解析: xpath续: 站长素材图片下载器

"""                                                           
                                       .-''-.               
.--.                    _..._        .' .-.  )              
|__|                  .'     '.     / .'  / /               
.--..-,.--.          .   .-.   .   (_/   / /                
|  ||  .-. |         |  '   '  |        / /                 
|  || |  | | _    _  |  |   |  |       / /         _    _   
|  || |  | || '  / | |  |   |  |      . '         | '  / |  
|  || |  '-.' | .' | |  |   |  |     / /    _.-').' | .' |  
|__|| |    /  | /  | |  |   |  |   .' '  _.'.-'' /  | /  |  
    | |   |   `'.  | |  |   |  |  /  /.-'_.'    |   `'.  |  
    |_|   '   .'|  '/|  |   |  | /    _.'       '   .'|  '/ 
           `-'  `--' '--'   '--'( _.-'           `-'  `--'  
Created on 2023/4/10 20:49.
@Author: haifei
"""
import time, os
from pyfiglet import Figlet
from urllib import request
from lxml import etree
import socket
# https://blog.csdn.net/sfwqwfew/article/details/127880014
socket.setdefaulttimeout(10.0)  # 设置全局的socket超时


# 站长素材：图片-人物-情侣，前10页
# https://sc.chinaz.com/tupian/qinglvtupian.html        第一页
# https://sc.chinaz.com/tupian/qinglvtupian_page.html   第page页


def hello_message():
    print('*' * 100)
    f = Figlet()
    print(f.renderText('irun2u'))
    print('Name: 站长素材图片下载器')
    print('Verson: 1.0')
    print('Index: http://www.irun2u.top')
    print('*' * 100)


def legal(s):
    if (s[0] != '+') and (s[0] != '-'):  # 无符号位，默认为正数
        return s
    else:  # 有符号位，对去掉符号位的num进行检验
        return s[1:]


def get_page():
    input_start = input('请输入起始页码：')
    input_end = input('请输入结束页码：')
    if not legal(input_start).isdigit() or not legal(input_end).isdigit():
        print('[note: 输入页码必须为数字]')
        # raise Exception('[note: 输入页码必须为数字]')
    else:
        page_start = int(input_start)
        page_end = int(input_end)
        if (page_start < 0) or (page_end < 0):
            print('[note: 页码数必须大于0]')
            # raise Exception('[note: 输入页码必须为数字]')
        elif page_start > page_end:
            print('[note: 起始页码必须小于等于结束页码]')
            # raise Exception('[note: 输入页码必须为数字]')
        else:
            return [page_start, page_end]


def create_request(page):
    if page == 1:
        base_url = 'https://sc.chinaz.com/tupian/qinglvtupian.html'
    else:
        base_url = 'https://sc.chinaz.com/tupian/qinglvtupian_'+ str(page) +'.html'
    headers = {
        'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/111.0.0.0 Safari/537.36'
    }
    _request = request.Request(url=base_url, headers=headers)
    return _request


def get_content(myrequest):
    response = request.urlopen(myrequest)
    content = response.read().decode('utf-8')
    return content


def download_data(page, mycontent):
    # 下载图片  urllib.request.urlretrieve('图片地址','文件的名字')
    tree = etree.HTML(mycontent)
    name_list = tree.xpath('//div[@class="item"]/img/@alt')
    src_list = tree.xpath('//div[@class="item"]/img/@data-original')
    # 一般设计图片的网站都会进行懒加载，等到真正可以看到图片时，src2属性会自动变成img标签的src属性
    if len(name_list) == len(src_list):
        for i in range(len(name_list)):
            name = name_list[i]
            src = src_list[i]
            # print(name, src)

            myurl = 'https:' + src
            mypath = './download/' + str(page) + '/'
            if not os.path.exists(mypath):
                os.makedirs(mypath)
            myfilename = mypath + name + '.jpg'

            print('正在下载第%d页第%d张图片：%s' % (page, i+1, myfilename))
            request.urlretrieve(url=myurl, filename=myfilename)



if __name__ == '__main__':
    start = time.time()
    hello_message()
    pages = get_page()
    if pages is not None:
        page_start = pages[0]
        page_end = pages[1]
        for page in range(page_start, page_end + 1):
            print('开始下载第'+ str(page) +'页')
            myrequest = create_request(page)    # 1、请求对象定制
            mycontent = get_content(myrequest)  # 2、发送请求获取网页源码
            download_data(page, mycontent)      # 3、下载数据到本地
        print('download finished')
    print('It takes', time.time() - start, "seconds.")