import requests

from lxml import etree

import os

# etree解析网页并返回

def parse(url):

headers = {

'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.88 Safari/537.36'

}

text = requests.get(url=url, headers=headers).text

html = etree.HTML(text)

return html

# 获取总页面数

def get_page(base_url):

html = parse(base_url)

pages = html.xpath('//div[@class="main"]//div[@class="pages"]/div/a[@class="num"][last()]/text()')[0]

return pages

# 获取每页超链接的url

def get_a_url(page_url):

html = parse(page_url)

a_url = html.xpath('//div[@class="w1180 clearfix"]//div[@class="tab_tj"]//ul[@class="clearfix"]//a/@href')

return a_url

#  获取每个超链接对应图片组的个数

def get_img_count(a_url):

html = parse(a_url)

img_count = len(html.xpath('//ul[@id="scroll"]/li'))

return img_count

# 获取每个超链接对应图片组的个数的url

def get_img_url(img_page_url):

html = parse(img_page_url)

img_url = html.xpath('//img[@class="pic-large"]/@src')[0]

return img_url

# 保存图片

def save_img(img_url, name):

headers = {

'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.88 Safari/537.36'

}

img_name = img_url.split('/')[-1]

res = requests.get(url=img_url, headers=headers)

img_data = res.content

if not os.path.isdir(f'.\\{name}_img'):

os.mkdir(f'.\\{name}_img')

with open(f'.\\{name}_img\\{img_name}', 'wb') as f:

f.write(img_data)

# 主函数

def main():

name = input("请输入想要下载的爱豆姓名：")

pinyin = input("请输入对应的汉语拼音：")

# 蔡徐坤是例外，单独处理

if name == '蔡徐坤':

pinyin = 'Angy'

base_url = f'http://www.win4000.com/mt/{pinyin}.html'

# 获取总页面数

try:

page_count = get_page(base_url)

except:

print("没有找到您的爱豆，要不换一个下载试试^_^")

exit()

# 获取用户想要下载的页面数

try:

page_num = int(input(f"爬取到该爱豆图片共【{page_count}】页，请输入想要下载的页数："))

except:

print("输入数字都能错？？？，搁这玩我呢…………")

exit()

# 判断用户输入是否合法

if page_num > int(page_count) or page_num < 1:

print(f"你想上天啊，总共就 {page_count} 页，你输 {page_num} 想死啊 %￥#&……*&$^")

else:

try:

# 遍历下载页面

for i in range(1, page_num+1):

page_url = f'http://www.win4000.com/mt/{pinyin}_{str(i)}.html'

a_url_list = get_a_url(page_url)

print(f"第【{i}】页获取成功" + '\n')

a_url_list_len = len(a_url_list)

print(f"第【{i}】页共有[{a_url_list_len}]组图片")

a_count = int(input(f"你想下载第【{i}】页多少组图片呢？"))

# 遍历每页的每组图片

for group in range(a_count):

# 获取每页对应图片组的个数

img_count = get_img_count(a_url_list[group])

print(f"第【{i}】页第[{group+1}]组图片爬取中……" + '\n')

# 遍历每个组对应图片的url

for j in range(1, img_count+1):

img_page_url = os.path.splitext(a_url_list[group])[0] + f'_{j}' + os.path.splitext(a_url_list[group])[1]

img_url = get_img_url(img_page_url)

print(f"第【{i}】页第[{group+1}]组图片下载成功，正在保存该组第 {j} 张图片")

save_img(img_url, name)

print(f"第【{i}】页第[{group+1}]组图片保存成功" + "o(*^＠^*)o" + '\n')

print(f"第【{i}】页下载完成" + "`(*>﹏

print(f"您的爱豆 {name} 图片 {page_num} 页下载完成，图片保存在当前文件夹下的 {name}_img 文件夹下")

input("按回车退出程序")

except:

print("未知错误，爬取失败。。。")

exit()

main()