From 607ce70f5c7c71b2eaa2c88c7b8e210925eaac0e Mon Sep 17 00:00:00 2001 From: marvzhang Date: Sat, 23 Nov 2019 18:13:47 +0800 Subject: [PATCH] =?UTF-8?q?=E5=87=86=E5=A4=87=E5=8F=AF=E9=85=8D=E7=BD=AE?= =?UTF-8?q?=E7=88=AC=E8=99=AB?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- backend/conf/config.yml | 2 +- backend/main.go | 2 + backend/routes/config_spider.go | 55 ++++++++++ backend/services/node.go | 2 +- backend/template/Spiderfile | 12 ++ .../config_spider/config_spider/__init__.py | 0 .../config_spider/config_spider/items.py | 14 +++ .../config_spider/middlewares.py | 103 ++++++++++++++++++ .../config_spider/config_spider/pipelines.py | 11 ++ .../config_spider/config_spider/settings.py | 90 +++++++++++++++ .../config_spider/spiders/__init__.py | 4 + .../config_spider/spiders/spider.py | 11 ++ backend/template/config_spider/scrapy.cfg | 11 ++ 13 files changed, 315 insertions(+), 2 deletions(-) create mode 100644 backend/routes/config_spider.go create mode 100644 backend/template/Spiderfile create mode 100644 backend/template/config_spider/config_spider/__init__.py create mode 100644 backend/template/config_spider/config_spider/items.py create mode 100644 backend/template/config_spider/config_spider/middlewares.py create mode 100644 backend/template/config_spider/config_spider/pipelines.py create mode 100644 backend/template/config_spider/config_spider/settings.py create mode 100644 backend/template/config_spider/config_spider/spiders/__init__.py create mode 100644 backend/template/config_spider/config_spider/spiders/spider.py create mode 100644 backend/template/config_spider/scrapy.cfg diff --git a/backend/conf/config.yml b/backend/conf/config.yml index 3805762a..a5e0b23b 100644 --- a/backend/conf/config.yml +++ b/backend/conf/config.yml @@ -20,7 +20,7 @@ log: server: host: 0.0.0.0 port: 8000 - master: "N" + master: "Y" secret: "crawlab" register: # mac地址 或者 ip地址，如果是ip，则需要手动指定IP diff --git a/backend/main.go b/backend/main.go index 2c92ab37..c9e4805d 100644 --- a/backend/main.go +++ b/backend/main.go @@ -140,6 +140,8 @@ func main() { authGroup.GET("/spiders/:id/dir", routes.GetSpiderDir) // 爬虫目录 authGroup.GET("/spiders/:id/stats", routes.GetSpiderStats) // 爬虫统计数据 authGroup.GET("/spider/types", routes.GetSpiderTypes) // 爬虫类型 + // 可配置爬虫 + authGroup.PUT("/config_spiders", routes.PutConfigSpider) // 添加可配置爬虫 // 任务 authGroup.GET("/tasks", routes.GetTaskList) // 任务列表 authGroup.GET("/tasks/:id", routes.GetTask) // 任务详情 diff --git a/backend/routes/config_spider.go b/backend/routes/config_spider.go new file mode 100644 index 00000000..6fa2927b --- /dev/null +++ b/backend/routes/config_spider.go @@ -0,0 +1,55 @@ +package routes + +import ( + "github.com/gin-gonic/gin" + "gopkg.in/yaml.v2" + "io/ioutil" + "net/http" +) + +type Field struct { + Name string `yaml:"name" json:"name"` + Css string `yaml:"css" json:"css"` + Xpath string `yaml:"xpath" json:"xpath"` + Attr string `yaml:"attr" json:"attr"` + Stage string `yaml:"stage" json:"stage"` +} + +type Stage struct { + List bool `yaml:"list" json:"list"` + Css string `yaml:"css" json:"css"` + Xpath string `yaml:"xpath" json:"xpath"` + Fields []Field `yaml:"fields" json:"fields"` +} + +type ConfigSpiderData struct { + Version string `yaml:"version" json:"version"` + StartUrl string `yaml:"startUrl" json:"start_url"` + Stages map[string]Stage `yaml:"stages" json:"stages"` +} + +func PutConfigSpider(c *gin.Context) { + // 构造配置数据 + data := ConfigSpiderData{} + + // 读取YAML文件 + yamlFile, err := ioutil.ReadFile("./template/Spiderfile") + if err != nil { + HandleError(http.StatusInternalServerError, c, err) + return + } + + // 反序列化 + if err := yaml.Unmarshal(yamlFile, &data); err != nil { + HandleError(http.StatusInternalServerError, c, err) + return + } + + // TODO: 生成爬虫文件 + + c.JSON(http.StatusOK, Response{ + Status: "ok", + Message: "success", + Data: data, + }) +} diff --git a/backend/services/node.go b/backend/services/node.go index dffe5ac9..be916f10 100644 --- a/backend/services/node.go +++ b/backend/services/node.go @@ -258,7 +258,7 @@ func InitNodeService() error { return err } - // 如果为主节点，每30秒刷新所有节点信息 + // 如果为主节点，每10秒刷新所有节点信息 if model.IsMaster() { spec := "*/10 * * * * *" if _, err := c.AddFunc(spec, UpdateNodeStatus); err != nil { diff --git a/backend/template/Spiderfile b/backend/template/Spiderfile new file mode 100644 index 00000000..7004bac5 --- /dev/null +++ b/backend/template/Spiderfile @@ -0,0 +1,12 @@ +version: 0.4.0 +startUrl: "https://baidu.com/s?wd=crawlab" +stages: + stage1: + list: false # default: false + css: "#content_left > .result" + fields: + - name: "title" + css: "a" + - name: "url" + css: "a" + attr: "href" diff --git a/backend/template/config_spider/config_spider/__init__.py b/backend/template/config_spider/config_spider/__init__.py new file mode 100644 index 00000000..e69de29b diff --git a/backend/template/config_spider/config_spider/items.py