├── .gitignore
├── Docker
    ├── Dockerfile
    └── requirements.txt
├── MyShow
    ├── GetData_zhihu.py
    ├── MyShow.py
    ├── static
    │   ├── css
    │   │   └── dashboard.css
    │   ├── favicon.ico
    │   └── js
    │   │   ├── bootstrap-typeahead.min.js
    │   │   ├── bootstrap.min.js
    │   │   ├── echarts.min.js
    │   │   └── jquery-3.0.0.min.js
    └── templates
    │   ├── base.html
    │   ├── error.html
    │   └── index.html
├── README.md
├── Text
    ├── Obama.txt
    ├── Walden.txt
    └── Zarathustra.txt
├── python_aiohttp.py
├── python_base.py
├── python_context.py
├── python_coroutine.py
├── python_csv.py
├── python_datetime.py
├── python_decorator.py
├── python_flask.py
├── python_functional.py
├── python_lda.py
├── python_magic_methods.py
├── python_markov_chain.py
├── python_metaclass.py
├── python_numpy.py
├── python_oneline.py
├── python_requests.py
├── python_restful_api.py
├── python_spider.py
├── python_sqlalchemy.py
├── python_thread_multiprocess.py
├── python_version36.py
├── python_visual.py
├── python_visual_animation.py
├── python_wechat.py
└── python_weibo.py


/.gitignore:
--------------------------------------------------------------------------------
 1 | # Created by .ignore support plugin (hsz.mobi)
 2 | *.[oa]
 3 | *.py[co]
 4 | *.exe
 5 | *.log
 6 | *.out
 7 | *.dat
 8 | *.temp
 9 | *.png
10 | *.pkl
11 | *.mp3
12 | *.mp4
13 | *.csv
14 | .*
15 | 
16 | test/
17 | data/
18 | build/
19 | captcha.jpeg
20 | 


--------------------------------------------------------------------------------
/Docker/Dockerfile:
--------------------------------------------------------------------------------
 1 | # Dockerfile by xianhu: build a docker image
 2 | # centos6:
 3 | #         docker build -t user/centos6 .
 4 | #         docker run -it --name test [-p -v] user/centos6
 5 | #         docker attach test
 6 | # centos7:
 7 | #         docker build -t user/centos7 .
 8 | #         docker run -dt --privileged --name test [-p -v] user/centos7
 9 | #         docker exec -it test /bin/bash
10 | 
11 | FROM centos:6.9
12 | MAINTAINER xianhu <qixianhu@qq.com>
13 | 
14 | # change system environments
15 | ENV LANG en_US.UTF-8
16 | ENV LC_ALL en_US.UTF-8
17 | 
18 | # change system local time
19 | RUN ln -sf /usr/share/zoneinfo/Asia/Shanghai /etc/localtime
20 | 
21 | # fix: warning: rpmts_HdrFromFdno
22 | RUN rpm --import /etc/pki/rpm-gpg/RPM*
23 | 
24 | # update yum and install something
25 | RUN yum update -y
26 | RUN yum install -y xz
27 | RUN yum install -y vim
28 | RUN yum install -y git
29 | RUN yum install -y gcc
30 | RUN yum install -y make
31 | RUN yum install -y wget
32 | RUN yum install -y screen
33 | RUN yum install -y gcc-c++
34 | RUN yum install -y crontabs
35 | RUN yum install -y zlib-devel
36 | RUN yum install -y sqlite-devel
37 | RUN yum install -y openssl-devel
38 | 
39 | # install python
40 | RUN yum install -y https://centos6.iuscommunity.org/ius-release.rpm
41 | # RUN yum install -y https://centos7.iuscommunity.org/ius-release.rpm
42 | RUN yum install -y python36u
43 | RUN yum install -y python36u-pip
44 | RUN yum install -y python36u-devel
45 | 
46 | # install nginx
47 | RUN yum install -y epel-release
48 | RUN yum install -y nginx
49 | 
50 | # clean yum cache
51 | RUN yum clean all
52 | 
53 | # install libs of python3
54 | ADD ./requirements.txt /root/
55 | WORKDIR /root/
56 | RUN pip3.6 install --upgrade pip
57 | RUN pip3.6 install -r requirements.txt
58 | 
59 | # clean everything
60 | RUN rm -rf /root/*
61 | 
62 | # centos6
63 | CMD /bin/bash
64 | 
65 | # centos7
66 | # ENTRYPOINT /usr/sbin/init
67 | 


--------------------------------------------------------------------------------
/Docker/requirements.txt:
--------------------------------------------------------------------------------
 1 | virtualenv
 2 | pylint
 3 | lxml
 4 | html5lib
 5 | xmltodict
 6 | pybloom_live
 7 | fake-useragent
 8 | beautifulsoup4
 9 | aiohttp
10 | requests
11 | redis
12 | PyMySQL
13 | elasticsearch
14 | Flask
15 | Flask-WTF
16 | Flask-Mail
17 | Flask-Login
18 | Flask-Moment
19 | Flask-Script
20 | Flask-RESTful
21 | Flask-Migrate
22 | Flask-HTTPAuth
23 | Flask-Bootstrap
24 | Flask-SQLAlchemy
25 | gunicorn
26 | uWSGI
27 | numpy
28 | scipy
29 | matplotlib
30 | pandas
31 | scikit-learn
32 | jupyter
33 | 


--------------------------------------------------------------------------------
/MyShow/GetData_zhihu.py:
--------------------------------------------------------------------------------
 1 | # _*_ coding: utf-8 _*_
 2 | 
 3 | import pymysql
 4 | 
 5 | con = pymysql.connect(host="xxxx", user="root", passwd="xxxx", db="xxxx", charset="utf8")
 6 | cursor = con.cursor()
 7 | con.autocommit(1)
 8 | 
 9 | 
10 | def get_all_topics():
11 |     cursor.execute("select distinct t_topic_id, t_topic_name from t_zhihutopics where t_topic_haschildren = 1;")
12 |     return [item for item in cursor.fetchall() if item[0].strip()]
13 | 
14 | 
15 | def get_topic_data(topic_id, topic_name):
16 |     data_dict = {
17 |         "type": "force",
18 |         "nodes": [
19 |             {"id": topic_id, "name": topic_name, "level": 0}
20 |         ],
21 |         "links": []
22 |     }
23 | 
24 |     nodes_set = set([topic_id])
25 |     dai_ids = set([topic_id])
26 |     while dai_ids:
27 |         cursor.execute("select * from t_zhihutopics where t_topic_parentid = %s;", [dai_ids.pop()])
28 |         for item in cursor.fetchall():
29 |             _, t_id, t_name, t_pid, t_haschild, _ = item
30 | 
31 |             if t_id not in nodes_set:
32 |                 nodes_set.add(t_id)
33 |                 data_dict["nodes"].append({"id": t_id, "name": t_name, "level": 1 if t_pid == topic_id else 2})
34 |             data_dict["links"].append({"source": t_pid, "target": t_id})
35 | 
36 |             if t_haschild == 1:
37 |                 dai_ids.add(t_id)
38 |     return data_dict
39 | 


--------------------------------------------------------------------------------
/MyShow/MyShow.py:
--------------------------------------------------------------------------------
  1 | # _*_ coding: utf-8 _*_
  2 | 
  3 | import logging
  4 | import GetData_zhihu
  5 | 
  6 | # flask
  7 | from flask import Flask, session, request
  8 | from flask import render_template, flash, redirect, url_for, jsonify
  9 | 
 10 | # flask extends
 11 | from flask_bootstrap import Bootstrap
 12 | from flask_wtf import FlaskForm
 13 | from wtforms import StringField, PasswordField, SubmitField
 14 | from wtforms.validators import Length, Email
 15 | 
 16 | # application
 17 | app = Flask(__name__)
 18 | app.config["SECRET_KEY"] = "hard to guess string"
 19 | 
 20 | # manager and bootstrap
 21 | bootstrap = Bootstrap(app=app)
 22 | 
 23 | # global data
 24 | zhihu_all_topics = GetData_zhihu.get_all_topics()
 25 | zhihu_all_topics_key = {}
 26 | zhihu_init_topics = GetData_zhihu.get_topic_data(topic_id="19559424", topic_name="数据分析")
 27 | 
 28 | 
 29 | # form class
 30 | class UserForm(FlaskForm):
 31 |     name = StringField("name", validators=[Email(message="邮箱格式不正确！")])
 32 |     password = PasswordField("password",  validators=[Length(min=6, message="密码长度至少6位！")])
 33 |     submit = SubmitField("提 交")
 34 | 
 35 | 
 36 | @app.route("/", methods=["GET", "POST"])
 37 | def temp():
 38 |     return redirect(url_for("index"))
 39 | 
 40 | 
 41 | @app.route("/index/", methods=["GET", "POST"])
 42 | def index():
 43 |     user_form = UserForm()
 44 |     if request.method == "POST":
 45 |         if user_form.validate_on_submit():
 46 |             session["username"] = user_form.name.data
 47 |         else:
 48 |             flash(user_form.errors["name"][0] if "name" in user_form.errors else user_form.errors["password"][0])
 49 |     else:
 50 |         if request.args.get("action") == "login_out":
 51 |             flash("您已成功退出系统！")
 52 |             session["username"] = None
 53 |             return redirect(url_for("index"))
 54 |         elif request.args.get("action") == "overview":
 55 |             session["page_type"] = "overview"
 56 |             return redirect(url_for("index"))
 57 |         elif request.args.get("action") == "zhihu_topics":
 58 |             session["page_type"] = "zhihu_topics"
 59 |             return redirect(url_for("index"))
 60 |     return render_template("index.html", name=session.get("username"), page_type=session.get("page_type", "overview"), form=user_form)
 61 | 
 62 | 
 63 | @app.route("/zhihu_get_topics_list/", methods=["post"])
 64 | def zhihu_get_topics_list():
 65 |     key = request.form.get("key")
 66 |     result = {"success": 1, "data": []}
 67 |     if key:
 68 |         if key in zhihu_all_topics_key:
 69 |             result = zhihu_all_topics_key[key]
 70 |         else:
 71 |             for item in zhihu_all_topics:
 72 |                 if item[1].find(key) >= 0:
 73 |                     result["data"].append({"id": item[0], "name": item[1]})
 74 |             if len(result["data"]) > 0:
 75 |                 result["success"] = 1
 76 |                 zhihu_all_topics_key[key] = result
 77 |                 logging.debug("all_topics_key increase: %s", len(zhihu_all_topics_key))
 78 |     return jsonify(result)
 79 | 
 80 | 
 81 | @app.route("/zhihu_get_topics_data/", methods=["post"])
 82 | def zhihu_get_topics_data():
 83 |     if request.form["id"] == "19554449":
 84 |         result = zhihu_init_topics
 85 |     else:
 86 |         result = GetData_zhihu.get_topic_data(request.form["id"], request.form["name"])
 87 |     return jsonify(result)
 88 | 
 89 | 
 90 | @app.errorhandler(404)
 91 | def page_not_found(excep):
 92 |     return render_template("error.html", error=excep, name=session.get("username")), 404
 93 | 
 94 | 
 95 | # main process
 96 | if __name__ == "__main__":
 97 |     logging.basicConfig(level=logging.DEBUG, format="%(asctime)s\t%(levelname)s\t%(message)s")
 98 |     logging.debug("app url_map: %s", app.url_map)
 99 | 
100 |     app.run()
101 | 


--------------------------------------------------------------------------------
/MyShow/static/css/dashboard.css:
--------------------------------------------------------------------------------
  1 | /*
  2 |  * Base structure
  3 |  */
  4 | 
  5 | /* Move down content because we have a fixed navbar that is 50px tall */
  6 | body {
  7 |   padding-top: 50px;
  8 | }
  9 | 
 10 | 
 11 | /*
 12 |  * Global add-ons
 13 |  */
 14 | 
 15 | .sub-header {
 16 |   padding-bottom: 10px;
 17 |   border-bottom: 1px solid #eee;
 18 | }
 19 | 
 20 | /*
 21 |  * Top navigation
 22 |  * Hide default border to remove 1px line.
 23 |  */
 24 | .navbar-fixed-top {
 25 |   border: 0;
 26 | }
 27 | 
 28 | /*
 29 |  * Sidebar
 30 |  */
 31 | 
 32 | /* Hide for mobile, show later */
 33 | .sidebar {
 34 |   display: none;
 35 | }
 36 | @media (min-width: 768px) {
 37 |   .sidebar {
 38 |     position: fixed;
 39 |     top: 51px;
 40 |     bottom: 0;
 41 |     left: 0;
 42 |     z-index: 1000;
 43 |     display: block;
 44 |     padding: 20px;
 45 |     overflow-x: hidden;
 46 |     overflow-y: auto; /* Scrollable contents if viewport is shorter than content. */
 47 |     background-color: #f5f5f5;
 48 |     border-right: 1px solid #eee;
 49 |   }
 50 | }
 51 | 
 52 | /* Sidebar navigation */
 53 | .nav-sidebar {
 54 |   margin-right: -21px; /* 20px padding + 1px border */
 55 |   margin-bottom: 20px;
 56 |   margin-left: -20px;
 57 | }
 58 | .nav-sidebar > li > a {
 59 |   padding-right: 20px;
 60 |   padding-left: 20px;
 61 | }
 62 | .nav-sidebar > .active > a,
 63 | .nav-sidebar > .active > a:hover,
 64 | .nav-sidebar > .active > a:focus {
 65 |   color: #fff;
 66 |   background-color: #428bca;
 67 | }
 68 | 
 69 | 
 70 | /*
 71 |  * Main content
 72 |  */
 73 | 
 74 | .main {
 75 |   padding: 20px;
 76 | }
 77 | @media (min-width: 768px) {
 78 |   .main {
 79 |     padding-right: 40px;
 80 |     padding-left: 40px;
 81 |   }
 82 | }
 83 | .main .page-header {
 84 |   margin-top: 0;
 85 | }
 86 | 
 87 | 
 88 | /*
 89 |  * Placeholder dashboard ideas
 90 |  */
 91 | 
 92 | .placeholders {
 93 |   margin-bottom: 30px;
 94 |   text-align: center;
 95 | }
 96 | .placeholders h4 {
 97 |   margin-bottom: 0;
 98 | }
 99 | .placeholder {
100 |   margin-bottom: 20px;
101 | }
102 | .placeholder img {
103 |   display: inline-block;
104 |   border-radius: 50%;
105 | }
106 | 


--------------------------------------------------------------------------------
/MyShow/static/favicon.ico:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/jackfrued/LearnPython/5477a83c8294243995460ff3bafe105f2a4e372f/MyShow/static/favicon.ico


--------------------------------------------------------------------------------
/MyShow/static/js/bootstrap-typeahead.min.js:
--------------------------------------------------------------------------------
1 | (function(root,factory){"use strict";if(typeof module!=="undefined"&&module.exports){module.exports=factory(require("jquery"))}else if(typeof define==="function"&&define.amd){define(["jquery"],function($){return factory($)})}else{factory(root.jQuery)}})(this,function($){"use strict";var Typeahead=function(element,options){this.$element=$(element);this.options=$.extend({},$.fn.typeahead.defaults,options);this.matcher=this.options.matcher||this.matcher;this.sorter=this.options.sorter||this.sorter;this.select=this.options.select||this.select;this.autoSelect=typeof this.options.autoSelect=="boolean"?this.options.autoSelect:true;this.highlighter=this.options.highlighter||this.highlighter;this.render=this.options.render||this.render;this.updater=this.options.updater||this.updater;this.displayText=this.options.displayText||this.displayText;this.source=this.options.source;this.delay=this.options.delay;this.$menu=$(this.options.menu);this.$appendTo=this.options.appendTo?$(this.options.appendTo):null;this.fitToElement=typeof this.options.fitToElement=="boolean"?this.options.fitToElement:false;this.shown=false;this.listen();this.showHintOnFocus=typeof this.options.showHintOnFocus=="boolean"||this.options.showHintOnFocus==="all"?this.options.showHintOnFocus:false;this.afterSelect=this.options.afterSelect;this.addItem=false;this.value=this.$element.val()||this.$element.text()};Typeahead.prototype={constructor:Typeahead,select:function(){var val=this.$menu.find(".active").data("value");this.$element.data("active",val);if(this.autoSelect||val){var newVal=this.updater(val);if(!newVal){newVal=""}this.$element.val(this.displayText(newVal)||newVal).text(this.displayText(newVal)||newVal).change();this.afterSelect(newVal)}return this.hide()},updater:function(item){return item},setSource:function(source){this.source=source},show:function(){var pos=$.extend({},this.$element.position(),{height:this.$element[0].offsetHeight});var scrollHeight=typeof this.options.scrollHeight=="function"?this.options.scrollHeight.call():this.options.scrollHeight;var element;if(this.shown){element=this.$menu}else if(this.$appendTo){element=this.$menu.appendTo(this.$appendTo);this.hasSameParent=this.$appendTo.is(this.$element.parent())}else{element=this.$menu.insertAfter(this.$element);this.hasSameParent=true}if(!this.hasSameParent){element.css("position","fixed");var offset=this.$element.offset();pos.top=offset.top;pos.left=offset.left}var dropup=$(element).parent().hasClass("dropup");var newTop=dropup?"auto":pos.top+pos.height+scrollHeight;var right=$(element).hasClass("dropdown-menu-right");var newLeft=right?"auto":pos.left;element.css({top:newTop,left:newLeft}).show();if(this.options.fitToElement===true){element.css("width",this.$element.outerWidth()+"px")}this.shown=true;return this},hide:function(){this.$menu.hide();this.shown=false;return this},lookup:function(query){var items;if(typeof query!="undefined"&&query!==null){this.query=query}else{this.query=this.$element.val()||this.$element.text()||""}if(this.query.length<this.options.minLength&&!this.options.showHintOnFocus){return this.shown?this.hide():this}var worker=$.proxy(function(){if($.isFunction(this.source)){this.source(this.query,$.proxy(this.process,this))}else if(this.source){this.process(this.source)}},this);clearTimeout(this.lookupWorker);this.lookupWorker=setTimeout(worker,this.delay)},process:function(items){var that=this;items=$.grep(items,function(item){return that.matcher(item)});items=this.sorter(items);if(!items.length&&!this.options.addItem){return this.shown?this.hide():this}if(items.length>0){this.$element.data("active",items[0])}else{this.$element.data("active",null)}if(this.options.addItem){items.push(this.options.addItem)}if(this.options.items=="all"){return this.render(items).show()}else{return this.render(items.slice(0,this.options.items)).show()}},matcher:function(item){var it=this.displayText(item);return~it.toLowerCase().indexOf(this.query.toLowerCase())},sorter:function(items){var beginswith=[];var caseSensitive=[];var caseInsensitive=[];var item;while(item=items.shift()){var it=this.displayText(item);if(!it.toLowerCase().indexOf(this.query.toLowerCase()))beginswith.push(item);else if(~it.indexOf(this.query))caseSensitive.push(item);else caseInsensitive.push(item)}return beginswith.concat(caseSensitive,caseInsensitive)},highlighter:function(item){var html=$("<div></div>");var query=this.query;var i=item.toLowerCase().indexOf(query.toLowerCase());var len=query.length;var leftPart;var middlePart;var rightPart;var strong;if(len===0){return html.text(item).html()}while(i>-1){leftPart=item.substr(0,i);middlePart=item.substr(i,len);rightPart=item.substr(i+len);strong=$("<strong></strong>").text(middlePart);html.append(document.createTextNode(leftPart)).append(strong);item=rightPart;i=item.toLowerCase().indexOf(query.toLowerCase())}return html.append(document.createTextNode(item)).html()},render:function(items){var that=this;var self=this;var activeFound=false;var data=[];var _category=that.options.separator;$.each(items,function(key,value){if(key>0&&value[_category]!==items[key-1][_category]){data.push({__type:"divider"})}if(value[_category]&&(key===0||value[_category]!==items[key-1][_category])){data.push({__type:"category",name:value[_category]})}data.push(value)});items=$(data).map(function(i,item){if((item.__type||false)=="category"){return $(that.options.headerHtml).text(item.name)[0]}if((item.__type||false)=="divider"){return $(that.options.headerDivider)[0]}var text=self.displayText(item);i=$(that.options.item).data("value",item);i.find("a").html(that.highlighter(text,item));if(text==self.$element.val()){i.addClass("active");self.$element.data("active",item);activeFound=true}return i[0]});if(this.autoSelect&&!activeFound){items.filter(":not(.dropdown-header)").first().addClass("active");this.$element.data("active",items.first().data("value"))}this.$menu.html(items);return this},displayText:function(item){return typeof item!=="undefined"&&typeof item.name!="undefined"&&item.name||item},next:function(event){var active=this.$menu.find(".active").removeClass("active");var next=active.next();if(!next.length){next=$(this.$menu.find("li")[0])}next.addClass("active")},prev:function(event){var active=this.$menu.find(".active").removeClass("active");var prev=active.prev();if(!prev.length){prev=this.$menu.find("li").last()}prev.addClass("active")},listen:function(){this.$element.on("focus",$.proxy(this.focus,this)).on("blur",$.proxy(this.blur,this)).on("keypress",$.proxy(this.keypress,this)).on("input",$.proxy(this.input,this)).on("keyup",$.proxy(this.keyup,this));if(this.eventSupported("keydown")){this.$element.on("keydown",$.proxy(this.keydown,this))}this.$menu.on("click",$.proxy(this.click,this)).on("mouseenter","li",$.proxy(this.mouseenter,this)).on("mouseleave","li",$.proxy(this.mouseleave,this)).on("mousedown",$.proxy(this.mousedown,this))},destroy:function(){this.$element.data("typeahead",null);this.$element.data("active",null);this.$element.off("focus").off("blur").off("keypress").off("input").off("keyup");if(this.eventSupported("keydown")){this.$element.off("keydown")}this.$menu.remove();this.destroyed=true},eventSupported:function(eventName){var isSupported=eventName in this.$element;if(!isSupported){this.$element.setAttribute(eventName,"return;");isSupported=typeof this.$element[eventName]==="function"}return isSupported},move:function(e){if(!this.shown)return;switch(e.keyCode){case 9:case 13:case 27:e.preventDefault();break;case 38:if(e.shiftKey)return;e.preventDefault();this.prev();break;case 40:if(e.shiftKey)return;e.preventDefault();this.next();break}},keydown:function(e){this.suppressKeyPressRepeat=~$.inArray(e.keyCode,[40,38,9,13,27]);if(!this.shown&&e.keyCode==40){this.lookup()}else{this.move(e)}},keypress:function(e){if(this.suppressKeyPressRepeat)return;this.move(e)},input:function(e){var currentValue=this.$element.val()||this.$element.text();if(this.value!==currentValue){this.value=currentValue;this.lookup()}},keyup:function(e){if(this.destroyed){return}switch(e.keyCode){case 40:case 38:case 16:case 17:case 18:break;case 9:case 13:if(!this.shown)return;this.select();break;case 27:if(!this.shown)return;this.hide();break}},focus:function(e){if(!this.focused){this.focused=true;if(this.options.showHintOnFocus&&this.skipShowHintOnFocus!==true){if(this.options.showHintOnFocus==="all"){this.lookup("")}else{this.lookup()}}}if(this.skipShowHintOnFocus){this.skipShowHintOnFocus=false}},blur:function(e){if(!this.mousedover&&!this.mouseddown&&this.shown){this.hide();this.focused=false}else if(this.mouseddown){this.skipShowHintOnFocus=true;this.$element.focus();this.mouseddown=false}},click:function(e){e.preventDefault();this.skipShowHintOnFocus=true;this.select();this.$element.focus();this.hide()},mouseenter:function(e){this.mousedover=true;this.$menu.find(".active").removeClass("active");$(e.currentTarget).addClass("active")},mouseleave:function(e){this.mousedover=false;if(!this.focused&&this.shown)this.hide()},mousedown:function(e){this.mouseddown=true;this.$menu.one("mouseup",function(e){this.mouseddown=false}.bind(this))}};var old=$.fn.typeahead;$.fn.typeahead=function(option){var arg=arguments;if(typeof option=="string"&&option=="getActive"){return this.data("active")}return this.each(function(){var $this=$(this);var data=$this.data("typeahead");var options=typeof option=="object"&&option;if(!data)$this.data("typeahead",data=new Typeahead(this,options));if(typeof option=="string"&&data[option]){if(arg.length>1){data[option].apply(data,Array.prototype.slice.call(arg,1))}else{data[option]()}}})};$.fn.typeahead.defaults={source:[],items:8,menu:'<ul class="typeahead dropdown-menu" role="listbox"></ul>',item:'<li><a class="dropdown-item" href="#" role="option"></a></li>',minLength:1,scrollHeight:0,autoSelect:true,afterSelect:$.noop,addItem:false,delay:0,separator:"category",headerHtml:'<li class="dropdown-header"></li>',headerDivider:'<li class="divider" role="separator"></li>'};$.fn.typeahead.Constructor=Typeahead;$.fn.typeahead.noConflict=function(){$.fn.typeahead=old;return this};$(document).on("focus.typeahead.data-api",'[data-provide="typeahead"]',function(e){var $this=$(this);if($this.data("typeahead"))return;$this.typeahead($this.data())})});


