added Results

.gitignore

@@ -110,3 +110,6 @@ node_modules/
 
 # egg-info
 *.egg-info
+
+# .DS_Store
+.DS_Store

README.md

@@ -34,6 +34,23 @@ cd frontend
 npm run dev
 ```
 
+## Screenshot
+
+#### Home Page
+![home](./docs/img/screenshot-home.png)
+
+#### Spider List
+
+![spider-list](./docs/img/screenshot-spiders.png)
+
+#### Spider Detail - Overview
+
+![spider-list](./docs/img/screenshot-spider-detail-overview.png)
+
+#### Task Detail - Results
+
+![spider-list](./docs/img/screenshot-task-detail-results.png)
+
 ## Architecture
 
 The architecture of Crawlab is as below. It's very similar to Celery architecture, but a few more modules including Frontend, Spiders and Flower are added to feature the crawling management functionality. 
@@ -60,3 +77,7 @@ After deploying the spider, you can click "Run" button on spider detail page and
 ### Tasks
 
 Tasks are triggered and run by the workers. Users can check the task status info and logs in the task detail page. 
+
+### App
+
+### Broker

crawlab/manage.py

@@ -86,12 +86,17 @@ def run_worker():
 
 
 @click.command()
-@click.argument('action', type=click.Choice([ActionType.APP, ActionType.FLOWER, ActionType.RUN_ALL]))
+@click.argument('action', type=click.Choice([ActionType.APP,
+                                             ActionType.FLOWER,
+                                             ActionType.WORKER,
+                                             ActionType.RUN_ALL]))
 def main(action):
     if action == ActionType.APP:
         run_app()
     elif action == ActionType.FLOWER:
         run_flower()
+    elif action == ActionType.WORKER:
+        run_worker()
     elif action == ActionType.RUN_ALL:
         p_flower = Process(target=run_flower)
         p_flower.start()

crawlab/routes/nodes.py

@@ -1,3 +1,4 @@
+from constants.task import TaskStatus
 from db.manager import db_manager
 from routes.base import BaseApi
 from utils import jsonify
@@ -64,8 +65,11 @@ class NodeApi(BaseApi):
             spider_id = item['spider_id']
             spider = db_manager.get('spiders', id=str(spider_id))
             item['spider_name'] = spider['name']
-            task = db_manager.get('tasks_celery', id=item['_id'])
-            item['status'] = task['status']
+            _task = db_manager.get('tasks_celery', id=item['_id'])
+            if _task:
+                item['status'] = _task['status']
+            else:
+                item['status'] = TaskStatus.UNAVAILABLE
         return jsonify({
             'status': 'ok',
             'items': items

crawlab/routes/spiders.py

@@ -30,14 +30,23 @@ class SpiderApi(BaseApi):
     col_name = 'spiders'
 
     arguments = (
+        # name of spider
         ('name', str),
+
+        # execute shell command
         ('cmd', str),
+
+        # spider source folder
         ('src', str),
+
+        # spider type
         ('type', str),
+
+        # spider language
         ('lang', str),
 
-        # for deploy only
-        ('node_id', str),
+        # spider results collection
+        ('col', str),
     )
 
     def get(self, id=None, action=None):
@@ -130,8 +139,6 @@ class SpiderApi(BaseApi):
         }
 
     def on_crawl(self, id):
-        args = self.parser.parse_args()
-
         job = execute_spider.delay(id)
 
         return {

crawlab/routes/tasks.py

@@ -2,6 +2,7 @@ from constants.task import TaskStatus
 from db.manager import db_manager
 from routes.base import BaseApi
 from utils import jsonify
+from utils.spider import get_spider_col_fields
 
 
 class TaskApi(BaseApi):
@@ -71,3 +72,17 @@ class TaskApi(BaseApi):
                        'status': 'ok',
                        'error': str(err)
                    }, 500
+
+    def get_results(self, id):
+        task = db_manager.get('tasks', id=id)
+        spider = db_manager.get('spiders', id=task['spider_id'])
+        col_name = spider.get('col')
+        if not col_name:
+            return []
+        fields = get_spider_col_fields(col_name)
+        items = db_manager.list(col_name, {'task_id': id})
