diff --git a/crawlab/requirements.txt b/crawlab/requirements.txt index a54862f2..901a56ca 100644 --- a/crawlab/requirements.txt +++ b/crawlab/requirements.txt @@ -1,35 +1,77 @@ +aiohttp==3.5.4 amqp==2.4.2 aniso8601==6.0.0 +Appium-Python-Client==0.40 APScheduler==3.6.0 +asn1crypto==0.24.0 +async-timeout==3.0.1 attrs==19.1.0 +Automat==0.7.0 Babel==2.6.0 +beautifulsoup4==4.7.1 billiard==3.6.0.0 +bs4==0.0.1 +cachetools==3.1.0 celery==4.3.0 certifi==2019.3.9 +cffi==1.12.3 chardet==3.0.4 Click==7.0 coloredlogs==10.0 +constantly==15.1.0 +cryptography==2.6.1 +cssselect==1.0.3 Flask==1.0.2 +Flask-APScheduler==1.11.0 Flask-Cors==3.0.7 Flask-RESTful==0.3.7 flask-restplus==0.12.1 flower==0.9.3 +gunicorn==19.9.0 +html5lib==1.0.1 humanfriendly==4.18 +hyperlink==19.0.0 idna==2.8 +idna-ssl==1.1.0 +incremental==17.5.0 itsdangerous==1.1.0 Jinja2==2.10 +jsonpickle==1.1 jsonschema==3.0.1 kombu==4.5.0 +lxml==4.3.3 MarkupSafe==1.1.1 mongoengine==0.17.0 +multidict==4.5.2 +parsel==1.5.1 +pyasn1==0.4.5 +pyasn1-modules==0.2.5 +pycparser==2.19 +PyDispatcher==2.0.5 +PyHamcrest==1.9.0 pymongo==3.7.2 +pyOpenSSL==19.0.0 pyrsistent==0.14.11 +python-dateutil==2.8.0 pytz==2018.9 +queuelib==1.5.0 redis==3.2.1 +redisbeat==1.1.4 +reppy==0.4.12 requests==2.21.0 +Scrapy==1.6.0 +selenium==3.141.0 +service-identity==18.1.0 six==1.12.0 +soupsieve==1.9.1 tornado==5.1.1 +Twisted==19.2.0 +typing-extensions==3.7.2 tzlocal==1.5.1 urllib3==1.24.1 vine==1.3.0 +w3lib==1.20.0 +webencodings==0.5.1 Werkzeug==0.15.2 +yarl==1.3.0 +zope.interface==4.6.0 diff --git a/docs/Architecture/App 2.md b/docs/Architecture/App 2.md deleted file mode 100644 index 5d5681fd..00000000 --- a/docs/Architecture/App 2.md +++ /dev/null @@ -1,2 +0,0 @@ -# App - diff --git a/docs/Concept/Deploy 2.md b/docs/Concept/Deploy 2.md deleted file mode 100644 index 12f55ebf..00000000 --- a/docs/Concept/Deploy 2.md +++ /dev/null @@ -1,6 +0,0 @@ -# 部署 - -所有爬虫在运行前需要被部署当相应当节点中。 - -部署时，爬虫会被打包到相应的目录中，方便环境隔离，开发环境的爬虫和生产环境的爬虫需要打包部署来实现隔离。 - diff --git a/docs/Examples/README 2.md b/docs/Examples/README 2.md deleted file mode 100644 index 65afe604..00000000 --- a/docs/Examples/README 2.md +++ /dev/null @@ -1,2 +0,0 @@ -# Examples - diff --git a/docs/QuickStart/Installation 2.md b/docs/QuickStart/Installation 2.md deleted file mode 100644 index 3fce3e1c..00000000 --- a/docs/QuickStart/Installation 2.md +++ /dev/null @@ -1,22 +0,0 @@ -# 安装 - -最快安装Crawlab的方式是克隆一份代码到本地 - -```bash -git clone https://github.com/tikazyq/crawlab -``` - -安装类库 - -```bash -# 安装后台类库 -pip install -r requirements.txt -``` - -```bash -# 安装前台类库 -cd frontend -npm install -``` - - diff --git a/docs/_book/Architecture/App 2.html b/docs/_book/Architecture/App 2.html deleted file mode 100644 index 0123e0e6..00000000 --- a/docs/_book/Architecture/App 2.html +++ /dev/null @@ -1,436 +0,0 @@ - - - - - - - App · GitBook - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
-
- - - - - - - - -
- -
- -
- - - - - - - - -
-
- -
-
- -
- -

App

- - -
- -
-
-
- -

results matching ""

-
    - -
    -
    - -

    No results matching ""

    - -
    -
    -
    - -
    -
    - -
    - - - - - - - - - - - - - - -
    - - -
    - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - diff --git a/docs/_book/Architecture/App.html b/docs/_book/Architecture/App.html index 0123e0e6..9d763304 100644 --- a/docs/_book/Architecture/App.html +++ b/docs/_book/Architecture/App.html @@ -397,7 +397,7 @@ @@ -407,6 +407,10 @@ + + + + diff --git a/docs/_book/Architecture/Celery.html b/docs/_book/Architecture/Celery.html index 128cf023..38ef5b59 100644 --- a/docs/_book/Architecture/Celery.html +++ b/docs/_book/Architecture/Celery.html @@ -397,7 +397,7 @@ @@ -407,6 +407,10 @@ + + + + diff --git a/docs/_book/Architecture/index.html b/docs/_book/Architecture/index.html index 581f6f17..de925ce3 100644 --- a/docs/_book/Architecture/index.html +++ b/docs/_book/Architecture/index.html @@ -397,7 +397,7 @@ @@ -407,6 +407,10 @@ + + + + diff --git a/docs/_book/Concept/Deploy 2.html b/docs/_book/Concept/Deploy 2.html deleted file mode 100644 index d7d110db..00000000 --- a/docs/_book/Concept/Deploy 2.html +++ /dev/null @@ -1,438 +0,0 @@ - - - - - - - 部署 · GitBook - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    -
    - - - - - - - - -
    - -
    - -
    - - - - - - - - -
    -
    - -
    -
    - -
    - -

    部署

    -

    所有爬虫在运行前需要被部署当相应当节点中。

    -

    部署时，爬虫会被打包到相应的目录中，方便环境隔离，开发环境的爬虫和生产环境的爬虫需要打包部署来实现隔离。

    - - -
    - -
    -
    -
    - -

    results matching ""

    -
      - -
      -
      - -

      No results matching ""