--------------------------------------------------------------------------------
/MyShow/static/js/bootstrap.min.js:
--------------------------------------------------------------------------------
1 | /*!
2 |  * Bootstrap v3.3.7 (http://getbootstrap.com)
3 |  * Copyright 2011-2016 Twitter, Inc.
4 |  * Licensed under the MIT license
5 |  */
6 | if("undefined"==typeof jQuery)throw new Error("Bootstrap's JavaScript requires jQuery");+function(a){"use strict";var b=a.fn.jquery.split(" ")[0].split(".");if(b[0]<2&&b[1]<9||1==b[0]&&9==b[1]&&b[2]<1||b[0]>3)throw new Error("Bootstrap's JavaScript requires jQuery version 1.9.1 or higher, but lower than version 4")}(jQuery),+function(a){"use strict";function b(){var a=document.createElement("bootstrap"),b={WebkitTransition:"webkitTransitionEnd",MozTransition:"transitionend",OTransition:"oTransitionEnd otransitionend",transition:"transitionend"};for(var c in b)if(void 0!==a.style[c])return{end:b[c]};return!1}a.fn.emulateTransitionEnd=function(b){var c=!1,d=this;a(this).one("bsTransitionEnd",function(){c=!0});var e=function(){c||a(d).trigger(a.support.transition.end)};return setTimeout(e,b),this},a(function(){a.support.transition=b(),a.support.transition&&(a.event.special.bsTransitionEnd={bindType:a.support.transition.end,delegateType:a.support.transition.end,handle:function(b){if(a(b.target).is(this))return b.handleObj.handler.apply(this,arguments)}})})}(jQuery),+function(a){"use strict";function b(b){return this.each(function(){var c=a(this),e=c.data("bs.alert");e||c.data("bs.alert",e=new d(this)),"string"==typeof b&&e[b].call(c)})}var c='[data-dismiss="alert"]',d=function(b){a(b).on("click",c,this.close)};d.VERSION="3.3.7",d.TRANSITION_DURATION=150,d.prototype.close=function(b){function c(){g.detach().trigger("closed.bs.alert").remove()}var e=a(this),f=e.attr("data-target");f||(f=e.attr("href"),f=f&&f.replace(/.*(?=#[^\s]*$)/,""));var g=a("#"===f?[]:f);b&&b.preventDefault(),g.length||(g=e.closest(".alert")),g.trigger(b=a.Event("close.bs.alert")),b.isDefaultPrevented()||(g.removeClass("in"),a.support.transition&&g.hasClass("fade")?g.one("bsTransitionEnd",c).emulateTransitionEnd(d.TRANSITION_DURATION):c())};var e=a.fn.alert;a.fn.alert=b,a.fn.alert.Constructor=d,a.fn.alert.noConflict=function(){return a.fn.alert=e,this},a(document).on("click.bs.alert.data-api",c,d.prototype.close)}(jQuery),+function(a){"use strict";function b(b){return this.each(function(){var d=a(this),e=d.data("bs.button"),f="object"==typeof b&&b;e||d.data("bs.button",e=new c(this,f)),"toggle"==b?e.toggle():b&&e.setState(b)})}var c=function(b,d){this.$element=a(b),this.options=a.extend({},c.DEFAULTS,d),this.isLoading=!1};c.VERSION="3.3.7",c.DEFAULTS={loadingText:"loading..."},c.prototype.setState=function(b){var c="disabled",d=this.$element,e=d.is("input")?"val":"html",f=d.data();b+="Text",null==f.resetText&&d.data("resetText",d[e]()),setTimeout(a.proxy(function(){d[e](null==f[b]?this.options[b]:f[b]),"loadingText"==b?(this.isLoading=!0,d.addClass(c).attr(c,c).prop(c,!0)):this.isLoading&&(this.isLoading=!1,d.removeClass(c).removeAttr(c).prop(c,!1))},this),0)},c.prototype.toggle=function(){var a=!0,b=this.$element.closest('[data-toggle="buttons"]');if(b.length){var c=this.$element.find("input");"radio"==c.prop("type")?(c.prop("checked")&&(a=!1),b.find(".active").removeClass("active"),this.$element.addClass("active")):"checkbox"==c.prop("type")&&(c.prop("checked")!==this.$element.hasClass("active")&&(a=!1),this.$element.toggleClass("active")),c.prop("checked",this.$element.hasClass("active")),a&&c.trigger("change")}else this.$element.attr("aria-pressed",!this.$element.hasClass("active")),this.$element.toggleClass("active")};var d=a.fn.button;a.fn.button=b,a.fn.button.Constructor=c,a.fn.button.noConflict=function(){return a.fn.button=d,this},a(document).on("click.bs.button.data-api",'[data-toggle^="button"]',function(c){var d=a(c.target).closest(".btn");b.call(d,"toggle"),a(c.target).is('input[type="radio"], input[type="checkbox"]')||(c.preventDefault(),d.is("input,button")?d.trigger("focus"):d.find("input:visible,button:visible").first().trigger("focus"))}).on("focus.bs.button.data-api blur.bs.button.data-api",'[data-toggle^="button"]',function(b){a(b.target).closest(".btn").toggleClass("focus",/^focus(in)?$/.test(b.type))})}(jQuery),+function(a){"use strict";function b(b){return this.each(function(){var d=a(this),e=d.data("bs.carousel"),f=a.extend({},c.DEFAULTS,d.data(),"object"==typeof b&&b),g="string"==typeof b?b:f.slide;e||d.data("bs.carousel",e=new c(this,f)),"number"==typeof b?e.to(b):g?e[g]():f.interval&&e.pause().cycle()})}var c=function(b,c){this.$element=a(b),this.$indicators=this.$element.find(".carousel-indicators"),this.options=c,this.paused=null,this.sliding=null,this.interval=null,this.$active=null,this.$items=null,this.options.keyboard&&this.$element.on("keydown.bs.carousel",a.proxy(this.keydown,this)),"hover"==this.options.pause&&!("ontouchstart"in document.documentElement)&&this.$element.on("mouseenter.bs.carousel",a.proxy(this.pause,this)).on("mouseleave.bs.carousel",a.proxy(this.cycle,this))};c.VERSION="3.3.7",c.TRANSITION_DURATION=600,c.DEFAULTS={interval:5e3,pause:"hover",wrap:!0,keyboard:!0},c.prototype.keydown=function(a){if(!/input|textarea/i.test(a.target.tagName)){switch(a.which){case 37:this.prev();break;case 39:this.next();break;default:return}a.preventDefault()}},c.prototype.cycle=function(b){return b||(this.paused=!1),this.interval&&clearInterval(this.interval),this.options.interval&&!this.paused&&(this.interval=setInterval(a.proxy(this.next,this),this.options.interval)),this},c.prototype.getItemIndex=function(a){return this.$items=a.parent().children(".item"),this.$items.index(a||this.$active)},c.prototype.getItemForDirection=function(a,b){var c=this.getItemIndex(b),d="prev"==a&&0===c||"next"==a&&c==this.$items.length-1;if(d&&!this.options.wrap)return b;var e="prev"==a?-1:1,f=(c+e)%this.$items.length;return this.$items.eq(f)},c.prototype.to=function(a){var b=this,c=this.getItemIndex(this.$active=this.$element.find(".item.active"));if(!(a>this.$items.length-1||a<0))return this.sliding?this.$element.one("slid.bs.carousel",function(){b.to(a)}):c==a?this.pause().cycle():this.slide(a>c?"next":"prev",this.$items.eq(a))},c.prototype.pause=function(b){return b||(this.paused=!0),this.$element.find(".next, .prev").length&&a.support.transition&&(this.$element.trigger(a.support.transition.end),this.cycle(!0)),this.interval=clearInterval(this.interval),this},c.prototype.next=function(){if(!this.sliding)return this.slide("next")},c.prototype.prev=function(){if(!this.sliding)return this.slide("prev")},c.prototype.slide=function(b,d){var e=this.$element.find(".item.active"),f=d||this.getItemForDirection(b,e),g=this.interval,h="next"==b?"left":"right",i=this;if(f.hasClass("active"))return this.sliding=!1;var j=f[0],k=a.Event("slide.bs.carousel",{relatedTarget:j,direction:h});if(this.$element.trigger(k),!k.isDefaultPrevented()){if(this.sliding=!0,g&&this.pause(),this.$indicators.length){this.$indicators.find(".active").removeClass("active");var l=a(this.$indicators.children()[this.getItemIndex(f)]);l&&l.addClass("active")}var m=a.Event("slid.bs.carousel",{relatedTarget:j,direction:h});return a.support.transition&&this.$element.hasClass("slide")?(f.addClass(b),f[0].offsetWidth,e.addClass(h),f.addClass(h),e.one("bsTransitionEnd",function(){f.removeClass([b,h].join(" ")).addClass("active"),e.removeClass(["active",h].join(" ")),i.sliding=!1,setTimeout(function(){i.$element.trigger(m)},0)}).emulateTransitionEnd(c.TRANSITION_DURATION)):(e.removeClass("active"),f.addClass("active"),this.sliding=!1,this.$element.trigger(m)),g&&this.cycle(),this}};var d=a.fn.carousel;a.fn.carousel=b,a.fn.carousel.Constructor=c,a.fn.carousel.noConflict=function(){return a.fn.carousel=d,this};var e=function(c){var d,e=a(this),f=a(e.attr("data-target")||(d=e.attr("href"))&&d.replace(/.*(?=#[^\s]+$)/,""));if(f.hasClass("carousel")){var g=a.extend({},f.data(),e.data()),h=e.attr("data-slide-to");h&&(g.interval=!1),b.call(f,g),h&&f.data("bs.carousel").to(h),c.preventDefault()}};a(document).on("click.bs.carousel.data-api","[data-slide]",e).on("click.bs.carousel.data-api","[data-slide-to]",e),a(window).on("load",function(){a('[data-ride="carousel"]').each(function(){var c=a(this);b.call(c,c.data())})})}(jQuery),+function(a){"use strict";function b(b){var c,d=b.attr("data-target")||(c=b.attr("href"))&&c.replace(/.*(?=#[^\s]+$)/,"");return a(d)}function c(b){return this.each(function(){var c=a(this),e=c.data("bs.collapse"),f=a.extend({},d.DEFAULTS,c.data(),"object"==typeof b&&b);!e&&f.toggle&&/show|hide/.test(b)&&(f.toggle=!1),e||c.data("bs.collapse",e=new d(this,f)),"string"==typeof b&&e[b]()})}var d=function(b,c){this.$element=a(b),this.options=a.extend({},d.DEFAULTS,c),this.$trigger=a('[data-toggle="collapse"][href="#'+b.id+'"],[data-toggle="collapse"][data-target="#'+b.id+'"]'),this.transitioning=null,this.options.parent?this.$parent=this.getParent():this.addAriaAndCollapsedClass(this.$element,this.$trigger),this.options.toggle&&this.toggle()};d.VERSION="3.3.7",d.TRANSITION_DURATION=350,d.DEFAULTS={toggle:!0},d.prototype.dimension=function(){var a=this.$element.hasClass("width");return a?"width":"height"},d.prototype.show=function(){if(!this.transitioning&&!this.$element.hasClass("in")){var b,e=this.$parent&&this.$parent.children(".panel").children(".in, .collapsing");if(!(e&&e.length&&(b=e.data("bs.collapse"),b&&b.transitioning))){var f=a.Event("show.bs.collapse");if(this.$element.trigger(f),!f.isDefaultPrevented()){e&&e.length&&(c.call(e,"hide"),b||e.data("bs.collapse",null));var g=this.dimension();this.$element.removeClass("collapse").addClass("collapsing")[g](0).attr("aria-expanded",!0),this.$trigger.removeClass("collapsed").attr("aria-expanded",!0),this.transitioning=1;var h=function(){this.$element.removeClass("collapsing").addClass("collapse in")[g](""),this.transitioning=0,this.$element.trigger("shown.bs.collapse")};if(!a.support.transition)return h.call(this);var i=a.camelCase(["scroll",g].join("-"));this.$element.one("bsTransitionEnd",a.proxy(h,this)).emulateTransitionEnd(d.TRANSITION_DURATION)[g](this.$element[0][i])}}}},d.prototype.hide=function(){if(!this.transitioning&&this.$element.hasClass("in")){var b=a.Event("hide.bs.collapse");if(this.$element.trigger(b),!b.isDefaultPrevented()){var c=this.dimension();this.$element[c](this.$element[c]())[0].offsetHeight,this.$element.addClass("collapsing").removeClass("collapse in").attr("aria-expanded",!1),this.$trigger.addClass("collapsed").attr("aria-expanded",!1),this.transitioning=1;var e=function(){this.transitioning=0,this.$element.removeClass("collapsing").addClass("collapse").trigger("hidden.bs.collapse")};return a.support.transition?void this.$element[c](0).one("bsTransitionEnd",a.proxy(e,this)).emulateTransitionEnd(d.TRANSITION_DURATION):e.call(this)}}},d.prototype.toggle=function(){this[this.$element.hasClass("in")?"hide":"show"]()},d.prototype.getParent=function(){return a(this.options.parent).find('[data-toggle="collapse"][data-parent="'+this.options.parent+'"]').each(a.proxy(function(c,d){var e=a(d);this.addAriaAndCollapsedClass(b(e),e)},this)).end()},d.prototype.addAriaAndCollapsedClass=function(a,b){var c=a.hasClass("in");a.attr("aria-expanded",c),b.toggleClass("collapsed",!c).attr("aria-expanded",c)};var e=a.fn.collapse;a.fn.collapse=c,a.fn.collapse.Constructor=d,a.fn.collapse.noConflict=function(){return a.fn.collapse=e,this},a(document).on("click.bs.collapse.data-api",'[data-toggle="collapse"]',function(d){var e=a(this);e.attr("data-target")||d.preventDefault();var f=b(e),g=f.data("bs.collapse"),h=g?"toggle":e.data();c.call(f,h)})}(jQuery),+function(a){"use strict";function b(b){var c=b.attr("data-target");c||(c=b.attr("href"),c=c&&/#[A-Za-z]/.test(c)&&c.replace(/.*(?=#[^\s]*$)/,""));var d=c&&a(c);return d&&d.length?d:b.parent()}function c(c){c&&3===c.which||(a(e).remove(),a(f).each(function(){var d=a(this),e=b(d),f={relatedTarget:this};e.hasClass("open")&&(c&&"click"==c.type&&/input|textarea/i.test(c.target.tagName)&&a.contains(e[0],c.target)||(e.trigger(c=a.Event("hide.bs.dropdown",f)),c.isDefaultPrevented()||(d.attr("aria-expanded","false"),e.removeClass("open").trigger(a.Event("hidden.bs.dropdown",f)))))}))}function d(b){return this.each(function(){var c=a(this),d=c.data("bs.dropdown");d||c.data("bs.dropdown",d=new g(this)),"string"==typeof b&&d[b].call(c)})}var e=".dropdown-backdrop",f='[data-toggle="dropdown"]',g=function(b){a(b).on("click.bs.dropdown",this.toggle)};g.VERSION="3.3.7",g.prototype.toggle=function(d){var e=a(this);if(!e.is(".disabled, :disabled")){var f=b(e),g=f.hasClass("open");if(c(),!g){"ontouchstart"in document.documentElement&&!f.closest(".navbar-nav").length&&a(document.createElement("div")).addClass("dropdown-backdrop").insertAfter(a(this)).on("click",c);var h={relatedTarget:this};if(f.trigger(d=a.Event("show.bs.dropdown",h)),d.isDefaultPrevented())return;e.trigger("focus").attr("aria-expanded","true"),f.toggleClass("open").trigger(a.Event("shown.bs.dropdown",h))}return!1}},g.prototype.keydown=function(c){if(/(38|40|27|32)/.test(c.which)&&!/input|textarea/i.test(c.target.tagName)){var d=a(this);if(c.preventDefault(),c.stopPropagation(),!d.is(".disabled, :disabled")){var e=b(d),g=e.hasClass("open");if(!g&&27!=c.which||g&&27==c.which)return 27==c.which&&e.find(f).trigger("focus"),d.trigger("click");var h=" li:not(.disabled):visible a",i=e.find(".dropdown-menu"+h);if(i.length){var j=i.index(c.target);38==c.which&&j>0&&j--,40==c.which&&j<i.length-1&&j++,~j||(j=0),i.eq(j).trigger("focus")}}}};var h=a.fn.dropdown;a.fn.dropdown=d,a.fn.dropdown.Constructor=g,a.fn.dropdown.noConflict=function(){return a.fn.dropdown=h,this},a(document).on("click.bs.dropdown.data-api",c).on("click.bs.dropdown.data-api",".dropdown form",function(a){a.stopPropagation()}).on("click.bs.dropdown.data-api",f,g.prototype.toggle).on("keydown.bs.dropdown.data-api",f,g.prototype.keydown).on("keydown.bs.dropdown.data-api",".dropdown-menu",g.prototype.keydown)}(jQuery),+function(a){"use strict";function b(b,d){return this.each(function(){var e=a(this),f=e.data("bs.modal"),g=a.extend({},c.DEFAULTS,e.data(),"object"==typeof b&&b);f||e.data("bs.modal",f=new c(this,g)),"string"==typeof b?f[b](d):g.show&&f.show(d)})}var c=function(b,c){this.options=c,this.$body=a(document.body),this.$element=a(b),this.$dialog=this.$element.find(".modal-dialog"),this.$backdrop=null,this.isShown=null,this.originalBodyPad=null,this.scrollbarWidth=0,this.ignoreBackdropClick=!1,this.options.remote&&this.$element.find(".modal-content").load(this.options.remote,a.proxy(function(){this.$element.trigger("loaded.bs.modal")},this))};c.VERSION="3.3.7",c.TRANSITION_DURATION=300,c.BACKDROP_TRANSITION_DURATION=150,c.DEFAULTS={backdrop:!0,keyboard:!0,show:!0},c.prototype.toggle=function(a){return this.isShown?this.hide():this.show(a)},c.prototype.show=function(b){var d=this,e=a.Event("show.bs.modal",{relatedTarget:b});this.$element.trigger(e),this.isShown||e.isDefaultPrevented()||(this.isShown=!0,this.checkScrollbar(),this.setScrollbar(),this.$body.addClass("modal-open"),this.escape(),this.resize(),this.$element.on("click.dismiss.bs.modal",'[data-dismiss="modal"]',a.proxy(this.hide,this)),this.$dialog.on("mousedown.dismiss.bs.modal",function(){d.$element.one("mouseup.dismiss.bs.modal",function(b){a(b.target).is(d.$element)&&(d.ignoreBackdropClick=!0)})}),this.backdrop(function(){var e=a.support.transition&&d.$element.hasClass("fade");d.$element.parent().length||d.$element.appendTo(d.$body),d.$element.show().scrollTop(0),d.adjustDialog(),e&&d.$element[0].offsetWidth,d.$element.addClass("in"),d.enforceFocus();var f=a.Event("shown.bs.modal",{relatedTarget:b});e?d.$dialog.one("bsTransitionEnd",function(){d.$element.trigger("focus").trigger(f)}).emulateTransitionEnd(c.TRANSITION_DURATION):d.$element.trigger("focus").trigger(f)}))},c.prototype.hide=function(b){b&&b.preventDefault(),b=a.Event("hide.bs.modal"),this.$element.trigger(b),this.isShown&&!b.isDefaultPrevented()&&(this.isShown=!1,this.escape(),this.resize(),a(document).off("focusin.bs.modal"),this.$element.removeClass("in").off("click.dismiss.bs.modal").off("mouseup.dismiss.bs.modal"),this.$dialog.off("mousedown.dismiss.bs.modal"),a.support.transition&&this.$element.hasClass("fade")?this.$element.one("bsTransitionEnd",a.proxy(this.hideModal,this)).emulateTransitionEnd(c.TRANSITION_DURATION):this.hideModal())},c.prototype.enforceFocus=function(){a(document).off("focusin.bs.modal").on("focusin.bs.modal",a.proxy(function(a){document===a.target||this.$element[0]===a.target||this.$element.has(a.target).length||this.$element.trigger("focus")},this))},c.prototype.escape=function(){this.isShown&&this.options.keyboard?this.$element.on("keydown.dismiss.bs.modal",a.proxy(function(a){27==a.which&&this.hide()},this)):this.isShown||this.$element.off("keydown.dismiss.bs.modal")},c.prototype.resize=function(){this.isShown?a(window).on("resize.bs.modal",a.proxy(this.handleUpdate,this)):a(window).off("resize.bs.modal")},c.prototype.hideModal=function(){var a=this;this.$element.hide(),this.backdrop(function(){a.$body.removeClass("modal-open"),a.resetAdjustments(),a.resetScrollbar(),a.$element.trigger("hidden.bs.modal")})},c.prototype.removeBackdrop=function(){this.$backdrop&&this.$backdrop.remove(),this.$backdrop=null},c.prototype.backdrop=function(b){var d=this,e=this.$element.hasClass("fade")?"fade":"";if(this.isShown&&this.options.backdrop){var f=a.support.transition&&e;if(this.$backdrop=a(document.createElement("div")).addClass("modal-backdrop "+e).appendTo(this.$body),this.$element.on("click.dismiss.bs.modal",a.proxy(function(a){return this.ignoreBackdropClick?void(this.ignoreBackdropClick=!1):void(a.target===a.currentTarget&&("static"==this.options.backdrop?this.$element[0].focus():this.hide()))},this)),f&&this.$backdrop[0].offsetWidth,this.$backdrop.addClass("in"),!b)return;f?this.$backdrop.one("bsTransitionEnd",b).emulateTransitionEnd(c.BACKDROP_TRANSITION_DURATION):b()}else if(!this.isShown&&this.$backdrop){this.$backdrop.removeClass("in");var g=function(){d.removeBackdrop(),b&&b()};a.support.transition&&this.$element.hasClass("fade")?this.$backdrop.one("bsTransitionEnd",g).emulateTransitionEnd(c.BACKDROP_TRANSITION_DURATION):g()}else b&&b()},c.prototype.handleUpdate=function(){this.adjustDialog()},c.prototype.adjustDialog=function(){var a=this.$element[0].scrollHeight>document.documentElement.clientHeight;this.$element.css({paddingLeft:!this.bodyIsOverflowing&&a?this.scrollbarWidth:"",paddingRight:this.bodyIsOverflowing&&!a?this.scrollbarWidth:""})},c.prototype.resetAdjustments=function(){this.$element.css({paddingLeft:"",paddingRight:""})},c.prototype.checkScrollbar=function(){var a=window.innerWidth;if(!a){var b=document.documentElement.getBoundingClientRect();a=b.right-Math.abs(b.left)}this.bodyIsOverflowing=document.body.clientWidth<a,this.scrollbarWidth=this.measureScrollbar()},c.prototype.setScrollbar=function(){var a=parseInt(this.$body.css("padding-right")||0,10);this.originalBodyPad=document.body.style.paddingRight||"",this.bodyIsOverflowing&&this.$body.css("padding-right",a+this.scrollbarWidth)},c.prototype.resetScrollbar=function(){this.$body.css("padding-right",this.originalBodyPad)},c.prototype.measureScrollbar=function(){var a=document.createElement("div");a.className="modal-scrollbar-measure",this.$body.append(a);var b=a.offsetWidth-a.clientWidth;return this.$body[0].removeChild(a),b};var d=a.fn.modal;a.fn.modal=b,a.fn.modal.Constructor=c,a.fn.modal.noConflict=function(){return a.fn.modal=d,this},a(document).on("click.bs.modal.data-api",'[data-toggle="modal"]',function(c){var d=a(this),e=d.attr("href"),f=a(d.attr("data-target")||e&&e.replace(/.*(?=#[^\s]+$)/,"")),g=f.data("bs.modal")?"toggle":a.extend({remote:!/#/.test(e)&&e},f.data(),d.data());d.is("a")&&c.preventDefault(),f.one("show.bs.modal",function(a){a.isDefaultPrevented()||f.one("hidden.bs.modal",function(){d.is(":visible")&&d.trigger("focus")})}),b.call(f,g,this)})}(jQuery),+function(a){"use strict";function b(b){return this.each(function(){var d=a(this),e=d.data("bs.tooltip"),f="object"==typeof b&&b;!e&&/destroy|hide/.test(b)||(e||d.data("bs.tooltip",e=new c(this,f)),"string"==typeof b&&e[b]())})}var c=function(a,b){this.type=null,this.options=null,this.enabled=null,this.timeout=null,this.hoverState=null,this.$element=null,this.inState=null,this.init("tooltip",a,b)};c.VERSION="3.3.7",c.TRANSITION_DURATION=150,c.DEFAULTS={animation:!0,placement:"top",selector:!1,template:'<div class="tooltip" role="tooltip"><div class="tooltip-arrow"></div><div class="tooltip-inner"></div></div>',trigger:"hover focus",title:"",delay:0,html:!1,container:!1,viewport:{selector:"body",padding:0}},c.prototype.init=function(b,c,d){if(this.enabled=!0,this.type=b,this.$element=a(c),this.options=this.getOptions(d),this.$viewport=this.options.viewport&&a(a.isFunction(this.options.viewport)?this.options.viewport.call(this,this.$element):this.options.viewport.selector||this.options.viewport),this.inState={click:!1,hover:!1,focus:!1},this.$element[0]instanceof document.constructor&&!this.options.selector)throw new Error("`selector` option must be specified when initializing "+this.type+" on the window.document object!");for(var e=this.options.trigger.split(" "),f=e.length;f--;){var g=e[f];if("click"==g)this.$element.on("click."+this.type,this.options.selector,a.proxy(this.toggle,this));else if("manual"!=g){var h="hover"==g?"mouseenter":"focusin",i="hover"==g?"mouseleave":"focusout";this.$element.on(h+"."+this.type,this.options.selector,a.proxy(this.enter,this)),this.$element.on(i+"."+this.type,this.options.selector,a.proxy(this.leave,this))}}this.options.selector?this._options=a.extend({},this.options,{trigger:"manual",selector:""}):this.fixTitle()},c.prototype.getDefaults=function(){return c.DEFAULTS},c.prototype.getOptions=function(b){return b=a.extend({},this.getDefaults(),this.$element.data(),b),b.delay&&"number"==typeof b.delay&&(b.delay={show:b.delay,hide:b.delay}),b},c.prototype.getDelegateOptions=function(){var b={},c=this.getDefaults();return this._options&&a.each(this._options,function(a,d){c[a]!=d&&(b[a]=d)}),b},c.prototype.enter=function(b){var c=b instanceof this.constructor?b:a(b.currentTarget).data("bs."+this.type);return c||(c=new this.constructor(b.currentTarget,this.getDelegateOptions()),a(b.currentTarget).data("bs."+this.type,c)),b instanceof a.Event&&(c.inState["focusin"==b.type?"focus":"hover"]=!0),c.tip().hasClass("in")||"in"==c.hoverState?void(c.hoverState="in"):(clearTimeout(c.timeout),c.hoverState="in",c.options.delay&&c.options.delay.show?void(c.timeout=setTimeout(function(){"in"==c.hoverState&&c.show()},c.options.delay.show)):c.show())},c.prototype.isInStateTrue=function(){for(var a in this.inState)if(this.inState[a])return!0;return!1},c.prototype.leave=function(b){var c=b instanceof this.constructor?b:a(b.currentTarget).data("bs."+this.type);if(c||(c=new this.constructor(b.currentTarget,this.getDelegateOptions()),a(b.currentTarget).data("bs."+this.type,c)),b instanceof a.Event&&(c.inState["focusout"==b.type?"focus":"hover"]=!1),!c.isInStateTrue())return clearTimeout(c.timeout),c.hoverState="out",c.options.delay&&c.options.delay.hide?void(c.timeout=setTimeout(function(){"out"==c.hoverState&&c.hide()},c.options.delay.hide)):c.hide()},c.prototype.show=function(){var b=a.Event("show.bs."+this.type);if(this.hasContent()&&this.enabled){this.$element.trigger(b);var d=a.contains(this.$element[0].ownerDocument.documentElement,this.$element[0]);if(b.isDefaultPrevented()||!d)return;var e=this,f=this.tip(),g=this.getUID(this.type);this.setContent(),f.attr("id",g),this.$element.attr("aria-describedby",g),this.options.animation&&f.addClass("fade");var h="function"==typeof this.options.placement?this.options.placement.call(this,f[0],this.$element[0]):this.options.placement,i=/\s?auto?\s?/i,j=i.test(h);j&&(h=h.replace(i,"")||"top"),f.detach().css({top:0,left:0,display:"block"}).addClass(h).data("bs."+this.type,this),this.options.container?f.appendTo(this.options.container):f.insertAfter(this.$element),this.$element.trigger("inserted.bs."+this.type);var k=this.getPosition(),l=f[0].offsetWidth,m=f[0].offsetHeight;if(j){var n=h,o=this.getPosition(this.$viewport);h="bottom"==h&&k.bottom+m>o.bottom?"top":"top"==h&&k.top-m<o.top?"bottom":"right"==h&&k.right+l>o.width?"left":"left"==h&&k.left-l<o.left?"right":h,f.removeClass(n).addClass(h)}var p=this.getCalculatedOffset(h,k,l,m);this.applyPlacement(p,h);var q=function(){var a=e.hoverState;e.$element.trigger("shown.bs."+e.type),e.hoverState=null,"out"==a&&e.leave(e)};a.support.transition&&this.$tip.hasClass("fade")?f.one("bsTransitionEnd",q).emulateTransitionEnd(c.TRANSITION_DURATION):q()}},c.prototype.applyPlacement=function(b,c){var d=this.tip(),e=d[0].offsetWidth,f=d[0].offsetHeight,g=parseInt(d.css("margin-top"),10),h=parseInt(d.css("margin-left"),10);isNaN(g)&&(g=0),isNaN(h)&&(h=0),b.top+=g,b.left+=h,a.offset.setOffset(d[0],a.extend({using:function(a){d.css({top:Math.round(a.top),left:Math.round(a.left)})}},b),0),d.addClass("in");var i=d[0].offsetWidth,j=d[0].offsetHeight;"top"==c&&j!=f&&(b.top=b.top+f-j);var k=this.getViewportAdjustedDelta(c,b,i,j);k.left?b.left+=k.left:b.top+=k.top;var l=/top|bottom/.test(c),m=l?2*k.left-e+i:2*k.top-f+j,n=l?"offsetWidth":"offsetHeight";d.offset(b),this.replaceArrow(m,d[0][n],l)},c.prototype.replaceArrow=function(a,b,c){this.arrow().css(c?"left":"top",50*(1-a/b)+"%").css(c?"top":"left","")},c.prototype.setContent=function(){var a=this.tip(),b=this.getTitle();a.find(".tooltip-inner")[this.options.html?"html":"text"](b),a.removeClass("fade in top bottom left right")},c.prototype.hide=function(b){function d(){"in"!=e.hoverState&&f.detach(),e.$element&&e.$element.removeAttr("aria-describedby").trigger("hidden.bs."+e.type),b&&b()}var e=this,f=a(this.$tip),g=a.Event("hide.bs."+this.type);if(this.$element.trigger(g),!g.isDefaultPrevented())return f.removeClass("in"),a.support.transition&&f.hasClass("fade")?f.one("bsTransitionEnd",d).emulateTransitionEnd(c.TRANSITION_DURATION):d(),this.hoverState=null,this},c.prototype.fixTitle=function(){var a=this.$element;(a.attr("title")||"string"!=typeof a.attr("data-original-title"))&&a.attr("data-original-title",a.attr("title")||"").attr("title","")},c.prototype.hasContent=function(){return this.getTitle()},c.prototype.getPosition=function(b){b=b||this.$element;var c=b[0],d="BODY"==c.tagName,e=c.getBoundingClientRect();null==e.width&&(e=a.extend({},e,{width:e.right-e.left,height:e.bottom-e.top}));var f=window.SVGElement&&c instanceof window.SVGElement,g=d?{top:0,left:0}:f?null:b.offset(),h={scroll:d?document.documentElement.scrollTop||document.body.scrollTop:b.scrollTop()},i=d?{width:a(window).width(),height:a(window).height()}:null;return a.extend({},e,h,i,g)},c.prototype.getCalculatedOffset=function(a,b,c,d){return"bottom"==a?{top:b.top+b.height,left:b.left+b.width/2-c/2}:"top"==a?{top:b.top-d,left:b.left+b.width/2-c/2}:"left"==a?{top:b.top+b.height/2-d/2,left:b.left-c}:{top:b.top+b.height/2-d/2,left:b.left+b.width}},c.prototype.getViewportAdjustedDelta=function(a,b,c,d){var e={top:0,left:0};if(!this.$viewport)return e;var f=this.options.viewport&&this.options.viewport.padding||0,g=this.getPosition(this.$viewport);if(/right|left/.test(a)){var h=b.top-f-g.scroll,i=b.top+f-g.scroll+d;h<g.top?e.top=g.top-h:i>g.top+g.height&&(e.top=g.top+g.height-i)}else{var j=b.left-f,k=b.left+f+c;j<g.left?e.left=g.left-j:k>g.right&&(e.left=g.left+g.width-k)}return e},c.prototype.getTitle=function(){var a,b=this.$element,c=this.options;return a=b.attr("data-original-title")||("function"==typeof c.title?c.title.call(b[0]):c.title)},c.prototype.getUID=function(a){do a+=~~(1e6*Math.random());while(document.getElementById(a));return a},c.prototype.tip=function(){if(!this.$tip&&(this.$tip=a(this.options.template),1!=this.$tip.length))throw new Error(this.type+" `template` option must consist of exactly 1 top-level element!");return this.$tip},c.prototype.arrow=function(){return this.$arrow=this.$arrow||this.tip().find(".tooltip-arrow")},c.prototype.enable=function(){this.enabled=!0},c.prototype.disable=function(){this.enabled=!1},c.prototype.toggleEnabled=function(){this.enabled=!this.enabled},c.prototype.toggle=function(b){var c=this;b&&(c=a(b.currentTarget).data("bs."+this.type),c||(c=new this.constructor(b.currentTarget,this.getDelegateOptions()),a(b.currentTarget).data("bs."+this.type,c))),b?(c.inState.click=!c.inState.click,c.isInStateTrue()?c.enter(c):c.leave(c)):c.tip().hasClass("in")?c.leave(c):c.enter(c)},c.prototype.destroy=function(){var a=this;clearTimeout(this.timeout),this.hide(function(){a.$element.off("."+a.type).removeData("bs."+a.type),a.$tip&&a.$tip.detach(),a.$tip=null,a.$arrow=null,a.$viewport=null,a.$element=null})};var d=a.fn.tooltip;a.fn.tooltip=b,a.fn.tooltip.Constructor=c,a.fn.tooltip.noConflict=function(){return a.fn.tooltip=d,this}}(jQuery),+function(a){"use strict";function b(b){return this.each(function(){var d=a(this),e=d.data("bs.popover"),f="object"==typeof b&&b;!e&&/destroy|hide/.test(b)||(e||d.data("bs.popover",e=new c(this,f)),"string"==typeof b&&e[b]())})}var c=function(a,b){this.init("popover",a,b)};if(!a.fn.tooltip)throw new Error("Popover requires tooltip.js");c.VERSION="3.3.7",c.DEFAULTS=a.extend({},a.fn.tooltip.Constructor.DEFAULTS,{placement:"right",trigger:"click",content:"",template:'<div class="popover" role="tooltip"><div class="arrow"></div><h3 class="popover-title"></h3><div class="popover-content"></div></div>'}),c.prototype=a.extend({},a.fn.tooltip.Constructor.prototype),c.prototype.constructor=c,c.prototype.getDefaults=function(){return c.DEFAULTS},c.prototype.setContent=function(){var a=this.tip(),b=this.getTitle(),c=this.getContent();a.find(".popover-title")[this.options.html?"html":"text"](b),a.find(".popover-content").children().detach().end()[this.options.html?"string"==typeof c?"html":"append":"text"](c),a.removeClass("fade top bottom left right in"),a.find(".popover-title").html()||a.find(".popover-title").hide()},c.prototype.hasContent=function(){return this.getTitle()||this.getContent()},c.prototype.getContent=function(){var a=this.$element,b=this.options;return a.attr("data-content")||("function"==typeof b.content?b.content.call(a[0]):b.content)},c.prototype.arrow=function(){return this.$arrow=this.$arrow||this.tip().find(".arrow")};var d=a.fn.popover;a.fn.popover=b,a.fn.popover.Constructor=c,a.fn.popover.noConflict=function(){return a.fn.popover=d,this}}(jQuery),+function(a){"use strict";function b(c,d){this.$body=a(document.body),this.$scrollElement=a(a(c).is(document.body)?window:c),this.options=a.extend({},b.DEFAULTS,d),this.selector=(this.options.target||"")+" .nav li > a",this.offsets=[],this.targets=[],this.activeTarget=null,this.scrollHeight=0,this.$scrollElement.on("scroll.bs.scrollspy",a.proxy(this.process,this)),this.refresh(),this.process()}function c(c){return this.each(function(){var d=a(this),e=d.data("bs.scrollspy"),f="object"==typeof c&&c;e||d.data("bs.scrollspy",e=new b(this,f)),"string"==typeof c&&e[c]()})}b.VERSION="3.3.7",b.DEFAULTS={offset:10},b.prototype.getScrollHeight=function(){return this.$scrollElement[0].scrollHeight||Math.max(this.$body[0].scrollHeight,document.documentElement.scrollHeight)},b.prototype.refresh=function(){var b=this,c="offset",d=0;this.offsets=[],this.targets=[],this.scrollHeight=this.getScrollHeight(),a.isWindow(this.$scrollElement[0])||(c="position",d=this.$scrollElement.scrollTop()),this.$body.find(this.selector).map(function(){var b=a(this),e=b.data("target")||b.attr("href"),f=/^#./.test(e)&&a(e);return f&&f.length&&f.is(":visible")&&[[f[c]().top+d,e]]||null}).sort(function(a,b){return a[0]-b[0]}).each(function(){b.offsets.push(this[0]),b.targets.push(this[1])})},b.prototype.process=function(){var a,b=this.$scrollElement.scrollTop()+this.options.offset,c=this.getScrollHeight(),d=this.options.offset+c-this.$scrollElement.height(),e=this.offsets,f=this.targets,g=this.activeTarget;if(this.scrollHeight!=c&&this.refresh(),b>=d)return g!=(a=f[f.length-1])&&this.activate(a);if(g&&b<e[0])return this.activeTarget=null,this.clear();for(a=e.length;a--;)g!=f[a]&&b>=e[a]&&(void 0===e[a+1]||b<e[a+1])&&this.activate(f[a])},b.prototype.activate=function(b){
7 | this.activeTarget=b,this.clear();var c=this.selector+'[data-target="'+b+'"],'+this.selector+'[href="'+b+'"]',d=a(c).parents("li").addClass("active");d.parent(".dropdown-menu").length&&(d=d.closest("li.dropdown").addClass("active")),d.trigger("activate.bs.scrollspy")},b.prototype.clear=function(){a(this.selector).parentsUntil(this.options.target,".active").removeClass("active")};var d=a.fn.scrollspy;a.fn.scrollspy=c,a.fn.scrollspy.Constructor=b,a.fn.scrollspy.noConflict=function(){return a.fn.scrollspy=d,this},a(window).on("load.bs.scrollspy.data-api",function(){a('[data-spy="scroll"]').each(function(){var b=a(this);c.call(b,b.data())})})}(jQuery),+function(a){"use strict";function b(b){return this.each(function(){var d=a(this),e=d.data("bs.tab");e||d.data("bs.tab",e=new c(this)),"string"==typeof b&&e[b]()})}var c=function(b){this.element=a(b)};c.VERSION="3.3.7",c.TRANSITION_DURATION=150,c.prototype.show=function(){var b=this.element,c=b.closest("ul:not(.dropdown-menu)"),d=b.data("target");if(d||(d=b.attr("href"),d=d&&d.replace(/.*(?=#[^\s]*$)/,"")),!b.parent("li").hasClass("active")){var e=c.find(".active:last a"),f=a.Event("hide.bs.tab",{relatedTarget:b[0]}),g=a.Event("show.bs.tab",{relatedTarget:e[0]});if(e.trigger(f),b.trigger(g),!g.isDefaultPrevented()&&!f.isDefaultPrevented()){var h=a(d);this.activate(b.closest("li"),c),this.activate(h,h.parent(),function(){e.trigger({type:"hidden.bs.tab",relatedTarget:b[0]}),b.trigger({type:"shown.bs.tab",relatedTarget:e[0]})})}}},c.prototype.activate=function(b,d,e){function f(){g.removeClass("active").find("> .dropdown-menu > .active").removeClass("active").end().find('[data-toggle="tab"]').attr("aria-expanded",!1),b.addClass("active").find('[data-toggle="tab"]').attr("aria-expanded",!0),h?(b[0].offsetWidth,b.addClass("in")):b.removeClass("fade"),b.parent(".dropdown-menu").length&&b.closest("li.dropdown").addClass("active").end().find('[data-toggle="tab"]').attr("aria-expanded",!0),e&&e()}var g=d.find("> .active"),h=e&&a.support.transition&&(g.length&&g.hasClass("fade")||!!d.find("> .fade").length);g.length&&h?g.one("bsTransitionEnd",f).emulateTransitionEnd(c.TRANSITION_DURATION):f(),g.removeClass("in")};var d=a.fn.tab;a.fn.tab=b,a.fn.tab.Constructor=c,a.fn.tab.noConflict=function(){return a.fn.tab=d,this};var e=function(c){c.preventDefault(),b.call(a(this),"show")};a(document).on("click.bs.tab.data-api",'[data-toggle="tab"]',e).on("click.bs.tab.data-api",'[data-toggle="pill"]',e)}(jQuery),+function(a){"use strict";function b(b){return this.each(function(){var d=a(this),e=d.data("bs.affix"),f="object"==typeof b&&b;e||d.data("bs.affix",e=new c(this,f)),"string"==typeof b&&e[b]()})}var c=function(b,d){this.options=a.extend({},c.DEFAULTS,d),this.$target=a(this.options.target).on("scroll.bs.affix.data-api",a.proxy(this.checkPosition,this)).on("click.bs.affix.data-api",a.proxy(this.checkPositionWithEventLoop,this)),this.$element=a(b),this.affixed=null,this.unpin=null,this.pinnedOffset=null,this.checkPosition()};c.VERSION="3.3.7",c.RESET="affix affix-top affix-bottom",c.DEFAULTS={offset:0,target:window},c.prototype.getState=function(a,b,c,d){var e=this.$target.scrollTop(),f=this.$element.offset(),g=this.$target.height();if(null!=c&&"top"==this.affixed)return e<c&&"top";if("bottom"==this.affixed)return null!=c?!(e+this.unpin<=f.top)&&"bottom":!(e+g<=a-d)&&"bottom";var h=null==this.affixed,i=h?e:f.top,j=h?g:b;return null!=c&&e<=c?"top":null!=d&&i+j>=a-d&&"bottom"},c.prototype.getPinnedOffset=function(){if(this.pinnedOffset)return this.pinnedOffset;this.$element.removeClass(c.RESET).addClass("affix");var a=this.$target.scrollTop(),b=this.$element.offset();return this.pinnedOffset=b.top-a},c.prototype.checkPositionWithEventLoop=function(){setTimeout(a.proxy(this.checkPosition,this),1)},c.prototype.checkPosition=function(){if(this.$element.is(":visible")){var b=this.$element.height(),d=this.options.offset,e=d.top,f=d.bottom,g=Math.max(a(document).height(),a(document.body).height());"object"!=typeof d&&(f=e=d),"function"==typeof e&&(e=d.top(this.$element)),"function"==typeof f&&(f=d.bottom(this.$element));var h=this.getState(g,b,e,f);if(this.affixed!=h){null!=this.unpin&&this.$element.css("top","");var i="affix"+(h?"-"+h:""),j=a.Event(i+".bs.affix");if(this.$element.trigger(j),j.isDefaultPrevented())return;this.affixed=h,this.unpin="bottom"==h?this.getPinnedOffset():null,this.$element.removeClass(c.RESET).addClass(i).trigger(i.replace("affix","affixed")+".bs.affix")}"bottom"==h&&this.$element.offset({top:g-b-f})}};var d=a.fn.affix;a.fn.affix=b,a.fn.affix.Constructor=c,a.fn.affix.noConflict=function(){return a.fn.affix=d,this},a(window).on("load",function(){a('[data-spy="affix"]').each(function(){var c=a(this),d=c.data();d.offset=d.offset||{},null!=d.offsetBottom&&(d.offset.bottom=d.offsetBottom),null!=d.offsetTop&&(d.offset.top=d.offsetTop),b.call(c,d)})})}(jQuery);


