import time
import requests
import os
import random
import bs4
from bs4 import BeautifulSoup

# 越多越好
meizi_headers = [
    "Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/39.0.2171.95 Safari/537.36",
    "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_9_2) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/35.0.1916.153 "
    "Safari/537.36",
    "Mozilla/5.0 (Windows NT 6.1; WOW64; rv:30.0) Gecko/20100101 Firefox/30.0",
    "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_9_2) AppleWebKit/537.75.14 (KHTML, like Gecko) Version/7.0.3 "
    "Safari/537.75.14",
    "Mozilla/5.0 (compatible; MSIE 10.0; Windows NT 6.2; Win64; x64; Trident/6.0)",
    'Mozilla/5.0 (Windows; U; Windows NT 5.1; it; rv:1.8.1.11) Gecko/20071127 Firefox/2.0.0.11',
    'Opera/9.25 (Windows NT 5.1; U; en)',
    'Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; .NET CLR 1.1.4322; .NET CLR 2.0.50727)',
    'Mozilla/5.0 (compatible; Konqueror/3.5; Linux) KHTML/3.5.5 (like Gecko) (Kubuntu)',
    'Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.8.0.12) Gecko/20070731 Ubuntu/dapper-security Firefox/1.5.0.12',
    'Lynx/2.8.5rel.1 libwww-FM/2.14 SSL-MM/1.4.1 GNUTLS/1.2.9',
    "Mozilla/5.0 (X11; Linux i686) AppleWebKit/535.7 (KHTML, like Gecko) Ubuntu/11.04 Chromium/16.0.912.77 "
    "Chrome/16.0.912.77 Safari/535.7",
    "Mozilla/5.0 (X11; Ubuntu; Linux i686; rv:10.0) Gecko/20100101 Firefox/10.0",
    'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/54.0.2840.99 Safari/537.36'
]


# 给请求指定一个请求头来模拟浏览器
global headers
headers = {'User-Agent': random.choice(meizi_headers)}

# 爬取地址
global url
url = 'https://www.mzitu.com/'

# 存储位置
global save_path
save_path = 'E:\python\study\day1\save_path'


def create_dir(file_path):
    if os.path.exists(file_path) is False:
        os.makedirs(file_path)

    # 切换当前工作目录
    os.chdir(file_path)


def download(page_no, file_path):
    # 下载逻辑
    # 发送get请求
    global headers
    res_sub = requests.get(page_no, headers=headers)
    # 解析html
    soup_sub = BeautifulSoup(res_sub.text, features="html.parser")

    img_a = soup_sub.find('div', class_="postlist").find_all('a')

    count = 0
    for a in img_a:
        count = count + 1
        if (count % 2) == 0:
            print('内页第几页：' + str(count))

            # 提取href
            href = a.attrs['href']

            print('套图地址：' + href)

            res_sub_1 = requests.get(href, headers=headers)
            soup_sub_1 = BeautifulSoup(res_sub_1.text, features='html.parser')

            try:
                # 获取套图最大数量
                max_page = soup_sub_1.find('div', class_="pagenavi").find_all('span')[6].text
                print('套图数量：' + max_page)

                for j in range(1, int(max_page) + 1):
                    print("子内页第几页：" + str(j))
                    # 等待1至3秒
                    time.sleep(random.randint(1, 3))

                    page_url_sub = href + '/' + str(j)

                    res_sub_2 = requests.get(page_url_sub, headers=headers)
                    soup_sub_2 = BeautifulSoup(res_sub_2.text, features='html.parser')

                    # 解析图片内容
                    img = soup_sub_2.find('div', class_="main-image").find('img')
                    if isinstance(img, bs4.element.Tag):
                        img_src = img.attrs['src']
                        array = img_src.split('/')
                        file_name = array[len(array)-1]
                        # 防盗链加入Referer
                        headers = {'User-Agent': random.choice(meizi_headers), 'Referer': page_url_sub}
                        img = requests.get(img_src, headers=headers)
                        print('开始保存图片')

                        f = open(file_name, 'ab')
                        f.write(img.content)
                        print('图片保存成功')
                        f.close()
            except Exception as e:
                print(e)


def main():
    # 拼接url
    # global url
    # url = url + code + '/detail#/XJLLB'

    # 发送get请求
    res = requests.get(url, headers=headers)

    # 使用自带的解析器解析
    soup = BeautifulSoup(res.text, features="html.parser")

    # 创建文件夹
    create_dir(save_path)

    # 获取首页总页数
    img_max = soup.find('div', class_='nav-links').find_all('a')[3].text

    for i in range(1, int(img_max) + 1):
        # 获取每页的url地址
        if i == 1:
            page_url = url
        else:
            page_url = url + 'page/' + str(i)

        # 文件存放地址
        file_path = save_path + '\\' + str(i)

        # 创建文件路径
        create_dir(file_path)

        # 下载每页图片
        download(page_url, file_path)
        break


if __name__ == '__main__':
    main()