/napi/landing_pages/wallpapers/iphone?page=1&per_page=20"

else:

url = f"https://unsplash.com/napi/landing_pages/wallpapers/iphone?page={i}&per_page=20"

list.append(url)

# 模拟浏览器

headers = {

"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML,like Gecko) Chrome/103.0.0.0 Safari/537.36"}

i = 1

for uri in list:

# 请求数据

request = requests.get(uri,headers=headers,verify=False)

# 设置charset格式

resp = request.content.decode('utf-8')

json_res = json.loads(resp)

photos = json_res["photos"]

j = 1

for photo in photos:

urls = photo["urls"]

img_url = urls["regular"]

img_content = requests.get(img_url)

# 获取图片内容

img_byte = img_content.content

path = f"D:/project_workspace/crawling_data/unsplash/{i}_{j}.jpg"

with open(path,"wb") as f:

f.write(img_byte)

time.sleep(0.1)

print(f"第{i}页第{j}张图片你下载成功")

j = j + 1

i = i + 1

return "success"

if __name__ == '__main__':

test()

图片下载如下

电脑壁纸爬取（国内）

base_url = "https://pic.netbian.com"

list = []

for i in range(1,100):

if i == 1:

url = "https://pic.netbian.com/4kmeinv/index.html"

else:

url = f"https://pic.netbian.com/4kmeinv/index_{i}.html"

list.append(url)

# 模拟浏览器

headers = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML,verify=False)

# 设置charset格式

resp = request.content.decode('gbk')

# 通过BeautifulSoup进行数据解析

soup = BeautifulSoup(resp,"lxml")

divs = soup.find_all("div",class_="slist")

j = 1

for imgs in divs:

img = imgs.find_all("img")

for im in img:

img_src = im["src"]

img_uri = base_url + img_src

img_content = requests.get(img_uri)

# 获取图片内容

img_byte = img_content.content

path = f"D:/project_workspace/crawling_data/{i}_{j}.jpg"