--------------------------------------------------------------------------------
/MyShow/templates/base.html:
--------------------------------------------------------------------------------
 1 | {% extends "bootstrap/base.html" %}
 2 | {% block title %}MyShow{% endblock %}
 3 | 
 4 | {% block head %}
 5 |     {{ super() }}
 6 |     <meta charset="utf-8">
 7 | 
 8 |     <!-- Icon -->
 9 |     <link rel="shortcut icon" href="{{ url_for('static', filename='favicon.ico') }}" type="image/x-icon">
10 | 
11 |     <!-- Custom styles for this template -->
12 |     <link href="{{ url_for('static', filename='css/dashboard.css') }}" rel="stylesheet">
13 | 
14 |     <!-- Loading Js Files  -->
15 |     <script src="{{ url_for('static', filename='js/jquery-3.0.0.min.js') }}"></script>
16 |     <script src="{{ url_for('static', filename='js/bootstrap.min.js') }}"></script>
17 |     <script src="{{ url_for('static', filename='js/echarts.min.js') }}"></script>
18 |     <script src="{{ url_for('static', filename='js/bootstrap-typeahead.min.js') }}"></script>
19 | {% endblock %}
20 | 
21 | {% block navbar %}
22 | <nav class="navbar navbar-inverse navbar-fixed-top" role="navigation">
23 |     <div class="container-fluid">
24 |         <div class="nav navbar-header navbar-left">
25 |             <a class="navbar-brand" href="/">数据展示</a>
26 |         </div>
27 |         <div id="navbar" class="nav navbar-nav navbar-right" style="margin-right: 10px">
28 |             {% if name %}
29 |             <div class="btn-group navbar-btn navbar-right">
30 |                 <button type="button" class="btn btn-success dropdown-toggle" data-toggle="dropdown">
31 |                     {{ name }}
32 |                     <span class="caret"></span>
33 |                 </button>
34 |                 <ul class="dropdown-menu" role="menu" id="login_out_menu">
35 |                     <li><a href="/index/?action=login_out">退出登录</a></li>
36 |                 </ul>
37 |             </div>
38 |             {% elif form %}
39 |             <form class="navbar-form navbar-right" role="form" method="post">
40 |                 {{ form.csrf_token }}
41 |                 <div class="form-group">
42 |                     {{ form.name(placeholder="Email...", class="form-control") }}
43 |                 </div>
44 |                 <div class="form-group">
45 |                     {{ form.password(placeholder="Password...", class="form-control") }}
46 |                 </div>
47 |                 {{ form.submit(class="btn btn-primary") }}
48 |             </form>
49 |             {% endif %}
50 |         </div>
51 |     </div>
52 | </nav>
53 | {% endblock %}
54 | 
55 | {% block content %}
56 | <div class="container">
57 |     {% block page_content %}
58 |     {% endblock %}
59 | </div>
60 | {% endblock %}
61 | 


--------------------------------------------------------------------------------
/MyShow/templates/error.html:
--------------------------------------------------------------------------------
1 | {% extends "base.html" %}
2 | {% block title %}数据展示 - Error{% endblock %}
3 | 
4 | {% block page_content %}
5 |     <div class="page-header">
6 |         <h1>{{ error }}</h1>
7 |     </div>
8 | {% endblock %}
9 | 


--------------------------------------------------------------------------------
/MyShow/templates/index.html:
--------------------------------------------------------------------------------
  1 | {% extends "base.html" %}
  2 | {% import "bootstrap/wtf.html" as wtf %}
  3 | 
  4 | {% block head %}
  5 | {{ super() }}
  6 | 
  7 | <script type="text/javascript">
  8 | var zhihu_topics = function () {
  9 |     var zhi_graph = echarts.init(document.getElementById("show_data_zhihu"));
 10 |     zhi_graph.showLoading();
 11 | 
 12 |     var set_zhi_graph = function (data) {
 13 |         zhi_graph.hideLoading();
 14 | 
 15 |         var categories = [];
 16 |         for (var i = 0; i < 3; i++) {
 17 |             categories[i] = {
 18 |                 name: "级别" + (i + 1)
 19 |             }
 20 |         }
 21 | 
 22 |         data.nodes.forEach(function (node) {
 23 |             node.symbolSize = 10;
 24 |             node.label = {
 25 |                 normal: {
 26 |                     show: true,
 27 |                     position: 'right'
 28 |                 }
 29 |             };
 30 |             node.draggable = true;
 31 |             node.category = node.level
 32 |         });
 33 | 
 34 |         data.links.forEach(function (link) {
 35 |             link.label = {
 36 |                 normal: {
 37 |                     show: false
 38 |                 }
 39 |             }
 40 |         });
 41 | 
 42 |         var option = {
 43 |             title: {
 44 |                 text: '知乎话题关系图',
 45 |                 subtext: '展示知乎话题之间的关系',
 46 |                 top: 'top',
 47 |                 left: 'left'
 48 |             },
 49 |             legend: [{
 50 |                 data: categories.map(function (a) {
 51 |                     return a.name;
 52 |                 })
 53 |             }],
 54 |             animation: false,
 55 |             series: [
 56 |                 {
 57 |                     type: 'graph',
 58 |                     layout: data.type,
 59 |                     data: data.nodes,
 60 |                     links: data.links,
 61 |                     categories: categories,
 62 |                     roam: true,
 63 |                     force: {
 64 |                         repulsion: 100
 65 |                     }
 66 |                 }
 67 |             ]
 68 |         };
 69 | 
 70 |         zhi_graph.setOption(option);
 71 |     };
 72 | 
 73 |     $.post("/zhihu_get_topics_data/", {id: "19554449", name: "数据"}, set_zhi_graph);
 74 | 
 75 |     var subjects = [
 76 |         { id: 1, name: '北京' },
 77 |         { id: 2, name: '南京' },
 78 |         { id: 3, name: '广州' },
 79 |         { id: 4, name: '深圳' }
 80 |     ];
 81 | 
 82 |     $('#zhihusearch').typeahead({
 83 |         source: function (query, process) {
 84 |             $.post("/zhihu_get_topics_list/", {key: query}, function (e) {
 85 |                 if (e.success) {
 86 |                     process(e.data);
 87 |                 }
 88 |             });
 89 |         }, {#source: subjects,#}
 90 |         items: 20,
 91 |         minLength: 1,
 92 |         updater: function (item) {
 93 |             return item;
 94 |         },
 95 |         displayText: function (item) {
 96 |             return ":" + item["name"];
 97 |         },
 98 |         afterSelect: function (item) {
 99 |             $.ajax({
100 |                 type: "post",
101 |                 async: true,
102 |                 url: "/zhihu_get_topics_data/",
103 |                 data: item,
104 |                 dataType: "json",
105 |                 beforeSend: function (xhr) {
106 |                     zhi_graph.showLoading();
107 |                     return true
108 |                 },
109 |                 success: function (result) {
110 |                     if (result) {
111 |                         set_zhi_graph(result)
112 |                     }
113 |                 },
114 |                 error: function (error) {
115 |                     alert("请求数据失败!");
116 |                     zhi_graph.hideLoading();
117 |                 }
118 |             });
119 |         }
120 |     });
121 | };
122 | </script>
123 | {% endblock %}
124 | 
125 | {% block page_content %}
126 | <div class="row">
127 |     <div class="col-sm-3 col-md-2 sidebar">
128 |         <ul class="nav nav-sidebar">
129 |             <li class={% if page_type == "overview" %} "active" {% else %} "" {% endif %} >
130 |                 <a href="/index/?action=overview">概 述</a>
131 |             </li>
132 |             <li class={% if page_type == "zhihu_topics" %} "active" {% else %} "" {% endif %} >
133 |                 <a href="/index/?action=zhihu_topics">知乎话题关系</a>
134 |             </li>
135 |         </ul>
136 |     </div>
137 | 
138 |     <div class="col-sm-9 col-sm-offset-3 col-md-10 col-md-offset-2 main" style="padding-left: 20px; padding-right: 20px">
139 |         {% for message in get_flashed_messages() %}
140 |         <div class="alert alert-warning">
141 |             <button type="button" class="close" data-dismiss="alert">&times;</button>
142 |             {{ message }}
143 |         </div>
144 |         {% endfor %}
145 | 
146 |         {% if page_type == "overview" %}
147 |             <h2>数据展示，点击左边菜单栏即可查看各类数据展示页面</h2>
148 |         {% elif page_type == "zhihu_topics" %}
149 |             <div class="nav navbar-nav navbar-right">
150 |                 <input type="text" class="form-control" id="zhihusearch" data-provide="typeahead" placeholder="Search Topic...">
151 |             </div>
152 |             <div id="show_data_zhihu" style="width: 900px; height:600px;"></div>
153 | 
154 |             <script type="text/javascript">
155 |                 zhihu_topics();
156 |             </script>
157 |         {% endif %}
158 |     </div>
159 | </div>
160 | {% endblock %}
161 | 
162 | {% block scripts %}
163 | <script type="text/javascript">
164 | </script>
165 | {% endblock %}
166 | 


--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
 1 | # LearnPython
 2 | 以撸代码的形式学习Python, 具体说明在[知乎专栏-撸代码,学知识](https://zhuanlan.zhihu.com/pythoner)  
 3 | 
 4 | ===================================================================================================
 5 | ### python_base.py: 千行代码入门Python
 6 | 
 7 | ### python_visual.py: 15张图入门Matplotlib
 8 | 
 9 | ### python_visual_animation.py: 使用Matplotlib画动态图实例
10 | 
11 | ### python_spider.py: 一个很“水”的Python爬虫入门代码文件
12 | 
13 | ### python_weibo.py: “史上最详细”的Python模拟登录新浪微博流程
14 | 
15 | ### python_lda.py: 玩点高级的--带你入门Topic模型LDA（小改进+附源码）
16 | 
17 | ### python_sqlalchemy.py: 作为一个Pythoner, 不会SQLAlchemy都不好意思跟同行打招呼！
18 | 
19 | ### python_oneline.py: 几个小例子告诉你, 一行Python代码能干哪些事
20 | 
21 | ### python_requests.py: Python中最好用的爬虫库Requests代码实例
22 | 
23 | ### python_functional.py: Python进阶: 函数式编程实例（附代码）
24 | 
25 | ### python_decorator.py: Python进阶: 通过实例详解装饰器（附代码）
26 | 
27 | ### python_datetime.py: 你真的了解Python中的日期时间处理吗？
28 | 
29 | ### python_metaclass.py: Python进阶: 一步步理解Python中的元类metaclass
30 | 
31 | ### python_coroutine.py: Python进阶: 理解Python中的异步IO和协程(Coroutine), 并应用在爬虫中
32 | 
33 | ### python_aiohttp.py: Python中最好用的异步爬虫库Aiohttp代码实例
34 | 
35 | ### python_thread_multiprocess.py: Python进阶: 聊聊IO密集型任务、计算密集型任务，以及多线程、多进程
36 | 
37 | ### python_version36.py: Python3.6正式版要来了, 你期待哪些新特性？
38 | 
39 | ### python_magic_methods: Python进阶: 实例讲解Python中的魔法函数(Magic Methods)
40 | 
41 | ### python_restful_api.py: 利用Python和Flask快速开发RESTful API
42 | 
43 | ### python_restful_api.py: RESTful API进阶: 连接数据库、添加参数、Token认证、返回代码说明等
44 | 
45 | ### python_context.py: With语句和上下文管理器ContextManager
46 | 
47 | ### python_flask.py: Flask相关说明
48 | 
49 | ### MyShow: 玩点好玩的--知乎全部话题关系可视化
50 | 
51 | ### python_markov_chain.py: 玩点好玩的--使用马尔可夫模型自动生成文章
52 | 
53 | ### python_wechat.py: 玩点好玩的--自己写一个微信小助手
54 | 
55 | ### python_csv.py: Python中CSV文件的简单读写  
56 | 
57 | ### python_numpy.py: 使用numpy进行矩阵操作
58 | ===================================================================================================
59 | 
60 | ### 您可以fork该项目, 并在修改后提交Pull request, 看到后会尽量进行代码合并
61 | 


--------------------------------------------------------------------------------
/python_aiohttp.py:
--------------------------------------------------------------------------------
  1 | # _*_ coding: utf-8 _*_
  2 | 
  3 | """
  4 | python_aiohttp.py by xianhu
  5 | """
  6 | 
  7 | import asyncio
  8 | import aiohttp
  9 | 
 10 | 
 11 | # 简单实例
 12 | async def aiohttp_test01(url):
 13 |     async with aiohttp.ClientSession() as session:
 14 |         async with session.get(url) as resp:
 15 |             print(resp.status)
 16 |             print(await resp.text())
 17 | 
 18 | loop = asyncio.get_event_loop()
 19 | tasks = [aiohttp_test01("https://api.github.com/events")]
 20 | loop.run_until_complete(asyncio.wait(tasks))
 21 | loop.close()
 22 | 
 23 | # 其他Http方法
 24 | # session.post('http://httpbin.org/post', data=b'data')
 25 | # session.put('http://httpbin.org/put', data=b'data')
 26 | # session.delete('http://httpbin.org/delete')
 27 | # session.head('http://httpbin.org/get')
 28 | # session.options('http://httpbin.org/get')
 29 | # session.patch('http://httpbin.org/patch', data=b'data')
 30 | 
 31 | # 自定义Headers
 32 | # payload = {'some': 'data'}
 33 | # headers = {'content-type': 'application/json'}
 34 | # await session.post(url, data=json.dumps(payload), headers=headers)
 35 | 
 36 | # 自定义Cookie
 37 | # cookies = {'cookies_are': 'working'}
 38 | # async with ClientSession(cookies=cookies) as session:
 39 | # 访问Cookie: session.cookie_jar
 40 | 
 41 | # 在URLs中传递参数
 42 | # 1. params = {'key1': 'value1', 'key2': 'value2'}
 43 | # 2. params = [('key', 'value1'), ('key', 'value2')]
 44 | # async with session.get('http://httpbin.org/get', params=params) as resp:
 45 | #     assert resp.url == 'http://httpbin.org/get?key2=value2&key1=value1'
 46 | 
 47 | # 发送数据
 48 | # payload = {'key1': 'value1', 'key2': 'value2'}
 49 | # async with session.post('http://httpbin.org/post', data=payload) as resp:
 50 | # async with session.post(url, data=json.dumps(payload)) as resp:
 51 | #     print(await resp.text())
 52 | 
 53 | # 发送文件(1)
 54 | # files = {'file': open('report.xls', 'rb')}
 55 | # await session.post(url, data=files)
 56 | 
 57 | # 发送数据(2)
 58 | # data = FormData()
 59 | # data.add_field('file',
 60 | #                open('report.xls', 'rb'),
 61 | #                filename='report.xls',
 62 | #                content_type='application/vnd.ms-excel')
 63 | # await session.post(url, data=data)
 64 | 
 65 | # 超时设置
 66 | # aync with session.get('https://github.com', timeout=60) as r:
 67 | 
 68 | # 代理支持
 69 | # async with aiohttp.ClientSession() as session:
 70 | #     async with session.get("http://python.org", proxy="http://some.proxy.com") as resp:
 71 | #         print(resp.status)
 72 | 
 73 | # async with aiohttp.ClientSession() as session:
 74 | #     proxy_auth = aiohttp.BasicAuth('user', 'pass')
 75 | #     async with session.get("http://python.org", proxy="http://some.proxy.com", proxy_auth=proxy_auth) as resp:
 76 | #         print(resp.status)
 77 | # session.get("http://python.org", proxy="http://user:pass@some.proxy.com")
 78 | 
 79 | # 返回的内容
 80 | # async with session.get('https://api.github.com/events') as resp:
 81 | #     print(await resp.text())
 82 | #     print(await resp.text(encoding='gbk'))
 83 | #     print(await resp.read())
 84 | #     print(await resp.json())
 85 | 
 86 | # 返回内容较大
 87 | # with open(filename, 'wb') as fd:
 88 | #     while True:
 89 | #         chunk = await resp.content.read(chunk_size)
 90 | #         if not chunk:
 91 | #             break
 92 | #         fd.write(chunk)
 93 | 
 94 | # 返回的其他变量
 95 | # async with session.get('http://httpbin.org/get') as resp:
 96 | #     print(resp.status)        # 状态码
 97 | #     print(resp.headers)       # Headers
 98 | #     print(resp.raw_headers)   # 原始Headers
 99 | #     print(resp.cookies)       # 返回的Cookie
100 | 
101 | # 访问历史History
102 | # resp = await session.get('http://example.com/some/redirect/')
103 | # resp: <ClientResponse(http://example.com/some/other/url/) [200]>
104 | # resp.history: (<ClientResponse(http://example.com/some/redirect/) [301]>,)
105 | 
106 | # 释放返回的Response
107 | # 1. async with session.get(url) as resp: pass
108 | # 2. await resp.release()
109 | 
110 | # 连接器: Connectors
111 | # conn = aiohttp.TCPConnector()
112 | # session = aiohttp.ClientSession(connector=conn)
113 | 
114 | # 限制连接池大小:
115 | # conn = aiohttp.TCPConnector(limit=30)
116 | # conn = aiohttp.TCPConnector(limit=None)
117 | 


--------------------------------------------------------------------------------
/python_context.py:
--------------------------------------------------------------------------------
 1 | # _*_ coding: utf-8 _*_
 2 | 
 3 | """
 4 | python_context.py by xianhu
 5 | """
 6 | 
 7 | import contextlib
 8 | 
 9 | 
10 | # 自定义打开文件操作
11 | class MyOpen(object):
12 | 
13 |     def __init__(self, file_name):
14 |         """初始化方法"""
15 |         self.file_name = file_name
16 |         self.file_handler = None
17 |         return
18 | 
19 |     def __enter__(self):
20 |         """enter方法，返回file_handler"""
21 |         print("enter:", self.file_name)
22 |         self.file_handler = open(self.file_name, "r")
23 |         return self.file_handler
24 | 
25 |     def __exit__(self, exc_type, exc_val, exc_tb):
26 |         """exit方法，关闭文件并返回True"""
27 |         print("exit:", exc_type, exc_val, exc_tb)
28 |         if self.file_handler:
29 |             self.file_handler.close()
30 |         return True
31 | 
32 | # 使用实例
33 | with MyOpen("python_base.py") as file_in:
34 |     for line in file_in:
35 |         print(line)
36 |         raise ZeroDivisionError
37 | # 代码块中主动引发一个除零异常，但整个程序不会引发异常
38 | 
39 | 
40 | # 内置库contextlib的使用
41 | @contextlib.contextmanager
42 | def open_func(file_name):
43 |     # __enter__方法
44 |     print("open file:", file_name, "in __enter__")
45 |     file_handler = open(file_name, "r")
46 | 
47 |     yield file_handler
48 | 
49 |     # __exit__方法
50 |     print("close file:", file_name, "in __exit__")
51 |     file_handler.close()
52 |     return
53 | 
54 | # 使用实例
55 | with open_func("python_base.py") as file_in:
56 |     for line in file_in:
57 |         print(line)
58 |         break
59 | 
60 | 
61 | # 内置库contextlib的使用
62 | class MyOpen2(object):
63 | 
64 |     def __init__(self, file_name):
65 |         """初始化方法"""
66 |         self.file_handler = open(file_name, "r")
67 |         return
68 | 
69 |     def close(self):
70 |         """关闭文件，会被自动调用"""
71 |         print("call close in MyOpen2")
72 |         if self.file_handler:
73 |             self.file_handler.close()
74 |         return
75 | 
76 | # 使用实例
77 | with contextlib.closing(MyOpen2("python_base.py")) as file_in:
78 |     pass
79 | 


--------------------------------------------------------------------------------
/python_coroutine.py:
--------------------------------------------------------------------------------
 1 | # _*_ coding: utf-8 _*_
 2 | 
 3 | """
 4 | python_coroutine.py by xianhu
 5 | """
 6 | 
 7 | import asyncio
 8 | import aiohttp
 9 | import threading
10 | 
11 | 
12 | # 生产者、消费者例子
13 | def consumer():         # 定义消费者，由于有yeild关键词，此消费者为一个生成器
14 |     print("[Consumer] Init Consumer ......")
15 |     r = "init ok"       # 初始化返回结果，并在启动消费者时，返回给生产者
16 |     while True:
17 |         n = yield r     # 消费者通过yield关键词接收生产者产生的消息，同时返回结果给生产者
18 |         print("[Consumer] conusme n = %s, r = %s" % (n, r))
19 |         r = "consume %s OK" % n     # 消费者消费结果，下个循环返回给生产者
20 | 
21 | 
22 | def produce(c):         # 定义生产者，此时的 c 为一个生成器
23 |     print("[Producer] Init Producer ......")
24 |     r = c.send(None)    # 启动消费者生成器，同时第一次接收返回结果
25 |     print("[Producer] Start Consumer, return %s" % r)
26 |     n = 0
27 |     while n < 5:
28 |         n += 1
29 |         print("[Producer] While, Producing %s ......" % n)
30 |         r = c.send(n)   # 向消费者发送消息，同时准备接收结果。此时会切换到消费者执行
31 |         print("[Producer] Consumer return: %s" % r)
32 |     c.close()           # 关闭消费者生成器
33 |     print("[Producer] Close Producer ......")
34 | 
35 | # produce(consumer())
36 | 
37 | 
38 | # 异步IO例子：适配Python3.4，使用asyncio库
39 | @asyncio.coroutine
40 | def hello(index):                   # 通过装饰器asyncio.coroutine定义协程
41 |     print('Hello world! index=%s, thread=%s' % (index, threading.currentThread()))
42 |     yield from asyncio.sleep(1)     # 模拟IO任务
43 |     print('Hello again! index=%s, thread=%s' % (index, threading.currentThread()))@asyncio.coroutine
44 | 
45 | loop = asyncio.get_event_loop()     # 得到一个事件循环模型
46 | tasks = [hello(1), hello(2)]        # 初始化任务列表
47 | loop.run_until_complete(asyncio.wait(tasks))    # 执行任务
48 | loop.close()                        # 关闭事件循环列表
49 | 
50 | 
51 | # 异步IO例子：适配Python3.5，使用async和await关键字
52 | async def hello1(index):            # 通过关键字async定义协程
53 |     print('Hello world! index=%s, thread=%s' % (index, threading.currentThread()))
54 |     await asyncio.sleep(1)          # 模拟IO任务
55 |     print('Hello again! index=%s, thread=%s' % (index, threading.currentThread()))
56 | 
57 | loop = asyncio.get_event_loop()     # 得到一个事件循环模型
58 | tasks = [hello1(1), hello1(2)]      # 初始化任务列表
59 | loop.run_until_complete(asyncio.wait(tasks))    # 执行任务
60 | loop.close()                        # 关闭事件循环列表
61 | 
62 | 
63 | # aiohttp 实例
64 | async def get(url):
65 |     async with aiohttp.ClientSession() as session:
66 |         async with session.get(url) as resp:
67 |             print(url, resp.status)
68 |             print(url, await resp.text())
69 | 
70 | loop = asyncio.get_event_loop()     # 得到一个事件循环模型
71 | tasks = [                           # 初始化任务列表
72 |     get("http://zhushou.360.cn/detail/index/soft_id/3283370"),
73 |     get("http://zhushou.360.cn/detail/index/soft_id/3264775"),
74 |     get("http://zhushou.360.cn/detail/index/soft_id/705490")
75 | ]
76 | loop.run_until_complete(asyncio.wait(tasks))    # 执行任务
77 | loop.close()                        # 关闭事件循环列表
78 | 


--------------------------------------------------------------------------------
/python_csv.py:
--------------------------------------------------------------------------------
 1 | # _*_ coding: utf-8 _*_
 2 | 
 3 | """
 4 | python_csv.py by xianhu
 5 | """
 6 | 
 7 | import csv
 8 | import datetime
 9 | 
10 | # 数据
11 | data = [
12 |     [1, "a,bc", 19.353, datetime.datetime(2001, 3, 17)],
13 |     [2, "ei,f", 13.287, datetime.datetime(2011, 4, 27)],
14 |     [3, "q\"ij", 15.852, datetime.datetime(2003, 7, 14)],
15 |     [4, "zh'n", 11.937, datetime.datetime(2012, 1, 9)],
16 |     [5, "i\'op", 12.057, datetime.datetime(2009, 5, 18)],
17 | ]
18 | 
19 | # 写文件
20 | with open("test.csv", "w") as file:
21 |     writer = csv.writer(file, dialect="excel")
22 |     # writer.writerows(data)
23 |     for item in data:
24 |         writer.writerow(item)
25 | 
26 | # 读文件
27 | with open("test.csv", "r") as file:
28 |     reader = csv.reader(file, dialect="excel")
29 |     for item in reader:
30 |         print(item)
31 | 
32 | # 读文件
33 | with open("test.csv", "r") as file:
34 |     reader = csv.DictReader(file, fieldnames=["id", "name", "float", "datetime"], dialect="excel")
35 |     data = [item for item in reader]
36 |     print(data)
37 | 
38 | # 写文件
39 | with open("test.csv", "w") as file:
40 |     writer = csv.DictWriter(file, fieldnames=["id", "name", "float", "datetime"], dialect="excel")
41 |     writer.writeheader()
42 |     for item in data:
43 |         writer.writerow(item)
44 | 


--------------------------------------------------------------------------------
/python_datetime.py:
--------------------------------------------------------------------------------
 1 | # _*_ coding: utf-8 _*_
 2 | 
 3 | import time
 4 | import calendar
 5 | import datetime
 6 | 
 7 | 
 8 | # time模块中的三种时间形式
 9 | print("time stamp:", time.time())               # 时间戳
10 | print("local time:", time.localtime())          # struct_time类型的本地时间
11 | print("utc time:", time.gmtime())               # struct_time类型的utc时间
12 | 
13 | # time模块中，三种时间形式之间的转换
14 | time_stamp = time.time()                        # 时间戳
15 | local_time = time.localtime(time_stamp)         # 时间戳转struct_time类型的本地时间
16 | utc_time = time.gmtime(time_stamp)              # 时间戳转struct_time类型的utc时间
17 | 
18 | time_stamp_1 = time.mktime(local_time)          # struct_time类型的本地时间转时间戳
19 | time_stamp_2 = calendar.timegm(utc_time)        # struct_time类型的utc时间转时间戳
20 | print(time_stamp, time_stamp_1, time_stamp_2)
21 | 
22 | 
23 | # time模块中，三种时间形式和字符串之间的转换
24 | print(time.ctime(time_stamp))           # 时间戳转字符串(本地时间字符串)
25 | 
26 | print(time.asctime(local_time))         # struct_time类型的本地时间转字符串
27 | print(time.asctime(utc_time))           # struct_time类型的utc时间转字符串
28 | 
29 | print(time.strftime("%Y-%m-%d, %H:%M:%S, %w", local_time))      # struct_time类型的本地时间转字符串：自定义格式
30 | print(time.strftime("%Y-%m-%d, %H:%M:%S, %w", utc_time))        # struct_time类型的utc时间转字符串：自定义格式
31 | 
32 | struct_time = time.strptime("2016-11-15, 15:32:12, 2", "%Y-%m-%d, %H:%M:%S, %w")       # 字符串转struct_time类型
33 | 
34 | 
35 | # datetime模块中datetime类的用法
36 | a_datetime_local = datetime.datetime.now()                      # 获取datetime.datetime类型的本地时间
37 | a_datetime_utc = datetime.datetime.utcnow()                     # 获取datetime.datetime类型的utc时间
38 | 
39 | print(a_datetime_local.strftime("%Y-%m-%d, %H:%M:%S, %w"))      # datetime.datetime类型转字符串
40 | print(a_datetime_utc.strftime("%Y-%m-%d, %H:%M:%S, %w"))        # datetime.datetime类型转字符串
41 | 
42 | a_datetime = datetime.datetime.strptime("2016-11-15, 15:32:12, 2", "%Y-%m-%d, %H:%M:%S, %w")    # 字符串转datetime.datetime格式
43 | 
44 | 
45 | # datetime.datetime类和时间戳、struct_time类型之间的转换
46 | time_stamp = a_datetime_local.timestamp()                           # datetime类型转时间戳
47 | print(time_stamp)
48 | 
49 | a_datetime_local = datetime.datetime.fromtimestamp(time.time())     # 时间戳转datetime.datetime类型的本地时间
50 | a_datetime_utc = datetime.datetime.utcfromtimestamp(time.time())    # 时间戳转datetime.datetime类型的utc时间
51 | print(a_datetime_local, a_datetime_utc)
52 | 
53 | print(a_datetime_local.timetuple())                 # datetime类型转struct_time类型
54 | print(a_datetime_utc.utctimetuple())                # datetime类型转struct_time类型
55 | 


