python爬虫案列04:爬取彼岸桌面4K壁纸
import requests
from lxml import etree
import os
url = 'https://pic.netbian.com/4kmeinv/index.html'
headers = {
'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/106.0.0.0 Safari/537.36'
}
if not os.path.exists('./picture'):
os.makedirs('./picture')
response = requests.get(url, headers=headers)
etree_html = etree.HTML(response.text)
lis = etree_html.xpath('//*[@id="main"]/div[3]//a/@href')
for li in lis:
response = requests.get(url="https://pic.netbian.com/" + li, headers=headers)
response.encoding = "gbk"
html = etree.HTML(response.text)
address = html.xpath('//*[@id="img"]/img/@src')[0]
name = html.xpath('//*[@id="img"]/img/@alt')[0] + ".jpg"
img_path = 'E:\\python\\01初识爬虫,requests使用\\picture\\' + name
with open(img_path, 'wb') as f:
response = requests.get(url="https://pic.netbian.com/" + address, headers=headers).content
f.write(response)
print("OK")
f.close()