+        return jsonify({
+            'status': 'ok',
+            'fields': fields,
+            'items': items
+        })

crawlab/tasks/spider.py

@@ -17,7 +17,6 @@ logger = get_logger(__name__)
 
 @celery_app.task(bind=True)
 def execute_spider(self, id: str):
-    print(self.state)
     task_id = self.request.id
     hostname = self.request.hostname
     spider = db_manager.get('spiders', id=id)
@@ -53,6 +52,7 @@ def execute_spider(self, id: str):
     # execute the command
     env = os.environ.copy()
     env['CRAWLAB_TASK_ID'] = task_id
+    env['CRAWLAB_COLLECTION'] = spider.get('col')
     p = subprocess.Popen(command.split(' '),
                          stdout=stdout.fileno(),
                          stderr=stderr.fileno(),

crawlab/utils/spider.py

@@ -1,6 +1,7 @@
 import os
 
 from constants.spider import FILE_SUFFIX_LANG_MAPPING, LangType, SUFFIX_IGNORE, SpiderType
+from db.manager import db_manager
 
 
 def get_lang_by_stats(stats: dict) -> LangType:
@@ -21,3 +22,12 @@ def get_spider_type(path: str) -> SpiderType:
     for file_name in os.listdir(path):
         if file_name == 'scrapy.cfg':
             return SpiderType.SCRAPY
+
+
+def get_spider_col_fields(col_name):
+    items = db_manager.list(col_name, {}, limit=100, sort_key='_id')
+    fields = set()
+    for item in items:
+        for k in item.keys():
+            fields.add(k)
+    return list(fields)

frontend/src/components/InfoView/SpiderInfoView.vue

@@ -15,10 +15,14 @@
         <el-form-item label="Source Folder">
           <el-input v-model="spiderForm.src" placeholder="Source Folder" disabled></el-input>
         </el-form-item>
-        <el-form-item label="Execute Command" prop="cmd" :rule="cmdRule" required>
+        <el-form-item label="Execute Command" prop="cmd" required>
           <el-input v-model="spiderForm.cmd" placeholder="Execute Command"
                     :disabled="isView"></el-input>
         </el-form-item>
+        <el-form-item label="Results Collection">
+          <el-input v-model="spiderForm.col" placeholder="Results Collection"
+                    :disabled="isView"></el-input>
+        </el-form-item>
         <el-form-item label="Spider Type">
           <el-select v-model="spiderForm.type" placeholder="Select Spider Type" :disabled="isView" clearable>
             <el-option value="scrapy" label="Scrapy"></el-option>
@@ -37,8 +41,8 @@
       </el-form>
     </el-row>
     <el-row class="button-container" v-if="!isView">
-      <el-button type="success" @click="onRun">Run</el-button>
-      <el-button type="primary" @click="onDeploy">Deploy</el-button>
+      <el-button type="danger" @click="onRun">Run</el-button>
+      <!--<el-button type="primary" @click="onDeploy">Deploy</el-button>-->
       <el-button type="success" @click="onSave">Save</el-button>
     </el-row>
   </div>

frontend/src/components/Overview/NodeOverview.vue

@@ -7,7 +7,7 @@
       </el-row>
 
       <!--last deploys-->
-      <el-row>
+      <el-row v-if="false">
         <deploy-table-view title="Latest Deploys"/>
       </el-row>
     </el-col>

frontend/src/components/Overview/SpiderOverview.vue

@@ -7,7 +7,7 @@
       </el-row>
 
       <!--last deploys-->
-      <el-row>
+      <el-row v-if="false">
         <deploy-table-view title="Latest Deploys"/>
       </el-row>
     </el-col>

frontend/src/components/TableView/GeneralTableView.vue

@@ -0,0 +1,77 @@
+<template>
+  <div class="general-table-view">
+    <el-table
+      :data="filteredData"
+      :header-cell-style="{background:'rgb(48, 65, 86)',color:'white'}"
+      border>
+      <template v-for="col in columns">
+        <el-table-column :key="col" :label="col" :property="col" align="center">
+        </el-table-column>
+      </template>
+    </el-table>
+    <div class="pagination">
+      <el-pagination
+        :current-page.sync="pagination.pageNum"
+        :page-sizes="[10, 20, 50, 100]"
+        :page-size.sync="pagination.pageSize"
+        layout="sizes, prev, pager, next"