--------------------------------------------------------------------------------
/python_decorator.py:
--------------------------------------------------------------------------------
  1 | # _*_ coding: utf-8 _*_
  2 | 
  3 | """
  4 | python_decorator.py by xianhu
  5 | """
  6 | 
  7 | import functools
  8 | 
  9 | 
 10 | # 构建不带参数的装饰器
 11 | def logging(func):
 12 |     @functools.wraps(func)
 13 |     def decorator(*args, **kwargs):
 14 |         print("%s called" % func.__name__)
 15 |         result = func(*args, **kwargs)
 16 |         print("%s end" % func.__name__)
 17 |         return result
 18 |     return decorator
 19 | 
 20 | 
 21 | # 使用装饰器
 22 | @logging
 23 | def test01(a, b):
 24 |     print("in function test01, a=%s, b=%s" % (a, b))
 25 |     return 1
 26 | 
 27 | 
 28 | # 使用装饰器
 29 | @logging
 30 | def test02(a, b, c=1):
 31 |     print("in function test02, a=%s, b=%s, c=%s" % (a, b, c))
 32 |     return 1
 33 | 
 34 | 
 35 | # 构建带参数的装饰器
 36 | def params_chack(*types, **kwtypes):
 37 |     def _outer(func):
 38 |         @functools.wraps(func)
 39 |         def _inner(*args, **kwargs):
 40 |             result = [isinstance(_param, _type) for _param, _type in zip(args, types)]
 41 |             assert all(result), "params_chack: invalid parameters"
 42 |             result = [isinstance(kwargs[_param], kwtypes[_param]) for _param in kwargs if _param in kwtypes]
 43 |             assert all(result), "params_chack: invalid parameters"
 44 |             return func(*args, **kwargs)
 45 |         return _inner
 46 |     return _outer
 47 | 
 48 | 
 49 | # 使用装饰器
 50 | @params_chack(int, (list, tuple))
 51 | def test03(a, b):
 52 |     print("in function test03, a=%s, b=%s" % (a, b))
 53 |     return 1
 54 | 
 55 | 
 56 | # 使用装饰器
 57 | @params_chack(int, str, c=(int, str))
 58 | def test04(a, b, c):
 59 |     print("in function test04, a=%s, b=%s, c=%s" % (a, b, c))
 60 |     return 1
 61 | 
 62 | 
 63 | # 在类的成员方法中使用装饰器
 64 | class ATest(object):
 65 |     @params_chack(object, int, str)
 66 |     def test(self, a, b):
 67 |         print("in function test of ATest, a=%s, b=%s" % (a, b))
 68 |         return 1
 69 | 
 70 | 
 71 | # 同时使用多个装饰器
 72 | @logging
 73 | @params_chack(int, str, (list, tuple))
 74 | def test05(a, b, c):
 75 |     print("in function test05, a=%s, b=%s, c=%s" % (a, b, c))
 76 |     return 1
 77 | 
 78 | 
 79 | # 构建不带参数的装饰器类
 80 | class Decorator(object):
 81 | 
 82 |     def __init__(self, func):
 83 |         self.func = func
 84 |         return
 85 | 
 86 |     def __call__(self, *args, **kwargs):
 87 |         print("%s called" % self.func.__name__)
 88 |         result = self.func(*args, **kwargs)
 89 |         print("%s end" % self.func.__name__)
 90 |         return result
 91 | 
 92 | 
 93 | # 使用装饰器
 94 | @Decorator
 95 | def test06(a, b, c):
 96 |     print("in function test06, a=%s, b=%s, c=%s" % (a, b, c))
 97 |     return 1
 98 | 
 99 | 
100 | # 构建带参数的装饰器类
101 | class ParamCheck(object):
102 | 
103 |     def __init__(self, *types, **kwtypes):
104 |         self.types = types
105 |         self.kwtypes = kwtypes
106 |         return
107 | 
108 |     def __call__(self, func):
109 |         @functools.wraps(func)
110 |         def _inner(*args, **kwargs):
111 |             result = [isinstance(_param, _type) for _param, _type in zip(args, self.types)]
112 |             assert all(result), "params_chack: invalid parameters"
113 |             result = [isinstance(kwargs[_param], self.kwtypes[_param]) for _param in kwargs if _param in self.kwtypes]
114 |             assert all(result), "params_chack: invalid parameters"
115 |             return func(*args, **kwargs)
116 |         return _inner
117 | 
118 | 
119 | # 使用装饰器
120 | @ParamCheck(int, str, (list, tuple))
121 | def test07(a, b, c):
122 |     print("in function test06, a=%s, b=%s, c=%s" % (a, b, c))
123 |     return 1
124 | 
125 | 
126 | # 装饰器实例: 函数缓存
127 | def funccache(func):
128 |     cache = {}
129 | 
130 |     @functools.wraps(func)
131 |     def _inner(*args):
132 |         if args not in cache:
133 |             cache[args] = func(*args)
134 |         return cache[args]
135 |     return _inner
136 | 
137 | 
138 | # 使用装饰器
139 | @funccache
140 | def test08(a, b, c):
141 |     # 其他复杂或耗时计算
142 |     return a + b + c
143 | 
144 | 
145 | # 使用Python自带的装饰器 @property
146 | class Person(object):
147 | 
148 |     def __init__(self):
149 |         self._name = None
150 |         return
151 | 
152 |     def get_name(self):
153 |         print("get_name")
154 |         return self._name
155 | 
156 |     def set_name(self, name):
157 |         print("set_name")
158 |         self._name = name
159 |         return
160 | 
161 |     name = property(fget=get_name, fset=set_name, doc="person name")
162 | 
163 | 
164 | # 使用Python自带的装饰器 @property
165 | class People(object):
166 | 
167 |     def __init__(self):
168 |         self._name = None
169 |         self._age = None
170 |         return
171 | 
172 |     @property
173 |     def name(self):
174 |         return self._name
175 | 
176 |     @name.setter
177 |     def name(self, name):
178 |         self._name = name
179 |         return
180 | 
181 |     @property
182 |     def age(self):
183 |         return self._age
184 | 
185 |     @age.setter
186 |     def age(self, age):
187 |         assert 0 < age < 120
188 |         self._age = age
189 |         return
190 | 
191 | 
192 | # 类静态方法和类方法
193 | class A(object):
194 |     var = 1
195 | 
196 |     def func(self):
197 |         print(self.var)
198 |         return
199 | 
200 |     @staticmethod
201 |     def static_func():
202 |         print(A.var)
203 |         return
204 | 
205 |     @classmethod
206 |     def class_func(cls):
207 |         print(cls.var)
208 |         cls().func()
209 |         return
210 | 


--------------------------------------------------------------------------------
/python_flask.py:
--------------------------------------------------------------------------------
  1 | # _*_ coding: utf-8 _*_
  2 | 
  3 | # Flask中的一些定义
  4 | # =============================================================================================================================
  5 | # WSGI: Web服务器网关接口，是一种Web服务使用的协议。
  6 | # 路由: 处理URL和函数之间关系的程序称为"路由"。
  7 | # 视图函数: 类似于index()这样的，被app.route装饰器注册为路由的函数，或者通过app.add_url_rule()添加路由映射关系的函数，被称为视图函数。
  8 | # app.route(): 路由装饰器，可以带参数，参数可以指定数据类型：int/float/path。path类似于字符串，但不将反斜线/当做分隔符。
  9 | # =============================================================================================================================
 10 | 
 11 | # Flask上下文全局变量
 12 | # =============================================================================================================================
 13 | # current_app: 程序上下文，当前激活程序的程序实例，所有线程公用一个该实例。
 14 | # g: 程序上下文，处理请求时用作临时存储的对象，每次请求都会重设这个变量。
 15 | # request: 请求上下文，请求对象，封装了客户端发出的 HTTP 请求中的内容，不同线程之间互不干扰。
 16 | # session: 请求上下问，用户会话，用于存储请求之间需要“记住”的值的词典。
 17 | # =============================================================================================================================
 18 | 
 19 | # Flask支持的4种钩子函数
 20 | # =============================================================================================================================
 21 | # before_first_request: 注册一个函数，在处理第一个请求之前运行。
 22 | # before_request: 注册一个函数，在每次请求之前运行。
 23 | # after_request: 注册一个函数，如果没有未处理的异常抛出，在每次请求之后运行。
 24 | # teardown_request:注册一个函数，即使有未处理的异常抛出，也在每次请求之后运行。
 25 | # =============================================================================================================================
 26 | 
 27 | # Jinja2模板使用
 28 | # =============================================================================================================================
 29 | # 渲染模板: render_template("user.html", name=name)
 30 | # (1) 变量: {{ name | capitalize }}
 31 | # (2) 控制结构:
 32 | #     {% if user %}
 33 | #       Hello, {{ user }}!
 34 | #     {% else %}
 35 | #       Hello, Stranger!
 36 | #     {% endif %}
 37 | #
 38 | #     <ul>
 39 | #     {% for comment in comments %}
 40 | #       <li>{{ comment }}</li> {% endfor %}
 41 | #     </ul>
 42 | # (3) 宏-类似于函数:
 43 | #     {% macro render_comment(comment) %}
 44 | #       <li>{{ comment }}</li>
 45 | #     {% endmacro %}
 46 | #
 47 | #     <ul>
 48 | #     {% for comment in comments %}
 49 | #       {{ render_comment(comment) }}
 50 | #     {% endfor %}
 51 | #     </ul>
 52 | # =============================================================================================================================
 53 | 
 54 | # Jinja2变量过滤器
 55 | # =============================================================================================================================
 56 | # safe: 渲染值时不转义
 57 | # capitalize: 把值的首字母转换成大写，其他字母转换成小写
 58 | # lower: 把值转换成小写形式
 59 | # upper: 把值转换成大写形式
 60 | # title: 把值中每个单词的首字母都转换成大写
 61 | # trim: 把值的首尾空格去掉
 62 | # striptags: 渲染之前把值中所有的 HTML 标签都删掉
 63 | # =============================================================================================================================
 64 | 
 65 | # Flask-Bootstrap基模板中定义的块
 66 | # =============================================================================================================================
 67 | # doc: 整个 HTML 文档
 68 | # html_attribs: <html> 标签的属性
 69 | # html: <html> 标签中的内容
 70 | # head: <head> 标签中的内容
 71 | # title: <title> 标签中的内容
 72 | # metas: 一组 <meta> 标签
 73 | # styles: 层叠样式表定义
 74 | # body_attribs: <body> 标签的属性
 75 | # body: <body> 标签中的内容
 76 | # navbar: 用户定义的导航条
 77 | # content: 用户定义的页面内容
 78 | # scripts: 文档底部的 JavaScript 声明
 79 | # =============================================================================================================================
 80 | 
 81 | # WTForms支持的HTML标准字段，注意添加app.config['SECRET_KEY'] = 'hard to guess string'
 82 | # =============================================================================================================================
 83 | # StringField 文本字段
 84 | # TextAreaField 多行文本字段
 85 | # PasswordField 密码文本字段
 86 | # HiddenField 隐藏文本字段
 87 | # DateField 值为datatime.data格式的文本字段
 88 | # DateTimeField 值为datatime.datatime格式的文本字段
 89 | # DecimalField 值为decimal.Decimal格式的文本字段
 90 | # IntegerField 值为整数的文本字段
 91 | # FloatField 值为浮点数的文本字段
 92 | # BooleanField 值为True或False的复选框
 93 | # RadioField 一组单选框
 94 | # SelectField 值唯一的下拉列表
 95 | # SelectMultipleField 可选多个值得下拉列表
 96 | # FileField 文件上传字段
 97 | # SubmitField 表单提交按钮
 98 | # FormField 把表单作为字段嵌入另一个表单
 99 | # FieldList 一组指定类型的字段
100 | # =============================================================================================================================
101 | 
102 | # WTForms验证函数
103 | # =============================================================================================================================
104 | # Email 验证电子邮件地址
105 | # EqualTo 比较两个字段的值;常用于要求输入两次密码进行确认的情况
106 | # IPAddress 验证 IPv4 网络地址
107 | # Length 验证输入字符串的长度
108 | # NumberRange 验证输入的值在数字范围内
109 | # Optional 无输入值时跳过其他验证函数
110 | # Required / DataRequired 确保字段中有数据
111 | # Regexp 使用正则表达式验证输入值
112 | # URL 验证 URL
113 | # AnyOf 确保输入值在可选值列表中
114 | # NoneOf 确保输入值不在可选值列表中
115 | # =============================================================================================================================
116 | 
117 | # uWSGI配置和nginx配置
118 | # =============================================================================================================================
119 | # uwsgi -s /tmp/uwsgi.sock -w MyShow:app --chmod-socket=666
120 | # server {
121 | #     listen          80;
122 | #     server_name     wangluopachong.com;
123 | #
124 | #     charset         utf-8;
125 | #
126 | #     location / {
127 | #         include uwsgi_params;
128 | #         uwsgi_pass unix:/tmp/uwsgi.sock;
129 | #     }
130 | # =============================================================================================================================
131 | 


--------------------------------------------------------------------------------
/python_functional.py:
--------------------------------------------------------------------------------
 1 | # _*_ coding: utf-8 _*_
 2 | 
 3 | from fn import _
 4 | from operator import add
 5 | from functools import partial, reduce
 6 | 
 7 | # 列表解析
 8 | a_list = [item**2 for item in range(5)]
 9 | print(a_list)
10 | 
11 | # 字典解析
12 | a_dict = {"%d^2" % item: item**2 for item in range(5)}
13 | print(a_dict)
14 | 
15 | # 生成器
16 | a_generator = (item**2 for item in range(5))
17 | print(a_generator)
18 | print(next(a_generator))
19 | print(next(a_generator))
20 | 
21 | # iter函数和next函数
22 | a_list_generator = iter(a_list)
23 | print(next(a_list_generator))
24 | print(next(a_list_generator))
25 | print(type(a_list), type(a_list_generator))
26 | 
27 | # lambda表达式
28 | a_func = lambda x, y: x**y
29 | print(a_func(2, 3))
30 | 
31 | # map函数
32 | print(map(abs, range(-4, 5)))
33 | print(list(map(abs, range(-4, 5))))
34 | print(list(map(lambda x: x**2, range(5))))
35 | print(list(map(lambda x, y: x**y, range(1, 5), range(1, 5))))
36 | 
37 | # reduce函数
38 | print(reduce(lambda x, y: x+y, range(10)))
39 | print(reduce(lambda x, y: x+y, range(10), 100))
40 | print(reduce(lambda x, y: x+y, [[1, 2], [3, 4]], [0]))
41 | 
42 | # filter函数
43 | print(filter(None, range(-4, 5)))
44 | print(list(filter(None, range(-4, 5))))
45 | print(list(filter(lambda x: x > 0, range(-4, 5))))
46 | 
47 | # all、any函数
48 | print(all([0, 1, 2]))
49 | print(any([0, 1, 2]))
50 | 
51 | # enumerate函数
52 | for index, item in enumerate(range(5)):
53 |     print("%d: %d" % (index, item))
54 | 
55 | # zip函数
56 | for a, b in zip([1, 2, 3], ["a", "b", "c"]):
57 |     print(a, b)
58 | a_dict = dict(zip([1, 2, 3], ["a", "b", "c"]))
59 | print(a_dict)
60 | 
61 | # partial函数
62 | print(int("10010", base=2))
63 | int_base_2 = partial(int, base=2)
64 | print(int_base_2("10010"))
65 | 
66 | # operator.add函数
67 | print(reduce(lambda x, y: x+y, range(10)))
68 | print(reduce(add, range(10)))
69 | 
70 | # fn的使用
71 | add_func_1 = (_ + 2)
72 | print(add_func_1(1))
73 | add_func_2 = (_ + _ * _)
74 | print(add_func_2(1, 2, 3))
75 | 


--------------------------------------------------------------------------------
/python_lda.py:
--------------------------------------------------------------------------------
  1 | # _*_ coding: utf-8 _*_
  2 | 
  3 | """
  4 | python_lda.py by xianhu
  5 | """
  6 | 
  7 | import os
  8 | import numpy
  9 | import logging
 10 | from collections import defaultdict
 11 | 
 12 | # 全局变量
 13 | MAX_ITER_NUM = 10000    # 最大迭代次数
 14 | VAR_NUM = 20            # 自动计算迭代次数时,计算方差的区间大小
 15 | 
 16 | 
 17 | class BiDictionary(object):
 18 |     """
 19 |     定义双向字典,通过key可以得到value,通过value也可以得到key
 20 |     """
 21 | 
 22 |     def __init__(self):
 23 |         """
 24 |         :key: 双向字典初始化
 25 |         """
 26 |         self.dict = {}            # 正向的数据字典,其key为self的key
 27 |         self.dict_reversed = {}   # 反向的数据字典,其key为self的value
 28 |         return
 29 | 
 30 |     def __len__(self):
 31 |         """
 32 |         :key: 获取双向字典的长度
 33 |         """
 34 |         return len(self.dict)
 35 | 
 36 |     def __str__(self):
 37 |         """
 38 |         :key: 将双向字典转化为字符串对象
 39 |         """
 40 |         str_list = ["%s\t%s" % (key, self.dict[key]) for key in self.dict]
 41 |         return "\n".join(str_list)
 42 | 
 43 |     def clear(self):
 44 |         """
 45 |         :key: 清空双向字典对象
 46 |         """
 47 |         self.dict.clear()
 48 |         self.dict_reversed.clear()
 49 |         return
 50 | 
 51 |     def add_key_value(self, key, value):
 52 |         """
 53 |         :key: 更新双向字典,增加一项
 54 |         """
 55 |         self.dict[key] = value
 56 |         self.dict_reversed[value] = key
 57 |         return
 58 | 
 59 |     def remove_key_value(self, key, value):
 60 |         """
 61 |         :key: 更新双向字典,删除一项
 62 |         """
 63 |         if key in self.dict:
 64 |             del self.dict[key]
 65 |             del self.dict_reversed[value]
 66 |         return
 67 | 
 68 |     def get_value(self, key, default=None):
 69 |         """
 70 |         :key: 通过key获取value,不存在返回default
 71 |         """
 72 |         return self.dict.get(key, default)
 73 | 
 74 |     def get_key(self, value, default=None):
 75 |         """
 76 |         :key: 通过value获取key,不存在返回default
 77 |         """
 78 |         return self.dict_reversed.get(value, default)
 79 | 
 80 |     def contains_key(self, key):
 81 |         """
 82 |         :key: 判断是否存在key值
 83 |         """
 84 |         return key in self.dict
 85 | 
 86 |     def contains_value(self, value):
 87 |         """
 88 |         :key: 判断是否存在value值
 89 |         """
 90 |         return value in self.dict_reversed
 91 | 
 92 |     def keys(self):
 93 |         """
 94 |         :key: 得到双向字典全部的keys
 95 |         """
 96 |         return self.dict.keys()
 97 | 
 98 |     def values(self):
 99 |         """
100 |         :key: 得到双向字典全部的values
101 |         """
102 |         return self.dict_reversed.keys()
103 | 
104 |     def items(self):
105 |         """
106 |         :key: 得到双向字典全部的items
107 |         """
108 |         return self.dict.items()
109 | 
110 | 
111 | class CorpusSet(object):
112 |     """
113 |     定义语料集类,作为LdaBase的基类
114 |     """
115 | 
116 |     def __init__(self):
117 |         """
118 |         :key: 初始化函数
119 |         """
120 |         # 定义关于word的变量
121 |         self.local_bi = BiDictionary()      # id和word之间的本地双向字典,key为id,value为word
122 |         self.words_count = 0                # 数据集中word的数量（排重之前的）
123 |         self.V = 0                          # 数据集中word的数量（排重之后的）
124 | 
125 |         # 定义关于article的变量
126 |         self.artids_list = []               # 全部article的id的列表,按照数据读取的顺序存储
127 |         self.arts_Z = []                    # 全部article中所有词的id信息,维数为 M * art.length()
128 |         self.M = 0                          # 数据集中article的数量
129 | 
130 |         # 定义推断中用到的变量（可能为空）
131 |         self.global_bi = None               # id和word之间的全局双向字典,key为id,value为word
132 |         self.local_2_global = {}            # 一个字典,local字典和global字典之间的对应关系
133 |         return
134 | 
135 |     def init_corpus_with_file(self, file_name):
136 |         """
137 |         :key: 利用数据文件初始化语料集数据。文件每一行的数据格式: id[tab]word1 word2 word3......
138 |         """
139 |         with open(file_name, "r", encoding="utf-8") as file_iter:
140 |             self.init_corpus_with_articles(file_iter)
141 |         return
142 | 
143 |     def init_corpus_with_articles(self, article_list):
144 |         """
145 |         :key: 利用article的列表初始化语料集。每一篇article的格式为: id[tab]word1 word2 word3......
146 |         """
147 |         # 清理数据--word数据
148 |         self.local_bi.clear()
149 |         self.words_count = 0
150 |         self.V = 0
151 | 
152 |         # 清理数据--article数据
153 |         self.artids_list.clear()
154 |         self.arts_Z.clear()
155 |         self.M = 0
156 | 
157 |         # 清理数据--清理local到global的映射关系
158 |         self.local_2_global.clear()
159 | 
160 |         # 读取article数据
161 |         for line in article_list:
162 |             frags = line.strip().split()
163 |             if len(frags) < 2:
164 |                 continue
165 | 
166 |             # 获取article的id
167 |             art_id = frags[0].strip()
168 | 
169 |             # 获取word的id
170 |             art_wordid_list = []
171 |             for word in [w.strip() for w in frags[1:] if w.strip()]:
172 |                 local_id = self.local_bi.get_key(word) if self.local_bi.contains_value(word) else len(self.local_bi)
173 | 
174 |                 # 这里的self.global_bi为None和为空是有区别的
175 |                 if self.global_bi is None:
176 |                     # 更新id信息
177 |                     self.local_bi.add_key_value(local_id, word)
178 |                     art_wordid_list.append(local_id)
179 |                 else:
180 |                     if self.global_bi.contains_value(word):
181 |                         # 更新id信息
182 |                         self.local_bi.add_key_value(local_id, word)
183 |                         art_wordid_list.append(local_id)
184 | 
185 |                         # 更新local_2_global
186 |                         self.local_2_global[local_id] = self.global_bi.get_key(word)
187 | 
188 |             # 更新类变量: 必须article中word的数量大于0
189 |             if len(art_wordid_list) > 0:
190 |                 self.words_count += len(art_wordid_list)
191 |                 self.artids_list.append(art_id)
192 |                 self.arts_Z.append(art_wordid_list)
193 | 
194 |         # 做相关初始计算--word相关
195 |         self.V = len(self.local_bi)
196 |         logging.debug("words number: " + str(self.V) + ", " + str(self.words_count))
197 | 
198 |         # 做相关初始计算--article相关
199 |         self.M = len(self.artids_list)
200 |         logging.debug("articles number: " + str(self.M))
201 |         return
202 | 
203 |     def save_wordmap(self, file_name):
204 |         """
205 |         :key: 保存word字典,即self.local_bi的数据
206 |         """
207 |         with open(file_name, "w", encoding="utf-8") as f_save:
208 |             f_save.write(str(self.local_bi))
209 |         return
210 | 
211 |     def load_wordmap(self, file_name):
212 |         """
213 |         :key: 加载word字典,即加载self.local_bi的数据
214 |         """
215 |         self.local_bi.clear()
216 |         with open(file_name, "r", encoding="utf-8") as f_load:
217 |             for _id, _word in [line.strip().split() for line in f_load if line.strip()]:
218 |                 self.local_bi.add_key_value(int(_id), _word.strip())
219 |         self.V = len(self.local_bi)
220 |         return
221 | 
222 | 
223 | class LdaBase(CorpusSet):
224 |     """
225 |     LDA模型的基类,相关说明:
226 |     》article的下标范围为[0, self.M), 下标为 m
227 |     》wordid的下标范围为[0, self.V), 下标为 w
228 |     》topic的下标范围为[0, self.K), 下标为 k 或 topic
229 |     》article中word的下标范围为[0, article.size()), 下标为 n
230 |     """
231 | 
232 |     def __init__(self):
233 |         """
234 |         :key: 初始化函数
235 |         """
236 |         CorpusSet.__init__(self)
237 | 
238 |         # 基础变量--1
239 |         self.dir_path = ""          # 文件夹路径,用于存放LDA运行的数据、中间结果等
240 |         self.model_name = ""        # LDA训练或推断的模型名称,也用于读取训练的结果
241 |         self.current_iter = 0       # LDA训练或推断的模型已经迭代的次数,用于继续模型训练过程
242 |         self.iters_num = 0          # LDA训练或推断过程中Gibbs抽样迭代的总次数,整数值或者"auto"
243 |         self.topics_num = 0         # LDA训练或推断过程中的topic的数量,即self.K值
244 |         self.K = 0                  # LDA训练或推断过程中的topic的数量,即self.topics_num值
245 |         self.twords_num = 0         # LDA训练或推断结束后输出与每个topic相关的word的个数
246 | 
247 |         # 基础变量--2
248 |         self.alpha = numpy.zeros(self.K)            # 超参数alpha,K维的float值,默认为50/K
249 |         self.beta = numpy.zeros(self.V)             # 超参数beta,V维的float值,默认为0.01
250 | 
251 |         # 基础变量--3
252 |         self.Z = []                                 # 所有word的topic信息,即Z(m, n),维数为 M * article.size()
253 | 
254 |         # 统计计数(可由self.Z计算得到)
255 |         self.nd = numpy.zeros((self.M, self.K))     # nd[m, k]用于保存第m篇article中第k个topic产生的词的个数,其维数为 M * K
256 |         self.ndsum = numpy.zeros((self.M, 1))       # ndsum[m, 0]用于保存第m篇article的总词数,维数为 M * 1
257 |         self.nw = numpy.zeros((self.K, self.V))     # nw[k, w]用于保存第k个topic产生的词中第w个词的数量,其维数为 K * V
258 |         self.nwsum = numpy.zeros((self.K, 1))       # nwsum[k, 0]用于保存第k个topic产生的词的总数,维数为 K * 1
259 | 
260 |         # 多项式分布参数变量
261 |         self.theta = numpy.zeros((self.M, self.K))  # Doc-Topic多项式分布的参数,维数为 M * K,由alpha值影响
262 |         self.phi = numpy.zeros((self.K, self.V))    # Topic-Word多项式分布的参数,维数为 K * V,由beta值影响
263 | 
264 |         # 辅助变量,目的是提高算法执行效率
265 |         self.sum_alpha = 0.0                        # 超参数alpha的和
266 |         self.sum_beta = 0.0                         # 超参数beta的和
267 | 
268 |         # 先验知识,格式为{word_id: [k1, k2, ...], ...}
269 |         self.prior_word = defaultdict(list)
270 | 
271 |         # 推断时需要的训练模型
272 |         self.train_model = None
273 |         return
274 | 
275 |     # --------------------------------------------------辅助函数---------------------------------------------------------
276 |     def init_statistics_document(self):
277 |         """
278 |         :key: 初始化关于article的统计计数。先决条件: self.M, self.K, self.Z
279 |         """
280 |         assert self.M > 0 and self.K > 0 and self.Z
281 | 
282 |         # 统计计数初始化
283 |         self.nd = numpy.zeros((self.M, self.K), dtype=numpy.int)
284 |         self.ndsum = numpy.zeros((self.M, 1), dtype=numpy.int)
285 | 
286 |         # 根据self.Z进行更新,更新self.nd[m, k]和self.ndsum[m, 0]
287 |         for m in range(self.M):
288 |             for k in self.Z[m]:
289 |                 self.nd[m, k] += 1
290 |             self.ndsum[m, 0] = len(self.Z[m])
291 |         return
292 | 
293 |     def init_statistics_word(self):
294 |         """
295 |         :key: 初始化关于word的统计计数。先决条件: self.V, self.K, self.Z, self.arts_Z
296 |         """
297 |         assert self.V > 0 and self.K > 0 and self.Z and self.arts_Z
298 | 
299 |         # 统计计数初始化
300 |         self.nw = numpy.zeros((self.K, self.V), dtype=numpy.int)
301 |         self.nwsum = numpy.zeros((self.K, 1), dtype=numpy.int)
302 | 
303 |         # 根据self.Z进行更新,更新self.nw[k, w]和self.nwsum[k, 0]
304 |         for m in range(self.M):
305 |             for k, w in zip(self.Z[m], self.arts_Z[m]):
306 |                 self.nw[k, w] += 1
307 |                 self.nwsum[k, 0] += 1
308 |         return
309 | 
310 |     def init_statistics(self):
311 |         """
312 |         :key: 初始化全部的统计计数。上两个函数的综合函数。
313 |         """
314 |         self.init_statistics_document()
315 |         self.init_statistics_word()
316 |         return
317 | 
318 |     def sum_alpha_beta(self):
319 |         """
320 |         :key: 计算alpha、beta的和
321 |         """
322 |         self.sum_alpha = self.alpha.sum()
323 |         self.sum_beta = self.beta.sum()
324 |         return
325 | 
326 |     def calculate_theta(self):
327 |         """
328 |         :key: 初始化并计算模型的theta值(M*K),用到alpha值
329 |         """
330 |         assert self.sum_alpha > 0
331 |         self.theta = (self.nd + self.alpha) / (self.ndsum + self.sum_alpha)
332 |         return
333 | 
334 |     def calculate_phi(self):
335 |         """
336 |         :key: 初始化并计算模型的phi值(K*V),用到beta值
337 |         """
338 |         assert self.sum_beta > 0
339 |         self.phi = (self.nw + self.beta) / (self.nwsum + self.sum_beta)
340 |         return
341 | 
342 |     # ---------------------------------------------计算Perplexity值------------------------------------------------------
343 |     def calculate_perplexity(self):
344 |         """
345 |         :key: 计算Perplexity值,并返回
346 |         """
347 |         # 计算theta和phi值
348 |         self.calculate_theta()
349 |         self.calculate_phi()
350 | 
351 |         # 开始计算
352 |         preplexity = 0.0
353 |         for m in range(self.M):
354 |             for w in self.arts_Z[m]:
355 |                 preplexity += numpy.log(numpy.sum(self.theta[m] * self.phi[:, w]))
356 |         return numpy.exp(-(preplexity / self.words_count))
357 | 
358 |     # --------------------------------------------------静态函数---------------------------------------------------------
359 |     @staticmethod
360 |     def multinomial_sample(pro_list):
361 |         """
362 |         :key: 静态函数,多项式分布抽样,此时会改变pro_list的值
363 |         :param pro_list: [0.2, 0.7, 0.4, 0.1],此时说明返回下标1的可能性大,但也不绝对
364 |         """
365 |         # 将pro_list进行累加
366 |         for k in range(1, len(pro_list)):
367 |             pro_list[k] += pro_list[k-1]
368 | 
369 |         # 确定随机数 u 落在哪个下标值,此时的下标值即为抽取的类别（random.rand()返回: [0, 1.0)）
370 |         u = numpy.random.rand() * pro_list[-1]
371 | 
372 |         return_index = len(pro_list) - 1
373 |         for t in range(len(pro_list)):
374 |             if pro_list[t] > u:
375 |                 return_index = t
376 |                 break
377 |         return return_index
378 | 
379 |     # ----------------------------------------------Gibbs抽样算法--------------------------------------------------------
380 |     def gibbs_sampling(self, is_calculate_preplexity):
381 |         """
382 |         :key: LDA模型中的Gibbs抽样过程
383 |         :param is_calculate_preplexity: 是否计算preplexity值
384 |         """
385 |         # 计算preplexity值用到的变量
386 |         pp_list = []
387 |         pp_var = numpy.inf
388 | 
389 |         # 开始迭代
390 |         last_iter = self.current_iter + 1
391 |         iters_num = self.iters_num if self.iters_num != "auto" else MAX_ITER_NUM
392 |         for self.current_iter in range(last_iter, last_iter+iters_num):
393 |             info = "......"
394 | 
395 |             # 是否计算preplexity值
396 |             if is_calculate_preplexity:
397 |                 pp = self.calculate_perplexity()
398 |                 pp_list.append(pp)
399 | 
400 |                 # 计算列表最新VAR_NUM项的方差
401 |                 pp_var = numpy.var(pp_list[-VAR_NUM:]) if len(pp_list) >= VAR_NUM else numpy.inf
402 |                 info = (", preplexity: " + str(pp)) + ((", var: " + str(pp_var)) if len(pp_list) >= VAR_NUM else "")
403 | 
404 |             # 输出Debug信息
405 |             logging.debug("\titeration " + str(self.current_iter) + info)
406 | 
407 |             # 判断是否跳出循环
408 |             if self.iters_num == "auto" and pp_var < (VAR_NUM / 2):
409 |                 break
410 | 
411 |             # 对每篇article的每个word进行一次抽样,抽取合适的k值
412 |             for m in range(self.M):
413 |                 for n in range(len(self.Z[m])):
414 |                     w = self.arts_Z[m][n]
415 |                     k = self.Z[m][n]
416 | 
417 |                     # 统计计数减一
418 |                     self.nd[m, k] -= 1
419 |                     self.ndsum[m, 0] -= 1
420 |                     self.nw[k, w] -= 1
421 |                     self.nwsum[k, 0] -= 1
422 | 
423 |                     if self.prior_word and (w in self.prior_word):
424 |                         # 带有先验知识,否则进行正常抽样
425 |                         k = numpy.random.choice(self.prior_word[w])
426 |                     else:
427 |                         # 计算theta值--下边的过程为抽取第m篇article的第n个词w的topic,即新的k
428 |                         theta_p = (self.nd[m] + self.alpha) / (self.ndsum[m, 0] + self.sum_alpha)
429 | 
430 |                         # 计算phi值--判断是训练模型,还是推断模型（注意self.beta[w_g]）
431 |                         if self.local_2_global and self.train_model:
432 |                             w_g = self.local_2_global[w]
433 |                             phi_p = (self.train_model.nw[:, w_g] + self.nw[:, w] + self.beta[w_g]) / \
434 |                                     (self.train_model.nwsum[:, 0] + self.nwsum[:, 0] + self.sum_beta)
435 |                         else:
436 |                             phi_p = (self.nw[:, w] + self.beta[w]) / (self.nwsum[:, 0] + self.sum_beta)
437 | 
438 |                         # multi_p为多项式分布的参数,此时没有进行标准化
439 |                         multi_p = theta_p * phi_p
440 | 
441 |                         # 此时的topic即为Gibbs抽样得到的topic,它有较大的概率命中多项式概率大的topic
442 |                         k = LdaBase.multinomial_sample(multi_p)
443 | 
444 |                     # 统计计数加一
445 |                     self.nd[m, k] += 1
446 |                     self.ndsum[m, 0] += 1
447 |                     self.nw[k, w] += 1
448 |                     self.nwsum[k, 0] += 1
449 | 
450 |                     # 更新Z值
451 |                     self.Z[m][n] = k
452 |         # 抽样完毕
453 |         return
454 | 
455 |     # -----------------------------------------Model数据存储、读取相关函数-------------------------------------------------
456 |     def save_parameter(self, file_name):
457 |         """
458 |         :key: 保存模型相关参数数据,包括: topics_num, M, V, K, words_count, alpha, beta
459 |         """
460 |         with open(file_name, "w", encoding="utf-8") as f_param:
461 |             for item in ["topics_num", "M", "V", "K", "words_count"]:
462 |                 f_param.write("%s\t%s\n" % (item, str(self.__dict__[item])))
463 |             f_param.write("alpha\t%s\n" % ",".join([str(item) for item in self.alpha]))
464 |             f_param.write("beta\t%s\n" % ",".join([str(item) for item in self.beta]))
465 |         return
466 | 
467 |     def load_parameter(self, file_name):
468 |         """
469 |         :key: 加载模型相关参数数据,和上一个函数相对应
470 |         """
471 |         with open(file_name, "r", encoding="utf-8") as f_param:
472 |             for line in f_param:
473 |                 key, value = line.strip().split()
474 |                 if key in ["topics_num", "M", "V", "K", "words_count"]:
475 |                     self.__dict__[key] = int(value)
476 |                 elif key in ["alpha", "beta"]:
477 |                     self.__dict__[key] = numpy.array([float(item) for item in value.split(",")])
478 |         return
479 | 
480 |     def save_zvalue(self, file_name):
481 |         """
482 |         :key: 保存模型关于article的变量,包括: arts_Z, Z, artids_list等
483 |         """
484 |         with open(file_name, "w", encoding="utf-8") as f_zvalue:
485 |             for m in range(self.M):
486 |                 out_line = [str(w) + ":" + str(k) for w, k in zip(self.arts_Z[m], self.Z[m])]
487 |                 f_zvalue.write(self.artids_list[m] + "\t" + " ".join(out_line) + "\n")
488 |         return
489 | 
490 |     def load_zvalue(self, file_name):
491 |         """
492 |         :key: 读取模型的Z变量。和上一个函数相对应
493 |         """
494 |         self.arts_Z = []
495 |         self.artids_list = []
496 |         self.Z = []
497 |         with open(file_name, "r", encoding="utf-8") as f_zvalue:
498 |             for line in f_zvalue:
499 |                 frags = line.strip().split()
500 |                 art_id = frags[0].strip()
501 |                 w_k_list = [value.split(":") for value in frags[1:]]
502 |                 # 添加到类中
503 |                 self.artids_list.append(art_id)
504 |                 self.arts_Z.append([int(item[0]) for item in w_k_list])
505 |                 self.Z.append([int(item[1]) for item in w_k_list])
506 |         return
507 | 
508 |     def save_twords(self, file_name):
509 |         """
510 |         :key: 保存模型的twords数据,要用到phi的数据
511 |         """
512 |         self.calculate_phi()
513 |         out_num = self.V if self.twords_num > self.V else self.twords_num
514 |         with open(file_name, "w", encoding="utf-8") as f_twords:
515 |             for k in range(self.K):
516 |                 words_list = sorted([(w, self.phi[k, w]) for w in range(self.V)], key=lambda x: x[1], reverse=True)
517 |                 f_twords.write("Topic %dth:\n" % k)
518 |                 f_twords.writelines(["\t%s %f\n" % (self.local_bi.get_value(w), p) for w, p in words_list[:out_num]])
519 |         return
520 | 
521 |     def load_twords(self, file_name):
522 |         """
523 |         :key: 加载模型的twords数据,即先验数据
524 |         """
525 |         self.prior_word.clear()
526 |         topic = -1
527 |         with open(file_name, "r", encoding="utf-8") as f_twords:
528 |             for line in f_twords:
529 |                 if line.startswith("Topic"):
530 |                     topic = int(line.strip()[6:-3])
531 |                 else:
532 |                     word_id = self.local_bi.get_key(line.strip().split()[0].strip())
533 |                     self.prior_word[word_id].append(topic)
534 |         return
535 | 
536 |     def save_tag(self, file_name):
537 |         """
538 |         :key: 输出模型最终给数据打标签的结果,用到theta值
539 |         """
540 |         self.calculate_theta()
541 |         with open(file_name, "w", encoding="utf-8") as f_tag:
542 |             for m in range(self.M):
543 |                 f_tag.write("%s\t%s\n" % (self.artids_list[m], " ".join([str(item) for item in self.theta[m]])))
544 |         return
545 | 
546 |     def save_model(self):
547 |         """
548 |         :key: 保存模型数据
549 |         """
550 |         name_predix = "%s-%05d" % (self.model_name, self.current_iter)
551 | 
552 |         # 保存训练结果
553 |         self.save_parameter(os.path.join(self.dir_path, "%s.%s" % (name_predix, "param")))
554 |         self.save_wordmap(os.path.join(self.dir_path, "%s.%s" % (name_predix, "wordmap")))
555 |         self.save_zvalue(os.path.join(self.dir_path, "%s.%s" % (name_predix, "zvalue")))
556 | 
557 |         #保存额外数据
558 |         self.save_twords(os.path.join(self.dir_path, "%s.%s" % (name_predix, "twords")))
559 |         self.save_tag(os.path.join(self.dir_path, "%s.%s" % (name_predix, "tag")))
560 |         return
561 | 
562 |     def load_model(self):
563 |         """
564 |         :key: 加载模型数据
565 |         """
566 |         name_predix = "%s-%05d" % (self.model_name, self.current_iter)
567 | 
568 |         # 加载训练结果
569 |         self.load_parameter(os.path.join(self.dir_path, "%s.%s" % (name_predix, "param")))
570 |         self.load_wordmap(os.path.join(self.dir_path, "%s.%s" % (name_predix, "wordmap")))
571 |         self.load_zvalue(os.path.join(self.dir_path, "%s.%s" % (name_predix, "zvalue")))
572 |         return
573 | 
574 | 
575 | class LdaModel(LdaBase):
576 |     """
577 |     LDA模型定义,主要实现训练、继续训练、推断的过程
578 |     """
579 | 
580 |     def init_train_model(self, dir_path, model_name, current_iter, iters_num=None, topics_num=10, twords_num=200,
581 |                          alpha=-1.0, beta=0.01, data_file="", prior_file=""):
582 |         """
583 |         :key: 初始化训练模型,根据参数current_iter（是否等于0）决定是初始化新模型,还是加载已有模型
584 |         :key: 当初始化新模型时,除了prior_file先验文件外,其余所有的参数都需要,且current_iter等于0
585 |         :key: 当加载已有模型时,只需要dir_path, model_name, current_iter（不等于0）, iters_num, twords_num即可
586 |         :param iters_num: 可以为整数值或者“auto”
587 |         """
588 |         if current_iter == 0:
589 |             logging.debug("init a new train model")
590 | 
591 |             # 初始化语料集
592 |             self.init_corpus_with_file(data_file)
593 | 
594 |             # 初始化部分变量
595 |             self.dir_path = dir_path
596 |             self.model_name = model_name
597 |             self.current_iter = current_iter
598 |             self.iters_num = iters_num
599 |             self.topics_num = topics_num
600 |             self.K = topics_num
601 |             self.twords_num = twords_num
602 | 
603 |             # 初始化alpha和beta
604 |             self.alpha = numpy.array([alpha if alpha > 0 else (50.0/self.K) for k in range(self.K)])
605 |             self.beta = numpy.array([beta if beta > 0 else 0.01 for w in range(self.V)])
606 | 
607 |             # 初始化Z值,以便统计计数
608 |             self.Z = [[numpy.random.randint(self.K) for n in range(len(self.arts_Z[m]))] for m in range(self.M)]
609 |         else:
610 |             logging.debug("init an existed model")
611 | 
612 |             # 初始化部分变量
613 |             self.dir_path = dir_path
614 |             self.model_name = model_name
615 |             self.current_iter = current_iter
616 |             self.iters_num = iters_num
617 |             self.twords_num = twords_num
618 | 
619 |             # 加载已有模型
620 |             self.load_model()
621 | 
622 |         # 初始化统计计数
623 |         self.init_statistics()
624 | 
625 |         # 计算alpha和beta的和值
626 |         self.sum_alpha_beta()
627 | 
628 |         # 初始化先验知识
629 |         if prior_file:
630 |             self.load_twords(prior_file)
631 | 
632 |         # 返回该模型
633 |         return self
634 | 
635 |     def begin_gibbs_sampling_train(self, is_calculate_preplexity=True):
636 |         """
637 |         :key: 训练模型,对语料集中的所有数据进行Gibbs抽样,并保存最后的抽样结果
638 |         """
639 |         # Gibbs抽样
640 |         logging.debug("sample iteration start, iters_num: " + str(self.iters_num))
641 |         self.gibbs_sampling(is_calculate_preplexity)
642 |         logging.debug("sample iteration finish")
643 | 
644 |         # 保存模型
645 |         logging.debug("save model")
646 |         self.save_model()
647 |         return
648 | 
649 |     def init_inference_model(self, train_model):
650 |         """
651 |         :key: 初始化推断模型
652 |         """
653 |         self.train_model = train_model
654 | 
655 |         # 初始化变量: 主要用到self.topics_num, self.K
656 |         self.topics_num = train_model.topics_num
657 |         self.K = train_model.K
658 | 
659 |         # 初始化变量self.alpha, self.beta,直接沿用train_model的值
660 |         self.alpha = train_model.alpha      # K维的float值,训练和推断模型中的K相同,故可以沿用
661 |         self.beta = train_model.beta        # V维的float值,推断模型中用于计算phi的V值应该是全局的word的数量,故可以沿用
662 |         self.sum_alpha_beta()               # 计算alpha和beta的和
663 | 
664 |         # 初始化数据集的self.global_bi
665 |         self.global_bi = train_model.local_bi
666 |         return
667 | 
668 |     def inference_data(self, article_list, iters_num=100, repeat_num=3):
669 |         """
670 |         :key: 利用现有模型推断数据
671 |         :param article_list: 每一行的数据格式为: id[tab]word1 word2 word3......
672 |         :param iters_num: 每一次迭代的次数
673 |         :param repeat_num: 重复迭代的次数
674 |         """
675 |         # 初始化语料集
676 |         self.init_corpus_with_articles(article_list)
677 | 
678 |         # 初始化返回变量
679 |         return_theta = numpy.zeros((self.M, self.K))
680 | 
681 |         # 重复抽样
682 |         for i in range(repeat_num):
683 |             logging.debug("inference repeat_num: " + str(i+1))
684 | 
685 |             # 初始化变量
686 |             self.current_iter = 0
687 |             self.iters_num = iters_num
688 | 
689 |             # 初始化Z值,以便统计计数
690 |             self.Z = [[numpy.random.randint(self.K) for n in range(len(self.arts_Z[m]))] for m in range(self.M)]
691 | 
692 |             # 初始化统计计数
693 |             self.init_statistics()
694 | 
695 |             # 开始推断
696 |             self.gibbs_sampling(is_calculate_preplexity=False)
697 | 
698 |             # 计算theta
699 |             self.calculate_theta()
700 |             return_theta += self.theta
701 | 
702 |         # 计算结果,并返回
703 |         return return_theta / repeat_num
704 | 
705 | 
706 | if __name__ == "__main__":
707 |     """
708 |     测试代码
709 |     """
710 |     logging.basicConfig(level=logging.DEBUG, format="%(asctime)s\t%(levelname)s\t%(message)s")
711 | 
712 |     # train或者inference
713 |     test_type = "train"
714 |     # test_type = "inference"
715 | 
716 |     # 测试新模型
717 |     if test_type == "train":
718 |         model = LdaModel()
719 |         # 由prior_file决定是否带有先验知识
720 |         model.init_train_model("data/", "model", current_iter=0, iters_num="auto", topics_num=10, data_file="corpus.txt")
721 |         # model.init_train_model("data/", "model", current_iter=0, iters_num="auto", topics_num=10, data_file="corpus.txt", prior_file="prior.twords")
722 |         model.begin_gibbs_sampling_train()
723 |     elif test_type == "inference":
724 |         model = LdaModel()
725 |         model.init_inference_model(LdaModel().init_train_model("data/", "model", current_iter=134))
726 |         data = [
727 |             "cn	咪咕 漫画 咪咕 漫画 漫画 更名 咪咕 漫画 资源 偷星 国漫 全彩 日漫 实时 在线看 随心所欲 登陆 漫画 资源 黑白 全彩 航海王",
728 |             "co	aircloud aircloud 硬件 设备 wifi 智能 手要 平板电脑 电脑 存储 aircloud 文件 远程 型号 aircloud 硬件 设备 wifi"
729 |         ]
730 |         result = model.inference_data(data)
731 | 
732 |     # 退出程序
733 |     exit()
734 | 