b/backend/template/config_spider/config_spider/items.py new file mode 100644 index 00000000..9784807c --- /dev/null +++ b/backend/template/config_spider/config_spider/items.py @@ -0,0 +1,14 @@ +# -*- coding: utf-8 -*- + +# Define here the models for your scraped items +# +# See documentation in: +# https://docs.scrapy.org/en/latest/topics/items.html + +import scrapy + + +class ConfigSpiderItem(scrapy.Item): + # define the fields for your item here like: + # name = scrapy.Field() + pass diff --git a/backend/template/config_spider/config_spider/middlewares.py b/backend/template/config_spider/config_spider/middlewares.py new file mode 100644 index 00000000..e864bd0b --- /dev/null +++ b/backend/template/config_spider/config_spider/middlewares.py @@ -0,0 +1,103 @@ +# -*- coding: utf-8 -*- + +# Define here the models for your spider middleware +# +# See documentation in: +# https://docs.scrapy.org/en/latest/topics/spider-middleware.html + +from scrapy import signals + + +class ConfigSpiderSpiderMiddleware(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 Request, 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 ConfigSpiderDownloaderMiddleware(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/backend/template/config_spider/config_spider/pipelines.py b/backend/template/config_spider/config_spider/pipelines.py new file mode 100644 index 00000000..5a61b924 --- /dev/null +++ b/backend/template/config_spider/config_spider/pipelines.py @@ -0,0 +1,11 @@ +# -*- coding: utf-8 -*- + +# Define your item pipelines here +# +# Don't forget to add your pipeline to the ITEM_PIPELINES setting +# See: https://docs.scrapy.org/en/latest/topics/item-pipeline.html + + +class ConfigSpiderPipeline(object): + def process_item(self, item, spider): + return item diff --git a/backend/template/config_spider/config_spider/settings.py b/backend/template/config_spider/config_spider/settings.py new file mode 100644 index 00000000..c1469614 --- /dev/null +++ b/backend/template/config_spider/config_spider/settings.py @@ -0,0 +1,90 @@ +# -*- coding: utf-8 -*- + +# Scrapy settings for config_spider project +# +# For simplicity, this file contains only settings considered important or +# commonly used. You can find more settings consulting the documentation: +# +# https://docs.scrapy.org/en/latest/topics/settings.html +# https://docs.scrapy.org/en/latest/topics/downloader-middleware.html +# https://docs.scrapy.org/en/latest/topics/spider-middleware.html + +BOT_NAME = 'config_spider' + +SPIDER_MODULES = ['config_spider.spiders'] +NEWSPIDER_MODULE = 'config_spider.spiders' + + +# Crawl responsibly by identifying yourself (and your website) on the user-agent +#USER_AGENT = 'config_spider (+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://docs.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://docs.scrapy.org/en/latest/topics/spider-middleware.html +#SPIDER_MIDDLEWARES = { +# 'config_spider.middlewares.ConfigSpiderSpiderMiddleware': 543, +#} + +# Enable or disable downloader middlewares +# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html +#DOWNLOADER_MIDDLEWARES = { +# 'config_spider.middlewares.ConfigSpiderDownloaderMiddleware': 543, +#} + +# Enable or disable extensions +# See https://docs.scrapy.org/en/latest/topics/extensions.html +#EXTENSIONS = { +# 'scrapy.extensions.telnet.TelnetConsole': None, +#} + +# Configure item pipelines +# See https://docs.scrapy.org/en/latest/topics/item-pipeline.html +#ITEM_PIPELINES = { +# 'config_spider.pipelines.ConfigSpiderPipeline': 300, +#} + +# Enable and configure the AutoThrottle extension (disabled by default) +# See https://docs.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://docs.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/backend/template/config_spider/config_spider/spiders/__init__.py b/backend/template/config_spider/config_spider/spiders/__init__.py new file mode 100644 index 00000000..ebd689ac --- /dev/null +++ b/backend/template/config_spider/config_spider/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/backend/template/config_spider/config_spider/spiders/spider.py b/backend/template/config_spider/config_spider/spiders/spider.py new file mode 100644 index 00000000..04432536 --- /dev/null +++ b/backend/template/config_spider/config_spider/spiders/spider.py @@ -0,0 +1,11 @@ +# -*- coding: utf-8 -*- +import scrapy + + +class SpiderSpider(scrapy.Spider): + name = 'spider' + allowed_domains = ['baidu.com'] + start_urls = ['http://baidu.com/'] + + def parse(self, response): + pass diff --git a/backend/template/config_spider/scrapy.cfg b/backend/template/config_spider/scrapy.cfg new file mode 100644 index 00000000..a78d91e3 --- /dev/null +++ b/backend/template/config_spider/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 = config_spider.settings + +[deploy] +#url = http://localhost:6800/ +project = config_spider