From b169f09e12c9575b9f4843a9c5494f11df34a8a0 Mon Sep 17 00:00:00 2001 From: Marvin Zhang Date: Tue, 16 Apr 2019 20:19:22 +0800 Subject: [PATCH] added lianjia example --- crawlab/utils/node.py | 3 +- frontend/src/i18n/zh.js | 1 + frontend/src/router/index.js | 2 +- frontend/src/store/index.js | 2 + frontend/src/store/modules/schedule.js | 34 ++++++ frontend/src/views/schedule/ScheduleList.vue | 112 +++++++++++++++++- spiders/csdn/csdn_spider.js | 8 +- spiders/example_juejin/juejin/pipelines.py | 3 +- spiders/realestate/realestate/__init__.py | 0 spiders/realestate/realestate/items.py | 37 ++++++ spiders/realestate/realestate/middlewares.py | 103 ++++++++++++++++ spiders/realestate/realestate/pipelines.py | 25 ++++ spiders/realestate/realestate/settings.py | 89 ++++++++++++++ .../realestate/realestate/spiders/__init__.py | 4 + .../realestate/realestate/spiders/lianjia.py | 31 +++++ spiders/realestate/scrapy.cfg | 11 ++ 16 files changed, 456 insertions(+), 9 deletions(-) create mode 100644 frontend/src/store/modules/schedule.js create mode 100644 spiders/realestate/realestate/__init__.py create mode 100644 spiders/realestate/realestate/items.py create mode 100644 spiders/realestate/realestate/middlewares.py create mode 100644 spiders/realestate/realestate/pipelines.py create mode 100644 spiders/realestate/realestate/settings.py create mode 100644 spiders/realestate/realestate/spiders/__init__.py create mode 100644 spiders/realestate/realestate/spiders/lianjia.py create mode 100644 spiders/realestate/scrapy.cfg diff --git a/crawlab/utils/node.py b/crawlab/utils/node.py index 07a45c01..3a0b7b92 100644 --- a/crawlab/utils/node.py +++ b/crawlab/utils/node.py @@ -33,9 +33,10 @@ def update_nodes_status(refresh=False): # new node if node is None: - node = {'_id': node_name, 'name': node_name, 'status': node_status} + node = {'_id': node_name, 'name': node_name, 'status': node_status, 'ip': 'localhost', 'port': '8000'} db_manager.save('nodes', node) + # existing node else: node['status'] = node_status db_manager.save('nodes', node) diff --git a/frontend/src/i18n/zh.js b/frontend/src/i18n/zh.js index ff19069b..7e127114 100644 --- a/frontend/src/i18n/zh.js +++ b/frontend/src/i18n/zh.js @@ -8,6 +8,7 @@ export default { 'Task': '任务', 'Tasks': '任务', 'Task Detail': '任务详情', + 'Schedules': '定时任务', 'Deploys': '部署', // 标签 diff --git a/frontend/src/router/index.js b/frontend/src/router/index.js index 46b1e741..9cf2acb0 100644 --- a/frontend/src/router/index.js +++ b/frontend/src/router/index.js @@ -140,7 +140,7 @@ export const constantRouterMap = [ title: 'Schedules', icon: 'fa fa-calendar' }, - hidden: true, + hidden: false, children: [ { path: '', diff --git a/frontend/src/store/index.js b/frontend/src/store/index.js index 25c179ba..92653f15 100644 --- a/frontend/src/store/index.js +++ b/frontend/src/store/index.js @@ -9,6 +9,7 @@ import spider from './modules/spider' import deploy from './modules/deploy' import task from './modules/task' import file from './modules/file' +import schedule from './modules/schedule' import lang from './modules/lang' import getters from './getters' @@ -25,6 +26,7 @@ const store = new Vuex.Store({ deploy, task, file, + schedule, lang }, getters diff --git a/frontend/src/store/modules/schedule.js b/frontend/src/store/modules/schedule.js new file mode 100644 index 00000000..04174f3a --- /dev/null +++ b/frontend/src/store/modules/schedule.js @@ -0,0 +1,34 @@ +import request from '../../api/request' + +const state = { + scheduleList: [], + scheduleForm: {} +} + +const getters = {} + +const mutations = { + SET_SCHEDULE_LIST (state, value) { + state.scheduleList = value + }, + SET_SCHEDULE_FORM (state, value) { + state.scheduleForm = value + } +} + +const actions = { + getScheduleList ({ state, commit }) { + request.get('/schedules') + .then(response => { + commit('SET_SCHEDULE_LIST', response.data.items) + }) + } +} + +export default { + namespaced: true, + state, + getters, + mutations, + actions +} diff --git a/frontend/src/views/schedule/ScheduleList.vue b/frontend/src/views/schedule/ScheduleList.vue index d1b8a5bb..b0dbb209 100644 --- a/frontend/src/views/schedule/ScheduleList.vue +++ b/frontend/src/views/schedule/ScheduleList.vue @@ -1,15 +1,121 @@ diff --git a/spiders/csdn/csdn_spider.js b/spiders/csdn/csdn_spider.js