--------------------------------------------------------------------------------
/python_magic_methods.py:
--------------------------------------------------------------------------------
 1 | # _*_ coding: utf-8 _*_
 2 | 
 3 | """
 4 | python_magic_methods.py by xianhu
 5 | """
 6 | 
 7 | 
 8 | # 定义一个能够自动比较大小的People类
 9 | class People(object):
10 | 
11 |     def __init__(self, name, age):
12 |         self.name = name
13 |         self.age = age
14 |         return
15 | 
16 |     def __str__(self):
17 |         return self.name + ":" + str(self.age)
18 | 
19 |     def __lt__(self, other):
20 |         return self.name < other.name if self.name != other.name else self.age < other.age
21 | 
22 | print("\t".join([str(item) for item in sorted([People("abc", 18), People("abe", 19), People("abe", 12), People("abc", 17)])]))
23 | 
24 | 
25 | # Python实现任意深度的赋值 例如a[0] = 'value1'; a[1][2] = 'value2'; a[3][4][5] = 'value3'
26 | class MyDict(dict):
27 | 
28 |     def __setitem__(self, key, value):          # 该函数不做任何改动 这里只是为了输出
29 |         print("setitem:", key, value, self)
30 |         super().__setitem__(key, value)
31 |         return
32 | 
33 |     def __getitem__(self, item):                # 主要技巧在该函数
34 |         print("getitem:", item, self)
35 |         # 基本思路: a[1][2]赋值时 需要先取出a[1] 然后给a[1]的[2]赋值
36 |         if item not in self:                    # 如果a[1]不存在
37 |             temp = MyDict()                     # 则需要新建一个dict
38 |             super().__setitem__(item, temp)     # 并使得a[1] = dict
39 |             return temp                         # 返回a[1] 使得a[1][2] = value有效
40 |         return super().__getitem__(item)        # 如果a[1]存在 则直接返回a[1]
41 | 
42 | # 使用例子:
43 | test = MyDict()
44 | test[0] = 'test'
45 | test[1][2] = 'test1'
46 | test[3][4][5] = 'test2'
47 | print("==========================")
48 | 


--------------------------------------------------------------------------------
/python_markov_chain.py:
--------------------------------------------------------------------------------
 1 | # _*_ coding: utf-8 _*_
 2 | 
 3 | import nltk
 4 | import random
 5 | 
 6 | file = open('Text/Walden.txt', 'r')
 7 | walden = file.read()
 8 | walden = walden.split()
 9 | 
10 | 
11 | def makePairs(arr):
12 |     pairs = []
13 |     for i in range(len(arr)):
14 |         if i < len(arr) - 1:
15 |             temp = (arr[i], arr[i + 1])
16 |             pairs.append(temp)
17 |     return pairs
18 | 
19 | 
20 | def generate(cfd, word='the', num=500):
21 |     for i in range(num):
22 |         # make an array with the words shown by proper count
23 |         arr = []
24 |         for j in cfd[word]:
25 |             for k in range(cfd[word][j]):
26 |                 arr.append(j)
27 |         print(word, end=' ')
28 | 
29 |         # choose the word randomly from the conditional distribution
30 |         word = arr[int((len(arr)) * random.random())]
31 | 
32 | pairs = makePairs(walden)
33 | cfd = nltk.ConditionalFreqDist(pairs)
34 | generate(cfd)
35 | 


--------------------------------------------------------------------------------
/python_metaclass.py:
--------------------------------------------------------------------------------
 1 | # _*_ coding: utf-8 _*_
 2 | 
 3 | """
 4 | python_metaclass.py by xianhu
 5 | """
 6 | 
 7 | 
 8 | class Foo(object):
 9 |     def hello(self):
10 |         print("hello world!")
11 |         return
12 | 
13 | foo = Foo()
14 | print(type(foo))            # <class '__main__.Foo'>
15 | print(type(foo.hello))      # <class 'method'>
16 | print(type(Foo))            # <class 'type'>
17 | 
18 | temp = Foo                  # 赋值给其他变量
19 | Foo.var = 11                # 增加参数
20 | print(Foo)                  # 作为函数参数
21 | 
22 | 
23 | # ========================================================================
24 | def init(self, name):
25 |     self.name = name
26 |     return
27 | 
28 | 
29 | def hello(self):
30 |     print("hello %s" % self.name)
31 |     return
32 | 
33 | Foo = type("Foo", (object,), {"__init__": init, "hello": hello, "cls_var": 10})
34 | foo = Foo("xianhu")
35 | print(foo.hello())
36 | print(Foo.cls_var)
37 | 
38 | print(foo.__class__)
39 | print(Foo.__class__)
40 | print(type.__class__)
41 | # ========================================================================
42 | 
43 | 
44 | class Author(type):
45 |     def __new__(mcs, name, bases, dict):
46 |         # 添加作者属性
47 |         dict["author"] = "xianhu"
48 |         return super(Author, mcs).__new__(mcs, name, bases, dict)
49 | 
50 | 
51 | class Foo(object, metaclass=Author):
52 |     pass
53 | 
54 | foo = Foo()
55 | print(foo.author)
56 | 


--------------------------------------------------------------------------------
/python_numpy.py:
--------------------------------------------------------------------------------
  1 | # _*_coding:utf-8-*_
  2 | import numpy as np  
  3 | # 定义矩阵变量并输出变量的一些属性
  4 | # 用np.array()生成矩阵
  5 | arr=np.array([[1,2,3],
  6 |               [4,5,6]])  
  7 | 
  8 | print(arr)
  9 | print('number of arr dimensions: ',arr.ndim)
 10 | print('~    ~    ~   shape: ',arr.shape)
 11 | print('~    ~    ~   size: ', arr.size)
 12 | 
 13 | # 输出结果：
 14 | [[1 2 3]
 15 |  [4 5 6]]
 16 | number of arr dimensions:  2
 17 | ~    ~    ~   shape:  (2, 3)
 18 | ~    ~    ~   size:  6  
 19 | 
 20 | # 定义一些特殊矩阵
 21 | # 指定矩阵数据类型
 22 | arr=np.array([[1,2,3],
 23 |               [4,5,6]],
 24 |               dtype=np.float64) # 我的电脑np.int是int32，还可以使用np.int32/np.int64/np.float32/np.float64
 25 | print(arr.dtype)
 26 | 
 27 | # 用np.zeros()生成全零矩阵
 28 | arr_zeros=np.zeros( (2,3) )
 29 | print(arr_zeros)
 30 | 
 31 | # 用np.ones()生成全一矩阵
 32 | arr_ones=np.ones( (2,3) )
 33 | print(arr_ones)
 34 | 
 35 | # 生成随机矩阵np.random.random()
 36 | arr_random=np.random.random((2,3))
 37 | print(arr_random)
 38 | 
 39 | # 用np.arange()生成数列
 40 | arr=np.arange(6,12)
 41 | print(arr)
 42 | 
 43 | # 用np.arange().reshape()将数列转成矩阵
 44 | arr=np.arange(6,12).reshape( (2,3) )
 45 | print(arr)
 46 | 
 47 | # 用np.linspace(开始，结束，多少点划分线段)，同样也可以用reshape()
 48 | arr=np.linspace(1,5,3)
 49 | print(arr)
 50 | 
 51 | # 矩阵运算
 52 | arr1=np.array([1,2,3,6])
 53 | arr2=np.arange(4)
 54 | 
 55 | # 矩阵减法，加法同理
 56 | arr_sub=arr1-arr2
 57 | print(arr1)
 58 | print(arr2)
 59 | print(arr_sub)
 60 | 
 61 | # 矩阵乘法
 62 | arr_multi=arr1**3 # 求每个元素的立方，在python中幂运算用**来表示
 63 | print(arr_multi)
 64 | 
 65 | arr_multi=arr1*arr2 # 元素逐个相乘
 66 | print(arr_multi) 
 67 | 
 68 | arr_multi=np.dot(arr1, arr2.reshape((4,1))) # 维度1*4和4*1矩阵相乘
 69 | print(arr_multi)
 70 | 
 71 | arr_multi=np.dot(arr1.reshape((4,1)), arr2.reshape((1,4))) # 维度4*1和1*4矩阵相乘
 72 | print(arr_multi)
 73 | 
 74 | arr_multi=arr1.dot(arr2.reshape((4,1))) # 也可以使用矩阵名.doc(矩阵名)
 75 | print(arr_multi)
 76 | 
 77 | # 三角运算：np.sin()/np.cos()/np.tan()
 78 | arr_sin=np.sin(arr1)
 79 | print(arr_sin)
 80 | 
 81 | # 逻辑运算
 82 | print(arr1<3) # 查看arr1矩阵中哪些元素小于3，返回[ True  True False False]
 83 | 
 84 | # 矩阵求和，求矩阵最大最小值
 85 | arr1=np.array([[1,2,3],
 86 |                [4,5,6]])
 87 | print(arr1)
 88 | print(np.sum(arr1)) # 矩阵求和
 89 | print(np.sum(arr1,axis=0)) # 矩阵每列求和
 90 | print(np.sum(arr1,axis=1).reshape(2,1)) # 矩阵每行求和
 91 | 
 92 | print(np.min(arr1)) # 求矩阵最小值
 93 | print(np.min(arr1,axis=0))
 94 | print(np.min(arr1,axis=1))
 95 | 
 96 | print(np.max(arr1)) # 求矩阵最大值
 97 | 
 98 | print(np.mean(arr1)) # 输出矩阵平均值，也可以用arr1.mean()
 99 | print(np.median(arr1)) # 输出矩阵中位数
100 | 
101 | # 输出矩阵某些值的位置
102 | arr1=np.arange(2,14).reshape((3,4))
103 | print(arr1)
104 | 
105 | print(np.argmin(arr1)) # 输出矩阵最小值的位置，0
106 | print(np.argmax(arr1)) # 输出矩阵最大值的位置，11
107 | 
108 | print(np.cumsum(arr1)) # 输出前一个数的和，前两个数的和，等等
109 | print(np.diff(arr1)) # 输出相邻两个数的差值
110 | 
111 | arr_zeros=np.zeros((3,4))
112 | print(np.nonzero(arr_zeros)) #输出矩阵非零元素位置，返回多个行向量，第i个行向量表示第i个维度
113 | print(np.nonzero(arr1))
114 | 
115 | print(np.sort(arr1)) # 矩阵逐行排序
116 | print(np.transpose(arr1)) # 矩阵转置，也可以用arr1.T
117 | 
118 | print(np.clip(arr1,5,9)) #将矩阵中小于5的数置5，大于9的数置9  
119 | 
120 | # numpy索引
121 | arr1=np.array([1,2,3,6])
122 | arr2=np.arange(2,8).reshape(2,3)
123 | 
124 | print(arr1)
125 | print(arr1[0]) # 索引从0开始计数
126 | 
127 | print(arr2)
128 | print(arr2[0][2]) # arr[行][列]，也可以用arr[行,列]
129 | print(arr2[0,:]) # 用:来代表所有元素的意思
130 | print(arr2[0,0:3]) # 表示输出第0行，从第0列到第2列所有元素
131 |                    # 注意python索引一般是左闭右开
132 | 
133 | # 通过for循环每次输出矩阵的一行
134 | for row in arr2:
135 |     print(row)
136 | 
137 | # 如果要每次输出矩阵的一列，就先将矩阵转置
138 | arr2_T=arr2.T
139 | print(arr2_T)
140 | for row in arr2_T:
141 |     print(row)
142 | 
143 | # 将矩阵压成一行逐个输出元素
144 | arr2_flat=arr2.flatten()
145 | print(arr2_flat)
146 | 
147 | for i in arr2.flat: # 也可以用arr2.flatten()
148 |     print(i)
149 | 
150 | # 矩阵合并与分割  
151 | # 矩阵合并
152 | arr1=np.array([1,2,3,6])
153 | arr2=np.arange(4)
154 | arr3=np.arange(2,16+1,2).reshape(2,4)
155 | print(arr1)
156 | print(arr2)
157 | print(arr3)
158 | 
159 | arr_hor=np.hstack((arr1,arr2)) # 水平合并，horizontal
160 | arr_ver=np.vstack((arr1,arr3)) # 垂直合并，vertical
161 | print(arr_hor)
162 | print(arr_ver)
163 | 
164 | # 矩阵分割
165 | print('arr3: ',arr3)
166 | print(np.split(arr3,4,axis=1)) # 将矩阵按列均分成4块
167 | print(np.split(arr3,2,axis=0)) # 将矩阵按行均分成2块
168 | print(np.hsplit(arr3,4)) # 将矩阵按列均分成4块
169 | print(np.vsplit(arr3,2)) # 将矩阵按行均分成2块
170 | print(np.array_split(arr3,3,axis=1)) # 将矩阵进行不均等划分  
171 | 
172 | # numpy复制：浅复制，深复制  
173 | # 浅复制
174 | arr1=np.array([3,1,2,3])
175 | print(arr1)
176 | a1=arr1
177 | b1=a1
178 | # 通过上述赋值运算，arr1,a1,b1都指向了同一个地址（浅复制）
179 | print(a1 is arr1)
180 | print(b1 is arr1)
181 | print(id(a1))
182 | print(id(b1))
183 | print(id(arr1))
184 | 
185 | # 会发现通过b1[0]改变内容，arr1,a1,b1的内容都改变了
186 | b1[0]=6
187 | print(b1)
188 | print(a1)
189 | print(arr1)
190 | 
191 | # 深复制
192 | arr2=np.array([3,1,2,3])
193 | print('\n')
194 | print(arr2)
195 | b2=arr2.copy() # 深复制，此时b2拥有不同于arr2的空间
196 | a2=b2.copy()
197 | # 通过上述赋值运算，arr1,a1,b1都指向了不同的地址（深复制）
198 | print(id(arr2))
199 | print(id(a2))
200 | print(id(b2))
201 | # 此时改变b2,a2的值，互不影响
202 | b2[0]=1
203 | a2[0]=2
204 | print(b2)
205 | print(a2)
206 | print(arr2)
207 |   
208 | # 线性代数模块（linalg）
209 | # 求范数
210 | a=np.array([5,12])
211 | print(a)
212 | b=np.linalg.norm(a) # norm表示范数，默认求2范数，ord=1求1范数，ord=np.inf求无穷范数
213 | print(b)
214 | 
215 | # 求矩阵的迹、行列式、秩、特征值、特征向量
216 | b = np.array([
217 |     [1, 2, 3],
218 |     [4, 5, 6],
219 |     [7, 8, 9]
220 | ])
221 | 
222 | print(np.trace(b))      # 15，求矩阵的迹（主对角线上各个元素的总和）
223 | 
224 | c=np.linalg.det(b)
225 | print(c)                # 输出一个很小的值6.66133814775e-16，求矩阵的行列式值
226 |                         # 如果希望输出为0，使用round(c, 2)，四舍五入保留小数点后两位
227 |                         # 不过对精度要求高可以使用decimal模块
228 | 
229 | c=np.linalg.matrix_rank(b)
230 | print(c)                # 2，求矩阵的秩
231 | 
232 | u,v=np.linalg.eig(b) # u为特征值
233 | print(u)
234 | print(v)
235 | 
236 | # 矩阵分解
237 | # Cholesky分解并重建
238 | d = np.array([
239 |     [2, 1],
240 |     [1, 2]
241 | ])
242 | 
243 | l = np.linalg.cholesky(d)
244 | print(l) # 得到下三角矩阵
245 | e=np.dot(l, l.T)
246 | print(e) # 重建得到矩阵d
247 | 
248 | 
249 | # 对不正定矩阵，进行SVD分解并重建
250 | U, s, V = np.linalg.svd(d)
251 | 
252 | S = np.array([
253 |     [s[0], 0],
254 |     [0, s[1]]
255 | ])
256 | 
257 | print(np.dot(U, np.dot(S, V))) # 重建得到矩阵d
258 | 
259 | # 矩阵乘法
260 | # https://docs.scipy.org/doc/numpy/reference/generated/numpy.dot.html#numpy.dot
261 | print(np.dot(3, 4)) # 12，0-D矩阵相乘（也就是标量相乘）
262 | 
263 | print(np.dot([2j, 3j], [2j, 3j])) # (-13+0j)，1-D矩阵相乘（实际上是向量做点积）
264 | 
265 | a=[[1, 0], [0, 1]]
266 | b=[[4, 1, 0], [2, 2, 0]]
267 | print(np.dot(a, b))
268 | '''
269 | array([[4, 1],
270 |     [2, 2]])
271 | 2-D矩阵相乘
272 | 这里是2*2矩阵和2*3矩阵相乘，结果为2*3矩阵
273 | '''
274 | 
275 | a=[[1, 0], [1, 2]]
276 | b=[2,2]
277 | c=np.dot(a,b)
278 | print(c) 
279 | '''
280 | [2 6]
281 | 注意这里b是向量
282 | numpy处理时并不是按照矩阵乘法规则计算
283 | 而是向量点积
284 | 也就是np.dot([1, 0],[1, 2])和np.dot([1, 2],[2,2])
285 | '''
286 | 
287 | # 再做个实验来区别向量乘法和矩阵乘法
288 | b=np.array([
289 |     [1, 2, 3],
290 |     [4, 5, 6],
291 |     [7, 8, 9]
292 | ])
293 | 
294 | # 这里插播一下，np.array([1,0,1])是3维向量，而不是1*3的矩阵
295 | c1=np.array([[1,0,2]]) 
296 | print(c1.shape) # (1, 3)，这是一个1*3的矩阵
297 | c2=np.array([1,0,2])
298 | print(c2.shape) # (3,)，这是一个3维向量
299 | 
300 | # print(np.dot(b,c1)) # 报错，不符合矩阵乘法规则
301 | print(np.dot(b,c2)) # [ 7 16 25]，点积运算
302 | 
303 | print(np.dot(c1,b)) # [[15 18 21]]，矩阵乘法运算规则
304 | print(np.dot(c2,b)) # [15 18 21]，点积运算
305 | 
306 | # 还要补充一下，如果是用python自带的*运算符计算则是广播机制
307 | print(b*c1) # print(b*c2)结果一样
308 | '''
309 | [[ 1  0  6]
310 |  [ 4  0 12]
311 |  [ 7  0 18]]
312 | '''
313 | print(b+c1) # print(b*c2)结果一样
314 | '''
315 | [[ 2  2  5]
316 |  [ 5  5  8]
317 |  [ 8  8 11]]
318 | '''
319 | 


--------------------------------------------------------------------------------
/python_oneline.py:
--------------------------------------------------------------------------------
 1 | # _*_ coding: utf-8 _*_
 2 | 
 3 | """
 4 | python_oneline.py by xianhu
 5 | """
 6 | 
 7 | 
 8 | # 首先来个python之禅
 9 | # python -c "import this"
10 | """
11 | The Zen of Python, by Tim Peters
12 | 
13 | Beautiful is better than ugly.
14 | Explicit is better than implicit.
15 | Simple is better than complex.
16 | Complex is better than complicated.
17 | Flat is better than nested.
18 | Sparse is better than dense.
19 | Readability counts.
20 | Special cases aren't special enough to break the rules.
21 | Although practicality beats purity.
22 | Errors should never pass silently.
23 | Unless explicitly silenced.
24 | In the face of ambiguity, refuse the temptation to guess.
25 | There should be one-- and preferably only one --obvious way to do it.
26 | Although that way may not be obvious at first unless you're Dutch.
27 | Now is better than never.
28 | Although never is often better than *right* now.
29 | If the implementation is hard to explain, it's a bad idea.
30 | If the implementation is easy to explain, it may be a good idea.
31 | Namespaces are one honking great idea -- let's do more of those!
32 | """
33 | 
34 | 
35 | # 一行代码启动一个Web服务
36 | # python -m SimpleHTTPServer 8080
37 | # python3 -m http.server 8080
38 | 
39 | 
40 | # 一行代码实现变量值互换
41 | a, b = 1, 2; a, b = b, a
42 | 
43 | 
44 | # 一行代码解决FizzBuzz问题: 打印数字1到100, 3的倍数打印“Fizz”来替换这个数, 5的倍数打印“Buzz”, 既是3又是5的倍数的打印“FizzBuzz”
45 | print(' '.join(["fizz"[x % 3 * 4:]+"buzz"[x % 5 * 4:] or str(x) for x in range(1, 101)]))
46 | 
47 | 
48 | # 一行代码输出特定字符"Love"拼成的心形
49 | print('\n'.join([''.join([('Love'[(x-y) % len('Love')] if ((x*0.05)**2+(y*0.1)**2-1)**3-(x*0.05)**2*(y*0.1)**3 <= 0 else ' ') for x in range(-30, 30)]) for y in range(30, -30, -1)]))
50 | 
51 | 
52 | # 一行代码输出Mandelbrot图像: Mandelbrot图像中的每个位置都对应于公式N=x+y*i中的一个复数
53 | print('\n'.join([''.join(['*'if abs((lambda a: lambda z, c, n: a(a, z, c, n))(lambda s, z, c, n: z if n == 0 else s(s, z*z+c, c, n-1))(0, 0.02*x+0.05j*y, 40)) < 2 else ' ' for x in range(-80, 20)]) for y in range(-20, 20)]))
54 | 
55 | 
56 | # 一行代码打印九九乘法表
57 | print('\n'.join([' '.join(['%s*%s=%-2s' % (y, x, x*y) for y in range(1, x+1)]) for x in range(1, 10)]))
58 | 
59 | 
60 | # 一行代码计算出1-100之间的素数(两个版本)
61 | print(' '.join([str(item) for item in filter(lambda x: not [x % i for i in range(2, x) if x % i == 0], range(2, 101))]))
62 | print(' '.join([str(item) for item in filter(lambda x: all(map(lambda p: x % p != 0, range(2, x))), range(2, 101))]))
63 | 
64 | 
65 | # 一行代码输出斐波那契数列
66 | print([x[0] for x in [(a[i][0], a.append([a[i][1], a[i][0]+a[i][1]])) for a in ([[1, 1]], ) for i in range(30)]])
67 | 
68 | 
69 | # 一行代码实现快排算法
70 | qsort = lambda arr: len(arr) > 1 and qsort(list(filter(lambda x: x <= arr[0], arr[1:]))) + arr[0:1] + qsort(list(filter(lambda x: x > arr[0], arr[1:]))) or arr
71 | 
72 | 
73 | # 一行代码解决八皇后问题
74 | [__import__('sys').stdout.write('\n'.join('.' * i + 'Q' + '.' * (8-i-1) for i in vec) + "\n========\n") for vec in __import__('itertools').permutations(range(8)) if 8 == len(set(vec[i]+i for i in range(8))) == len(set(vec[i]-i for i in range(8)))]
75 | 
76 | 
77 | # 一行代码实现数组的flatten功能: 将多维数组转化为一维
78 | flatten = lambda x: [y for l in x for y in flatten(l)] if isinstance(x, list) else [x]
79 | 
80 | 
81 | # 一行代码实现list, 有点类似与上个功能的反功能
82 | array = lambda x: [x[i:i+3] for i in range(0, len(x), 3)]
83 | 
84 | 
85 | # 一行代码实现求解2的1000次方的各位数之和
86 | print(sum(map(int, str(2**1000))))
87 | 
88 | 
89 | # 最后推荐一篇文章: [Python One-liner Games](http://arunrocks.com/python-one-liner-games/)
90 | exit()
91 | 


