使用python爬取4K壁纸保存到本地文件夹的全过程

pip install 模块名称 -i https://mirrors.aliyun.com/pypi/simple

清华大学
https://pypi.tuna.tsinghua.edu.cn/simple
 
阿里云
https://mirrors.aliyun.com/pypi/simple/
 
豆瓣
https://pypi.douban.com/simple/ 
 
百度云
https://mirror.baidu.com/pypi/simple/
 
中科大
https://pypi.mirrors.ustc.edu.cn/simple/
 
华为云
https://mirrors.huaweicloud.com/repository/pypi/simple/
 
腾讯云
https://mirrors.cloud.tencent.com/pypi/simple/

import requests  # 用于发送HTTP请求
from lxml import etree  # 用于解析HTML页面
import time  # 用于控制爬取速度
import os  # 用于文件操作

def get_imgurl_list(url, imgurl_list):
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/95.0.4638.69 Safari/537.36'
    }
    response = requests.get(url=url, headers=headers)
    html_str = response.text
    html_data = etree.HTML(html_str)
    li_list = html_data.xpath("//ul[@class='clearfix']/li")
    for li in li_list:
        imgurl = li.xpath(".//a/img/@data-original")[0]
        imgurl_list.append(imgurl)

def get_down_img(imgurl_list):
    os.mkdir("美女")
    n = 0
    for img_url in imgurl_list:
        headers = {
            'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/95.0.4638.69 Safari/537.36'
        }
        img_data = requests.get(url=img_url, headers=headers).content
        img_path = './美女/' + str(n) + '.jpg'
        with open(img_path, 'wb') as f:
            f.write(img_data)
        n += 1

if __name__ == '__main__':
    page_number = 10  # 爬取页数
    imgurl_list = []  # 存放图片链接
    for i in range(0, page_number + 1):
        url = f'https://www.moyublog.com/95-2-2-{i}.html'
        print(url)
        get_imgurl_list(url, imgurl_list)
    get_down_img(imgurl_list)

import requests  # python基础爬虫库
from lxml import etree  # 可以将网页转换为Elements对象
import time  # 防止爬取过快可以睡眠一秒
import os
def get_imgurl_list(url, imgurl_list):
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/95.0.4638.69 Safari/537.36'}
    # 发送请求
    response = requests.get(url=url, headers=headers)
    # 获取网页源码
    html_str = response.text
    # 将html字符串转换为etree对象方便后面使用xpath进行解析
    html_data = etree.HTML(html_str)
    # 利用xpath取到所有的li标签
    li_list = html_data.xpath("//ul[@class='clearfix']/li")
    # 打印一下li标签个数看是否和一页的电影个数对得上
    print(len(li_list))  # 输出20，没有问题
    for li in li_list:
        imgurl = li.xpath(".//a/img/@data-original")[0]
        print(imgurl)
        # 写入列表
        imgurl_list.append(imgurl)
def get_down_img(imgurl_list):
    os.mkdir("美女")
    n = 0
    for img_url in imgurl_list:
        headers = {
            'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/95.0.4638.69 Safari/537.36'}
        img_data = requests.get(url=img_url, headers=headers).content  #
        # 拼接图片存放地址和名字
        img_path = './美女/' + str(n) + '.jpg'
        # 将图片写入指定位置
        with open(img_path, 'wb') as f:
            f.write(img_data)
        # 图片编号递增
        n = n + 1
 
 
if __name__ == '__main__':
    page_number = 10  # 爬取页数
    imgurl_list = []  # 存放图片链接
    # 1. 循环构建每页的链接
    for i in range(0, page_number + 1):
        # 页数拼接
        url = f'https://www.moyublog.com/95-2-2-{i}.html'
        print(url)
        # 2. 获取图片链接
        get_imgurl_list(url, imgurl_list)
    # 3. 下载图片
    get_down_img(imgurl_list)