+        :total="data.length">
+      </el-pagination>
+    </div>
+  </div>
+</template>
+
+<script>
+export default {
+  name: 'GeneralTableView',
+  data () {
+    return {
+      pagination: {
+        pageNum: 1,
+        pageSize: 10
+      }
+    }
+  },
+  props: {
+    columns: {
+      type: Array,
+      default () {
+        return []
+      }
+    },
+    data: {
+      type: Array,
+      default () {
+        return []
+      }
+    }
+  },
+  computed: {
+    filteredData () {
+      return this.data
+        .map(d => {
+          for (let k in d) {
+            if (d.hasOwnProperty(k)) {
+              if (d[k] === undefined || d[k] === null) continue
+              if (typeof d[k] === 'object') {
+                if (d[k].$oid) {
+                  d[k] = d[k].$oid
+                }
+              }
+            }
+          }
+          return d
+        })
+        .filter((d, index) => {
+          // pagination
+          const { pageNum, pageSize } = this.pagination
+          return (pageSize * (pageNum - 1) <= index) && (index < pageSize * pageNum)
+        })
+    }
+  }
+}
+</script>
+
+<style scoped>
+
+</style>

frontend/src/components/TableView/TaskTableView.vue

@@ -4,7 +4,7 @@
       <h5 class="title">{{title}}</h5>
       <el-button type="success" plain class="small-btn" size="mini" icon="fa fa-refresh" @click="onRefresh"></el-button>
     </el-row>
-    <el-table border height="240px" :data="taskList">
+    <el-table border height="480px" :data="taskList">
       <el-table-column property="node" label="Node" width="220" align="center">
         <template slot-scope="scope">
           <a class="a-tag" @click="onClickNode(scope.row)">{{scope.row.node_id}}</a>
@@ -65,7 +65,11 @@ export default {
       this.$router.push(`/tasks/${row._id}`)
     },
     onRefresh () {
-      this.$store.dispatch('spider/getTaskList', this.spiderForm._id.$oid)
+      if (this.$route.path.split('/')[1] === 'spiders') {
+        this.$store.dispatch('spider/getTaskList', this.$route.params.id)
+      } else if (this.$route.path.split('/')[1] === 'nodes') {
+        this.$store.dispatch('node/getTaskList', this.$route.params.id)
+      }
     }
   }
 }

frontend/src/store/modules/spider.js

@@ -60,7 +60,8 @@ const actions = {
       src: state.spiderForm.src,
       cmd: state.spiderForm.cmd,
       type: state.spiderForm.type,
-      lang: state.spiderForm.lang
+      lang: state.spiderForm.lang,
+      col: state.spiderForm.col
     })
       .then(() => {
         dispatch('getSpiderList')

frontend/src/store/modules/task.js

@@ -5,7 +5,9 @@ const state = {
   // TaskList
   taskList: [],
   taskForm: {},
-  taskLog: ''
+  taskLog: '',
+  taskResultsData: [],
+  taskResultsColumns: []
 }
 
 const getters = {}
@@ -19,6 +21,12 @@ const mutations = {
   },
   SET_TASK_LOG (state, value) {
     state.taskLog = value
+  },
+  SET_TASK_RESULTS_DATA (state, value) {
+    state.taskResultsData = value
+  },
+  SET_TASK_RESULTS_COLUMNS (state, value) {
+    state.taskResultsColumns = value
   }
 }
 
@@ -54,6 +62,13 @@ const actions = {
       .then(response => {
         commit('SET_TASK_LOG', response.data.log)
       })
+  },
+  getTaskResults ({ state, commit }, id) {
+    return request.get(`/tasks/${id}/get_results`)
+      .then(response => {
+        commit('SET_TASK_RESULTS_DATA', response.data.items)
+        commit('SET_TASK_RESULTS_COLUMNS', response.data.fields)
+      })
   }
 }
 

frontend/src/views/deploy/DeployList.vue

@@ -93,10 +93,10 @@ export default {
       },
       // tableData,
       columns: [
-        { name: 'version', label: 'Version', width: '180' },
+        // { name: 'version', label: 'Version', width: '180' },
         // { name: 'ip', label: 'IP', width: '160' },
         // { name: 'port', label: 'Port', width: '80' },
-        { name: 'finish_ts', label: 'Finish Time', width: '180' },
+        { name: 'finish_ts', label: 'Time', width: '180' },
         { name: 'spider_name', label: 'Spider', width: '180', sortable: true },