      - -
      -
      -
      - -
      -
      - -
      - - - - - - - - - - - - - - -
      - - -
      - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - diff --git a/docs/_book/Concept/Deploy.html b/docs/_book/Concept/Deploy.html index d7d110db..1026cf5a 100644 --- a/docs/_book/Concept/Deploy.html +++ b/docs/_book/Concept/Deploy.html @@ -399,7 +399,7 @@ @@ -409,6 +409,10 @@ + + + + diff --git a/docs/_book/Concept/Node.html b/docs/_book/Concept/Node.html index cb720ede..80428986 100644 --- a/docs/_book/Concept/Node.html +++ b/docs/_book/Concept/Node.html @@ -398,7 +398,7 @@ @@ -408,6 +408,10 @@ + + + + diff --git a/docs/_book/Concept/Spider.html b/docs/_book/Concept/Spider.html index 887c941e..3021513d 100644 --- a/docs/_book/Concept/Spider.html +++ b/docs/_book/Concept/Spider.html @@ -403,7 +403,7 @@ @@ -413,6 +413,10 @@ + + + + diff --git a/docs/_book/Concept/Task.html b/docs/_book/Concept/Task.html index eca91bc3..6b2584cd 100644 --- a/docs/_book/Concept/Task.html +++ b/docs/_book/Concept/Task.html @@ -398,7 +398,7 @@ @@ -408,6 +408,10 @@ + + + + diff --git a/docs/_book/Concept/index.html b/docs/_book/Concept/index.html index b9d9296a..9af87425 100644 --- a/docs/_book/Concept/index.html +++ b/docs/_book/Concept/index.html @@ -397,7 +397,7 @@ @@ -407,6 +407,10 @@ + + + + diff --git a/docs/_book/Examples/index 2.html b/docs/_book/Examples/index 2.html deleted file mode 100644 index 285296a5..00000000 --- a/docs/_book/Examples/index 2.html +++ /dev/null @@ -1,436 +0,0 @@ - - - - - - - Examples · GitBook - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
      -
      - - - - - - - - -
      - -
      - -
      - - - - - - - - -
      -
      - -
      -
      - -
      - -

      Examples

      - - -
      - -
      -
      -
      - -

      results matching ""

      -
        - -
        -
        - -

        No results matching ""

        - -
        -
        -
        - -
        -
        - -
        - - - - - - - - - - - - - - -
        - - -
        - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - diff --git a/docs/_book/Examples/index.html b/docs/_book/Examples/index.html index 285296a5..f936aeaa 100644 --- a/docs/_book/Examples/index.html +++ b/docs/_book/Examples/index.html @@ -397,7 +397,7 @@ @@ -407,6 +407,10 @@ + + + + diff --git a/docs/_book/QuickStart/Installation 2.html b/docs/_book/QuickStart/Installation 2.html deleted file mode 100644 index fcbd254f..00000000 --- a/docs/_book/QuickStart/Installation 2.html +++ /dev/null @@ -1,447 +0,0 @@ - - - - - - - 安装 · GitBook - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        -
        - - - - - - - - -
        - -
        - -
        - - - - - - - - -
        -
        - -
        -
        - -
        - -

        安装

        -

        最快安装Crawlab的方式是克隆一份代码到本地

        -
        git clone https://github.com/tikazyq/crawlab
-
        -

        安装类库

        -
        # 安装后台类库
-pip install -r requirements.txt
-
        -
        # 安装前台类库
-cd frontend
-npm install
-
        - - -
        - -
        -
        -
        - -

        results matching ""

        -
          - -
          -
          - -

          No results matching ""

