first spider

first spider using scrapy

Author: coderfruit

first_spider/firstspider/__pycache__/__init__.cpython-36.pyc

@@ -0,0 +1,27 @@
+# -*- coding: utf-8 -*-
+
+# Define here the models for your scraped items
+#
+# See documentation in:
+# https://doc.scrapy.org/en/latest/topics/items.html
+
+importscrapy
+
+
+classFirstspiderItem(scrapy.Item):
+# define the fields for your item here like:
+# name = scrapy.Field()
+positionName=scrapy.Field()
+
+rate=scrapy.Field()
+
+companyName=scrapy.Field()
+
+salary=scrapy.Field()
+
+workLocation=scrapy.Field()
+
+publishTime=scrapy.Field()
+
+
+

first_spider/firstspider/__pycache__/items.cpython-36.pyc

@@ -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
+
+fromscrapyimportsignals
+
+
+classFirstspiderSpiderMiddleware(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
+deffrom_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)
+returns
+
+defprocess_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.
+returnNone
+
+defprocess_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.
+foriinresult:
+yieldi
+
+defprocess_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
+
+defprocess_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).
+forrinstart_requests:
+yieldr
+
+defspider_opened(self, spider):
+spider.logger.info('Spider opened: %s'%spider.name)
+
+
+classFirstspiderDownloaderMiddleware(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
+deffrom_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)
+returns
+
+defprocess_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
+returnNone
+
+defprocess_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
+returnresponse
+
+defprocess_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
+
+defspider_opened(self, spider):
+spider.logger.info('Spider opened: %s'%spider.name)

first_spider/firstspider/__pycache__/pipelines.cpython-36.pyc

@@ -0,0 +1,26 @@
+# -*- 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
+importcsv
+importjson
+
+
+classFirstspiderPipeline(object):
+def__init__(self):
+self.f=open("data.csv",mode="w",newline="")
+self.wr=csv.writer(self.f)
+self.wr.writerow(["职位名称","反馈率","公司名称","薪资","工作地点","发布时间"])
+
+defprocess_item(self, item, spider):
+# data=json.dumps(dict(item),ensure_ascii=False)+",\n"
+# data=dict(item)
+# print(data)
+data=[item["positionName"],item["rate"],item["companyName"],item["salary"],item["workLocation"],item["publishTime"]]
+self.wr.writerow(data)
+returnitem
+
+defclose_spider(self,spider):
+self.f.close()

first_spider/firstspider/__pycache__/settings.cpython-36.pyc

@@ -0,0 +1,92 @@
+# -*- coding: utf-8 -*-
+
+# Scrapy settings for firstspider 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='firstspider'
+
+SPIDER_MODULES= ['firstspider.spiders']
+NEWSPIDER_MODULE='firstspider.spiders'
+
+
+# Crawl responsibly by identifying yourself (and your website) on the user-agent
+#USER_AGENT = 'firstspider (+http://www.yourdomain.com)'
+
+# Obey robots.txt rules
+#是否遵循robot协议，如果要爬取数据，需要将其设置为False或者注释掉
+#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 ={
+#爬虫中间件，可以有多个，后面的数字代表优先级，数字越小，优先级越高
+# 'firstspider.middlewares.FirstspiderSpiderMiddleware': 543,
+#}
+
+# Enable or disable downloader middlewares
+# See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
+#DOWNLOADER_MIDDLEWARES ={
+# 'firstspider.middlewares.FirstspiderDownloaderMiddleware': 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={
+'firstspider.pipelines.FirstspiderPipeline': 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'

first_spider/firstspider/chromedriver.exe

@@ -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.