# -*- coding:utf-8 -*-
import os
import requests
from bs4 import BeautifulSoup
from gevent import monkey; monkey.patch_socket()
import gevent

# 指定一个浏览器头
HEADERS = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 \(KHTML, '
                  'like Gecko) Chrome/58.0.3029.110 Safari/537.36'
}
# 代理，免费的代理只能维持一会可能就没用了，自行更换
PROXIES = {
    'http': '111.23.10.27:8080'
}
BASE_DIR = os.path.join(os.path.dirname(os.path.abspath(__file__)), 'imgs')
BASE_URL = 'http://mm.155.pw/xinggan/'

def get_url(page_id):
    """获取页面地址"""
    foot_url = '.html'
    return BASE_URL + str(page_id) + foot_url

def get_html(url):
    """发出请求获得HTML源码的函数"""
    try:
        # Requests库的get请求
        resp = requests.get(url, headers=HEADERS).text
    except:
        # 如果请求被阻，就使用代理
        resp = requests.get(url, headers=HEADERS, proxies=PROXIES).text
    return resp

def main(page_id):
    """遍历所有网址图片存入数组"""
    # for url in all_page(start, end):
    url = get_url(page_id)
    soup = BeautifulSoup(get_html(url), 'lxml')
    arr = soup.find_all('img', 'post-item-img')
    path = soup.head.title.string.split(' ')[0]
    isExists = os.path.exists(os.path.join(BASE_DIR, path))
    # 如果不存在
    if not isExists:
        print('makedir', path)
        # 创建文件夹
        os.makedirs(os.path.join(BASE_DIR, path))
    # 如果存在了就返回False
    else:
        print(path, 'already exists')
    # 切换到创建的文件夹
    os.chdir(os.path.join(BASE_DIR, path))
    for img in arr:
        urls = img['data-original']
        imgs = requests.get(urls)
        path1 = urls.split('/')[-1]
        with open(path1, 'wb') as path:
            path.write(imgs.content)
        print('成功' + ':' + path1)

if __name__ == '__main__':
    for i in range(2101, 2105):
        g = gevent.spawn(main, i)
        g.join()