          - -
          -
          -
          - -
          -
          - -
          - - - - - - - - - - - - - - -
          - - -
          - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - diff --git a/docs/_book/QuickStart/Installation.html b/docs/_book/QuickStart/Installation.html index fcbd254f..49bad4b8 100644 --- a/docs/_book/QuickStart/Installation.html +++ b/docs/_book/QuickStart/Installation.html @@ -408,7 +408,7 @@ npm install @@ -418,6 +418,10 @@ npm install + + + + diff --git a/docs/_book/QuickStart/Run.html b/docs/_book/QuickStart/Run.html index c94c094b..6018fc53 100644 --- a/docs/_book/QuickStart/Run.html +++ b/docs/_book/QuickStart/Run.html @@ -440,7 +440,7 @@ npm run serve @@ -450,6 +450,10 @@ npm run serve + + + + diff --git a/docs/_book/QuickStart/index.html b/docs/_book/QuickStart/index.html index c4cf78f8..9691dcad 100644 --- a/docs/_book/QuickStart/index.html +++ b/docs/_book/QuickStart/index.html @@ -401,7 +401,7 @@ @@ -411,6 +411,10 @@ + + + + diff --git a/docs/_book/gitbook/fonts/fontawesome/FontAwesome 2.otf b/docs/_book/gitbook/fonts/fontawesome/FontAwesome 2.otf deleted file mode 100644 index d4de13e8..00000000 Binary files a/docs/_book/gitbook/fonts/fontawesome/FontAwesome 2.otf and /dev/null differ diff --git a/docs/_book/gitbook/gitbook-plugin-fontsettings/fontsettings 2.js b/docs/_book/gitbook/gitbook-plugin-fontsettings/fontsettings 2.js deleted file mode 100644 index ff7be714..00000000 --- a/docs/_book/gitbook/gitbook-plugin-fontsettings/fontsettings 2.js +++ /dev/null @@ -1,240 +0,0 @@ -require(['gitbook', 'jquery'], function(gitbook, $) { - // Configuration - var MAX_SIZE = 4, - MIN_SIZE = 0, - BUTTON_ID; - - // Current fontsettings state - var fontState; - - // Default themes - var THEMES = [ - { - config: 'white', - text: 'White', - id: 0 - }, - { - config: 'sepia', - text: 'Sepia', - id: 1 - }, - { - config: 'night', - text: 'Night', - id: 2 - } - ]; - - // Default font families - var FAMILIES = [ - { - config: 'serif', - text: 'Serif', - id: 0 - }, - { - config: 'sans', - text: 'Sans', - id: 1 - } - ]; - - // Return configured themes - function getThemes() { - return THEMES; - } - - // Modify configured themes - function setThemes(themes) { - THEMES = themes; - updateButtons(); - } - - // Return configured font families - function getFamilies() { - return FAMILIES; - } - - // Modify configured font families - function setFamilies(families) { - FAMILIES = families; - updateButtons(); - } - - // Save current font settings - function saveFontSettings() { - gitbook.storage.set('fontState', fontState); - update(); - } - - // Increase font size - function enlargeFontSize(e) { - e.preventDefault(); - if (fontState.size >= MAX_SIZE) return; - - fontState.size++; - saveFontSettings(); - } - - // Decrease font size - function reduceFontSize(e) { - e.preventDefault(); - if (fontState.size <= MIN_SIZE) return; - - fontState.size--; - saveFontSettings(); - } - - // Change font family - function changeFontFamily(configName, e) { - if (e && e instanceof Event) { - e.preventDefault(); - } - - var familyId = getFontFamilyId(configName); - fontState.family = familyId; - saveFontSettings(); - } - - // Change type of color theme - function changeColorTheme(configName, e) { - if (e && e instanceof Event) { - e.preventDefault(); - } - - var $book = gitbook.state.$book; - - // Remove currently applied color theme - if (fontState.theme !== 0) - $book.removeClass('color-theme-'+fontState.theme); - - // Set new color theme - var themeId = getThemeId(configName); - fontState.theme = themeId; - if (fontState.theme !== 0) - $book.addClass('color-theme-'+fontState.theme); - - saveFontSettings(); - } - - // Return the correct id for a font-family config key - // Default to first font-family - function getFontFamilyId(configName) { - // Search for plugin configured font family - var configFamily = $.grep(FAMILIES, function(family) { - return family.config == configName; - })[0]; - // Fallback to default font family - return (!!configFamily)? configFamily.id : 0; - } - - // Return the correct id for a theme config key - // Default to first theme - function getThemeId(configName) { - // Search for plugin configured theme - var configTheme = $.grep(THEMES, function(theme) { - return theme.config == configName; - })[0]; - // Fallback to default theme - return (!!configTheme)? configTheme.id : 0; - } - - function update() { - var $book = gitbook.state.$book; - - $('.font-settings .font-family-list li').removeClass('active'); - $('.font-settings .font-family-list li:nth-child('+(fontState.family+1)+')').addClass('active'); - - $book[0].className = $book[0].className.replace(/\bfont-\S+/g, ''); - $book.addClass('font-size-'+fontState.size); - $book.addClass('font-family-'+fontState.family); - - if(fontState.theme !== 0) { - $book[0].className = $book[0].className.replace(/\bcolor-theme-\S+/g, ''); - $book.addClass('color-theme-'+fontState.theme); - } - } - - function init(config) { - // Search for plugin configured font family - var configFamily = getFontFamilyId(config.family), - configTheme = getThemeId(config.theme); - - // Instantiate font state object - fontState = gitbook.storage.get('fontState', { - size: config.size || 2, - family: configFamily, - theme: configTheme - }); - - update(); - } - - function updateButtons() { - // Remove existing fontsettings buttons - if (!!BUTTON_ID) { - gitbook.toolbar.removeButton(BUTTON_ID); - } - - // Create buttons in toolbar - BUTTON_ID = gitbook.toolbar.createButton({ - icon: 'fa fa-font', - label: 'Font Settings', - className: 'font-settings', - dropdown: [ - [ - { - text: 'A', - className: 'font-reduce', - onClick: reduceFontSize - }, - { - text: 'A', - className: 'font-enlarge', - onClick: enlargeFontSize - } - ], - $.map(FAMILIES, function(family) { - family.onClick = function(e) { - return changeFontFamily(family.config, e); - }; - - return family; - }), - $.map(THEMES, function(theme) { - theme.onClick = function(e) { - return changeColorTheme(theme.config, e); - }; - - return theme; - }) - ] - }); - } - - // Init configuration at start - gitbook.events.bind('start', function(e, config) { - var opts = config.fontsettings; - - // Generate buttons at start - updateButtons(); - - // Init current settings - init(opts); - }); - - // Expose API - gitbook.fontsettings = { - enlargeFontSize: enlargeFontSize, - reduceFontSize: reduceFontSize, - setTheme: changeColorTheme, - setFamily: changeFontFamily, - getThemes: getThemes, - setThemes: setThemes, - getFamilies: getFamilies, - setFamilies: setFamilies - }; -}); - - diff --git a/docs/_book/gitbook/gitbook-plugin-highlight/ebook 2.css b/docs/_book/gitbook/gitbook-plugin-highlight/ebook 2.css deleted file mode 100644 index cecaaab5..00000000 --- a/docs/_book/gitbook/gitbook-plugin-highlight/ebook 2.css +++ /dev/null @@ -1,135 +0,0 @@ -pre, -code { - /* http://jmblog.github.io/color-themes-for-highlightjs */ - /* Tomorrow Comment */ - /* Tomorrow Red */ - /* Tomorrow Orange */ - /* Tomorrow Yellow */ - /* Tomorrow Green */ - /* Tomorrow Aqua */ - /* Tomorrow Blue */ - /* Tomorrow Purple */ -} -pre .hljs-comment, -code .hljs-comment, -pre .hljs-title, -code .hljs-title { - color: #8e908c; -} -pre .hljs-variable, -code .hljs-variable, -pre .hljs-attribute, -code .hljs-attribute, -pre .hljs-tag, -code .hljs-tag, -pre .hljs-regexp, -code .hljs-regexp, -pre .hljs-deletion, -code .hljs-deletion, -pre .ruby .hljs-constant, -code .ruby .hljs-constant, -pre .xml .hljs-tag .hljs-title, -code .xml .hljs-tag .hljs-title, -pre .xml .hljs-pi, -code .xml .hljs-pi, -pre .xml .hljs-doctype, -code .xml .hljs-doctype, -pre .html .hljs-doctype, -code .html .hljs-doctype, -pre .css .hljs-id, -code .css .hljs-id, -pre .css .hljs-class, -code .css .hljs-class, -pre .css .hljs-pseudo, -code .css .hljs-pseudo { - color: #c82829; -} -pre .hljs-number, -code .hljs-number, -pre .hljs-preprocessor, -code .hljs-preprocessor, -pre .hljs-pragma, -code .hljs-pragma, -pre .hljs-built_in, -code .hljs-built_in, -pre .hljs-literal, -code .hljs-literal, -pre .hljs-params, -code .hljs-params, -pre .hljs-constant, -code .hljs-constant { - color: #f5871f; -} -pre .ruby .hljs-class .hljs-title, -code .ruby .hljs-class .hljs-title, -pre .css .hljs-rules .hljs-attribute, -code .css .hljs-rules .hljs-attribute { - color: #eab700; -} -pre .hljs-string, -code .hljs-string, -pre .hljs-value, -code .hljs-value, -pre .hljs-inheritance, -code .hljs-inheritance, -pre .hljs-header, -code .hljs-header, -pre .hljs-addition, -code .hljs-addition, -pre .ruby .hljs-symbol, -code .ruby .hljs-symbol, -pre .xml .hljs-cdata, -code .xml .hljs-cdata { - color: #718c00; -} -pre .css .hljs-hexcolor, -code .css .hljs-hexcolor { - color: #3e999f; -} -pre .hljs-function, -code .hljs-function, -pre .python .hljs-decorator, -code .python .hljs-decorator, -pre .python .hljs-title, -code .python .hljs-title, -pre .ruby .hljs-function .hljs-title, -code .ruby .hljs-function .hljs-title, -pre .ruby .hljs-title .hljs-keyword, -code .ruby .hljs-title .hljs-keyword, -pre .perl .hljs-sub, -code .perl .hljs-sub, -pre .javascript .hljs-title, -code .javascript .hljs-title, -pre .coffeescript .hljs-title, -code .coffeescript .hljs-title { - color: #4271ae; -} -pre .hljs-keyword, -code .hljs-keyword, -pre .javascript .hljs-function, -code .javascript .hljs-function { - color: #8959a8; -} -pre .hljs, -code .hljs { - display: block; - background: white; - color: #4d4d4c; - padding: 0.5em; -} -pre .coffeescript .javascript, -code .coffeescript .javascript, -pre .javascript .xml, -code .javascript .xml, -pre .tex .hljs-formula, -code .tex .hljs-formula, -pre .xml .javascript, -code .xml .javascript, -pre .xml .vbscript, -code .xml .vbscript, -pre .xml .css, -code .xml .css, -pre .xml .hljs-cdata, -code .xml .hljs-cdata { - opacity: 0.5; -} diff --git a/docs/_book/gitbook/gitbook-plugin-lunr/lunr.min 2.js b/docs/_book/gitbook/gitbook-plugin-lunr/lunr.min 2.js deleted file mode 100644 index 6aa6bc7d..00000000 --- a/docs/_book/gitbook/gitbook-plugin-lunr/lunr.min 2.js +++ /dev/null @@ -1,7 +0,0 @@ -/** - * lunr - http://lunrjs.com - A bit like Solr, but much smaller and not as bright - 0.5.12 - * Copyright (C) 2015 Oliver Nightingale - * MIT Licensed - * @license - */ -!function(){var t=function(e){var n=new t.Index;return n.pipeline.add(t.trimmer,t.stopWordFilter,t.stemmer),e&&e.call(n,n),n};t.version="0.5.12",t.utils={},t.utils.warn=function(t){return function(e){t.console&&console.warn&&console.warn(e)}}(this),t.EventEmitter=function(){this.events={}},t.EventEmitter.prototype.addListener=function(){var t=Array.prototype.slice.call(arguments),e=t.pop(),n=t;if("function"!=typeof e)throw new TypeError("last argument must be a function");n.forEach(function(t){this.hasHandler(t)||(this.events[t]=[]),this.events[t].push(e)},this)},t.EventEmitter.prototype.removeListener=function(t,e){if(this.hasHandler(t)){var n=this.events[t].indexOf(e);this.events[t].splice(n,1),this.events[t].length||delete this.events[t]}},t.EventEmitter.prototype.emit=function(t){if(this.hasHandler(t)){var e=Array.prototype.slice.call(arguments,1);this.events[t].forEach(function(t){t.apply(void 0,e)})}},t.EventEmitter.prototype.hasHandler=function(t){return t in this.events},t.tokenizer=function(t){return arguments.length&&null!=t&&void 0!=t?Array.isArray(t)?t.map(function(t){return t.toLowerCase()}):t.toString().trim().toLowerCase().split(/[\s\-]+/):[]},t.Pipeline=function(){this._stack=[]},t.Pipeline.registeredFunctions={},t.Pipeline.registerFunction=function(e,n){n in this.registeredFunctions&&t.utils.warn("Overwriting existing registered function: "+n),e.label=n,t.Pipeline.registeredFunctions[e.label]=e},t.Pipeline.warnIfFunctionNotRegistered=function(e){var n=e.label&&e.label in this.registeredFunctions;n||t.utils.warn("Function is not registered with pipeline. This may cause problems when serialising the index.