         { name: 'node_id', label: 'Node', width: 'auto' }
       ],
@@ -121,6 +121,11 @@ export default {
         }
         return false
       })
+        .filter((d, index) => {
+          // pagination
+          const { pageNum, pageSize } = this.pagination
+          return (pageSize * (pageNum - 1) <= index) && (index < pageSize * pageNum)
+        })
     }
   },
   methods: {

frontend/src/views/node/NodeDetail.vue

@@ -13,7 +13,7 @@
       <el-tab-pane label="Overview" name="overview">
         <node-overview></node-overview>
       </el-tab-pane>
-      <el-tab-pane label="Deployed Spiders" name="spiders">
+      <el-tab-pane label="Deployed Spiders" name="spiders" v-if="false">
         Deployed Spiders
       </el-tab-pane>
     </el-tabs>

frontend/src/views/spider/SpiderList.vue

@@ -158,7 +158,7 @@ export default {
         { name: 'name', label: 'Name', width: 'auto' },
         { name: 'type', label: 'Spider Type', width: '160', sortable: true },
         { name: 'lang', label: 'Language', width: '160', sortable: true },
-        { name: 'update_ts', label: 'Last Update', width: '120' }
+        { name: 'last_run_ts', label: 'Last Run', width: '120' }
       ],
       spiderFormRules: {
         name: [{ required: true, message: 'Required Field', trigger: 'change' }]

frontend/src/views/task/TaskDetail.vue

@@ -12,6 +12,9 @@
           </pre>
         </div>
       </el-tab-pane>
+      <el-tab-pane label="Results" name="results">
+        <general-table-view :data="taskResultsData" :columns="taskResultsColumns"/>
+      </el-tab-pane>
     </el-tabs>
   </div>
 </template>
@@ -21,10 +24,12 @@ import {
   mapState
 } from 'vuex'
 import TaskOverview from '../../components/Overview/TaskOverview'
+import GeneralTableView from '../../components/TableView/GeneralTableView'
 
 export default {
   name: 'TaskDetail',
   components: {
+    GeneralTableView,
     TaskOverview
   },
   data () {
@@ -34,7 +39,9 @@ export default {
   },
   computed: {
     ...mapState('task', [
-      'taskLog'
+      'taskLog',
+      'taskResultsData',
+      'taskResultsColumns'
     ]),
     ...mapState('file', [
       'currentPath'
@@ -53,6 +60,7 @@ export default {
   created () {
     this.$store.dispatch('task/getTaskData', this.$route.params.id)
     this.$store.dispatch('task/getTaskLog', this.$route.params.id)
+    this.$store.dispatch('task/getTaskResults', this.$route.params.id)
   }
 }
 </script>

frontend/src/views/task/TaskList.vue

@@ -13,7 +13,7 @@
                    icon="el-icon-refresh"
                    class="refresh"
                    @click="onRefresh">
-          Search
+          Refresh
         </el-button>
       </div>
     </div>

spiders/baidu/baidu/settings.py

@@ -19,8 +19,8 @@ NEWSPIDER_MODULE = 'baidu.spiders'
 #USER_AGENT = 'baidu (+http://www.yourdomain.com)'
 
 # Obey robots.txt rules
-# ROBOTSTXT_OBEY = True
-ROBOTSTXT_OBEY = False
+ROBOTSTXT_OBEY = True
+# ROBOTSTXT_OBEY = False
 
 # Configure maximum concurrent requests performed by Scrapy (default: 16)
 #CONCURRENT_REQUESTS = 32

spiders/example_juejin/juejin/items.py

@@ -0,0 +1,17 @@
+# -*- coding: utf-8 -*-
+
+# Define here the models for your scraped items
+#
+# See documentation in:
+# http://doc.scrapy.org/en/latest/topics/items.html
+
+import scrapy
+
+
+class JuejinItem(scrapy.Item):
+    # define the fields for your item here like:
+    _id = scrapy.Field()
+    title = scrapy.Field()
+    link = scrapy.Field()
+    like = scrapy.Field()
+    task_id = scrapy.Field()

spiders/example_juejin/juejin/middlewares.py

@@ -0,0 +1,56 @@
+# -*- coding: utf-8 -*-
+
+# Define here the models for your spider middleware
+#
+# See documentation in:
+# http://doc.scrapy.org/en/latest/topics/spider-middleware.html
+
+from scrapy import signals
+
+
+class JuejinSpiderMiddleware(object):
+    # Not all methods need to be defined. If a method is not defined,
+    # scrapy acts as if the spider middleware does not modify the
+    # passed objects.
