/**
 * @author: 个人姓名
 * @date: ${DATE} ${TIME}
 * @className: ${NAME}
 * @description:
 */

#!/usr/bin/env python
# -*- coding: utf-8 -*-
import asyncio
import aiohttp
import time
from pyquery import PyQuery as pq
import sys
import codecs
import json


async def get_post_url(url):
    '''
    得到每一页的所有链接
    '''
    async with aiohttp.ClientSession() as client:
        async with client.get(url) as response:
            body = await response.text(encoding="utf-8")
            # print(body)
            post_list = parser(body)
            for post_url in post_list:
                post = {}
                post["url"] = post_url
                post_urls.append(post_url)


async def get_post_info(url):
    '''
    根据链接得到标题 作者 发帖时间等内容
    '''
    async with aiohttp.ClientSession() as client:
        async with client.get(url) as response:
            body = await response.text(encoding="utf-8")
            post_info = paser_post(body)
            if post_info is not None:
                post_info["url"] = url
                post_lists.append(post_info)


def paser_post(html):
    '''
    解析列表页
    '''
    post_info = {}
    doc = pq(html)
    main_post = doc('div#tpc')
    post_author = main_post.find('div.author a.u').text()
    post_time = main_post.find('div.author span.stime').text()
    post_title = doc('h1#j_data').text()
    post_info["title"] = post_title
    post_info['time'] = post_time
    post_info['author'] = post_author
    if not post_title and not post_time and not post_author:
        return None
    return post_info


def parser(html):
    '''
    解析帖子页
    '''
    post_list = []
    doc = pq(html)
    links_item = doc('table[id="pl"]').find('tbody').find('tr[mid]')
    for link_item in links_item.items():
        post_link = link_item.find('td.p_title').find('a').attr('href')
        post_link = "https://bbs.hupu.com" + post_link
        post_list.append(post_link)
    return post_list


# 得到开始时间
start_time = time.time()
# 存储数据的列表
post_lists = []
# 每一个帖子链接的列表
post_urls = []
# 创建时间循环
loop = asyncio.get_event_loop()

# 将步行街前一百的链接加入事件循环, 同时访问这100页, 得到所有的帖子链接
urls = [
    "https://bbs.hupu.com/bxj-postdate-{}".format(i) for i in range(1, 101)]
tasks = [get_post_url(url) for url in urls]
loop.run_until_complete(asyncio.wait(tasks))
# 输出帖子总数
print(len(post_urls))
# 将所有帖子链接加入事件循环, 得要内容
for i in range(0, len(post_urls), 1000):
    lenth = len(post_urls) - i
    if lenth >= 1000:
        lenth = 1000
    print(i)
    end_time = time.time()
    print("cast time", end_time - start_time)
    tasks = [get_post_info(post_urls[num + i]) for num in range(lenth)]
    loop.run_until_complete(asyncio.wait(tasks))
loop.close()

# 存储所有数据.
post_dicts = {"posts": post_lists, "lenth": len(post_lists)}
with codecs.open("post.json", "w", "utf-8") as f:
    f.write(json.dumps(post_dicts, indent=True))
end_time = time.time()

print("cast time", end_time - start_time)

{
    "version": "0.1.0",
    "command": "python",
    "isShellCommand": true,
    "args": ["${file}"],
    "showOutput": "always",
    "options":
        {
        "env":
            {
            "PYTHONIOENCODING": "UTF-8"
            }
        }
}

// 将设置放入此文件中以覆盖默认设置
{
    "window.zoomLevel": 2,
    //字号
    "editor.fontSize": 14,
    // 字体
    "editor.fontFamily": "Hack, Menlo, Monaco, 'Courier New', monospace",
    //80个字符的提示线
    "editor.rulers": [80],
    "editor.acceptSuggestionOnEnter": true,
    // Arguments passed in. Each argument is a separate item in the array.
    //pep8自动格式化
    "python.formatting.autopep8Args":[
        "--max-line-length=80",
        "--indent-size=4"
    ],