--------------------------------------------------------------------------------
/python_requests.py:
--------------------------------------------------------------------------------
  1 | # _*_ coding: utf-8 _*_
  2 | 
  3 | """
  4 | python_requests.py by xianhu
  5 | """
  6 | 
  7 | import requests.adapters
  8 | 
  9 | # 不同方式获取网页内容, 返回一个Response对象, 请求的参数可以为url或Request对象
 10 | r0 = requests.get("https://github.com/timeline.json")
 11 | r1 = requests.post("http://httpbin.org/post")
 12 | r2 = requests.put("http://httpbin.org/put")
 13 | r3 = requests.delete("http://httpbin.org/delete")
 14 | r4 = requests.head("http://httpbin.org/get")
 15 | r5 = requests.options("http://httpbin.org/get")
 16 | r6 = requests.patch("http://httpbin.org/get")
 17 | 
 18 | # Request对象:
 19 | # class requests.Request(method=None, url=None, headers=None, files=None, data=None, params=None, auth=None, cookies=None, hooks=None, json=None)
 20 | 
 21 | # 上边所有的获取方式都调用底层的request方法, 所以request方法有的参数, 上边几个函数都应该有:
 22 | # requests.request(method, url, **kwargs)
 23 | # kwargs包括: params / data / json / headers / cookies / files / auth / timeout / allow_redirects(bool) / proxies / verify(bool) / stream / cert
 24 | 
 25 | # Response对象: class requests.Response
 26 | # 包含的主要属性: content / cookies / encoding / headers / history / is_permanent_redirect / is_redirect / reason / status_code / text / url 等
 27 | # 包含的主要方法: iter_content(chunk_size=1, decode_unicode=False) / iter_lines(chunk_size=512, decode_unicode=None, delimiter=None)
 28 | # 包含的主要方法: close() / json(**kwargs) / raise_for_status() 等
 29 | 
 30 | # 以字典的形式传递URL参数, 也可以直接以?xx=xx&xx=xx的形式将其放在url后
 31 | params = {"key1": "value1", "key2": "value2"}
 32 | r = requests.get("http://httpbin.org/get", params=params)
 33 | print(r.url)                # http://httpbin.org/get?key2=value2&key1=value1
 34 | 
 35 | # 以字典的形式传递URL参数: 字典里带有列表
 36 | params = {"key1": "value1", "key2": ["value2", "value3"]}
 37 | r = requests.get("http://httpbin.org/get", params=params)
 38 | print(r.url)                # http://httpbin.org/get?key1=value1&key2=value2&key2=value3
 39 | 
 40 | # 获取网页内容
 41 | r = requests.get("https://github.com/timeline.json")
 42 | print(r.text)               # 返回正常的网页内容, 即解压解码之后的内容
 43 | print(r.content)            # 返回byte类型的网页内容, 即值解压, 没有解码
 44 | print(r.json())             # 如果网页内容为json, 直接返回一个json对象
 45 | print(r.encoding)           # 返回网页的编码: "utf-8"
 46 | 
 47 | # Requests会自动解码来自服务器的内容, 也可以自己更改
 48 | r.encoding = "ISO-8859-1"
 49 | print(r.text)               # 此时使用新的r.encoding解码后的新值
 50 | 
 51 | # 编码的其他操作
 52 | # requests.utils.get_encodings_from_content(content): Returns encodings from given content string.
 53 | # requests.utils.get_encoding_from_headers(headers): Returns encodings from given HTTP Header Dict.
 54 | # requests.utils.get_unicode_from_response(r): Returns the requested content back in unicode.
 55 | 
 56 | # 原始响应内容: 获取来自服务器的原始套接字响应
 57 | r = requests.get("https://github.com/timeline.json", stream=True)
 58 | print(r.raw)                # <requests.packages.urllib3.response.HTTPResponse object at 0x101194810>
 59 | print(r.raw.read(10))       # "\x1f\x8b\x08\x00\x00\x00\x00\x00\x00\x03"
 60 | 
 61 | # 一般情况下, 应该以下面的模式将文本流保存到文件
 62 | with open("test", "wb") as fd:
 63 |     for chunk in r.iter_content(chunk_size=256):
 64 |         fd.write(chunk)
 65 | # 注意: 设置的timeout对connect和read起作用. 但一旦和服务器建立连接, r.content或r.iter_content就处于一个read的状态, 不受timeout影响
 66 | 
 67 | # 定制请求头: 一个字典
 68 | headers = {"user-agent": "my-app/0.0.1"}
 69 | r = requests.get("https://api.github.com/some/endpoint", headers=headers)
 70 | print(r.request.headers)    # 获取request的头部
 71 | print(r.headers)            # 获取response的头部
 72 | # {
 73 | #     "content-encoding": "gzip",
 74 | #     "transfer-encoding": "chunked",
 75 | #     "connection": "close",
 76 | #     "server": "nginx/1.0.4",
 77 | #     "x-runtime": "148ms",
 78 | #     "etag": "e1ca502697e5c9317743dc078f67693f",
 79 | #     "content-type": "application/json"
 80 | # }
 81 | print(r.headers["Content-Type"])        # "application/json"
 82 | print(r.headers.get("content-type"))    # "application/json"
 83 | 
 84 | # 更加复杂的POST请求: 表单
 85 | post_dict = {"key1": "value1", "key2": "value2"}
 86 | r = requests.post("http://httpbin.org/post", data=post_dict)
 87 | print(r.text)
 88 | 
 89 | # POST一个多部分编码(Multipart-Encoded)的文件
 90 | files = {"file": open("report.xls", "rb")}
 91 | r = requests.post("http://httpbin.org/post", files=files)
 92 | print(r.text)
 93 | 
 94 | # 你可以显式地设置文件名, 文件类型和请求头
 95 | files = {"file": ("report.xls", open("report.xls", "rb"), "application/vnd.ms-excel", {"Expires": "0"})}
 96 | r = requests.post("http://httpbin.org/post", files=files)
 97 | print(r.text)
 98 | 
 99 | # 你也可以发送文本字符串
100 | files = {"file": ("report.csv", "some,data,to,send\nanother,row,to,send\n")}
101 | r = requests.post("http://httpbin.org/post", files=files)
102 | print(r.text)
103 | 
104 | # 响应状态码
105 | r = requests.get("http://httpbin.org/get")
106 | print(r.status_code)                            # 200
107 | print(r.status_code == requests.codes.ok)       # True 响应状态码查询
108 | 
109 | # 如果发送了一个错误请求(4XX客户端错误, 或5XX服务器错误响应), 可以通过 Response.raise_for_status() 来抛出异常:
110 | bad_r = requests.get("http://httpbin.org/status/404")
111 | print(bad_r.status_code)                        # 404
112 | bad_r.raise_for_status()                        # 引发异常
113 | 
114 | # Cookie: 如果某个响应中包含一些cookie, 则会被放到response.cookies(CookieJar类型)中
115 | r = requests.get("http://example.com/some/cookie/setting/url")
116 | print(r.cookies["example_cookie_name"])         # "example_cookie_value"
117 | 
118 | # 要想发送你的cookies到服务器, 可以使用cookies参数(一个字典)
119 | cookies = {"cookies_are": "working"}
120 | r = requests.get("http://httpbin.org/cookies", cookies=cookies)
121 | print(r.text)
122 | 
123 | # cookie的其他操作
124 | # requests.utils.dict_from_cookiejar(cj): Returns a key/value dictionary from a CookieJar.
125 | # requests.utils.cookiejar_from_dict(cookie_dict, cookiejar=None, overwrite=True): Returns a CookieJar from a key/value dictionary.
126 | # requests.utils.add_dict_to_cookiejar(cj, cookie_dict): Returns a CookieJar from a key/value dictionary.
127 | 
128 | # 通用CookieJar类, 一个cookielib.CookieJar, 但是提供一个dict接口
129 | # class requests.cookies.RequestsCookieJar(policy=None): Compatibility class; is a cookielib.CookieJar, but exposes a dict interface.
130 | 
131 | # 会话对象: 会话对象让你能够跨请求保持某些参数, 它也会在同一个Session实例发出的所有请求之间保持cookie
132 | s = requests.Session()
133 | s.get("http://httpbin.org/cookies/set/sessioncookie/123456789")
134 | s.get("http://httpbin.org/cookies")
135 | for cookie in s.cookies:
136 |     print(cookie)
137 | 
138 | # 如果你要手动为会话添加cookie, 就是用Cookie utility函数来操纵Session.cookies
139 | requests.utils.add_dict_to_cookiejar(s.cookies, {"cookie_key": "cookie_value"})
140 | 
141 | # 会话也可用来为请求方法提供缺省数据, 这是通过为会话对象的属性提供数据来实现的
142 | s.auth = ("user", "pass")
143 | s.headers.update({"x-test": "true"})
144 | s.get("http://httpbin.org/headers", headers={"x-test2": "true"})        # both "x-test" and "x-test2" are sent
145 | 
146 | # 不过需要注意, 就算使用了会话, 方法级别的参数也不会被跨请求保持, 下面的例子只会给第一个请求发送cookie
147 | s.get("http://httpbin.org/cookies", cookies={"from-my": "browser"})     # 带有cookie
148 | s.get("http://httpbin.org/cookies")                                     # 不带cookie
149 | 
150 | # 会话还可以用作前后文管理器
151 | with requests.Session() as s:
152 |     s.get("http://httpbin.org/cookies/set/sessioncookie/123456789")
153 | # class requests.Session类, 和requests外层有的函数/属性基本一致, 只不过是封装了一层跨域请求的功能
154 | 
155 | # 重定向与请求历史, 默认情况下, 除了HEAD, Requests会自动处理所有重定向, 可以通过allow_redirects参数禁用重定向处理
156 | # 可以使用响应对象的history方法来追踪重定向, Response.history 是一个Response对象的列表, 按照从最老到最近的请求进行排序
157 | r = requests.get("http://github.com", allow_redirects=True)
158 | print(r.status_code)        # 200
159 | print(r.history)            # [<Response [301]>]
160 | r = requests.get("http://github.com", allow_redirects=False)
161 | print(r.status_code)        # 301
162 | print(r.history)            # []
163 | 
164 | # 超时, 设置timeout参数
165 | requests.get("http://github.com", timeout=0.001)
166 | # Traceback (most recent call last):
167 | #   File "<stdin>", line 1, in <module>
168 | # requests.exceptions.Timeout: HTTPConnectionPool(host="github.com", port=80): Request timed out. (timeout=0.001)
169 | 
170 | # 注意: timeout仅对连接过程有效, 与响应体的下载无关
171 | # timeout并不是整个下载响应的时间限制, 而是如果服务器在timeout秒内没有应答, 将会引发一个异常
172 | # 更精确地说, 是在timeout秒内没有从基础套接字上接收到任何字节的数据时
173 | requests.get("https://github.com", timeout=5)
174 | 
175 | # 上边的timeout值将会用作 connect 和 read 二者的timeout, 如果要分别制定, 就传入一个元组
176 | requests.get("https://github.com", timeout=(3.05, 27))
177 | 
178 | # 错误与异常: 遇到网络问题(如: DNS 查询失败、拒绝连接等)时, Requests 会抛出一个 ConnectionError 异常
179 | # 如果 HTTP 请求返回了不成功的状态码, Response.raise_for_status() 会抛出一个 HTTPError 异常
180 | # 若请求超时, 则抛出一个 Timeout 异常
181 | # 若请求超过了设定的最大重定向次数, 则会抛出一个 TooManyRedirects 异常
182 | # 所有Requests显式抛出的异常都继承自 requests.exceptions.RequestException
183 | 
184 | # 所有异常:
185 | # exception requests.RequestException(*args, **kwargs): There was an ambiguous exception that occurred while handling your request.
186 | # exception requests.ConnectionError(*args, **kwargs): A Connection error occurred.
187 | # exception requests.HTTPError(*args, **kwargs): An HTTP error occurred.
188 | # exception requests.URLRequired(*args, **kwargs): A valid URL is required to make a request.
189 | # exception requests.TooManyRedirects(*args, **kwargs): Too many redirects.
190 | # exception requests.ConnectTimeout(*args, **kwargs): The request timed out while trying to connect to the remote server.
191 | # exception requests.ReadTimeout(*args, **kwargs): The server did not send any data in the allotted amount of time.
192 | # exception requests.Timeout(*args, **kwargs): The request timed out.
193 | 
194 | # SSL证书验证, verify设置为True表示检查证书, 设置为False表示忽略证书
195 | requests.get("https://kennethreitz.com", verify=True)       # 未设置SSL证书, 抛出异常
196 | # requests.exceptions.SSLError: hostname "kennethreitz.com" doesn"t match either of "*.herokuapp.com", "herokuapp.com"
197 | requests.get("https://github.com", verify=True)             # <Response [200]>, 已设置SSL证书
198 | # 对于私有证书，你也可以传递一个 CA_BUNDLE 文件的路径给 verify
199 | 
200 | # 你也可以指定一个本地证书用作客户端证书, 可以是单个文件（包含密钥和证书）或一个包含两个文件路径的元组:
201 | requests.get("https://kennethreitz.com", cert=("/path/server.crt", "/path/key"))
202 | requests.get("https://kennethreitz.com", cert="/wrong_path/server.pem")
203 | # SSLError: [Errno 336265225] _ssl.c:347: error:140B0009:SSL routines:SSL_CTX_use_PrivateKey_file:PEM lib
204 | # 警告: 本地证书的私有 key 必须是解密状态. 目前Requests不支持使用加密的 key
205 | 
206 | # 流式上传, 允许你发送大的数据流或文件而无需先把它们读入内存
207 | with open("massive-body") as f:
208 |     requests.post("http://some.url/streamed", data=f)
209 | 
210 | # 事件挂钩, 可用的钩子: response(从一个请求产生的响应)
211 | # 你可以通过传递一个 {hook_name: callback_function} 字典给 hooks 请求参数为每个请求分配一个钩子函数
212 | def print_url(resp):
213 |     print(resp.url)
214 |     return
215 | requests.get("http://httpbin.org", hooks=dict(response=print_url))
216 | 
217 | # 代理
218 | proxies = {
219 |     "http": "http://10.10.1.10:3128",
220 |     "https": "http://10.10.1.10:1080",
221 | }
222 | requests.get("http://example.org", proxies=proxies)
223 | # 若代理需要使用HTTP Basic Auth, 可以使用http://user:password@host:port/, 比如"http": "http://user:pass@10.10.1.10:3128/"
224 | 
225 | # 除了基本的 HTTP 代理, Request 还支持 SOCKS 协议的代理, 此时需要单独安装:
226 | # $ pip install requests[socks]
227 | proxies = {
228 |     "http": "socks5://user:pass@host:port",
229 |     "https": "socks5://user:pass@host:port"
230 | }
231 | requests.get("http://example.org", proxies=proxies)
232 | 
233 | # Requests 传输适配器
234 | # 从 v1.0.0 以后，Requests 的内部采用了模块化设计。部分原因是为了实现传输适配器（Transport Adapter）。
235 | # 传输适配器提供了一个机制，让你可以为 HTTP 服务定义交互方法。尤其是它允许你应用服务前的配置。
236 | # Requests 自带了一个传输适配器，也就是 HTTPAdapter。 这个适配器使用了强大的 urllib3，为 Requests 提供了默认的 HTTP 和 HTTPS 交互。
237 | # 每当 Session 被初始化，就会有适配器附着在 Session 上，其中一个供 HTTP 使用，另一个供 HTTPS 使用。
238 | # Request 允许用户创建和使用他们自己的传输适配器，实现他们需要的特殊功能。创建好以后，传输适配器可以被加载到一个会话对象上，附带着一个说明，告诉会话适配器应该应用在哪个 web 服务上。
239 | s = requests.Session()
240 | s.mount("http://baidu.com", requests.adapters.HTTPAdapter())
241 | 
242 | # 出现错误: Connection pool is full, discarding connection: xxxx.com
243 | s.mount('https://', requests.adapters.HTTPAdapter(pool_connections=100, pool_maxsize=100))
244 | 
245 | # 关闭InsecurePlatformWarning
246 | # requests.packages.urllib3.disable_warnings()
247 | 


--------------------------------------------------------------------------------
/python_restful_api.py:
--------------------------------------------------------------------------------
  1 | # _*_ coding: utf-8 _*_
  2 | 
  3 | """
  4 | python_restful_api.py by xianhu
  5 | """
  6 | 
  7 | import sqlalchemy
  8 | import sqlalchemy.orm
  9 | import sqlalchemy.ext.declarative
 10 | from flask import Flask, g
 11 | from flask_restful import reqparse, Api, Resource
 12 | from flask_httpauth import HTTPTokenAuth
 13 | 
 14 | 
 15 | # Flask相关变量声明
 16 | app = Flask(__name__)
 17 | api = Api(app)
 18 | 
 19 | # 认证相关
 20 | auth = HTTPTokenAuth(scheme="token")
 21 | TOKENS = {
 22 |     "fejiasdfhu",
 23 |     "fejiuufjeh"
 24 | }
 25 | 
 26 | 
 27 | @auth.verify_token
 28 | def verify_token(token):
 29 |     if token in TOKENS:
 30 |         g.current_user = token
 31 |         return True
 32 |     return False
 33 | 
 34 | 
 35 | # 数据库相关变量声明
 36 | engine = sqlalchemy.create_engine("mysql+pymysql://username:password@ip/db_name", encoding="utf8", echo=False)
 37 | BaseModel = sqlalchemy.ext.declarative.declarative_base()
 38 | 
 39 | 
 40 | # 构建数据模型User
 41 | class User(BaseModel):
 42 |     __tablename__ = "Users"
 43 |     __table_args__ = {
 44 |         "mysql_engine": "InnoDB",
 45 |         "mysql_charset": "utf8",
 46 |     }
 47 | 
 48 |     # 表结构,具体更多的数据类型自行百度
 49 |     id = sqlalchemy.Column("id", sqlalchemy.Integer, primary_key=True, autoincrement=True)
 50 |     name = sqlalchemy.Column("name", sqlalchemy.String(50), nullable=False)
 51 |     age = sqlalchemy.Column("age", sqlalchemy.Integer, nullable=False)
 52 | 
 53 | 
 54 | # 构建数据模型的json格式
 55 | def get_json(user):
 56 |     return {"id": user.id, "name": user.name, "age": user.age}
 57 | 
 58 | 
 59 | # 利用Session对象连接数据库
 60 | DBSessinon = sqlalchemy.orm.sessionmaker(bind=engine)
 61 | session = DBSessinon()
 62 | BaseModel.metadata.drop_all(engine)
 63 | BaseModel.metadata.create_all(engine)
 64 | 
 65 | # RESTfulAPI的参数解析 -- put / post参数解析
 66 | parser_put = reqparse.RequestParser()
 67 | parser_put.add_argument("name", type=str, required=True, help="need name data")
 68 | parser_put.add_argument("age", type=int, required=True, help="need age data")
 69 | 
 70 | # RESTfulAPI的参数解析 -- get参数解析
 71 | parser_get = reqparse.RequestParser()
 72 | parser_get.add_argument("limit", type=int, required=False)
 73 | parser_get.add_argument("offset", type=int, required=False)
 74 | parser_get.add_argument("sortby", type=str, required=False)
 75 | 
 76 | 
 77 | # 操作（put / get / delete）单一资源
 78 | class Todo(Resource):
 79 |     # 添加认证
 80 |     decorators = [auth.login_required]
 81 | 
 82 |     def put(self, user_id):
 83 |         """
 84 |         更新用户数据: curl http://127.0.0.1:5000/users/1 -X PUT -d "name=Allen&age=20" -H "Authorization: token fejiasdfhu"
 85 |         """
 86 |         args = parser_put.parse_args()
 87 |         user_ids_set = set([user.id for user in session.query(User.id)])
 88 |         print(user_ids_set)
 89 | 
 90 |         # 用户不存在，返回404
 91 |         if user_id not in user_ids_set:
 92 |             return None, 404
 93 | 
 94 |         # 更新用户数据
 95 |         user = session.query(User).filter(User.id == user_id)[0]
 96 |         user.name = args["name"]
 97 |         user.age = args["age"]
 98 |         session.merge(user)
 99 |         session.commit()
100 | 
101 |         # 更新成功，返回201
102 |         return get_json(user), 201
103 | 
104 |     def get(self, user_id):
105 |         """
106 |         获取用户数据: curl http://127.0.0.1:5000/users/1 -X GET -H "Authorization: token fejiasdfhu"
107 |         """
108 |         users = session.query(User).filter(User.id == user_id)
109 | 
110 |         # 用户不存在，返回404
111 |         if users.count() == 0:
112 |             return None, 404
113 | 
114 |         # 返回用户数据
115 |         return get_json(users[0]), 200
116 | 
117 |     def delete(self, user_id):
118 |         """
119 |         删除用户数据: curl http://127.0.0.1:5000/users/1 -X DELETE -H "Authorization: token fejiasdfhu"
120 |         """
121 |         session.query(User).filter(User.id == user_id).delete()
122 |         return None, 204
123 | 
124 | 
125 | # 操作（post / get）资源列表
126 | class TodoList(Resource):
127 |     # 添加认证
128 |     decorators = [auth.login_required]
129 | 
130 |     def get(self):
131 |         """
132 |         获取全部用户数据: curl http://127.0.0.1:5000/users -X GET -d "limit=2&offset=0&sortby=name" -H "Authorization: token fejiasdfhu"
133 |         """
134 |         args = parser_get.parse_args()
135 |         users = session.query(User)
136 | 
137 |         # 根据条件查询
138 |         if "sortby" in args:
139 |             users = users.order_by(User.name if args["sortby"] == "name" else User.age)
140 |         if "offset" in args:
141 |             users = users.offset(args["offset"])
142 |         if "limit" in args:
143 |             users = users.limit(args["limit"])
144 | 
145 |         # 返回结果
146 |         return [get_json(user) for user in users], 200
147 | 
148 |     def post(self):
149 |         """
150 |         添加一个新用户: curl http://127.0.0.1:5000/users -X POST -d "name=Brown&age=20" -H "Authorization: token fejiasdfhu"
151 |         """
152 |         args = parser_put.parse_args()
153 | 
154 |         # 构建新用户
155 |         user = User(name=args["name"], age=args["age"])
156 |         session.add(user)
157 |         session.commit()
158 | 
159 |         # 资源添加成功，返回201
160 |         return get_json(user), 201
161 | 
162 | 
163 | # 设置路由
164 | api.add_resource(TodoList, "/users")
165 | api.add_resource(Todo, "/users/<int:user_id>")
166 | 
167 | 
168 | if __name__ == "__main__":
169 |     app.run(debug=True)
170 | 
171 | 
172 | """ 常见返回代码
173 | 200 OK - [GET]：服务器成功返回用户请求的数据
174 | 201 CREATED - [POST/PUT/PATCH]：用户新建或修改数据成功
175 | 202 Accepted - [*]：表示一个请求已经进入后台排队（异步任务）
176 | 204 NO CONTENT - [DELETE]：用户删除数据成功
177 | 400 INVALID REQUEST - [POST/PUT/PATCH]：用户发出的请求有错误，服务器没有进行新建或修改数据的操作
178 | 401 Unauthorized - [*]：表示用户没有权限（令牌、用户名、密码错误）
179 | 403 Forbidden - [*] 表示用户得到授权（与401错误相对），但是访问是被禁止的
180 | 404 NOT FOUND - [*]：用户发出的请求针对的是不存在的记录，服务器没有进行操作
181 | 406 Not Acceptable - [GET]：用户请求的格式不可得
182 | 410 Gone -[GET]：用户请求的资源被永久删除，且不会再得到的
183 | 422 Unprocesable entity - [POST/PUT/PATCH] 当创建一个对象时，发生一个验证错误
184 | 500 INTERNAL SERVER ERROR - [*]：服务器发生错误，用户将无法判断发出的请求是否成功
185 | """
186 | 


--------------------------------------------------------------------------------
/python_spider.py:
--------------------------------------------------------------------------------
 1 | # _*_ coding: utf-8 _*_
 2 | 
 3 | """
 4 | python_spider.py by xianhu
 5 | """
 6 | 
 7 | import urllib.error
 8 | import urllib.parse
 9 | import urllib.request
10 | import http.cookiejar
11 | 
12 | # 首先定义下边可能需要的变量
13 | url = "https://www.baidu.com"
14 | headers = {"User-Agent": "Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)"}
15 | 
16 | # 最简单的网页抓取方式
17 | response = urllib.request.urlopen(url, timeout=10)
18 | html = response.read().decode("utf-8")
19 | 
20 | 
21 | # 使用Request实例代替url
22 | request = urllib.request.Request(url, data=None, headers={})
23 | response = urllib.request.urlopen(request, timeout=10)
24 | 
25 | 
26 | # 发送数据，即在Request()中添加data参数
27 | data = urllib.parse.urlencode({"act": "login", "email": "xianhu@qq.com", "password": "123456"})
28 | request1 = urllib.request.Request(url, data=data)           # POST方法
29 | request2 = urllib.request.Request(url+"?%s" % data)         # GET方法
30 | response = urllib.request.urlopen(request, timeout=10)
31 | 
32 | 
33 | # 发送Header，即在Request()中添加headers参数
34 | request = urllib.request.Request(url, data=data, headers=headers)   # 参数中添加header参数
35 | request.add_header("Referer", "http://www.baidu.com")               # 另一种添加header的方式,添加Referer是为了应对"反盗链"
36 | response = urllib.request.urlopen(request, timeout=10)
37 | 
38 | 
39 | # 网页抓取引发异常：urllib.error.HTTPError, urllib.error.URLError, 两者存在继承关系
40 | try:
41 |     urllib.request.urlopen(request, timeout=10)
42 | except urllib.error.HTTPError as e:
43 |     print(e.code, e.reason)
44 | except urllib.error.URLError as e:
45 |     print(e.errno, e.reason)
46 | 
47 | 
48 | # 使用代理，以防止IP被封或IP次数受限：
49 | proxy_handler = urllib.request.ProxyHandler(proxies={"http": "111.123.76.12:8080"})
50 | 
51 | opener = urllib.request.build_opener(proxy_handler)     # 利用代理创建opener实例
52 | response = opener.open(url)                             # 直接利用opener实例打开url
53 | 
54 | urllib.request.install_opener(opener)                   # 安装全局opener，然后利用urlopen打开url
55 | response = urllib.request.urlopen(url)
56 | 
57 | 
58 | # 使用cookie和cookiejar,应对服务器检查
59 | cookie_jar = http.cookiejar.CookieJar()
60 | cookie_jar_handler = urllib.request.HTTPCookieProcessor(cookiejar=cookie_jar)
61 | opener = urllib.request.build_opener(cookie_jar_handler)
62 | response = opener.open(url)
63 | 
64 | 
65 | # 发送在浏览器中获取的cookie,两种方式:
66 | # (1)直接放到headers里
67 | headers = {
68 |     "User-Agent": "Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)",
69 |     "Cookie": "PHPSESSID=btqkg9amjrtoeev8coq0m78396; USERINFO=n6nxTHTY%2BJA39z6CpNB4eKN8f0KsYLjAQTwPe%2BhLHLruEbjaeh4ulhWAS5RysUM%2B; "
70 | }
71 | request = urllib.request.Request(url, headers=headers)
72 | 
73 | # (2)构建cookie,添加到cookiejar中
74 | cookie = http.cookiejar.Cookie(name="xx", value="xx", domain="xx", ...)
75 | cookie_jar.set_cookie(cookie)
76 | response = opener.open(url)
77 | 
78 | 
79 | # 同时使用代理和cookiejar
80 | opener = urllib.request.build_opener(cookie_jar_handler)
81 | opener.add_handler(proxy_handler)
82 | response = opener.open("https://www.baidu.com/")
83 | 
84 | 
85 | # 抓取网页中的图片：同样适用于抓取网络上的文件。右击鼠标，找到图片属性中的地址，然后进行保存。
86 | response = urllib.request.urlopen("http://ww3.sinaimg.cn/large/7d742c99tw1ee7dac2766j204q04qmxq.jpg", timeout=120)
87 | with open("test.jpg", "wb") as file_img:
88 |     file_img.write(response.read())
89 | 
90 | 
91 | # HTTP认证：即HTTP身份验证
92 | password_mgr = urllib.request.HTTPPasswordMgrWithDefaultRealm()     # 创建一个PasswordMgr
93 | password_mgr.add_password(realm=None, uri=url, user='username', passwd='password')   # 添加用户名和密码
94 | handler = urllib.request.HTTPBasicAuthHandler(password_mgr)         # 创建HTTPBasicAuthHandler
95 | opener = urllib.request.build_opener(handler)                       # 创建opner
96 | response = opener.open(url, timeout=10)                             # 获取数据
97 | 