+
+    @classmethod
+    def from_crawler(cls, crawler):
+        # This method is used by Scrapy to create your spiders.
+        s = cls()
+        crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)
+        return s
+
+    def process_spider_input(self, response, spider):
+        # Called for each response that goes through the spider
+        # middleware and into the spider.
+
+        # Should return None or raise an exception.
+        return None
+
+    def process_spider_output(self, response, result, spider):
+        # Called with the results returned from the Spider, after
+        # it has processed the response.
+
+        # Must return an iterable of Request, dict or Item objects.
+        for i in result:
+            yield i
+
+    def process_spider_exception(self, response, exception, spider):
+        # Called when a spider or process_spider_input() method
+        # (from other spider middleware) raises an exception.
+
+        # Should return either None or an iterable of Response, dict
+        # or Item objects.
+        pass
+
+    def process_start_requests(self, start_requests, spider):
+        # Called with the start requests of the spider, and works
+        # similarly to the process_spider_output() method, except
+        # that it doesn’t have a response associated.
+
+        # Must return only requests (not items).
+        for r in start_requests:
+            yield r
+
+    def spider_opened(self, spider):
+        spider.logger.info('Spider opened: %s' % spider.name)

spiders/example_juejin/juejin/pipelines.py

@@ -0,0 +1,27 @@
+# -*- coding: utf-8 -*-
+
+# Define your item pipelines here
+#
+# Don't forget to add your pipeline to the ITEM_PIPELINES setting
+# See: http://doc.scrapy.org/en/latest/topics/item-pipeline.html
+import os
+
+from pymongo import MongoClient
+
+MONGO_HOST = '192.168.99.100'
+MONGO_PORT = 27017
+MONGO_DB = 'crawlab_test'
+
+
+class JuejinPipeline(object):
+    mongo = MongoClient(host=MONGO_HOST, port=MONGO_PORT)
+    db = mongo[MONGO_DB]
+    col_name = os.environ.get('CRAWLAB_COLLECTION')
+    if not col_name:
+        col_name = 'test'
+    col = db[col_name]
+
+    def process_item(self, item, spider):
+        item['task_id'] = os.environ.get('CRAWLAB_TASK_ID')
+        self.col.save(item)
+        return item

spiders/example_juejin/juejin/settings.py

@@ -0,0 +1,89 @@
+# -*- coding: utf-8 -*-
+
+# Scrapy settings for juejin project
+#
+# For simplicity, this file contains only settings considered important or
+# commonly used. You can find more settings consulting the documentation:
+#
+#     http://doc.scrapy.org/en/latest/topics/settings.html
+#     http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
+#     http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html
+
+BOT_NAME = 'juejin'
+
+SPIDER_MODULES = ['juejin.spiders']
+NEWSPIDER_MODULE = 'juejin.spiders'
+
+# Crawl responsibly by identifying yourself (and your website) on the user-agent
+USER_AGENT = 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.99 Safari/537.36'
+
+# Obey robots.txt rules
+ROBOTSTXT_OBEY = True
+
+# Configure maximum concurrent requests performed by Scrapy (default: 16)
+# CONCURRENT_REQUESTS = 32
+
+# Configure a delay for requests for the same website (default: 0)
+# See http://scrapy.readthedocs.org/en/latest/topics/settings.html#download-delay
