python爬虫学习（第四爬）

今天来爬取壁纸图片

url = "http://www.bizhi88.com/"

还是先获取页面源代码，找到每张图片具体的链接

url = "http://www.bizhi88.com/"
headers = {
    "user-agent":"Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:90.0) Gecko/20100101 Firefox/90.0"
}
resp = requests.get(url=url,headers=headers)
resp.encoding = "utf-8"
html = etree.HTML(resp.text)
li_src = html.xpath('/html/body/div[3]/div')

得到每张图片的src后 再进行request操作

取到图片对应的数据  然后写入存储路径即可

完整代码：

import requests
from lxml import etree

def get_one_page(url):
    headers = {
        "user-agent":"Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:90.0) Gecko/20100101 Firefox/90.0"
    }
    resp = requests.get(url=url,headers=headers)
    resp.encoding = "utf-8"
    html = etree.HTML(resp.text)
    li_src = html.xpath('/html/body/div[3]/div')
    for l_src in li_src:
        every_src = l_src.xpath('./a[1]/@href')[0]
        every_src = "http://www.bizhi88.com"+every_src
        resp1 = requests.get(url = every_src,headers=headers)
        resp1.encoding = "utf-8"
        html1 = etree.HTML(resp1.text)
        photo = html1.xpath('/html/body/div[3]/div[1]/div/div[1]/img/@src')[0]
        photo_name = html1.xpath('/html/body/div[3]/div[1]/div/ul/li[2]/a/text()')[0]
        path = r'/home/chq/桌面/2021暑假/python爬虫/photo/'
        image_data = requests.get(url=photo,headers=headers).content
        with open(path+photo_name,'wb') as fp:
            fp.write(image_data)
            print("下载完毕！",photo_name)

if __name__ == '__main__':
    url = "http://www.bizhi88.com/"
    get_one_page(url)