\n",e)},t.Pipeline.load=function(e){var n=new t.Pipeline;return e.forEach(function(e){var i=t.Pipeline.registeredFunctions[e];if(!i)throw new Error("Cannot load un-registered function: "+e);n.add(i)}),n},t.Pipeline.prototype.add=function(){var e=Array.prototype.slice.call(arguments);e.forEach(function(e){t.Pipeline.warnIfFunctionNotRegistered(e),this._stack.push(e)},this)},t.Pipeline.prototype.after=function(e,n){t.Pipeline.warnIfFunctionNotRegistered(n);var i=this._stack.indexOf(e);if(-1==i)throw new Error("Cannot find existingFn");i+=1,this._stack.splice(i,0,n)},t.Pipeline.prototype.before=function(e,n){t.Pipeline.warnIfFunctionNotRegistered(n);var i=this._stack.indexOf(e);if(-1==i)throw new Error("Cannot find existingFn");this._stack.splice(i,0,n)},t.Pipeline.prototype.remove=function(t){var e=this._stack.indexOf(t);-1!=e&&this._stack.splice(e,1)},t.Pipeline.prototype.run=function(t){for(var e=[],n=t.length,i=this._stack.length,o=0;n>o;o++){for(var r=t[o],s=0;i>s&&(r=this._stack[s](r,o,t),void 0!==r);s++);void 0!==r&&e.push(r)}return e},t.Pipeline.prototype.reset=function(){this._stack=[]},t.Pipeline.prototype.toJSON=function(){return this._stack.map(function(e){return t.Pipeline.warnIfFunctionNotRegistered(e),e.label})},t.Vector=function(){this._magnitude=null,this.list=void 0,this.length=0},t.Vector.Node=function(t,e,n){this.idx=t,this.val=e,this.next=n},t.Vector.prototype.insert=function(e,n){this._magnitude=void 0;var i=this.list;if(!i)return this.list=new t.Vector.Node(e,n,i),this.length++;if(en.idx?n=n.next:(i+=e.val*n.val,e=e.next,n=n.next);return i},t.Vector.prototype.similarity=function(t){return this.dot(t)/(this.magnitude()*t.magnitude())},t.SortedSet=function(){this.length=0,this.elements=[]},t.SortedSet.load=function(t){var e=new this;return e.elements=t,e.length=t.length,e},t.SortedSet.prototype.add=function(){var t,e;for(t=0;t1;){if(r===t)return o;t>r&&(e=o),r>t&&(n=o),i=n-e,o=e+Math.floor(i/2),r=this.elements[o]}return r===t?o:-1},t.SortedSet.prototype.locationFor=function(t){for(var e=0,n=this.elements.length,i=n-e,o=e+Math.floor(i/2),r=this.elements[o];i>1;)t>r&&(e=o),r>t&&(n=o),i=n-e,o=e+Math.floor(i/2),r=this.elements[o];return r>t?o:t>r?o+1:void 0},t.SortedSet.prototype.intersect=function(e){for(var n=new t.SortedSet,i=0,o=0,r=this.length,s=e.length,a=this.elements,h=e.elements;;){if(i>r-1||o>s-1)break;a[i]!==h[o]?a[i]h[o]&&o++:(n.add(a[i]),i++,o++)}return n},t.SortedSet.prototype.clone=function(){var e=new t.SortedSet;return e.elements=this.toArray(),e.length=e.elements.length,e},t.SortedSet.prototype.union=function(t){var e,n,i;return this.length>=t.length?(e=this,n=t):(e=t,n=this),i=e.clone(),i.add.apply(i,n.toArray()),i},t.SortedSet.prototype.toJSON=function(){return this.toArray()},t.Index=function(){this._fields=[],this._ref="id",this.pipeline=new t.Pipeline,this.documentStore=new t.Store,this.tokenStore=new t.TokenStore,this.corpusTokens=new t.SortedSet,this.eventEmitter=new t.EventEmitter,this._idfCache={},this.on("add","remove","update",function(){this._idfCache={}}.bind(this))},t.Index.prototype.on=function(){var t=Array.prototype.slice.call(arguments);return this.eventEmitter.addListener.apply(this.eventEmitter,t)},t.Index.prototype.off=function(t,e){return this.eventEmitter.removeListener(t,e)},t.Index.load=function(e){e.version!==t.version&&t.utils.warn("version mismatch: current "+t.version+" importing "+e.version);var n=new this;return n._fields=e.fields,n._ref=e.ref,n.documentStore=t.Store.load(e.documentStore),n.tokenStore=t.TokenStore.load(e.tokenStore),n.corpusTokens=t.SortedSet.load(e.corpusTokens),n.pipeline=t.Pipeline.load(e.pipeline),n},t.Index.prototype.field=function(t,e){var e=e||{},n={name:t,boost:e.boost||1};return this._fields.push(n),this},t.Index.prototype.ref=function(t){return this._ref=t,this},t.Index.prototype.add=function(e,n){var i={},o=new t.SortedSet,r=e[this._ref],n=void 0===n?!0:n;this._fields.forEach(function(n){var r=this.pipeline.run(t.tokenizer(e[n.name]));i[n.name]=r,t.SortedSet.prototype.add.apply(o,r)},this),this.documentStore.set(r,o),t.SortedSet.prototype.add.apply(this.corpusTokens,o.toArray());for(var s=0;s0&&(i=1+Math.log(this.documentStore.length/n)),this._idfCache[e]=i},t.Index.prototype.search=function(e){var n=this.pipeline.run(t.tokenizer(e)),i=new t.Vector,o=[],r=this._fields.reduce(function(t,e){return t+e.boost},0),s=n.some(function(t){return this.tokenStore.has(t)},this);if(!s)return[];n.forEach(function(e,n,s){var a=1/s.length*this._fields.length*r,h=this,l=this.tokenStore.expand(e).reduce(function(n,o){var r=h.corpusTokens.indexOf(o),s=h.idf(o),l=1,u=new t.SortedSet;if(o!==e){var c=Math.max(3,o.length-e.length);l=1/Math.log(c)}return r>-1&&i.insert(r,a*s*l),Object.keys(h.tokenStore.get(o)).forEach(function(t){u.add(t)}),n.union(u)},new t.SortedSet);o.push(l)},this);var a=o.reduce(function(t,e){return t.intersect(e)});return a.map(function(t){return{ref:t,score:i.similarity(this.documentVector(t))}},this).sort(function(t,e){return e.score-t.score})},t.Index.prototype.documentVector=function(e){for(var n=this.documentStore.get(e),i=n.length,o=new t.Vector,r=0;i>r;r++){var s=n.elements[r],a=this.tokenStore.get(s)[e].tf,h=this.idf(s);o.insert(this.corpusTokens.indexOf(s),a*h)}return o},t.Index.prototype.toJSON=function(){return{version:t.version,fields:this._fields,ref:this._ref,documentStore:this.documentStore.toJSON(),tokenStore:this.tokenStore.toJSON(),corpusTokens:this.corpusTokens.toJSON(),pipeline:this.pipeline.toJSON()}},t.Index.prototype.use=function(t){var e=Array.prototype.slice.call(arguments,1);e.unshift(this),t.apply(this,e)},t.Store=function(){this.store={},this.length=0},t.Store.load=function(e){var n=new this;return n.length=e.length,n.store=Object.keys(e.store).reduce(function(n,i){return n[i]=t.SortedSet.load(e.store[i]),n},{}),n},t.Store.prototype.set=function(t,e){this.has(t)||this.length++,this.store[t]=e},t.Store.prototype.get=function(t){return this.store[t]},t.Store.prototype.has=function(t){return t in this.store},t.Store.prototype.remove=function(t){this.has(t)&&(delete this.store[t],this.length--)},t.Store.prototype.toJSON=function(){return{store:this.store,length:this.length}},t.stemmer=function(){var t={ational:"ate",tional:"tion",enci:"ence",anci:"ance",izer:"ize",bli:"ble",alli:"al",entli:"ent",eli:"e",ousli:"ous",ization:"ize",ation:"ate",ator:"ate",alism:"al",iveness:"ive",fulness:"ful",ousness:"ous",aliti:"al",iviti:"ive",biliti:"ble",logi:"log"},e={icate:"ic",ative:"",alize:"al",iciti:"ic",ical:"ic",ful:"",ness:""},n="[^aeiou]",i="[aeiouy]",o=n+"[^aeiouy]*",r=i+"[aeiou]*",s="^("+o+")?"