Python爬取必应搜索首页图片

爬取必应搜索首页图片

---

安装库：

pip install beautifulsoup4
pip install lxml
pip install requests

"""
爬取每日必应首页图片：

必应首页图片一共七张
"""

import requests
from bs4 import BeautifulSoup
from requests.exceptions import RequestException
import re
import os


def get_page(url):
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/72.0.3626.109 Safari/537.36'
    }

    try:
        response = requests.get(url, headers=headers)
        if response.status_code == 200:
            return response.text
        return None
    except RequestException:
        return None


def download(url, path, fname):
    response = requests.get(url)
    if response:
        with open(os.path.join(path, fname), 'wb') as f:
            f.write(response.content)
            print('download: {} successful.'.format(fname))
    else:
        print('faild: {}.'.format(fname))


for i in range(8):
    url = 'https://cn.bing.com/HPImageArchive.aspx?idx={}&n=1'.format(i)
    html = get_page(url)
    soup = BeautifulSoup(html, 'lxml')
    text = soup.find(name='url').string
    img_url = 'https://cn.bing.com' + text
    img_name = re.match('^/th\?id=(.*?)&', text).group(1)
    download(img_url, 'E:/wallpaper/bing', img_name)

---

效果

---

ends…