update SpiderDetail

.idea/httpRequests/http-requests-log.http

@@ -1,3 +1,84 @@
+GET http://localhost:5000/api/files?path=/Users/yeqing/projects/crawlab
+Content-Type: application/json
+
+{}
+
+<> 2019-02-17T105049.200.json
+
+###
+
+GET http://localhost:5000/api/files?path=/Users/yeqing/projects/crawlab
+Content-Type: application/json
+
+{}
+
+<> 2019-02-17T105013.200.json
+
+###
+
+GET http://localhost:5000/api/files?path=/Users/yeqing/projects/crawlab-frontend/src
+Content-Type: application/json
+
+{}
+
+<> 2019-02-17T104952.200.json
+
+###
+
+GET http://localhost:5000/api/files?path=/Users/yeqing/projects/crawlab-frontend
+Content-Type: application/json
+
+{}
+
+<> 2019-02-17T104905.200.json
+
+###
+
+GET http://localhost:5000/api/files?path=/Users/yeqing/projects/crawlab-frontend
+Content-Type: application/json
+
+{}
+
+<> 2019-02-17T104843.200.json
+
+###
+
+GET http://localhost:5000/api/files?path=/Users/yeqing/projects/crawlab-frontend
+Content-Type: application/json
+
+{}
+
+<> 2019-02-17T104612.200.json
+
+###
+
+GET http://localhost:5000/api/files?path=/Users/yeqing/projects/crawlab-frontend
+Content-Type: application/json
+
+{}
+
+<> 2019-02-17T104523.400.json
+
+###
+
+GET http://localhost:5000/api/file?path=/Users/yeqing/projects/crawlab-frontend
+Content-Type: application/json
+
+{}
+
+<> 2019-02-17T104518.404.html
+
+###
+
+GET http://localhost:5000/api/file?path=/Users/yeqing/projects/crawlab-frontend
+Content-Type: application/json
+
+{}
+
+<> 2019-02-17T104351.404.html
+
+###
+
 PUT http://localhost:5000/api/spiders
 Content-Type: application/json
 

app.py

@@ -18,6 +18,7 @@ import routes.nodes
 import routes.spiders
 import routes.deploys
 import routes.tasks
+import routes.files
 import routes.test
 
 # start flask app

constants/file.py

@@ -0,0 +1,3 @@
+class FileType:
+    FILE = 1
+    FOLDER = 2

routes/files.py

@@ -0,0 +1,35 @@
+import os
+
+from flask_restful import reqparse, Resource
+
+from app import api
+from utils import jsonify
+
+
+class FileApi(Resource):
+    parser = reqparse.RequestParser()
+    arguments = []
+
+    def __init__(self):
+        super(FileApi).__init__()
+        self.parser.add_argument('path', type=str)
+
+    def get(self):
+        args = self.parser.parse_args()
+        path = args.get('path')
+        folders = []
+        files = []
+        for _path in os.listdir(path):
+            if os.path.isfile(os.path.join(path, _path)):
+                files.append(_path)
+            elif os.path.isdir(os.path.join(_path)):
+                folders.append(_path)
+        return jsonify({
+            'status': 'ok',
+            'files': sorted(files),
+            'folders': sorted(folders),
+        })
+
+
+api.add_resource(FileApi,
+                 '/api/files')

spiders/taobao/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 = taobao.settings
+
+[deploy]
+#url = http://localhost:6800/
+project = taobao

spiders/taobao/taobao/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 TaobaoItem(scrapy.Item):
+    # define the fields for your item here like:
+    # name = scrapy.Field()
+    pass

spiders/taobao/taobao/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 TaobaoSpiderMiddleware(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 TaobaoDownloaderMiddleware(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)

spiders/taobao/taobao/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://doc.scrapy.org/en/latest/topics/item-pipeline.html
+
+
+class TaobaoPipeline(object):
+    def process_item(self, item, spider):
+        return item

spiders/taobao/taobao/settings.py

@@ -0,0 +1,90 @@
+# -*- coding: utf-8 -*-
+
+# Scrapy settings for taobao 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 = 'taobao'
+
+SPIDER_MODULES = ['taobao.spiders']
+NEWSPIDER_MODULE = 'taobao.spiders'
+
+
+# Crawl responsibly by identifying yourself (and your website) on the user-agent
+#USER_AGENT = 'taobao (+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 = {
+#    'taobao.middlewares.TaobaoSpiderMiddleware': 543,
+#}
+
+# Enable or disable downloader middlewares
+# See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
+#DOWNLOADER_MIDDLEWARES = {
+#    'taobao.middlewares.TaobaoDownloaderMiddleware': 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 = {
+#    'taobao.pipelines.TaobaoPipeline': 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'

spiders/taobao/taobao/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/taobao/taobao/spiders/taobao_spider.py

@@ -0,0 +1,11 @@
+# -*- coding: utf-8 -*-
+import scrapy
+
+
+class TaobaoSpiderSpider(scrapy.Spider):
+    name = 'taobao-spider'
+    allowed_domains = ['taobao.com']
+    start_urls = ['http://taobao.com/']
+
+    def parse(self, response):
+        pass

test/test.http

@@ -44,3 +44,10 @@ Content-Type: application/json
 {}
 
 ###
+### Send GET request with json body by path
+GET http://localhost:5000/api/files?path=/Users/yeqing/projects/crawlab
+Content-Type: application/json
+
+{}
+
+###