+r+o,a="^("+o+")?"+r+o+"("+r+")?$",h="^("+o+")?"+r+o+r+o,l="^("+o+")?"+i,u=new RegExp(s),c=new RegExp(h),f=new RegExp(a),d=new RegExp(l),p=/^(.+?)(ss|i)es$/,m=/^(.+?)([^s])s$/,v=/^(.+?)eed$/,y=/^(.+?)(ed|ing)$/,g=/.$/,S=/(at|bl|iz)$/,w=new RegExp("([^aeiouylsz])\\1$"),x=new RegExp("^"+o+i+"[^aeiouwxy]$"),k=/^(.+?[^aeiou])y$/,b=/^(.+?)(ational|tional|enci|anci|izer|bli|alli|entli|eli|ousli|ization|ation|ator|alism|iveness|fulness|ousness|aliti|iviti|biliti|logi)$/,E=/^(.+?)(icate|ative|alize|iciti|ical|ful|ness)$/,_=/^(.+?)(al|ance|ence|er|ic|able|ible|ant|ement|ment|ent|ou|ism|ate|iti|ous|ive|ize)$/,F=/^(.+?)(s|t)(ion)$/,O=/^(.+?)e$/,P=/ll$/,N=new RegExp("^"+o+i+"[^aeiouwxy]$"),T=function(n){var i,o,r,s,a,h,l;if(n.length<3)return n;if(r=n.substr(0,1),"y"==r&&(n=r.toUpperCase()+n.substr(1)),s=p,a=m,s.test(n)?n=n.replace(s,"$1$2"):a.test(n)&&(n=n.replace(a,"$1$2")),s=v,a=y,s.test(n)){var T=s.exec(n);s=u,s.test(T[1])&&(s=g,n=n.replace(s,""))}else if(a.test(n)){var T=a.exec(n);i=T[1],a=d,a.test(i)&&(n=i,a=S,h=w,l=x,a.test(n)?n+="e":h.test(n)?(s=g,n=n.replace(s,"")):l.test(n)&&(n+="e"))}if(s=k,s.test(n)){var T=s.exec(n);i=T[1],n=i+"i"}if(s=b,s.test(n)){var T=s.exec(n);i=T[1],o=T[2],s=u,s.test(i)&&(n=i+t[o])}if(s=E,s.test(n)){var T=s.exec(n);i=T[1],o=T[2],s=u,s.test(i)&&(n=i+e[o])}if(s=_,a=F,s.test(n)){var T=s.exec(n);i=T[1],s=c,s.test(i)&&(n=i)}else if(a.test(n)){var T=a.exec(n);i=T[1]+T[2],a=c,a.test(i)&&(n=i)}if(s=O,s.test(n)){var T=s.exec(n);i=T[1],s=c,a=f,h=N,(s.test(i)||a.test(i)&&!h.test(i))&&(n=i)}return s=P,a=c,s.test(n)&&a.test(n)&&(s=g,n=n.replace(s,"")),"y"==r&&(n=r.toLowerCase()+n.substr(1)),n};return T}(),t.Pipeline.registerFunction(t.stemmer,"stemmer"),t.stopWordFilter=function(e){return e&&t.stopWordFilter.stopWords[e]!==e?e:void 0},t.stopWordFilter.stopWords={a:"a",able:"able",about:"about",across:"across",after:"after",all:"all",almost:"almost",also:"also",am:"am",among:"among",an:"an",and:"and",any:"any",are:"are",as:"as",at:"at",be:"be",because:"because",been:"been",but:"but",by:"by",can:"can",cannot:"cannot",could:"could",dear:"dear",did:"did","do":"do",does:"does",either:"either","else":"else",ever:"ever",every:"every","for":"for",from:"from",get:"get",got:"got",had:"had",has:"has",have:"have",he:"he",her:"her",hers:"hers",him:"him",his:"his",how:"how",however:"however",i:"i","if":"if","in":"in",into:"into",is:"is",it:"it",its:"its",just:"just",least:"least",let:"let",like:"like",likely:"likely",may:"may",me:"me",might:"might",most:"most",must:"must",my:"my",neither:"neither",no:"no",nor:"nor",not:"not",of:"of",off:"off",often:"often",on:"on",only:"only",or:"or",other:"other",our:"our",own:"own",rather:"rather",said:"said",say:"say",says:"says",she:"she",should:"should",since:"since",so:"so",some:"some",than:"than",that:"that",the:"the",their:"their",them:"them",then:"then",there:"there",these:"these",they:"they","this":"this",tis:"tis",to:"to",too:"too",twas:"twas",us:"us",wants:"wants",was:"was",we:"we",were:"were",what:"what",when:"when",where:"where",which:"which","while":"while",who:"who",whom:"whom",why:"why",will:"will","with":"with",would:"would",yet:"yet",you:"you",your:"your"},t.Pipeline.registerFunction(t.stopWordFilter,"stopWordFilter"),t.trimmer=function(t){var e=t.replace(/^\W+/,"").replace(/\W+$/,"");return""===e?void 0:e},t.Pipeline.registerFunction(t.trimmer,"trimmer"),t.TokenStore=function(){this.root={docs:{}},this.length=0},t.TokenStore.load=function(t){var e=new this;return e.root=t.root,e.length=t.length,e},t.TokenStore.prototype.add=function(t,e,n){var n=n||this.root,i=t[0],o=t.slice(1);return i in n||(n[i]={docs:{}}),0===o.length?(n[i].docs[e.ref]=e,void(this.length+=1)):this.add(o,e,n[i])},t.TokenStore.prototype.has=function(t){if(!t)return!1;for(var e=this.root,n=0;no;o++){for(var r=t[o],s=0;i>s&&(r=this._stack[s](r,o,t),void 0!==r);s++);void 0!==r&&e.push(r)}return e},t.Pipeline.prototype.reset=function(){this._stack=[]},t.Pipeline.prototype.toJSON=function(){return this._stack.map(function(e){return t.Pipeline.warnIfFunctionNotRegistered(e),e.label})},t.Vector=function(){this._magnitude=null,this.list=void 0,this.length=0},t.Vector.Node=function(t,e,n){this.idx=t,this.val=e,this.next=n},t.Vector.prototype.insert=function(e,n){this._magnitude=void 0;var i=this.list;if(!i)return this.list=new t.Vector.Node(e,n,i),this.length++;if(en.idx?n=n.next:(i+=e.val*n.val,e=e.next,n=n.next);return i},t.Vector.prototype.similarity=function(t){return this.dot(t)/(this.magnitude()*t.magnitude())},t.SortedSet=function(){this.length=0,this.elements=[]},t.SortedSet.load=function(t){var e=new this;return e.elements=t,e.length=t.length,e},t.SortedSet.prototype.add=function(){var t,e;for(t=0;t1;){if(r===t)return o;t>r&&(e=o),r>t&&(n=o),i=n-e,o=e+Math.floor(i/2),r=this.elements[o]}return r===t?o:-1},t.SortedSet.prototype.locationFor=function(t){for(var e=0,n=this.elements.length,i=n-e,o=e+Math.floor(i/2),r=this.elements[o];i>1;)t>r&&(e=o),r>t&&(n=o),i=n-e,o=e+Math.floor(i/2),r=this.elements[o];return r>t?o:t>r?o+1:void 0},t.SortedSet.prototype.intersect=function(e){for(var n=new t.SortedSet,i=0,o=0,r=this.length,s=e.length,a=this.elements,h=e.elements;;){if(i>r-1||o>s-1)break;a[i]!==h[o]?a[i]h[o]&&o++:(n.add(a[i]),i++,o++)}return n},t.SortedSet.prototype.clone=function(){var e=new t.SortedSet;return e.elements=this.toArray(),e.length=e.elements.length,e},t.SortedSet.prototype.union=function(t){var e,n,i;return this.length>=t.length?(e=this,n=t):(e=t,n=this),i=e.clone(),i.add.apply(i,n.toArray()),i},t.SortedSet.prototype.toJSON=function(){return this.toArray()},t.Index=function(){this._fields=[],this._ref="id",this.pipeline=new t.Pipeline,this.documentStore=new t.Store,this.tokenStore=new t.TokenStore,this.corpusTokens=new t.SortedSet,this.eventEmitter=new t.EventEmitter,this._idfCache={},this.on("add","remove","update",function(){this._idfCache={}}.bind(this))},t.Index.prototype.on=function(){var t=Array.prototype.slice.call(arguments);return this.eventEmitter.addListener.apply(this.eventEmitter,t)},t.Index.prototype.off=function(t,e){return this.eventEmitter.removeListener(t,e)},t.Index.load=function(e){e.version!