    // Format the document upon saving. 保存文件后自动格式化
    "python.formatting.formatOnSave": true,
    // 忽略的pep8提示
    "python.linting.pylintArgs": [
        "--include-naming-hint=n",
        "--disable=W0311",
        "--disable=C0103",
        "--disable=E1101",
        "--disable=C0111",
        "--disable=W0621"
    ],
    //去除尾部的空格
    "files.trimTrailingWhitespace": true,
    //失去焦点时自动保存
    "files.autoSave": "onFocusChange",
    //显示缩进空格
      "editor.renderWhitespace": "boundary",
    "editor.renderLineHighlight": "line",
   //忽略的文件
  "files.exclude": {
    "**/.git": true,
    "**/.svn": true,
    "**/.hg": true,
    "**/.DS_Store": true,
        ".vscode": true,
        "**/__pycache__": true,
        "**/**/*.pyc": true
  },
  //关闭显示打开的文件
  "explorer.openEditors.visible": 0,
  //关闭回车的自动补全
    "editor.acceptSuggestionOnEnter": false


}

softwareupdate --ignore ThunderboltFirmwareUpdate1.2

xcode-select --install

sh -c "$(curl -fsSL https://raw.github.com/robbyrussell/oh-my-zsh/master/tools/install.sh)"

PROMPT=$'%{$purple%}%n%{$reset_color%} in %{$limegreen%}%~%{$reset_color%}$(ruby_prompt_info " with%{$fg[red]%} " v g "%{$reset_color%}")$vcs_info_msg_0_%{$orange%}%{$reset_color%} at %{$hotpink%}%* %{$orange%}
λ%{$reset_color%} '

ruby -e "$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/master/install)"

brew install tree
brew install git
brew install openssl
brew python3
brew mysql

sudo easy_install pip

mkdir ~/.pip/
cd ~/.pip/
subl pip.conf

[global]
trusted-host = pypi.douban.com
index-url = http://pypi.douban.com/simple/

ssh-keygen -t rsa -C "your_email@example.com"

cd ~/.ssh
subl id_rsa.pub

ssh -T git@github.com

git config --global user.name "用户名"
git config --global user.email "邮箱地址"

npm install -g hexo-cli

hexo init mrxin.github.io
cd mrxin.github.io
npm install

deploy:
  type: git
  repository: https://github.com/MrXin/MrXin.github.io.git
  branch: master

npm install hexo-deployer-git --save

hexo g
hexo d

npm install hexo-generator-feed@1 --save

cd /usr/local/share/
sudo chmod -R 755 zsh
sudo chown -R root:staff zsh

#!/usr/bin/env python
# -*- coding: utf-8 -*-

import requests
from bs4 import BeautifulSoup

url = 'http://list.jd.com/list.html?cat=9987%2C653%2C655&page=1'
req = requests.get(url)


soup = BeautifulSoup(req.text, "html.parser")
items = soup.select('li.gl-item')
# print len(items)
for item in items:
    sku = item.find('div')['data-sku']
    print sku,
    price_url = 'http://p.3.cn/prices/mgets?skuIds=J_' + str(sku)
    price = requests.get(price_url).json()[0]['p']
    print price,
    nameinfo = item.find('div', class_="p-name").find('a')
    name = nameinfo['title']
    item_url = 'http:' + nameinfo['href']
    print name, item_url,
    commit = item.find('div', class_="p-commit").find('a')
    if commit:
        print commit.get_text()

http://p.3.cn/prices/mgets?skuIds=J_ + skuId

http://c0.3.cn/stock?skuId=965009&cat=652,829,854&area=1_2812_51141_0&extraParam={"originid":"1"}

http://item.m.jd.com/ware/thirdAddress.json?address=jd1356&wareId=965009&provinceId=1&cityId=2812&countryId=51141

http://pe.3.cn/prices/pcpmgets?skuids=965012&origin=5&area=1_2812_51141