import os # python自带扩展不需要安装
import requests   # pip install requests
from urllib import request  # python自带扩展不需要安装
from bs4 import BeautifulSoup  # 安装命令：pip install bs4

#!/usr/bin/env python
# -*- coding: utf-8 -*-
# @Time    : 2021/06/06 14:48
# @Author  : Liu
# @Site    : 
# @File    : 美图小姐姐.py
# @Software: PyCharm

import requests
import time
import os
import re
from urllib import request
from bs4 import BeautifulSoup

url_address = "https://www.umei.cc"

def get_url_path(url):
    """
    获取地址内容信息
    :param url:
    :return:
    """
    # time.sleep(1)  # 获取源码的时候睡眠一秒
    obj = requests.get(url)
    obj.encoding = obj.apparent_encoding
    return obj.text


def get_page_info():
    """
    抓取每页信息
    :return:
    """
    nums = int(input("输入抓取的页数："))
    for i in range(nums):
        if i < 1:
            url = f"{ url_address }/meinvtupian/meinvxiezhen/"
        else:
            url = f"{ url_address }/meinvtupian/meinvxiezhen/index_{i + 1}.htm"
        ret = get_url_path(url)  # 获取页面信息
        get_bs4(ret)  # 逐页抓取页面信息
        print(f"第{i+1}页完成")
    pass


def get_bs4(ret):
    soup = BeautifulSoup(ret, "html.parser")
    li_list = soup.select(".TypeList")[0].find_all(name="li")
    for i in li_list:
        # 先获取第一张图片
        img_src = url_address + i.a["href"]
        ret1 = get_url_path(img_src)  # 获取页面信息
        get_image_info(ret1, i.a.span.string, 1)

        # print(ret1)

        # 获取分页后的页面图片数量
        # script_reg = r'<script type="text\/javascript">Next\("\d+","(?P<num>\d+)",.*?\)<\/script>'
        script_reg = r'<a href="/meinvtupian/meinvxiezhen/(?P<num>[0-9_]+).htm">尾页</a>'
        num_str = re.search(script_reg, ret1, re.S).group("num")
        page_num = int(num_str.split("_")[1])  # 获取图片数量

        img_lst = os.path.basename(i.a["href"]).split(".")  # 获取图片的后缀
        img_dir = os.path.dirname(i.a["href"])   # 获取图片的地址路径
        for j in range(2, page_num+1):
            img_src = f"{ url_address }{img_dir}/{img_lst[0]}_{j}.{img_lst[1]}"
            res = get_url_path(img_src)  # 获取页面信息
            get_image_info(res, i.a.span.string, j)


def get_image_info(ret, name, i):
    soup = BeautifulSoup(ret, "html.parser")
    img = soup.select(".ImageBody img")[0]
    image_path = img["src"]  # 获取图片地址
    image_name = name  # 获取图片中文所属
    img_name = f"{image_name}_{i}.{os.path.basename(image_path).split('.')[1]}"  # 获取图片真实名字
    # 图片存储
    image_dir = f"girl/{image_name}"
    if not os.path.isdir(image_dir):
        os.makedirs(image_dir)
    # 远程打开图片写入到本地  第一种方式open
    # with open(f"{image_dir}/{img_name}", mode="wb") as add:
    #     add.write(requests.get(image_path).content)
    # 远程打开图片写入到本地  第二种方式urllib
    request.urlretrieve(image_path, filename=f"{image_dir}/{img_name}")


print("已经开始执行了,可能需要等待一会，请您耐心等待！")
begin_time = int(time.time())
get_page_info()
end_time = int(time.time())
print(f"当前脚本执行了{end_time - begin_time}秒")
print("执行已经结束了")

import os
import requests
from bs4 import BeautifulSoup
from urllib import request

url_address = 'https://www.umei.cc'
list_url = url_address + '/meinvtupian/meinvxiezhen/'
obj = requests.get(list_url)
obj.encoding = obj.apparent_encoding
content = obj.text

# 格式化页面
soup = BeautifulSoup(content, 'html.parser')
li_soup = soup.select(".TypeList")[0].findAll("li")
dir = "./girls/"
for i in li_soup:
    if not os.path.isdir(dir):
        os.makedirs(dir)
    img_path = i.img["src"]
    img_suffix = os.path.basename(img_path).split('.')[1]
    img_url = dir + i.span.string + '.' + img_suffix
    request.urlretrieve(img_path, img_url)