==t.version&&t.utils.warn("version mismatch: current "+t.version+" importing "+e.version);var n=new this;return n._fields=e.fields,n._ref=e.ref,n.documentStore=t.Store.load(e.documentStore),n.tokenStore=t.TokenStore.load(e.tokenStore),n.corpusTokens=t.SortedSet.load(e.corpusTokens),n.pipeline=t.Pipeline.load(e.pipeline),n},t.Index.prototype.field=function(t,e){var e=e||{},n={name:t,boost:e.boost||1};return this._fields.push(n),this},t.Index.prototype.ref=function(t){return this._ref=t,this},t.Index.prototype.add=function(e,n){var i={},o=new t.SortedSet,r=e[this._ref],n=void 0===n?!0:n;this._fields.forEach(function(n){var r=this.pipeline.run(t.tokenizer(e[n.name]));i[n.name]=r,t.SortedSet.prototype.add.apply(o,r)},this),this.documentStore.set(r,o),t.SortedSet.prototype.add.apply(this.corpusTokens,o.toArray());for(var s=0;s0&&(i=1+Math.log(this.documentStore.length/n)),this._idfCache[e]=i},t.Index.prototype.search=function(e){var n=this.pipeline.run(t.tokenizer(e)),i=new t.Vector,o=[],r=this._fields.reduce(function(t,e){return t+e.boost},0),s=n.some(function(t){return this.tokenStore.has(t)},this);if(!s)return[];n.forEach(function(e,n,s){var a=1/s.length*this._fields.length*r,h=this,l=this.tokenStore.expand(e).reduce(function(n,o){var r=h.corpusTokens.indexOf(o),s=h.idf(o),l=1,u=new t.SortedSet;if(o!==e){var c=Math.max(3,o.length-e.length);l=1/Math.log(c)}return r>-1&&i.insert(r,a*s*l),Object.keys(h.tokenStore.get(o)).forEach(function(t){u.add(t)}),n.union(u)},new t.SortedSet);o.push(l)},this);var a=o.reduce(function(t,e){return t.intersect(e)});return a.map(function(t){return{ref:t,score:i.similarity(this.documentVector(t))}},this).sort(function(t,e){return e.score-t.score})},t.Index.prototype.documentVector=function(e){for(var n=this.documentStore.get(e),i=n.length,o=new t.Vector,r=0;i>r;r++){var s=n.elements[r],a=this.tokenStore.get(s)[e].tf,h=this.idf(s);o.insert(this.corpusTokens.indexOf(s),a*h)}return o},t.Index.prototype.toJSON=function(){return{version:t.version,fields:this._fields,ref:this._ref,documentStore:this.documentStore.toJSON(),tokenStore:this.tokenStore.toJSON(),corpusTokens:this.corpusTokens.toJSON(),pipeline:this.pipeline.toJSON()}},t.Index.prototype.use=function(t){var e=Array.prototype.slice.call(arguments,1);e.unshift(this),t.apply(this,e)},t.Store=function(){this.store={},this.length=0},t.Store.load=function(e){var n=new this;return n.length=e.length,n.store=Object.keys(e.store).reduce(function(n,i){return n[i]=t.SortedSet.load(e.store[i]),n},{}),n},t.Store.prototype.set=function(t,e){this.has(t)||this.length++,this.store[t]=e},t.Store.prototype.get=function(t){return this.store[t]},t.Store.prototype.has=function(t){return t in this.store},t.Store.prototype.remove=function(t){this.has(t)&&(delete this.store[t],this.length--)},t.Store.prototype.toJSON=function(){return{store:this.store,length:this.length}},t.stemmer=function(){var t={ational:"ate",tional:"tion",enci:"ence",anci:"ance",izer:"ize",bli:"ble",alli:"al",entli:"ent",eli:"e",ousli:"ous",ization:"ize",ation:"ate",ator:"ate",alism:"al",iveness:"ive",fulness:"ful",ousness:"ous",aliti:"al",iviti:"ive",biliti:"ble",logi:"log"},e={icate:"ic",ative:"",alize:"al",iciti:"ic",ical:"ic",ful:"",ness:""},n="[^aeiou]",i="[aeiouy]",o=n+"[^aeiouy]*",r=i+"[aeiou]*",s="^("+o+")?"+r+o,a="^("+o+")?"+r+o+"("+r+")?$",h="^("+o+")?"+r+o+r+o,l="^("+o+")?"+i,u=new RegExp(s),c=new RegExp(h),f=new RegExp(a),d=new RegExp(l),p=/^(.+?)(ss|i)es$/,m=/^(.+?)([^s])s$/,v=/^(.+?)eed$/,y=/^(.+?)(ed|ing)$/,g=/.$/,S=/(at|bl|iz)$/,w=new RegExp("([^aeiouylsz])\\1$"),x=new RegExp("^"+o+i+"[^aeiouwxy]$"),k=/^(.+?[^aeiou])y$/,b=/^(.+?)(ational|tional|enci|anci|izer|bli|alli|entli|eli|ousli|ization|ation|ator|alism|iveness|fulness|ousness|aliti|iviti|biliti|logi)$/,E=/^(.+?)(icate|ative|alize|iciti|ical|ful|ness)$/,_=/^(.+?)(al|ance|ence|er|ic|able|ible|ant|ement|ment|ent|ou|ism|ate|iti|ous|ive|ize)$/,F=/^(.+?)(s|t)(ion)$/,O=/^(.+?)e$/,P=/ll$/,N=new RegExp("^"+o+i+"[^aeiouwxy]$"),T=function(n){var i,o,r,s,a,h,l;if(n.length<3)return n;if(r=n.substr(0,1),"y"==r&&(n=r.toUpperCase()+n.substr(1)),s=p,a=m,s.test(n)?n=n.replace(s,"$1$2"):a.test(n)&&(n=n.replace(a,"$1$2")),s=v,a=y,s.test(n)){var T=s.exec(n);s=u,s.test(T[1])&&(s=g,n=n.replace(s,""))}else if(a.test(n)){var T=a.exec(n);i=T[1],a=d,a.test(i)&&(n=i,a=S,h=w,l=x,a.test(n)?n+="e":h.test(n)?(s=g,n=n.replace(s,"")):l.test(n)&&(n+="e"))}if(s=k,s.test(n)){var T=s.exec(n);i=T[1],n=i+"i"}if(s=b,s.test(n)){var T=s.exec(n);i=T[1],o=T[2],s=u,s.test(i)&&(n=i+t[o])}if(s=E,s.test(n)){var T=s.exec(n);i=T[1],o=T[2],s=u,s.test(i)&&(n=i+e[o])}if(s=_,a=F,s.test(n)){var T=s.exec(n);i=T[1],s=c,s.test(i)&&(n=i)}else if(a.test(n)){var T=a.exec(n);i=T[1]+T[2],a=c,a.test(i)&&(n=i)}if(s=O,s.test(n)){var T=s.exec(n);i=T[1],s=c,a=f,h=N,(s.test(i)||a.test(i)&&!h.test(i))&&(n=i)}return s=P,a=c,s.test(n)&&a.test(n)&&(s=g,n=n.replace(s,"")),"y"==r&&(n=r.toLowerCase()+n.substr(1)),n};return T}(),t.Pipeline.registerFunction(t.stemmer,"stemmer"),t.stopWordFilter=function(e){return e&&t.stopWordFilter.stopWords[e]!==e?e:void 0},t.stopWordFilter.stopWords={a:"a",able:"able",about:"about",across:"across",after:"after",all:"all",almost:"almost",also:"also",am:"am",among:"among",an:"an",and:"and",any:"any",are:"are",as:"as",at:"at",be:"be",because:"because",been:"been",but:"but",by:"by",can:"can",cannot:"cannot",could:"could",dear:"dear",did:"did","do":"do",does:"does",either:"either","else":"else",ever:"ever",every:"every","for":"for",from:"from",get:"get",got:"got",had:"had",has:"has",have:"have",he:"he",her:"her",hers:"hers",him:"him",his:"his",how:"how",however:"however",i:"i","if":"if","in":"in",into:"into",is:"is",it:"it",its:"its",just:"just",least:"least",let:"let",like:"like",likely:"likely",may:"may",me:"me",might:"might",most:"most",must:"must",my:"my",neither:"neither",no:"no",nor:"nor",not:"not",of:"of",off:"off",often:"often",on:"on",only:"only",or:"or",other:"other",our:"our",own:"own",rather:"rather",said:"said",say:"say",says:"says",she:"she",should:"should",since:"since",so:"so",some:"some",than:"than",that:"that",the:"the",their:"their",them:"them",then:"then",there:"there",these:"these",they:"they","this":"this",tis:"tis",to:"to",too:"too",twas:"twas",us:"us",wants:"wants",was:"was",we:"we",were:"were",what:"what",when:"when",where:"where",which:"which","while":"while",who:"who",whom:"whom",why:"why",will:"will","with":"with",would:"would",yet:"yet",you:"you",your:"your"},t.Pipeline.registerFunction(t.stopWordFilter,"stopWordFilter"),t.trimmer=function(t){var