diff --git a/crawlab/routes/sites.py b/crawlab/routes/sites.py index d9bd4593..6874af2b 100644 --- a/crawlab/routes/sites.py +++ b/crawlab/routes/sites.py @@ -56,10 +56,17 @@ class SiteApi(BaseApi): sort_direction=ASCENDING ) + sites = [] + for site in items: + # get spider count + site['spider_count'] = db_manager.count('spiders', {'site': site['_id']}) + + sites.append(site) + return { 'status': 'ok', 'total_count': db_manager.count(self.col_name, filter_), 'page_num': page_num, 'page_size': page_size, - 'items': jsonify(items) + 'items': jsonify(sites) } diff --git a/crawlab/routes/spiders.py b/crawlab/routes/spiders.py index 5473d824..51bae78c 100644 --- a/crawlab/routes/spiders.py +++ b/crawlab/routes/spiders.py @@ -128,6 +128,12 @@ class SpiderApi(BaseApi): if last_task is not None: spider['task_ts'] = last_task['create_ts'] + # get site + if spider.get('site') is not None: + site = db_manager.get('sites', spider['site']) + if site is not None: + spider['site_name'] = site['name'] + # file stats stats = get_file_suffix_stats(dir_path) diff --git a/frontend/src/i18n/zh.js b/frontend/src/i18n/zh.js index a6c9a5b6..dd1d529e 100644 --- a/frontend/src/i18n/zh.js +++ b/frontend/src/i18n/zh.js @@ -138,6 +138,7 @@ export default { 'Category': '类别', 'Select': '请选择', 'Select Category': '请选择类别', + 'Spider Count': '爬虫数', // 文件 'Choose Folder': '选择文件', diff --git a/frontend/src/views/site/SiteList.vue b/frontend/src/views/site/SiteList.vue index d4393a42..9c053dc5 100644 --- a/frontend/src/views/site/SiteList.vue +++ b/frontend/src/views/site/SiteList.vue @@ -41,6 +41,17 @@ + + + >> .el-select .el-select__caret { line-height: 32px; } + + .table >>> .domain { + text-decoration: underline; + } diff --git a/frontend/src/views/spider/SpiderList.vue b/frontend/src/views/spider/SpiderList.vue index 14a9ffea..874dcc0b 100644 --- a/frontend/src/views/spider/SpiderList.vue +++ b/frontend/src/views/spider/SpiderList.vue @@ -160,8 +160,9 @@ export default { // tableData, columns: [ { name: 'name', label: 'Name', width: 'auto' }, - { name: 'type', label: 'Spider Type', width: '160', sortable: true }, - { name: 'lang', label: 'Language', width: '160', sortable: true }, + { name: 'site_name', label: 'Site', width: '120' }, + { name: 'type', label: 'Spider Type', width: '120', sortable: true }, + { name: 'lang', label: 'Language', width: '120', sortable: true }, { name: 'task_ts', label: 'Last Run', width: '160' }, { name: 'last_7d_tasks', label: 'Last 7-Day Tasks', width: '80' }, { name: 'last_5_errors', label: 'Last 5-Run Errors', width: '80' } diff --git a/spiders/jd/jd/__init__.py b/spiders/jd/jd/__init__.py new file mode 100644 index 00000000..e69de29b diff --git a/spiders/jd/jd/items.py b/spiders/jd/jd/items.py new file mode 100644 index 00000000..9a7ba1cb --- /dev/null +++ b/spiders/jd/jd/items.py @@ -0,0 +1,14 @@ +# -*- 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 JdItem(scrapy.Item): + # define the fields for your item here like: + name = scrapy.Field() + price = scrapy.Field() diff --git a/spiders/jd/jd/middlewares.py b/spiders/jd/jd/middlewares.py new file mode 100644 index 00000000..6fceded5 --- /dev/null +++ b/spiders/jd/jd/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 JdSpiderMiddleware(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 JdDownloaderMiddleware(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/jd/jd/pipelines.py b/spiders/jd/jd/pipelines.py new file mode 100644 index 00000000..b862b7e7 --- /dev/null +++ b/spiders/jd/jd/pipelines.py @@ -0,0 +1,17 @@ +# -*- coding: utf-8 -*- + +# Define your item pipelines here +# +# Don't forget to add your pipeline to the ITEM_PIPELINES setting +# See: https://doc.scrapy.org/en/latest/topics/item-pipeline.html +from pymongo import MongoClient + + +class JdPipeline(object): + mongo = MongoClient(host=MONGO_HOST, port=MONGO_PORT) + db = mongo[MONGO_DB] + col_name = os.environ.get('CRAWLAB_COLLECTION') or 'jd_products' + col = db[col_name] + + def process_item(self, item, spider): + return item diff --git a/spiders/jd/jd/settings.py b/spiders/jd/jd/settings.py new file mode 100644 index 00000000..d83206b2 --- /dev/null +++ b/spiders/jd/jd/settings.py @@ -0,0 +1,90 @@ +# -*- coding: utf-8 -*- + +# Scrapy settings for jd 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 = 'jd' + +SPIDER_MODULES = ['jd.spiders'] +NEWSPIDER_MODULE = 'jd.spiders' + + +# Crawl responsibly by identifying yourself (and your website) on the user-agent +#USER_AGENT = 'jd (+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 = { +# 'jd.middlewares.JdSpiderMiddleware': 543, +#} + +# Enable or disable downloader middlewares +# See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html +#DOWNLOADER_MIDDLEWARES = { +# 'jd.middlewares.JdDownloaderMiddleware': 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 = { + 'jd.pipelines.JdPipeline': 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/jd/jd/spiders/__init__.py b/spiders/jd/jd/spiders/__init__.py new file mode 100644 index 00000000..ebd689ac --- /dev/null +++ b/spiders/jd/jd/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/jd/jd/spiders/jd_spider.py b/spiders/jd/jd/spiders/jd_spider.py new file mode 100644 index 00000000..01113a7e --- /dev/null +++ b/spiders/jd/jd/spiders/jd_spider.py @@ -0,0 +1,11 @@ +# -*- coding: utf-8 -*- +import scrapy + + +class JdSpiderSpider(scrapy.Spider): + name = 'jd_spider' + allowed_domains = ['jd.com'] + start_urls = ['http://jd.com/'] + + def parse(self, response): + pass diff --git a/spiders/jd/scrapy.cfg b/spiders/jd/scrapy.cfg new file mode 100644 index 00000000..87cf0280 --- /dev/null +++ b/spiders/jd/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 = jd.settings + +[deploy] +#url = http://localhost:6800/ +project = jd