--------------------------------------------------------------------------------
/python_sqlalchemy.py:
--------------------------------------------------------------------------------
  1 | # _*_ coding: utf-8 _*_
  2 | 
  3 | """
  4 | python_sqlalchemy.py by xianhu
  5 | """
  6 | 
  7 | import sqlalchemy
  8 | import sqlalchemy.orm
  9 | import sqlalchemy.ext.declarative
 10 | 
 11 | # 利用数据库字符串构造engine, echo为True将打印所有的sql语句, 其他数据库的链接方式可自行百度
 12 | # engine = sqlalchemy.create_engine("mysql+pymysql://username:password@hostname/dbname", encoding="utf8", echo=True)
 13 | engine = sqlalchemy.create_engine("mysql+pymysql://dba_0:mimadba_0@101.200.174.172/data_secret", encoding="utf8", echo=False)
 14 | 
 15 | """
 16 | # 利用engine创建connection,因为使用了with所以不需要close操作,这部分不是重点
 17 | with engine.connect() as conn:
 18 |     # 最基础的用法
 19 |     result = conn.execute("select * from tablename limit 10;")
 20 |     for item in result:
 21 |         print(item)
 22 | 
 23 |     # execute的几种用法,这里具体还是得参考pymysql的用法,不需要执行commit操作
 24 |     conn.execute("insert into tablename(id, url, title) values(1, 'url1', 'title1');")
 25 |     conn.execute("insert into tablename(id, url, title) values(%s, %s, %s);", 2, "url2", "title2")
 26 |     conn.execute("insert into tablename(id, url, title) values(%s, %s, %s)", (3, "url3", "title3"))
 27 |     conn.execute("insert into tablename(id, url, title) values(%s, %s, %s)", [(31, "url31", "title31"), (32, "url32", "title32")])
 28 | 
 29 |     # 使用事务可以进行批量提交和回滚
 30 |     trans = conn.begin()
 31 |     try:
 32 |         conn.execute("insert into tablename(id, url, title) values(%s, %s, %s)", [(4, "url4", "title4"), (5, "url5", "title5")])
 33 |         trans.commit()
 34 |     except Exception as excep:
 35 |         trans.rollback()
 36 |         raise
 37 |     trans.close()
 38 | """
 39 | 
 40 | # 首先需要生成一个BaseModel类,作为所有模型类的基类
 41 | BaseModel = sqlalchemy.ext.declarative.declarative_base()
 42 | 
 43 | 
 44 | # 构建数据模型User
 45 | class User(BaseModel):
 46 |     __tablename__ = "Users"         # 表名
 47 |     __table_args__ = {
 48 |         "mysql_engine": "InnoDB",   # 表的引擎
 49 |         "mysql_charset": "utf8",    # 表的编码格式
 50 |     }
 51 | 
 52 |     # 表结构,具体更多的数据类型自行百度
 53 |     id = sqlalchemy.Column("id", sqlalchemy.Integer, primary_key=True, autoincrement=True)
 54 |     name = sqlalchemy.Column("name", sqlalchemy.String(50), nullable=False)
 55 |     age = sqlalchemy.Column("age", sqlalchemy.Integer, default=0)
 56 | 
 57 |     # 添加角色id外键,关联到表Roles的id属性
 58 |     role_id = sqlalchemy.Column("role_id", sqlalchemy.Integer, sqlalchemy.ForeignKey("Roles.id"))
 59 | 
 60 |     # 添加关系属性,关联到本实例的role_id外键属性上
 61 |     role = sqlalchemy.orm.relationship("Role", foreign_keys="User.role_id")
 62 | 
 63 |     # 添加关系属性,关联到本实例的role_id外键属性上,如果使用了这种方式,Role模型中的users可以省略
 64 |     # role = sqlalchemy.orm.relationship("Role", foreign_keys="User.role_id", backref=sqlalchemy.orm.backref("users"))
 65 | 
 66 | 
 67 | # 构建数据模型Role
 68 | class Role(BaseModel):
 69 |     __tablename__ = "Roles"         # 表名
 70 |     __table_args__ = {
 71 |         "mysql_engine": "InnoDB",   # 表的引擎
 72 |         "mysql_charset": "utf8",    # 表的编码格式
 73 |     }
 74 | 
 75 |     # 表结构,具体更多的数据类型自行百度
 76 |     id = sqlalchemy.Column("id", sqlalchemy.Integer, primary_key=True)
 77 |     name = sqlalchemy.Column("name", sqlalchemy.String(50), unique=True)
 78 | 
 79 |     # 添加关系属性,关联到实例User的role_id外键属性上
 80 |     users = sqlalchemy.orm.relationship("User", foreign_keys="User.role_id")
 81 | 
 82 | 
 83 | # 利用Session对象连接数据库
 84 | DBSessinon = sqlalchemy.orm.sessionmaker(bind=engine)   # 创建会话类
 85 | session = DBSessinon()                                  # 创建会话对象
 86 | 
 87 | 
 88 | # 删除所有表
 89 | BaseModel.metadata.drop_all(engine)
 90 | # 创建所有表,如果表已经存在,则不会创建
 91 | BaseModel.metadata.create_all(engine)
 92 | 
 93 | try:
 94 |     # 清空数据,不需要commit操作
 95 |     session.query(User).filter(User.id != -1).delete()
 96 |     session.query(Role).filter(Role.id != -1).delete()
 97 |     # 删除数据的另外一种形式:session.delete()
 98 | 
 99 |     # 插入数据,这里的一个实例只插入一次,第二次插入不生效
100 |     session.add(Role(id=1, name="student"))
101 |     session.add(Role(id=2, name="teacher"))
102 |     session.commit()
103 | 
104 |     session.add(User(name="James", age=20, role_id=1))
105 |     session.add(User(name="Wade", age=40, role_id=2))
106 |     session.commit()
107 | 
108 |     user = User(name="Kobe", age=24, role_id=1)
109 |     session.add(user)
110 |     session.commit()
111 | 
112 |     # 修改数据
113 |     user.name = "Allen"
114 |     session.merge(user)                         # 使用merge方法,如果存在则修改,如果不存在则插入
115 |     session.query(User).filter(User.id == user.id).update({User.name: "Allen"})         # 使用update方法
116 |     session.query(User).filter(User.id == user.id).update({User.age: User.age + 1})     # 使用update方法,自增操作
117 | 
118 |     # 查询数据
119 |     roles = session.query(Role)                 # 返回全部结果
120 |     for role in roles:
121 |         print("Role:", role.id, role.name)
122 | 
123 |     users = session.query(User)                 # 返回全部结果
124 |     for user in users:
125 |         print("User:", user.id, user.name, user.age, user.role_id)
126 | 
127 |     # 其他获取数据的方式
128 |     print("get(id):", session.query(User).get(1))                       # 返回结果集中id为1的项
129 |     print("get[1:3]:", session.query(User)[1:3])                        # 返回结果集中的第2-3项
130 | 
131 |     # 其他高级查询,这里以Users表为例
132 |     users = session.query(User).filter(User.id > 6)                     # 条件查询
133 |     users = session.query(User).filter(User.id > 6).all()               # 条件查询,返回查询的全部数据
134 |     user = session.query(User).filter(User.id > 6).first()              # 条件查询,返回查询数据的第一项
135 |     users = session.query(User).filter(User.id > 6).limit(10)           # 条件查询,返回最多10条数据
136 |     users = session.query(User).filter(User.id > 6).offset(2)           # 条件查询,从第3条数据开始返回
137 | 
138 |     users = session.query(User).filter(User.id > 6, User.name == "Kobe")                    # 条件查询,and操作
139 |     users = session.query(User).filter(User.id > 6).filter(User.name == "Kobe")             # 条件查询,and操作
140 |     users = session.query(User).filter(sqlalchemy.or_(User.id > 6, User.name == "Kobe"))    # 条件查询,or操作
141 |     users = session.query(User).filter(User.id.in_((1, 2)))                                 # 条件查询,in操作
142 |     users = session.query(User).filter(sqlalchemy.not_(User.name))                          # 条件查询,not操作
143 | 
144 |     user_count = session.query(User.id).count()                                             # 统计全部user的数量
145 |     user_count = session.query(sqlalchemy.func.count(User.id)).scalar()                     # scalar操作返回第一行数据的第一个字段
146 |     session.query(sqlalchemy.func.count("*")).select_from(User).scalar()                    # scalar操作返回第一行数据的第一个字段
147 |     session.query(sqlalchemy.func.count(1)).select_from(User).scalar()                      # scalar操作返回第一行数据的第一个字段
148 |     session.query(sqlalchemy.func.count(User.id)).filter(User.id > 0).scalar()              # filter() 中包含 User，因此不需要指定表
149 | 
150 |     session.query(sqlalchemy.func.sum(User.age)).scalar()                                   # 求和运算,运用scalar函数
151 |     session.query(sqlalchemy.func.avg(User.age)).scalar()                                   # 求均值运算,运用scalar函数
152 |     session.query(sqlalchemy.func.md5(User.name)).filter(User.id == 1).scalar()             # 运用md5函数
153 | 
154 |     users = session.query(sqlalchemy.distinct(User.name))               # 去重查询,根据name进行去重
155 |     users = session.query(User).order_by(User.name)                     # 排序查询,正序查询
156 |     users = session.query(User).order_by(User.name.desc())              # 排序查询,倒序查询
157 |     users = session.query(User).order_by(sqlalchemy.desc(User.name))    # 排序查询,倒序查询的另外一种形式
158 | 
159 |     users = session.query(User.id, User.name)                           # 只查询部分属性
160 |     users = session.query(User.name.label("user_name"))                 # 结果集的列取别名
161 |     for user in users:
162 |         print("label test:", user.user_name)                            # 这里使用别名
163 | 
164 |     users = session.query(sqlalchemy.func.count(User.name).label("count"), User.age).group_by(User.age)    # 分组查询
165 |     for user in users:
166 |         print("age:{0}, count:{1}".format(user.age, user.count))
167 | 
168 |     # 多表查询
169 |     result = session.query(User, Role).filter(User.role_id == Role.id)
170 |     for user, role in result:
171 |         print("user %s's role is %s" % (user.name, role.name))
172 |     users = session.query(User).join(Role, User.role_id == Role.id)
173 |     for user in users:
174 |         print("user join, name:", user.name)
175 | 
176 |     # 关联属性的用法
177 |     roles = session.query(Role)
178 |     for role in roles:
179 |         print("role:%s users:" % role.name)
180 |         for user in role.users:
181 |             print("\t%s" % user.name)
182 |     users = session.query(User)
183 |     for user in users:
184 |         print("user %s's role is %s" % (user.name, user.role.name))
185 | 
186 | except Exception as excep:
187 |     session.rollback()
188 |     raise
189 | 
190 | session.close()
191 | 


--------------------------------------------------------------------------------
/python_thread_multiprocess.py:
--------------------------------------------------------------------------------
  1 | # _*_ coding: utf-8 _*_
  2 | 
  3 | """
  4 | python_thread_multiprocee.py by xianhu
  5 | """
  6 | 
  7 | import time
  8 | import threading
  9 | import multiprocessing
 10 | 
 11 | # 定义全局变量Queue
 12 | g_queue = multiprocessing.Queue()
 13 | g_search_list = list(range(10000))
 14 | 
 15 | 
 16 | # 定义一个IO密集型任务：利用time.sleep()
 17 | def task_io(task_id):
 18 |     print("IOTask[%s] start" % task_id)
 19 |     while not g_queue.empty():
 20 |         time.sleep(1)
 21 |         try:
 22 |             data = g_queue.get(block=True, timeout=1)
 23 |             print("IOTask[%s] get data: %s" % (task_id, data))
 24 |         except Exception as excep:
 25 |             print("IOTask[%s] error: %s" % (task_id, str(excep)))
 26 |     print("IOTask[%s] end" % task_id)
 27 |     return
 28 | 
 29 | 
 30 | # 定义一个计算密集型任务：利用一些复杂加减乘除、列表查找等
 31 | def task_cpu(task_id):
 32 |     print("CPUTask[%s] start" % task_id)
 33 |     while not g_queue.empty():
 34 |         count = 0
 35 |         for i in range(10000):
 36 |             count += pow(3*2, 3*2) if i in g_search_list else 0
 37 |         try:
 38 |             data = g_queue.get(block=True, timeout=1)
 39 |             print("CPUTask[%s] get data: %s" % (task_id, data))
 40 |         except Exception as excep:
 41 |             print("CPUTask[%s] error: %s" % (task_id, str(excep)))
 42 |     print("CPUTask[%s] end" % task_id)
 43 |     return task_id
 44 | 
 45 | 
 46 | def init_queue():
 47 |     print("init g_queue start")
 48 |     while not g_queue.empty():
 49 |         g_queue.get()
 50 |     for _index in range(10):
 51 |         g_queue.put(_index)
 52 |     print("init g_queue end")
 53 |     return
 54 | 
 55 | 
 56 | if __name__ == '__main__':
 57 |     print("cpu count:", multiprocessing.cpu_count(), "\n")
 58 | 
 59 |     print("========== 直接执行IO密集型任务 ==========")
 60 |     init_queue()
 61 |     time_0 = time.time()
 62 |     task_io(0)
 63 |     print("结束：", time.time() - time_0, "\n")
 64 | 
 65 |     print("========== 多线程执行IO密集型任务 ==========")
 66 |     init_queue()
 67 |     time_0 = time.time()
 68 |     thread_list = [threading.Thread(target=task_io, args=(i,)) for i in range(5)]
 69 |     for t in thread_list:
 70 |         t.start()
 71 |     for t in thread_list:
 72 |         if t.is_alive():
 73 |             t.join()
 74 |     print("结束：", time.time() - time_0, "\n")
 75 | 
 76 |     print("========== 多进程执行IO密集型任务 ==========")
 77 |     init_queue()
 78 |     time_0 = time.time()
 79 |     process_list = [multiprocessing.Process(target=task_io, args=(i,)) for i in range(multiprocessing.cpu_count())]
 80 |     for p in process_list:
 81 |         p.start()
 82 |     for p in process_list:
 83 |         if p.is_alive():
 84 |             p.join()
 85 |     print("结束：", time.time() - time_0, "\n")
 86 | 
 87 |     print("========== 直接执行CPU密集型任务 ==========")
 88 |     init_queue()
 89 |     time_0 = time.time()
 90 |     task_cpu(0)
 91 |     print("结束：", time.time() - time_0, "\n")
 92 | 
 93 |     print("========== 多线程执行CPU密集型任务 ==========")
 94 |     init_queue()
 95 |     time_0 = time.time()
 96 |     thread_list = [threading.Thread(target=task_cpu, args=(i,)) for i in range(5)]
 97 |     for t in thread_list:
 98 |         t.start()
 99 |     for t in thread_list:
100 |         if t.is_alive():
101 |             t.join()
102 |     print("结束：", time.time() - time_0, "\n")
103 | 
104 |     print("========== 多进程执行cpu密集型任务 ==========")
105 |     init_queue()
106 |     time_0 = time.time()
107 |     process_list = [multiprocessing.Process(target=task_cpu, args=(i,)) for i in range(multiprocessing.cpu_count())]
108 |     for p in process_list:
109 |         p.start()
110 |     for p in process_list:
111 |         if p.is_alive():
112 |             p.join()
113 |     print("结束：", time.time() - time_0, "\n")
114 | 
115 |     exit()
116 | 


--------------------------------------------------------------------------------
/python_version36.py:
--------------------------------------------------------------------------------
 1 | # _*_ coding: utf-8 _*_
 2 | 
 3 | """
 4 | python_version36.py by xianhu
 5 | """
 6 | 
 7 | import asyncio
 8 | import decimal
 9 | from typing import List, Dict
10 | 
11 | # Formatted string literals
12 | name = "Fred"
13 | print(f"He said his name is {name}.")  # 'He said his name is Fred.'
14 | print("He said his name is {name}.".format(**locals()))
15 | 
16 | width = 10
17 | precision = 4
18 | value = decimal.Decimal("12.34567")
19 | print(f"result: {value:{width}.{precision}}")  #'result:      12.35'
20 | 
21 | 
22 | # variable annotations
23 | def test(a: List[int], b: int) -> int:
24 |     return a[0] + b
25 | print(test([3, 1], 2))
26 | 
27 | primes: List[int] = []
28 | captain: str
29 | 
30 | class Starship(object):
31 |     stats: Dict[str, int] = {}
32 | 
33 | 
34 | # Underscores in Numeric Literals
35 | a = 1_000_000_000_000_000       # 1000000000000000
36 | b = 0x_FF_FF_FF_FF              # 4294967295
37 | 
38 | '{:_}'.format(1000000)          # '1_000_000'
39 | '{:_x}'.format(0xFFFFFFFF)      # 'ffff_ffff'
40 | 
41 | 
42 | # Asynchronous Generators
43 | async def ticker(delay, to):
44 |     """Yield numbers from 0 to *to* every *delay* seconds."""
45 |     for i in range(to):
46 |         yield i
47 |         await asyncio.sleep(delay)
48 | 
49 | 
50 | # Asynchronous Comprehensions
51 | result = [i async for i in aiter() if i % 2]
52 | result = [await fun() for fun in funcs if await condition()]
53 | 


--------------------------------------------------------------------------------
/python_visual.py:
--------------------------------------------------------------------------------
  1 | # _*_ coding: utf-8 _*_
  2 | 
  3 | """
  4 | python_visual.py by xianhu
  5 | """
  6 | 
  7 | import numpy as np
  8 | import matplotlib
  9 | import matplotlib.mlab as mlab
 10 | import matplotlib.pyplot as plt
 11 | import matplotlib.font_manager as fm
 12 | from mpl_toolkits.mplot3d import Axes3D
 13 | 
 14 | # 解决中文乱码问题
 15 | myfont = fm.FontProperties(fname="/Library/Fonts/Songti.ttc", size=14)
 16 | matplotlib.rcParams["axes.unicode_minus"] = False
 17 | 
 18 | 
 19 | def simple_plot():
 20 |     """
 21 |     simple plot
 22 |     """
 23 |     # 生成测试数据
 24 |     x = np.linspace(-np.pi, np.pi, 256, endpoint=True)
 25 |     y_cos, y_sin = np.cos(x), np.sin(x)
 26 | 
 27 |     # 生成画布，并设定标题
 28 |     plt.figure(figsize=(8, 6), dpi=80)
 29 |     plt.title("简单曲线图", fontproperties=myfont)
 30 |     plt.grid(True)
 31 | 
 32 |     # 设置X轴
 33 |     plt.xlabel("X轴", fontproperties=myfont)
 34 |     plt.xlim(-4.0, 4.0)
 35 |     plt.xticks(np.linspace(-4, 4, 9, endpoint=True))
 36 | 
 37 |     # 设置Y轴
 38 |     plt.ylabel("Y轴", fontproperties=myfont)
 39 |     plt.ylim(-1.0, 1.0)
 40 |     plt.yticks(np.linspace(-1, 1, 9, endpoint=True))
 41 | 
 42 |     # 画两条曲线
 43 |     plt.plot(x, y_cos, "b--", linewidth=2.0, label="cos示例")
 44 |     plt.plot(x, y_sin, "g-", linewidth=2.0, label="sin示例")
 45 | 
 46 |     # 设置图例位置,loc可以为[upper, lower, left, right, center]
 47 |     plt.legend(loc="upper left", prop=myfont, shadow=True)
 48 | 
 49 |     # 图形显示
 50 |     plt.show()
 51 |     return
 52 | # simple_plot()
 53 | 
 54 | 
 55 | def simple_advanced_plot():
 56 |     """
 57 |     simple advanced plot
 58 |     """
 59 |     # 生成测试数据
 60 |     x = np.linspace(-np.pi, np.pi, 256, endpoint=True)
 61 |     y_cos, y_sin = np.cos(x), np.sin(x)
 62 | 
 63 |     # 生成画布, 并设定标题
 64 |     plt.figure(figsize=(8, 6), dpi=80)
 65 |     plt.title("复杂曲线图", fontproperties=myfont)
 66 |     plt.grid(True)
 67 | 
 68 |     # 画图的另外一种方式
 69 |     ax_1 = plt.subplot(111)
 70 |     ax_1.plot(x, y_cos, color="blue", linewidth=2.0, linestyle="--", label="左cos")
 71 |     ax_1.legend(loc="upper left", prop=myfont, shadow=True)
 72 | 
 73 |     # 设置Y轴(左边)
 74 |     ax_1.set_ylabel("左cos的y轴", fontproperties=myfont)
 75 |     ax_1.set_ylim(-1.0, 1.0)
 76 |     ax_1.set_yticks(np.linspace(-1, 1, 9, endpoint=True))
 77 | 
 78 |     # 画图的另外一种方式
 79 |     ax_2 = ax_1.twinx()
 80 |     ax_2.plot(x, y_sin, color="green", linewidth=2.0, linestyle="-", label="右sin")
 81 |     ax_2.legend(loc="upper right", prop=myfont, shadow=True)
 82 | 
 83 |     # 设置Y轴(右边)
 84 |     ax_2.set_ylabel("右sin的y轴", fontproperties=myfont)
 85 |     ax_2.set_ylim(-2.0, 2.0)
 86 |     ax_2.set_yticks(np.linspace(-2, 2, 9, endpoint=True))
 87 | 
 88 |     # 设置X轴(共同)
 89 |     ax_1.set_xlabel("x轴", fontproperties=myfont)
 90 |     ax_1.set_xlim(-4.0, 4.0)
 91 |     ax_1.set_xticks(np.linspace(-4, 4, 9, endpoint=True))
 92 | 
 93 |     # 图形显示
 94 |     plt.show()
 95 |     return
 96 | # simple_advanced_plot()
 97 | 
 98 | 
 99 | def subplot_plot():
100 |     """
101 |     subplot plot
102 |     """
103 |     # 子图的style列表
104 |     style_list = ["g+-", "r*-", "b.-", "yo-"]
105 | 
106 |     # 依次画图
107 |     for num in range(4):
108 |         # 生成测试数据
109 |         x = np.linspace(0.0, 2+num, num=10*(num+1))
110 |         y = np.sin((5-num) * np.pi * x)
111 | 
112 |         # 子图的生成方式
113 |         plt.subplot(2, 2, num+1)
114 |         plt.title("子图 %d" % (num+1), fontproperties=myfont)
115 |         plt.plot(x, y, style_list[num])
116 | 
117 |     # 图形显示
118 |     plt.show()
119 |     return
120 | # subplot_plot()
121 | 
122 | 
123 | def bar_plot():
124 |     """
125 |     bar plot
126 |     """
127 |     # 生成测试数据
128 |     means_men = (20, 35, 30, 35, 27)
129 |     means_women = (25, 32, 34, 20, 25)
130 | 
131 |     # 设置标题
132 |     plt.title("柱状图", fontproperties=myfont)
133 | 
134 |     # 设置相关参数
135 |     index = np.arange(len(means_men))
136 |     bar_width = 0.35
137 | 
138 |     # 画柱状图
139 |     plt.bar(index, means_men, width=bar_width, alpha=0.2, color="b", label="男生")
140 |     plt.bar(index+bar_width, means_women, width=bar_width, alpha=0.8, color="r", label="女生")
141 |     plt.legend(loc="upper right", prop=myfont, shadow=True)
142 | 
143 |     # 设置柱状图标示
144 |     for x, y in zip(index, means_men):
145 |         plt.text(x, y+0.3, y, ha="center", va="bottom")
146 |     for x, y in zip(index, means_women):
147 |         plt.text(x+bar_width, y+0.3, y, ha="center", va="bottom")
148 | 
149 |     # 设置刻度范围/坐标轴名称等
150 |     plt.ylim(0, 45)
151 |     plt.xlabel("分组Group", fontproperties=myfont)
152 |     plt.ylabel("得分Scores", fontproperties=myfont)
153 |     plt.xticks(index+(bar_width/2), ("A组", "B组", "C组", "D组", "E组"), fontproperties=myfont)
154 | 
155 |     # 图形显示
156 |     plt.show()
157 |     return
158 | # bar_plot()
159 | 
160 | 
161 | def barh_plot():
162 |     """
163 |     barh plot
164 |     """
165 |     # 生成测试数据
166 |     means_men = (20, 35, 30, 35, 27)
167 |     means_women = (25, 32, 34, 20, 25)
168 | 
169 |     # 设置标题
170 |     plt.title("横向柱状图", fontproperties=myfont)
171 | 
172 |     # 设置相关参数
173 |     index = np.arange(len(means_men))
174 |     bar_height = 0.35
175 | 
176 |     # 画柱状图(水平方向)
177 |     plt.barh(index, means_men, height=bar_height, alpha=0.2, color="b", label="Men")
178 |     plt.barh(index+bar_height, means_women, height=bar_height, alpha=0.8, color="r", label="Women")
179 |     plt.legend(loc="upper right", shadow=True)
180 | 
181 |     # 设置柱状图标示
182 |     for x, y in zip(index, means_men):
183 |         plt.text(y+0.3, x, y, ha="left", va="center")
184 |     for x, y in zip(index, means_women):
185 |         plt.text(y+0.3, x+bar_height, y, ha="left", va="center")
186 | 
187 |     # 设置刻度范围/坐标轴名称等
188 |     plt.xlim(0, 45)
189 |     plt.xlabel("Scores")
190 |     plt.ylabel("Group")
191 |     plt.yticks(index+(bar_height/2), ("A", "B", "C", "D", "E"))
192 | 
193 |     # 图形显示
194 |     plt.show()
195 |     return
196 | # barh_plot()
197 | 
198 | 
199 | def bar_advanced_plot():
200 |     """
201 |     bar advanced plot
202 |     """
203 |     # 生成测试数据
204 |     means_men = np.array((20, 35, 30, 35, 27, 25, 32, 34, 20, 25))
205 |     means_women = np.array((25, 32, 34, 20, 25, 20, 35, 30, 35, 27))
206 | 
207 |     # 设置标题
208 |     plt.title("高级柱状图", fontproperties=myfont)
209 | 
210 |     # 设置相关参数
211 |     index = np.arange(len(means_men))
212 |     bar_width = 0.8
213 | 
214 |     # 画柱状图(两种:X轴以上/X轴以下)
215 |     plt.bar(index, means_men, width=bar_width, alpha=0.4, color="b", label="Men")
216 |     plt.bar(index, -means_women, width=bar_width, alpha=0.4, color="r", label="Women")
217 | 
218 |     # 画折线图(两种,和柱状图对应)
219 |     plt.plot(index, means_men, marker="o", linestyle="-", color="r", label="Men line")
220 |     plt.plot(index, -means_women, marker=".", linestyle="--", color="b", label="Women line")
221 | 
222 |     # 设置图形标示(两种,和柱状图对应)
223 |     for x, y in zip(index, means_men):
224 |         plt.text(x, y+1, y, ha="center", va="bottom")
225 |     for x, y in zip(index, means_women):
226 |         plt.text(x, -y-1, y, ha="center", va="top")
227 | 
228 |     # 设置Y轴和图例位置
229 |     plt.ylim(-45, 80)
230 |     plt.legend(loc="upper left", shadow=True)
231 | 
232 |     # 图形显示
233 |     plt.show()
234 |     return
235 | # bar_advanced_plot()
236 | 
237 | 
238 | def table_plot():
239 |     """
240 |     table plot
241 |     """
242 |     # 生成测试数据
243 |     data = np.array([
244 |         [1, 4, 2, 5, 2],
245 |         [2, 1, 1, 3, 6],
246 |         [5, 3, 6, 4, 1]
247 |     ])
248 | 
249 |     # 设置标题
250 |     plt.title("层次柱状图", fontproperties=myfont)
251 | 
252 |     # 设置相关参数
253 |     index = np.arange(len(data[0]))
254 |     color_index = ["r", "g", "b"]
255 | 
256 |     # 声明底部位置
257 |     bottom = np.array([0, 0, 0, 0, 0])
258 | 
259 |     # 依次画图,并更新底部位置
260 |     for i in range(len(data)):
261 |         plt.bar(index, data[i], width=0.5, color=color_index[i], bottom=bottom, alpha=0.7, label="标签 %d" % i)
262 |         bottom += data[i]
263 | 
264 |     # 设置图例位置
265 |     plt.legend(loc="upper left", prop=myfont, shadow=True)
266 | 
267 |     # 图形显示
268 |     plt.show()
269 |     return
270 | # table_plot()
271 | 
272 | 
273 | def histograms_plot():
274 |     """
275 |     histograms plot
276 |     """
277 |     # 生成测试数据
278 |     mu, sigma = 100, 15
279 |     x = mu + sigma * np.random.randn(10000)
280 | 
281 |     # 设置标题
282 |     plt.title("直方图", fontproperties=myfont)
283 | 
284 |     # 画直方图, 并返回相关结果
285 |     n, bins, patches = plt.hist(x, bins=50, normed=1, cumulative=False, color="green", alpha=0.6, label="直方图")
286 | 
287 |     # 根据直方图返回的结果, 画折线图
288 |     y = mlab.normpdf(bins, mu, sigma)
289 |     plt.plot(bins, y, "r--", label="线条")
290 | 
291 |     # 设置图例位置
292 |     plt.legend(loc="upper left", prop=myfont, shadow=True)
293 | 
294 |     # 图形显示
295 |     plt.show()
296 |     return
297 | # histograms_plot()
298 | 
299 | 
300 | def pie_plot():
301 |     """
302 |     pie plot
303 |     """
304 |     # 生成测试数据
305 |     sizes = [15, 30, 45, 10]
306 |     labels = ["Frogs", "中文", "Dogs", "Logs"]
307 |     colors = ["yellowgreen", "gold", "lightskyblue", "lightcoral"]
308 | 
309 |     # 设置标题
310 |     plt.title("饼图", fontproperties=myfont)
311 | 
312 |     # 设置突出参数
313 |     explode = [0, 0.05, 0, 0]
314 | 
315 |     # 画饼状图
316 |     patches, l_text, p_text = plt.pie(sizes, explode=explode, labels=labels, colors=colors, autopct="%1.1f%%", shadow=True, startangle=90)
317 |     for text in l_text:
318 |         text.set_fontproperties(myfont)
319 |     plt.axis("equal")
320 | 
321 |     # 图形显示
322 |     plt.show()
323 |     return
324 | # pie_plot()
325 | 
326 | 
327 | def scatter_plot():
328 |     """
329 |     scatter plot
330 |     """
331 |     # 生成测试数据
332 |     point_count = 1000
333 |     x_index = np.random.random(point_count)
334 |     y_index = np.random.random(point_count)
335 | 
336 |     # 设置标题
337 |     plt.title("散点图", fontproperties=myfont)
338 | 
339 |     # 设置相关参数
340 |     color_list = np.random.random(point_count)
341 |     scale_list = np.random.random(point_count) * 100
342 | 
343 |     # 画散点图
344 |     plt.scatter(x_index, y_index, s=scale_list, c=color_list, marker="o")
345 | 
346 |     # 图形显示
347 |     plt.show()
348 |     return
349 | # scatter_plot()
350 | 
351 | 
352 | def fill_plot():
353 |     """
354 |     fill plot
355 |     """
356 |     # 生成测试数据
357 |     x = np.linspace(-2*np.pi, 2*np.pi, 1000, endpoint=True)
358 |     y = np.sin(x)
359 | 
360 |     # 设置标题
361 |     plt.title("填充图", fontproperties=myfont)
362 | 
363 |     # 画图
364 |     plt.plot(x, y, color="blue", alpha=1.00)
365 | 
366 |     # 填充图形, plt.fill_between(x, y1, y2, where=None, *kwargs)
367 |     plt.fill_between(x, 0, y, where=(y > 0), color="blue", alpha=0.25)
368 |     plt.fill_between(x, 0, y, where=(y < 0), color="red", alpha=0.25)
369 | 
370 |     # 图形显示
371 |     plt.show()
372 |     return
373 | # fill_plot()
374 | 
375 | 
376 | def radar_plot():
377 |     """
378 |     radar plot
379 |     """
380 |     # 生成测试数据
381 |     labels = np.array(["A组", "B组", "C组", "D组", "E组", "F组"])
382 |     data = np.array([68, 83, 90, 77, 89, 73])
383 |     theta = np.linspace(0, 2*np.pi, len(data), endpoint=False)
384 | 
385 |     # 数据预处理
386 |     data = np.concatenate((data, [data[0]]))
387 |     theta = np.concatenate((theta, [theta[0]]))
388 | 
389 |     # 画图方式
390 |     plt.subplot(111, polar=True)
391 |     plt.title("雷达图", fontproperties=myfont)
392 | 
393 |     # 设置"theta grid"/"radar grid"
394 |     plt.thetagrids(theta*(180/np.pi), labels=labels, fontproperties=myfont)
395 |     plt.rgrids(np.arange(20, 100, 20), labels=np.arange(20, 100, 20), angle=0)
396 |     plt.ylim(0, 100)
397 | 
398 |     # 画雷达图,并填充雷达图内部区域
399 |     plt.plot(theta, data, "bo-", linewidth=2)
400 |     plt.fill(theta, data, color="red", alpha=0.25)
401 | 
402 |     # 图形显示
403 |     plt.show()
404 |     return
405 | # radar_plot()
406 | 
407 | 
408 | def three_dimension_scatter():
409 |     """
410 |     3d scatter plot
411 |     """
412 |     # 生成测试数据
413 |     x = np.random.random(100)
414 |     y = np.random.random(100)
415 |     z = np.random.random(100)
416 |     color = np.random.random(100)
417 |     scale = np.random.random(100) * 100
418 | 
419 |     # 生成画布(两种形式)
420 |     fig = plt.figure()
421 |     fig.suptitle("三维散点图", fontproperties=myfont)
422 | 
423 |     # ax = fig.gca(projection="3d")
424 |     ax = fig.add_subplot(111, projection="3d")
425 | 
426 |     # 画三维散点图
427 |     ax.scatter(x, y, z, s=scale, c=color, marker=".")
428 | 
429 |     # 设置坐标轴图标
430 |     ax.set_xlabel("X Label")
431 |     ax.set_ylabel("Y Label")
432 |     ax.set_zlabel("Z Label")
433 | 
434 |     # 设置坐标轴范围
435 |     ax.set_xlim(0, 1)
436 |     ax.set_ylim(0, 1)
437 |     ax.set_zlim(0, 1)
438 | 
439 |     # 图形显示
440 |     plt.show()
441 |     return
442 | # three_dimension_scatter()
443 | 
444 | 
445 | def three_dimension_line():
446 |     """
447 |     3d line plot
448 |     """
449 |     # 生成测试数据
450 |     x = np.linspace(0, 1, 1000)
451 |     y = np.linspace(0, 1, 1000)
452 |     z = np.sin(x * 2 * np.pi) / (y + 0.1)
453 | 
454 |     # 生成画布(两种形式)
455 |     fig = plt.figure()
456 |     ax = fig.gca(projection="3d", title="plot title")
457 |     # ax = fig.add_subplot(111, projection="3d", title="plot title")
458 | 
459 |     # 画三维折线图
460 |     ax.plot(x, y, z, color="red", linestyle="-")
461 | 
462 |     # 设置坐标轴图标
463 |     ax.set_xlabel("X Label")
464 |     ax.set_ylabel("Y Label")
465 |     ax.set_zlabel("Z Label")
466 | 
467 |     # 图形显示
468 |     plt.show()
469 |     return
470 | # three_dimension_line()
471 | 
472 | 
473 | def three_dimension_bar():
474 |     """
475 |     3d bar plot
476 |     """
477 |     # 生成测试数据(位置数据)
478 |     xpos = [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]
479 |     ypos = [2, 3, 4, 5, 1, 6, 2, 1, 7, 2]
480 |     zpos = [0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
481 | 
482 |     # 生成测试数据(柱形参数)
483 |     dx = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
484 |     dy = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
485 |     dz = [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]
486 | 
487 |     # 生成画布(两种形式)
488 |     fig = plt.figure()
489 |     ax = fig.gca(projection="3d", title="plot title")
490 | 
491 |     # 画三维柱状图
492 |     ax.bar3d(xpos, ypos, zpos, dx, dy, dz, alpha=0.5)
493 | 
494 |     # 设置坐标轴图标
495 |     ax.set_xlabel("X Label")
496 |     ax.set_ylabel("Y Label")
497 |     ax.set_zlabel("Z Label")
498 | 
499 |     # 图形显示
500 |     plt.show()
501 |     return
502 | # three_dimension_bar()
503 | 