index edda3b00..0f65c0ad 100644 --- a/spiders/csdn/csdn_spider.js +++ b/spiders/csdn/csdn_spider.js @@ -1,6 +1,10 @@ const puppeteer = require('puppeteer'); const MongoClient = require('mongodb').MongoClient; +const MONGO_HOST = process.env.MONGO_HOST; +const MONGO_PORT = process.env.MONGO_PORT; +const MONGO_DB = process.env.MONGO_DB; + (async () => { // browser const browser = await (puppeteer.launch({ @@ -53,8 +57,8 @@ const MongoClient = require('mongodb').MongoClient; }); // open database connection - const client = await MongoClient.connect('mongodb://127.0.0.1:27017'); - let db = await client.db('crawlab_test'); + const client = await MongoClient.connect(`mongodb://${MONGO_HOST}:${MONGO_PORT}`); + let db = await client.db(MONGO_DB); const colName = process.env.CRAWLAB_COLLECTION || 'results_juejin'; const taskId = process.env.CRAWLAB_TASK_ID; const col = db.collection(colName); diff --git a/spiders/example_juejin/juejin/pipelines.py b/spiders/example_juejin/juejin/pipelines.py index 4a497f54..1c4ffdc1 100644 --- a/spiders/example_juejin/juejin/pipelines.py +++ b/spiders/example_juejin/juejin/pipelines.py @@ -9,9 +9,8 @@ import os from pymongo import MongoClient MONGO_HOST = os.environ['MONGO_HOST'] -MONGO_PORT = os.environ['MONGO_PORT'] +MONGO_PORT = int(os.environ['MONGO_PORT']) MONGO_DB = os.environ['MONGO_DB'] -print(MONGO_HOST) class JuejinPipeline(object): diff --git a/spiders/realestate/realestate/__init__.py b/spiders/realestate/realestate/__init__.py new file mode 100644 index 00000000..e69de29b diff --git a/spiders/realestate/realestate/items.py b/spiders/realestate/realestate/items.py new file mode 100644 index 00000000..189b92ed --- /dev/null +++ b/spiders/realestate/realestate/items.py @@ -0,0 +1,37 @@ +# -*- coding: utf-8 -*- + +# Define here the models for your scraped items +# +# See documentation in: +# https://doc.scrapy.org/en/latest/topics/items.html + +import scrapy + + +class RealEstateItem(scrapy.Item): + # _id + _id = scrapy.Field() + + # task_id + task_id = scrapy.Field() + + # 房产名 + name = scrapy.Field() + + # url + url = scrapy.Field() + + # 类别 + type = scrapy.Field() + + # 价格（万） + price = scrapy.Field() + + # 大小 + size = scrapy.Field() + + # 小区 + region = scrapy.Field() + + # 城市 + city = scrapy.Field() diff --git a/spiders/realestate/realestate/middlewares.py b/spiders/realestate/realestate/middlewares.py new file mode 100644 index 00000000..ed845f57 --- /dev/null +++ b/spiders/realestate/realestate/middlewares.py @@ -0,0 +1,103 @@ +# -*- coding: utf-8 -*- + +# Define here the models for your spider middleware +# +# See documentation in: +# https://doc.scrapy.org/en/latest/topics/spider-middleware.html + +from scrapy import signals + + +class RealestateSpiderMiddleware(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) + + +class RealestateDownloaderMiddleware(object): + # Not all methods need to be defined. If a method is not defined, + # scrapy acts as if the downloader 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_request(self, request, spider): + # Called for each request that goes through the downloader + # middleware. + + # Must either: + # - return None: continue processing this request + # - or return a Response object + # - or return a Request object + # - or raise IgnoreRequest: process_exception() methods of + # installed downloader middleware will be called + return None + + def process_response(self, request, response, spider): + # Called with the response returned from the downloader. + + # Must either; + # - return a Response object + # - return a Request object + # - or raise IgnoreRequest + return response + + def process_exception(self, request, exception, spider): + # Called when a download handler or a process_request() + # (from other downloader middleware) raises an exception. + + # Must either: + # - return None: continue processing this exception + # - return a Response object: stops process_exception() chain + # - return a Request object: stops process_exception() chain + pass + + def spider_opened(self, spider): + spider.logger.info('Spider opened: %s' % spider.name) diff --git a/spiders/realestate/realestate/pipelines.py b/spiders/realestate/realestate/pipelines.py new file mode 100644 index 00000000..a73934b3 --- /dev/null +++ b/spiders/realestate/realestate/pipelines.py @@ -0,0 +1,25 @@ +# -*- 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 = os.environ['MONGO_HOST'] +MONGO_PORT = int(os.environ['MONGO_PORT']) +MONGO_DB = os.environ['MONGO_DB'] + + +class MongoPipeline(object): + mongo = MongoClient(host=MONGO_HOST, port=MONGO_PORT) + db = mongo[MONGO_DB] + col_name = os.environ.get('CRAWLAB_COLLECTION') + 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 diff --git a/spiders/realestate/realestate/settings.py b/spiders/realestate/realestate/settings.py new file mode 100644 index 00000000..da1ada29 --- /dev/null +++ b/spiders/realestate/realestate/settings.py @@ -0,0 +1,89 @@ +# -*- coding: utf-8 -*- + +# Scrapy settings for realestate project +# +# For simplicity, this file contains only settings considered important or +# commonly used. You can find more settings consulting the documentation: +# +# https://doc.scrapy.org/en/latest/topics/settings.html +# https://doc.scrapy.org/en/latest/topics/downloader-middleware.html +# https://doc.scrapy.org/en/latest/topics/spider-middleware.html + +BOT_NAME = 'realestate' + +SPIDER_MODULES = ['realestate.spiders'] +NEWSPIDER_MODULE = 'realestate.spiders' + +# Crawl responsibly by identifying yourself (and your website) on the user-agent +# USER_AGENT = 'realestate (+http://www.yourdomain.com)' + +# 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 https://doc.scrapy.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 https://doc.scrapy.org/en/latest/topics/spider-middleware.html +# SPIDER_MIDDLEWARES = { +# 'realestate.middlewares.RealestateSpiderMiddleware': 543, +# } + +# Enable or disable downloader middlewares +# See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html +# DOWNLOADER_MIDDLEWARES = { +# 'realestate.middlewares.RealestateDownloaderMiddleware': 543, +# } + +# Enable or disable extensions +# See https://doc.scrapy.org/en/latest/topics/extensions.html +# EXTENSIONS = { +# 'scrapy.extensions.telnet.TelnetConsole': None, +# } + +# Configure item pipelines +# See https://doc.scrapy.org/en/latest/topics/item-pipeline.html +ITEM_PIPELINES = { + 'realestate.pipelines.MongoPipeline': 300, +} + +# Enable and configure the AutoThrottle extension (disabled by default) +# See https://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 https://doc.scrapy.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' diff --git a/spiders/realestate/realestate/spiders/__init__.py b/spiders/realestate/realestate/spiders/__init__.py new file mode 100644 index 00000000..ebd689ac --- /dev/null +++ b/spiders/realestate/realestate/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. diff --git a/spiders/realestate/realestate/spiders/lianjia.py b/spiders/realestate/realestate/spiders/lianjia.py new file mode 100644 index 00000000..cad054f3 --- /dev/null +++ b/spiders/realestate/realestate/spiders/lianjia.py @@ -0,0 +1,31 @@ +# -*- coding: utf-8 -*- +import scrapy + +from realestate.items import RealEstateItem + + +class LianjiaSpider(scrapy.Spider): + name = 'lianjia' + allowed_domains = ['lianjia.com'] + start_urls = ['https://cq.lianjia.com/ershoufang/'] + + def start_requests(self): + for i in range(100): + url = 'https://cq.lianjia.com/ershoufang/pg%s' % i + yield scrapy.Request(url=url) + + def parse(self, response): + for item in response.css('.sellListContent > li'): + yield RealEstateItem( + name=item.css('.title > a::text').extract_first(), + url=item.css('.title > a::attr("href")').extract_first(), + type='secondhand', + price=item.css('.totalPrice > span::text').extract_first(), + region=item.css('.houseInfo > a::text').extract_first(), + size=item.css('.houseInfo::text').extract_first().split(' | ')[2] + ) + + # 分页 + # a_next = response.css('.house-lst-page-box > a')[-1] + # href = a_next.css('a::attr("href")') + # yield scrapy.Response(url='https://cq.lianjia.com' + href) diff --git a/spiders/realestate/scrapy.cfg b/spiders/realestate/scrapy.cfg new file mode 100644 index 00000000..d630e123 --- /dev/null +++ b/spiders/realestate/scrapy.cfg @@ -0,0 +1,11 @@ +# Automatically created by: scrapy startproject +# +# For more information about the [deploy] section see: +# https://scrapyd.readthedocs.io/en/latest/deploy.html + +[settings] +default = realestate.settings + +[deploy] +#url = http://localhost:6800/ +project = realestate