+# See also autothrottle settings and docs
+# DOWNLOAD_DELAY = 3
+# The download delay setting will honor only one of:
+# CONCURRENT_REQUESTS_PER_DOMAIN = 16
+# CONCURRENT_REQUESTS_PER_IP = 16
+
+# Disable cookies (enabled by default)
+# COOKIES_ENABLED = False
+
+# Disable Telnet Console (enabled by default)
+# TELNETCONSOLE_ENABLED = False
+
+# Override the default request headers:
+# DEFAULT_REQUEST_HEADERS = {
+#   'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
+#   'Accept-Language': 'en',
+# }
+
+# Enable or disable spider middlewares
+# See http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html
+# SPIDER_MIDDLEWARES = {
+#    'juejin.middlewares.JuejinSpiderMiddleware': 543,
+# }
+
+# Enable or disable downloader middlewares
+# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
+# DOWNLOADER_MIDDLEWARES = {
+#    'juejin.middlewares.MyCustomDownloaderMiddleware': 543,
+# }
+
+# Enable or disable extensions
+# See http://scrapy.readthedocs.org/en/latest/topics/extensions.html
+# EXTENSIONS = {
+#    'scrapy.extensions.telnet.TelnetConsole': None,
+# }
+
+# Configure item pipelines
+# See http://scrapy.readthedocs.org/en/latest/topics/item-pipeline.html
+ITEM_PIPELINES = {
+    'juejin.pipelines.JuejinPipeline': 300,
+}
+
+# Enable and configure the AutoThrottle extension (disabled by default)
+# See http://doc.scrapy.org/en/latest/topics/autothrottle.html
+# AUTOTHROTTLE_ENABLED = True
+# The initial download delay
+# AUTOTHROTTLE_START_DELAY = 5
+# The maximum download delay to be set in case of high latencies
+# AUTOTHROTTLE_MAX_DELAY = 60
+# The average number of requests Scrapy should be sending in parallel to
+# each remote server
+# AUTOTHROTTLE_TARGET_CONCURRENCY = 1.0
+# Enable showing throttling stats for every response received:
+# AUTOTHROTTLE_DEBUG = False
+
+# Enable and configure HTTP caching (disabled by default)
+# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html#httpcache-middleware-settings
+# HTTPCACHE_ENABLED = True
+# HTTPCACHE_EXPIRATION_SECS = 0
+# HTTPCACHE_DIR = 'httpcache'
+# HTTPCACHE_IGNORE_HTTP_CODES = []
+# HTTPCACHE_STORAGE = 'scrapy.extensions.httpcache.FilesystemCacheStorage'

spiders/example_juejin/juejin/spiders/__init__.py

@@ -0,0 +1,4 @@
+# This package will contain the spiders of your Scrapy project
+#
+# Please refer to the documentation for information on how to create and manage
+# your spiders.

spiders/example_juejin/juejin/spiders/juejin_spider.py

@@ -0,0 +1,17 @@
+# -*- coding: utf-8 -*-
+import scrapy
+from juejin.items import JuejinItem
+
+
+class JuejinSpiderSpider(scrapy.Spider):
+    name = 'juejin_spider'
+    allowed_domains = ['juejin.com']
+    start_urls = ['https://juejin.im/search?query=celery']
+
+    def parse(self, response):
+        for item in response.css('ul.main-list > li.item'):
+            yield JuejinItem(
+                title=item.css('.title span').extract_first(),
+                link=item.css('a::attr("href")').extract_first(),
+                like=item.css('.like .count::text').extract_first(),
+            )

spiders/example_juejin/scrapy.cfg

@@ -0,0 +1,11 @@
+# Automatically created by: scrapy startproject
+#
+# For more information about the [deploy] section see:
+# https://scrapyd.readthedocs.org/en/latest/deploy.html
+
+[settings]
+default = juejin.settings
+
+[deploy]
+#url = http://localhost:6800/
+project = juejin