--------------------------------------------------------------------------------
/python_visual_animation.py:
--------------------------------------------------------------------------------
  1 | # _*_ coding: utf-8 _*_
  2 | 
  3 | """
  4 | python_visual_animation.py by xianhu
  5 | """
  6 | 
  7 | import numpy as np
  8 | import matplotlib
  9 | import matplotlib.pyplot as plt
 10 | import matplotlib.font_manager as fm
 11 | from mpl_toolkits.mplot3d import Axes3D
 12 | 
 13 | # 解决中文乱码问题
 14 | myfont = fm.FontProperties(fname="/Library/Fonts/Songti.ttc", size=14)
 15 | matplotlib.rcParams["axes.unicode_minus"] = False
 16 | 
 17 | 
 18 | def simple_plot():
 19 |     """
 20 |     simple plot
 21 |     """
 22 |     # 生成画布
 23 |     plt.figure(figsize=(8, 6), dpi=80)
 24 | 
 25 |     # 打开交互模式
 26 |     plt.ion()
 27 | 
 28 |     # 循环
 29 |     for index in range(100):
 30 |         # 清除原有图像
 31 |         plt.cla()
 32 | 
 33 |         # 设定标题等
 34 |         plt.title("动态曲线图", fontproperties=myfont)
 35 |         plt.grid(True)
 36 | 
 37 |         # 生成测试数据
 38 |         x = np.linspace(-np.pi + 0.1*index, np.pi+0.1*index, 256, endpoint=True)
 39 |         y_cos, y_sin = np.cos(x), np.sin(x)
 40 | 
 41 |         # 设置X轴
 42 |         plt.xlabel("X轴", fontproperties=myfont)
 43 |         plt.xlim(-4 + 0.1*index, 4 + 0.1*index)
 44 |         plt.xticks(np.linspace(-4 + 0.1*index, 4+0.1*index, 9, endpoint=True))
 45 | 
 46 |         # 设置Y轴
 47 |         plt.ylabel("Y轴", fontproperties=myfont)
 48 |         plt.ylim(-1.0, 1.0)
 49 |         plt.yticks(np.linspace(-1, 1, 9, endpoint=True))
 50 | 
 51 |         # 画两条曲线
 52 |         plt.plot(x, y_cos, "b--", linewidth=2.0, label="cos示例")
 53 |         plt.plot(x, y_sin, "g-", linewidth=2.0, label="sin示例")
 54 | 
 55 |         # 设置图例位置,loc可以为[upper, lower, left, right, center]
 56 |         plt.legend(loc="upper left", prop=myfont, shadow=True)
 57 | 
 58 |         # 暂停
 59 |         plt.pause(0.1)
 60 | 
 61 |     # 关闭交互模式
 62 |     plt.ioff()
 63 | 
 64 |     # 图形显示
 65 |     plt.show()
 66 |     return
 67 | # simple_plot()
 68 | 
 69 | 
 70 | def scatter_plot():
 71 |     """
 72 |     scatter plot
 73 |     """
 74 |     # 打开交互模式
 75 |     plt.ion()
 76 | 
 77 |     # 循环
 78 |     for index in range(50):
 79 |         # 清除原有图像
 80 |         # plt.cla()
 81 | 
 82 |         # 设定标题等
 83 |         plt.title("动态散点图", fontproperties=myfont)
 84 |         plt.grid(True)
 85 | 
 86 |         # 生成测试数据
 87 |         point_count = 5
 88 |         x_index = np.random.random(point_count)
 89 |         y_index = np.random.random(point_count)
 90 | 
 91 |         # 设置相关参数
 92 |         color_list = np.random.random(point_count)
 93 |         scale_list = np.random.random(point_count) * 100
 94 | 
 95 |         # 画散点图
 96 |         plt.scatter(x_index, y_index, s=scale_list, c=color_list, marker="o")
 97 | 
 98 |         # 暂停
 99 |         plt.pause(0.2)
100 | 
101 |     # 关闭交互模式
102 |     plt.ioff()
103 | 
104 |     # 显示图形
105 |     plt.show()
106 |     return
107 | # scatter_plot()
108 | 
109 | 
110 | def three_dimension_scatter():
111 |     """
112 |     3d scatter plot
113 |     """
114 |     # 生成画布
115 |     fig = plt.figure()
116 | 
117 |     # 打开交互模式
118 |     plt.ion()
119 | 
120 |     # 循环
121 |     for index in range(50):
122 |         # 清除原有图像
123 |         fig.clf()
124 | 
125 |         # 设定标题等
126 |         fig.suptitle("三维动态散点图", fontproperties=myfont)
127 | 
128 |         # 生成测试数据
129 |         point_count = 100
130 |         x = np.random.random(point_count)
131 |         y = np.random.random(point_count)
132 |         z = np.random.random(point_count)
133 |         color = np.random.random(point_count)
134 |         scale = np.random.random(point_count) * 100
135 | 
136 |         # 生成画布
137 |         ax = fig.add_subplot(111, projection="3d")
138 | 
139 |         # 画三维散点图
140 |         ax.scatter(x, y, z, s=scale, c=color, marker=".")
141 | 
142 |         # 设置坐标轴图标
143 |         ax.set_xlabel("X Label")
144 |         ax.set_ylabel("Y Label")
145 |         ax.set_zlabel("Z Label")
146 | 
147 |         # 设置坐标轴范围
148 |         ax.set_xlim(0, 1)
149 |         ax.set_ylim(0, 1)
150 |         ax.set_zlim(0, 1)
151 | 
152 |         # 暂停
153 |         plt.pause(0.2)
154 | 
155 |     # 关闭交互模式
156 |     plt.ioff()
157 | 
158 |     # 图形显示
159 |     plt.show()
160 |     return
161 | # three_dimension_scatter()
162 | 


--------------------------------------------------------------------------------
/python_wechat.py:
--------------------------------------------------------------------------------
  1 | # _*_ coding: utf-8 _*_
  2 | 
  3 | """
  4 | python_wechat.py by xianhu
  5 | 主要包括如下功能：
  6 | (1) 自动提醒群红包
  7 | (2) 自动监测被撤回消息
  8 | (3) 群关键字提醒，群被@提醒
  9 | """
 10 | 
 11 | import time
 12 | import itchat
 13 | import logging
 14 | from itchat.content import *
 15 | 
 16 | # 初始化
 17 | my = itchat.new_instance()
 18 | my.auto_login(hotReload=False, enableCmdQR=2)
 19 | 
 20 | # my还包括的以下属性，注意用点.查看：
 21 | # (1) alive 是否还活着，isLogging 是否已登陆
 22 | # (2) loginInfo 登陆信息，其中的User属性为自己的信息User字典类，包括UserName, NickName, RemarkName, Sex(1 or 2), Signature, Province, City等
 23 | # (3) memberList 通讯录列表，每一项为一个User字典类，包括UserName, NickName, RemarkName, Sex(1 or 2), Signature, Province, City等
 24 | # (4) chatroomList 群聊列表，每一项为一个Chatroom字典类，包括UserName, NickName, RemarkName, MemberCount, MemberList, Self等
 25 | # (5) mpList 订阅号列表，每一项为一个MassivePlatform字典类，包括UserName, NickName等
 26 | 
 27 | my.global_keys = ["创业", "人工智能", "企业服务"]
 28 | my.to_user_name = "filehelper"      # 消息接受者
 29 | my.update_time = time.time()        # 信息更新时间
 30 | my.msg_store = {}                   # 消息存储队列
 31 | my.friends = {}                     # 好友字典列表
 32 | my.groups = {}                      # 群聊字典列表
 33 | 
 34 | 
 35 | def update_my_infos():
 36 |     """
 37 |     更新信息
 38 |     """
 39 |     # 获取并更新通讯录: {UserName: UserInstance}
 40 |     my.friends = {user["UserName"]: user for user in my.get_friends(update=True)}
 41 |     # 获取并更新群列表: {UserName: UserInstance}
 42 |     my.groups = {group["UserName"]: group for group in my.get_chatrooms(update=True)}
 43 |     return
 44 | update_my_infos()
 45 | 
 46 | 
 47 | class Message(object):
 48 |     """
 49 |     消息类
 50 |     """
 51 |     def __init__(self, msg):
 52 |         """
 53 |         构造函数：提取消息内容
 54 |         消息来源分类：
 55 |         （1）来自好友的消息
 56 |         （2）来自群的消息
 57 |         提取消息内容，消息类型分类：
 58 |         （1）文字（2）图片（3）语音（4）视频（5）地址（6）名片（7）提醒（8）分享（9）附件
 59 |         """
 60 |         # 更新信息，十分钟更新一次
 61 |         # logging.warning("message: %s", msg)
 62 |         if time.time() - my.update_time > 600:
 63 |             update_my_infos()
 64 |             my.update_time = time.time()
 65 | 
 66 |         self.msg_id = msg["MsgId"]                      # 消息ID
 67 |         self.from_user_name = msg["FromUserName"]       # 消息发送者ID，如果为群消息，则为群ID
 68 | 
 69 |         self.msg_type = msg["MsgType"]                  # 消息类型，这里参考下边的we_type
 70 |         self.msg_content = msg["Content"]               # 消息内容，这里参考下边的we_text
 71 |         self.msg_time = msg["CreateTime"]               # 消息发送时间，时间戳格式
 72 | 
 73 |         self.msg_file = msg["FileName"]                 # 消息中所带文件的名称
 74 |         self.msg_file_length = msg["FileSize"]          # 消息中所带文件的大小，字符串类型
 75 |         self.msg_voice_length = msg["VoiceLength"]      # 消息中所带语音的长度（毫秒）
 76 |         self.msg_play_length = msg["PlayLength"]        # 消息中所带视频的长度（秒）
 77 |         self.msg_url = msg["Url"]                       # 消息中所带链接的地址
 78 | 
 79 |         self.user_user_name = msg["User"].get("UserName", "")       # 消息发送者ID，如果为群消息，则为群ID
 80 |         self.user_nick_name = msg["User"].get("NickName", "")       # 消息发送者昵称，如果为群消息，则为群名
 81 |         self.user_remark_name = msg["User"].get("RemarkName", "")   # 消息发送者备注名称，如果为群消息，则为群备注名称
 82 |         self.wind_name = self.user_remark_name if self.user_remark_name else (
 83 |             self.user_nick_name if self.user_nick_name else (
 84 |                 my.friends[self.user_user_name]["NickName"] if self.user_user_name in my.friends else (
 85 |                     my.groups[self.user_user_name]["NickName"] if self.user_user_name in my.groups else "未知窗口"
 86 |                 )
 87 |             )
 88 |         )
 89 | 
 90 |         self.actual_user_name = msg.get("ActualUserName", "")       # 群消息中，消息发送者的ID
 91 |         self.actual_nick_name = msg.get("ActualNickName", "")       # 群消息中，消息发送者的群昵称
 92 |         self.actual_remark_name = self.actual_nick_name \
 93 |             if (self.actual_user_name not in my.friends) or (not my.friends[self.actual_user_name]["RemarkName"]) \
 94 |             else my.friends[self.actual_user_name]["RemarkName"]
 95 | 
 96 |         self.is_at = msg.get("IsAt", None)              # 是否在群内被@
 97 |         self.we_type = msg["Type"]                      # 消息类型
 98 |         self.we_text = msg["Text"]                      # 消息内容
 99 | 
100 |         logging.warning("wind_name=%s, send_name=%s, we_type=%s, we_text=%s", self.wind_name, self.actual_remark_name, self.we_type, self.we_text)
101 |         return
102 | 
103 | 
104 | def process_message_group(msg):
105 |     """
106 |     处理群消息
107 |     """
108 |     # ==== 处理红包消息 ====
109 |     if msg.we_type == "Note" and msg.we_text.find("收到红包，请在手机上查看") >= 0:
110 |         my.send("【%s】中有人发红包啦，快抢！" % msg.wind_name, toUserName=my.to_user_name)
111 | 
112 |     # ==== 处理关键词消息 ====
113 |     for key in my.global_keys:
114 |         if msg.we_type == "Text" and msg.we_text.find(key) >= 0:
115 |             my.send("【%s】中【%s】提及了关键字：%s" % (msg.wind_name, msg.actual_remark_name, key), toUserName=my.to_user_name)
116 |             my.send(msg.we_text, toUserName=my.to_user_name)
117 |             break
118 | 
119 |     # ==== 群内是否被@ ====
120 |     if msg.we_type == "Text" and msg.is_at:
121 |         my.send("【%s】中【%s】@了你" % (msg.wind_name, msg.actual_remark_name), toUserName=my.to_user_name)
122 |         my.send(msg.we_text, toUserName=my.to_user_name)
123 |     return
124 | 
125 | 
126 | def process_message_revoke(msg):
127 |     """
128 |     处理撤回消息
129 |     """
130 |     # 消息存储，删除过期消息
131 |     my.msg_store[msg.msg_id] = msg
132 |     for _id in [_id for _id in my.msg_store if time.time() - my.msg_store[_id].msg_time > 120]:
133 |         my.msg_store.pop(_id)
134 | 
135 |     # 保存消息中的内容（图片、语音等）
136 |     if msg.we_type in ["Picture", "Recording"]:
137 |         try:
138 |             msg.we_text(".Cache/" + msg.msg_file)
139 |             logging.warning("process_message_revoke: download %s to .Cache/", msg.msg_file)
140 |         except Exception as excep:
141 |             logging.error("process_message_revoke: download %s to .Cache/ error: %s", msg.msg_file, excep)
142 | 
143 |     # ==== 撤回消息处理（必须为最后一步） ====
144 |     if msg.we_type == "Note" and msg.we_text.find("撤回了一条消息") >= 0:
145 |         old_msg = my.msg_store.get(msg.msg_content[msg.msg_content.find("<msgid>")+7: msg.msg_content.find("</msgid>")])
146 |         if not old_msg:
147 |             logging.warning("process_message_revoke: no message id in my.msg_store")
148 |             return
149 | 
150 |         if old_msg.from_user_name.startswith("@@"):
151 |             my.send("【%s】中【%s】撤回了自己发送的消息:\nType: %s\n%s" %
152 |                     (old_msg.wind_name, old_msg.actual_remark_name, old_msg.we_type, old_msg.msg_file), toUserName=my.to_user_name)
153 |         else:
154 |             my.send("【%s】撤回了自己发送的消息:\nType: %s\n%s" %
155 |                     (old_msg.wind_name, old_msg.we_type, old_msg.msg_file), toUserName=my.to_user_name)
156 | 
157 |         if old_msg.we_type in ["Text", "Card"]:
158 |             my.send(str(old_msg.we_text), toUserName=my.to_user_name)
159 |         elif old_msg.we_type == "Sharing":
160 |             my.send(old_msg.we_text + "\n" + old_msg.msg_url, toUserName=my.to_user_name)
161 |         elif old_msg.we_type == "Picture":
162 |             my.send_image(".Cache/" + old_msg.msg_file, toUserName=my.to_user_name)
163 |         elif old_msg.we_type == "Recording":
164 |             my.send_file(".Cache/" + old_msg.msg_file, toUserName=my.to_user_name)
165 |     return
166 | 
167 | 
168 | @my.msg_register([TEXT, PICTURE, RECORDING, VIDEO, MAP, CARD, NOTE, SHARING, ATTACHMENT], isFriendChat=True, isGroupChat=True)
169 | def text_reply(msg):
170 |     """
171 |     消息自动接收, 接受全部的消息（自己发送的消息除外）
172 |     """
173 |     # 跳过来自自己的消息
174 |     if msg["FromUserName"] == my.loginInfo["User"]["UserName"]:
175 |         return
176 | 
177 |     # 消息提取
178 |     msg = Message(msg)
179 | 
180 |     # 消息过滤, 只监测文字、图片、语音、名片、注解、分享等
181 |     if msg.we_type not in ["Text", "Picture", "Recording", "Card", "Note", "Sharing"]:
182 |         logging.warning("process_message_group: message type isn't included, ignored")
183 |         return
184 | 
185 |     # 处理群消息
186 |     if msg.from_user_name.startswith("@@"):
187 |         process_message_group(msg)
188 | 
189 |     # 处理撤回消息
190 |     process_message_revoke(msg)
191 |     return
192 | 
193 | 
194 | # 运行程序
195 | my.run(debug=False)
196 | 
197 | """
198 | 好友消息：
199 | {
200 |     'MsgId': '5254859004542036569',
201 |     'FromUserName': '@f3b7fdc54717ea8dc22cb3edef59688e82ef34874e3236801537b94f6cd73e1e',
202 |     'ToUserName': '@e79dde912b8f817514c01f399ca9ba12',
203 |     'MsgType': 1,
204 |     'Content': '[微笑]己改',
205 |     'Status': 3,
206 |     'ImgStatus': 1,
207 |     'CreateTime': 1498448860,
208 |     'VoiceLength': 0,
209 |     'PlayLength': 0,
210 |     'FileName': '',
211 |     'FileSize': '',
212 |     'MediaId': '',
213 |     'Url': '',
214 |     'AppMsgType': 0,
215 |     'StatusNotifyCode': 0,
216 |     'StatusNotifyUserName': '',
217 |     'HasProductId': 0,
218 |     'Ticket': '',
219 |     'ImgHeight': 0,
220 |     'ImgWidth': 0,
221 |     'SubMsgType': 0,
222 |     'NewMsgId': 5254859004542036569,
223 |     'OriContent': '',
224 |     'User': <User: {
225 |         'MemberList': <ContactList: []>,
226 |         'Uin': 0,
227 |         'UserName': '@f3b7fdc54717ea8dc22cb3edef59688e82ef34874e3236801537b94f6cd73e1e',
228 |         'NickName': '付贵吉祥',
229 |         'HeadImgUrl': '/cgi-bin/mmwebwx-bin/webwxgeticon?seq=688475226&username=@f3b7fdc54717ea8dc22cb3edef59688e82ef34874e3236801537b94f6cd73e1e&skey=@',
230 |         'ContactFlag': 3,
231 |         'MemberCount': 0,
232 |         'RemarkName': '付贵吉祥@中建5号楼',
233 |         'HideInputBarFlag': 0,
234 |         'Sex': 1,
235 |         'Signature': '漫漫人生路...',
236 |         'VerifyFlag': 0,
237 |         'OwnerUin': 0,
238 |         'PYInitial': 'FGJX',
239 |         'PYQuanPin': 'fuguijixiang',
240 |         'RemarkPYInitial': 'FGJXZJ5HL',
241 |         'RemarkPYQuanPin': 'fuguijixiangzhongjian5haolou',
242 |         'StarFriend': 0,
243 |         'AppAccountFlag': 0,
244 |         'Statues': 0,
245 |         'AttrStatus': 135205,
246 |         'Province': '山东',
247 |         'City': '',
248 |         'Alias': '',
249 |         'SnsFlag': 17,
250 |         'UniFriend': 0,
251 |         'DisplayName': '',
252 |         'ChatRoomId': 0,
253 |         'KeyWord': '',
254 |         'EncryChatRoomId': '',
255 |         'IsOwner': 0
256 |     }>,
257 |     'Type': 'Text',
258 |     'Text': '[微笑]己改'
259 | }
260 | """
261 | 
262 | """
263 | 群消息：
264 | {
265 |     'MsgId': '7844877618948840992',
266 |     'FromUserName': '@@8dc5df044444d1fb8e3972e755b47adf9d07f5a032cae90a4d822b74ee1e4880',
267 |     'ToUserName': '@e79dde912b8f817514c01f399ca9ba12',
268 |     'MsgType': 1,
269 |     'Content': '就是那个，那个协议我们手上有吗',
270 |     'Status': 3,
271 |     'ImgStatus': 1,
272 |     'CreateTime': 1498448972,
273 |     'VoiceLength': 0,
274 |     'PlayLength': 0,
275 |     'FileName': '',
276 |     'FileSize': '',
277 |     'MediaId': '',
278 |     'Url': '',
279 |     'AppMsgType': 0,
280 |     'StatusNotifyCode': 0,
281 |     'StatusNotifyUserName': '',
282 |     'HasProductId': 0,
283 |     'Ticket': '',
284 |     'ImgHeight': 0,
285 |     'ImgWidth': 0,
286 |     'SubMsgType': 0,
287 |     'NewMsgId': 7844877618948840992,
288 |     'OriContent': '',
289 |     'ActualNickName': '5-1-1003',
290 |     'IsAt': False,
291 |     'ActualUserName': '@a0922f18795e4c3b6d7d09c492ace233',
292 |     'User': <Chatroom: {
293 |         'MemberList': <ContactList: [
294 |             <ChatroomMember: {
295 |                 'MemberList': <ContactList: []>,
296 |                 'Uin': 0,
297 |                 'UserName': '@e79dde912b8f817514c01f399ca9ba12',
298 |                 'NickName': '齐现虎',
299 |                 'AttrStatus': 2147600869,
300 |                 'PYInitial': '',
301 |                 'PYQuanPin': '',
302 |                 'RemarkPYInitial': '',
303 |                 'RemarkPYQuanPin': '',
304 |                 'MemberStatus': 0,
305 |                 'DisplayName': '5-1-1601',
306 |                 'KeyWord': 'qix'
307 |             }>,
308 |             <ChatroomMember: {
309 |                 'MemberList': <ContactList: []>,
310 |                 'Uin': 0,
311 |                 'UserName': '@a9620e3d4b82eab2521ccdbb985afc37',
312 |                 'NickName': 'A高佳祥15069179911',
313 |                 'AttrStatus': 102503,
314 |                 'PYInitial': '',
315 |                 'PYQuanPin': '',
316 |                 'RemarkPYInitial': '',
317 |                 'RemarkPYQuanPin': '',
318 |                 'MemberStatus': 0,
319 |                 'DisplayName': '5-2-220315069179911',
320 |                 'KeyWord': 'gao'
321 |             }>,
322 |             .......
323 |         ]>,
324 |         'Uin': 0,
325 |         'UserName': '@@8dc5df044444d1fb8e3972e755b47adf9d07f5a032cae90a4d822b74ee1e4880',
326 |         'NickName': '中建锦绣澜庭二期5#楼',
327 |         'HeadImgUrl': '/cgi-bin/mmwebwx-bin/webwxgetheadimg?seq=0&username=@@8dc5df044444d1fb8e3972e755b47adf9d07f5a032cae90a4d822b74ee1e4880&skey=@',
328 |         'ContactFlag': 3,
329 |         'MemberCount': 106,
330 |         'RemarkName': '',
331 |         'HideInputBarFlag': 0,
332 |         'Sex': 0,
333 |         'Signature': '',
334 |         'VerifyFlag': 0,
335 |         'OwnerUin': 0,
336 |         'PYInitial': 'ZJJXLTEJ5L',
337 |         'PYQuanPin': 'zhongjianjinxiulantingerji5lou',
338 |         'RemarkPYInitial': '',
339 |         'RemarkPYQuanPin': '',
340 |         'StarFriend': 0,
341 |         'AppAccountFlag': 0,
342 |         'Statues': 0,
343 |         'AttrStatus': 0,
344 |         'Province': '',
345 |         'City': '',
346 |         'Alias': '',
347 |         'SnsFlag': 0,
348 |         'UniFriend': 0,
349 |         'DisplayName': '',
350 |         'ChatRoomId': 0,
351 |         'KeyWord': '',
352 |         'EncryChatRoomId': '@d1e510bc8cbd192468e9c85c6f5a9d81',
353 |         'IsOwner': 1,
354 |         'IsAdmin': None,
355 |         'Self': <ChatroomMember: {
356 |             'MemberList': <ContactList: []>,
357 |             'Uin': 0,
358 |             'UserName': '@e79dde912b8f817514c01f399ca9ba12',
359 |             'NickName': '齐现虎',
360 |             'AttrStatus': 2147600869,
361 |             'PYInitial': '',
362 |             'PYQuanPin': '',
363 |             'RemarkPYInitial': '',
364 |             'RemarkPYQuanPin': '',
365 |             'MemberStatus': 0,
366 |             'DisplayName': '5-1-1601',
367 |             'KeyWord': 'qix'
368 |         }>,
369 |         'HeadImgUpdateFlag': 1,
370 |         'ContactType': 0,
371 |         'ChatRoomOwner': '@e79dde912b8f817514c01f399ca9ba12'
372 |     }>,
373 |     'Type': 'Text',
374 |     'Text': '就是那个，那个协议我们手上有吗'
375 | }
376 | 
377 | 警示消息：好友类
378 | {
379 |     'MsgId': '1529895072288746571',
380 |     'FromUserName': '@4076708be2e09ef83f249f168553d0dd55b4f734aee7d276e92ddbe98625476a',
381 |     'ToUserName': '@f97583d8ffbaee6189854116897c677f',
382 |     'MsgType': 10000,
383 |     'Content': '你已添加了呼啸而过的小青春，现在可以开始聊天了。',
384 |     'Status': 4,
385 |     'ImgStatus': 1,
386 |     'CreateTime': 1498533407,
387 |     'VoiceLength': 0,
388 |     'PlayLength': 0,
389 |     'FileName': '',
390 |     'FileSize': '',
391 |     'MediaId': '',
392 |     'Url': '',
393 |     'AppMsgType': 0,
394 |     'StatusNotifyCode': 0,
395 |     'StatusNotifyUserName': '',
396 |     'HasProductId': 0,
397 |     'Ticket': '',
398 |     'ImgHeight': 0,
399 |     'ImgWidth': 0,
400 |     'SubMsgType': 0,
401 |     'NewMsgId': 1529895072288746571,
402 |     'OriContent': '',
403 |     'User': <User: {
404 |         'userName': '@4076708be2e09ef83f249f168553d0dd55b4f734aee7d276e92ddbe98625476a',
405 |         'MemberList': <ContactList: []>
406 |     }>,
407 |     'Type': 'Note',
408 |     'Text': '你已添加了呼啸而过的小青春，现在可以开始聊天了。'
409 | }
410 | 
411 | 警示消息：群类
412 | {
413 |     'MsgId': '1049646282086057263',
414 |     'FromUserName': '@@300f57b68ca7ef593ae3221eef7dba5377466c86122aaa15a8ffc1031310e210',
415 |     'ToUserName': '@006f63e8086ab07fcbe3771dc824c4a6',
416 |     'MsgType': 10000,
417 |     'Content': '你邀请"大姐"加入了群聊',
418 |     'Status': 3,
419 |     'ImgStatus': 1,
420 |     'CreateTime': 1498533901,
421 |     'VoiceLength': 0,
422 |     'PlayLength': 0,
423 |     'FileName': '',
424 |     'FileSize': '',
425 |     'MediaId': '',
426 |     'Url': '',
427 |     'AppMsgType': 0,
428 |     'StatusNotifyCode': 0,
429 |     'StatusNotifyUserName': '',
430 |     'HasProductId': 0,
431 |     'Ticket': '',
432 |     'ImgHeight': 0,
433 |     'ImgWidth': 0,
434 |     'SubMsgType': 0,
435 |     'NewMsgId': 1049646282086057263,
436 |     'OriContent': '',
437 |     'ActualUserName': '@006f63e8086ab07fcbe3771dc824c4a6',
438 |     'ActualNickName': '某某某',
439 |     'IsAt': False,
440 |     'User': <Chatroom: {
441 |         'UserName': '@@300f57b68ca7ef593ae3221eef7dba5377466c86122aaa15a8ffc1031310e210',
442 |         'MemberList': <ContactList: []>
443 |     }>,
444 |     'Type': 'Note',
445 |     'Text': '你邀请"大姐"加入了群聊'
446 | }
447 | """
448 | 


--------------------------------------------------------------------------------
/python_weibo.py:
--------------------------------------------------------------------------------
  1 | # _*_ coding: utf-8 _*_
  2 | 
  3 | """
  4 | python_weibo.py by xianhu
  5 | """
  6 | 
  7 | import re
  8 | import rsa
  9 | import time
 10 | import json
 11 | import base64
 12 | import logging
 13 | import binascii
 14 | import requests
 15 | import urllib.parse
 16 | 
 17 | 
 18 | class WeiBoLogin(object):
 19 |     """
 20 |     class of WeiBoLogin, to login weibo.com
 21 |     """
 22 | 
 23 |     def __init__(self):
 24 |         """
 25 |         constructor
 26 |         """
 27 |         self.user_name = None
 28 |         self.pass_word = None
 29 |         self.user_uniqueid = None
 30 |         self.user_nick = None
 31 | 
 32 |         self.session = requests.Session()
 33 |         self.session.headers.update({"User-Agent": "Mozilla/5.0 (Windows NT 6.3; WOW64; rv:41.0) Gecko/20100101 Firefox/41.0"})
 34 |         self.session.get("http://weibo.com/login.php")
 35 |         return
 36 | 
 37 |     def login(self, user_name, pass_word):
 38 |         """
 39 |         login weibo.com, return True or False
 40 |         """
 41 |         self.user_name = user_name
 42 |         self.pass_word = pass_word
 43 |         self.user_uniqueid = None
 44 |         self.user_nick = None
 45 | 
 46 |         # get json data
 47 |         s_user_name = self.get_username()
 48 |         json_data = self.get_json_data(su_value=s_user_name)
 49 |         if not json_data:
 50 |             return False
 51 |         s_pass_word = self.get_password(json_data["servertime"], json_data["nonce"], json_data["pubkey"])
 52 | 
 53 |         # make post_data
 54 |         post_data = {
 55 |             "entry": "weibo",
 56 |             "gateway": "1",
 57 |             "from": "",
 58 |             "savestate": "7",
 59 |             "userticket": "1",
 60 |             "vsnf": "1",
 61 |             "service": "miniblog",
 62 |             "encoding": "UTF-8",
 63 |             "pwencode": "rsa2",
 64 |             "sr": "1280*800",
 65 |             "prelt": "529",
 66 |             "url": "http://weibo.com/ajaxlogin.php?framelogin=1&callback=parent.sinaSSOController.feedBackUrlCallBack",
 67 |             "rsakv": json_data["rsakv"],
 68 |             "servertime": json_data["servertime"],
 69 |             "nonce": json_data["nonce"],
 70 |             "su": s_user_name,
 71 |             "sp": s_pass_word,
 72 |             "returntype": "TEXT",
 73 |         }
 74 | 
 75 |         # get captcha code
 76 |         if json_data["showpin"] == 1:
 77 |             url = "http://login.sina.com.cn/cgi/pin.php?r=%d&s=0&p=%s" % (int(time.time()), json_data["pcid"])
 78 |             with open("captcha.jpeg", "wb") as file_out:
 79 |                 file_out.write(self.session.get(url).content)
 80 |             code = input("请输入验证码:")
 81 |             post_data["pcid"] = json_data["pcid"]
 82 |             post_data["door"] = code
 83 | 
 84 |         # login weibo.com
 85 |         login_url_1 = "http://login.sina.com.cn/sso/login.php?client=ssologin.js(v1.4.18)&_=%d" % int(time.time())
 86 |         json_data_1 = self.session.post(login_url_1, data=post_data).json()
 87 |         if json_data_1["retcode"] == "0":
 88 |             params = {
 89 |                 "callback": "sinaSSOController.callbackLoginStatus",
 90 |                 "client": "ssologin.js(v1.4.18)",
 91 |                 "ticket": json_data_1["ticket"],
 92 |                 "ssosavestate": int(time.time()),
 93 |                 "_": int(time.time()*1000),
 94 |             }
 95 |             response = self.session.get("https://passport.weibo.com/wbsso/login", params=params)
 96 |             json_data_2 = json.loads(re.search(r"\((?P<result>.*)\)", response.text).group("result"))
 97 |             if json_data_2["result"] is True:
 98 |                 self.user_uniqueid = json_data_2["userinfo"]["uniqueid"]
 99 |                 self.user_nick = json_data_2["userinfo"]["displayname"]
100 |                 logging.warning("WeiBoLogin succeed: %s", json_data_2)
101 |             else:
102 |                 logging.warning("WeiBoLogin failed: %s", json_data_2)
103 |         else:
104 |             logging.warning("WeiBoLogin failed: %s", json_data_1)
105 |         return True if self.user_uniqueid and self.user_nick else False
106 | 
107 |     def get_username(self):
108 |         """
109 |         get legal username
110 |         """
111 |         username_quote = urllib.parse.quote_plus(self.user_name)
112 |         username_base64 = base64.b64encode(username_quote.encode("utf-8"))
113 |         return username_base64.decode("utf-8")
114 | 
115 |     def get_json_data(self, su_value):
116 |         """
117 |         get the value of "servertime", "nonce", "pubkey", "rsakv" and "showpin", etc
118 |         """
119 |         params = {
120 |             "entry": "weibo",
121 |             "callback": "sinaSSOController.preloginCallBack",
122 |             "rsakt": "mod",
123 |             "checkpin": "1",
124 |             "client": "ssologin.js(v1.4.18)",
125 |             "su": su_value,
126 |             "_": int(time.time()*1000),
127 |         }
128 |         try:
129 |             response = self.session.get("http://login.sina.com.cn/sso/prelogin.php", params=params)
130 |             json_data = json.loads(re.search(r"\((?P<data>.*)\)", response.text).group("data"))
131 |         except Exception as excep:
132 |             json_data = {}
133 |             logging.error("WeiBoLogin get_json_data error: %s", excep)
134 | 
135 |         logging.debug("WeiBoLogin get_json_data: %s", json_data)
136 |         return json_data
137 | 
138 |     def get_password(self, servertime, nonce, pubkey):
139 |         """
140 |         get legal password
141 |         """
142 |         string = (str(servertime) + "\t" + str(nonce) + "\n" + str(self.pass_word)).encode("utf-8")
143 |         public_key = rsa.PublicKey(int(pubkey, 16), int("10001", 16))
144 |         password = rsa.encrypt(string, public_key)
145 |         password = binascii.b2a_hex(password)
146 |         return password.decode()
147 | 
148 | 
149 | if __name__ == "__main__":
150 |     logging.basicConfig(level=logging.DEBUG, format="%(asctime)s\t%(levelname)s\t%(message)s")
151 |     weibo = WeiBoLogin()
152 |     weibo.login("username", "password")
153 | 


--------------------------------------------------------------------------------