python爬取一组小姐姐图片实例

import time
import requests
from lxml import etree

href = tree.xpath('//*[@id="features"]/div/div[1]/div/div[1]/a/@href')

 for url_img in href:
            img_url = requests.get(url_img,headers=head)
            # print(img_url.text)
            time.sleep(1)
            t = etree.html(img_url.text)
            url_list = t.xpath("/html/body/section/div/div/div[1]/div[2]/p[2]/img/@src")

 with open(f"./img/{name}",mode="wb") as f:
        f.write(download_img.content)
        print("正在下载:" +name)
        time.sleep(1)

import time
import requests
from lxml import etree
 
def get_page_url():
    for i in range(1, 4): # 循环3页
        url = f"https://mm.tvv.tw/cateGory/xinggan/{i}/"
 
        # 请求页面得到源代码
        res = requests.get(url,headers=head)
        # 对源代码进行解析
        tree = etree.HTML(res.text)
        # 得到每个图片的封面url（href）
        href = tree.xpath('//*[@id="features"]/div/div[1]/div/div[1]/a/@href')
        # print("-------------------------------------------------------")
        time.sleep(3)
        for url_img in href:
            img_url = requests.get(url_img,headers=head)
            # print(img_url.text)
            time.sleep(1)
            t = etree.HTML(img_url.text)
            url_list = t.xpath("/html/body/section/div/div/div[1]/div[2]/p[2]/img/@src")
            # print(url_list)
            time.sleep(1)
            for url_src in url_list:
                get_img(url_src)
 
def get_img(url):
    name = url.rsplit("/",1)[1]
    time.sleep(2)
    download_img = requests.get(url,headers=head)
    with open(f"./img/{name}",mode="wb") as f:
        f.write(download_img.content)
        print("正在下载:" +name)
        time.sleep(1)
    f.close()
 
 
 
 
if __name__ == '__main__':
    head = {"user-agent": "Mozilla/5.0 (windows NT 10.0; Win64; x64) AppleWEBKit/537.36 (KHTML, like Gecko) Chrome/97.0.4692.71 Safari/537.36"}
    get_page_url()