e=t.replace(/^\W+/,"").replace(/\W+$/,"");return""===e?void 0:e},t.Pipeline.registerFunction(t.trimmer,"trimmer"),t.TokenStore=function(){this.root={docs:{}},this.length=0},t.TokenStore.load=function(t){var e=new this;return e.root=t.root,e.length=t.length,e},t.TokenStore.prototype.add=function(t,e,n){var n=n||this.root,i=t[0],o=t.slice(1);return i in n||(n[i]={docs:{}}),0===o.length?(n[i].docs[e.ref]=e,void(this.length+=1)):this.add(o,e,n[i])},t.TokenStore.prototype.has=function(t){if(!t)return!1;for(var e=this.root,n=0;n 0) { - gitbook.toolbar.createButton({ - icon: 'fa fa-share-alt', - label: 'Share', - position: 'right', - dropdown: [menu] - }); - } - - // Direct actions to share - $.each(SITES, function(sideId, site) { - if (!opts[sideId]) return; - - gitbook.toolbar.createButton({ - icon: site.icon, - label: site.text, - position: 'right', - onClick: site.onClick - }); - }); - }); -}); diff --git a/docs/_book/gitbook/images/apple-touch-icon-precomposed-152 2.png b/docs/_book/gitbook/images/apple-touch-icon-precomposed-152 2.png deleted file mode 100644 index f0adcfd0..00000000 Binary files a/docs/_book/gitbook/images/apple-touch-icon-precomposed-152 2.png and /dev/null differ diff --git a/docs/_book/index.html b/docs/_book/index.html index f3830184..02bbe10d 100644 --- a/docs/_book/index.html +++ b/docs/_book/index.html @@ -548,7 +548,7 @@ MONGO_DB = 'crawlab_test' @@ -558,6 +558,10 @@ MONGO_DB = 'crawlab_test' + + + + diff --git a/frontend/docs/file-manager-prototype.png b/frontend/docs/file-manager-prototype.png deleted file mode 100644 index 270435b7..00000000 Binary files a/frontend/docs/file-manager-prototype.png and /dev/null differ diff --git a/frontend/src/api/login.js b/frontend/src/api/login.js deleted file mode 100644 index 4699f07e..00000000 --- a/frontend/src/api/login.js +++ /dev/null @@ -1,27 +0,0 @@ -import request from '@/utils/request' - -export function login (username, password) { - return request({ - url: '/user/login', - method: 'post', - data: { - username, - password - } - }) -} - -export function getInfo (token) { - return request({ - url: '/user/info', - method: 'get', - params: { token } - }) -} - -export function logout () { - return request({ - url: '/user/logout', - method: 'post' - }) -} diff --git a/frontend/src/api/table.js b/frontend/src/api/table.js deleted file mode 100644 index 95d1df60..00000000 --- a/frontend/src/api/table.js +++ /dev/null @@ -1,9 +0,0 @@ -import request from '@/utils/request' - -export function getList (params) { - return request({ - url: '/table/list', - method: 'get', - params - }) -} diff --git a/frontend/src/store/index.js b/frontend/src/store/index.js index 33ae9f40..57fb5065 100644 --- a/frontend/src/store/index.js +++ b/frontend/src/store/index.js @@ -1,7 +1,7 @@ import Vue from 'vue' import Vuex from 'vuex' import app from './modules/app' -import user from './modules/user' +// import user from './modules/user' import tagsView from './modules/tagsView' import dialogView from './modules/dialogView' import node from './modules/node' @@ -19,7 +19,7 @@ Vue.use(Vuex) const store = new Vuex.Store({ modules: { app, - user, + // user, tagsView, dialogView, node, diff --git a/spiders/sites_inspector/sites_inspector.py b/spiders/sites_inspector/sites_inspector.py new file mode 100644 index 00000000..80c9c60a --- /dev/null +++ b/spiders/sites_inspector/sites_inspector.py @@ -0,0 +1,76 @@ +import asyncio +import os +from datetime import datetime + +import aiohttp +import requests + +from pymongo import MongoClient + +# MONGO_HOST = os.environ['MONGO_HOST'] +# MONGO_PORT = int(os.environ['MONGO_PORT']) +# MONGO_DB = os.environ['MONGO_DB'] +MONGO_HOST = 'localhost' +MONGO_PORT = 27017 +MONGO_DB = 'crawlab_test' + +mongo = MongoClient(host=MONGO_HOST, port=MONGO_PORT) +db = mongo[MONGO_DB] +col = db['sites'] + + +async def process_response(resp, **kwargs): + url = kwargs.get('url') + status = resp.status # 读取状态 + if status == 200: + col.update({'_id': url}, {'$set': {'has_robots': True}}) + else: + # 错误状态 + col.update({'_id': url}, {'$set': {'has_robots': False}}) + + +async def process_home_page_response(resp, **kwargs): + url = kwargs.get('url') + duration = kwargs.get('duration') + status = resp.status # 读取状态 + col.update({'_id': url}, {'$set': {'home_http_status': status, 'home_response_time': duration}}) + + +async def request_site(url: str, semaphore): + _url = 'http://' + url + '/robots.txt' + print('crawling ' + _url) + async with semaphore: + async with aiohttp.ClientSession() as session: # <1> 开启一个会话 + async with session.get(_url) as resp: # 发送请求 + await process_response(resp=resp, url=url) + print('crawled ' + _url) + # resp = requests.get(_url) + return resp + + +async def request_site_home_page(url: str, semophore): + _url = 'http://' + url + print('crawling ' + _url) + async with semophore: + tic = datetime.now() + async with aiohttp.ClientSession() as session: # <1> 开启一个会话 + async with session.get(_url) as resp: # 发送请求 + toc = datetime.now() + duration = (toc - tic).total_seconds() + await process_home_page_response(resp=resp, url=url, duration=duration) + print('crawled ' + _url) + + +async def run(): + semaphore = asyncio.Semaphore(50) # 限制并发量为50 + sites = [site for site in col.find({'rank': {'$lte': 5000}})] + urls = [site['_id'] for site in sites] + to_get = [request_site(url, semaphore) for url in urls] + to_get += [request_site_home_page(url, semaphore) for url in urls] + await asyncio.wait(to_get) + + +if __name__ == '__main__': + loop = asyncio.get_event_loop() + loop.run_until_complete(run()) + loop.close()