scrapy爬取 51job

spider.py

# -*- coding: utf-8 -*- import scrapy # .. 上级目录 .当前目录 # 从上级目录中的items文件中引入JobSpidererItem数据模型类 from ..items import JobSpidererItem class JobsSpider(scrapy.Spider): name = 'jobs' allowed_domains = ['search.51job.com'] start_urls = ['http://search.51job.com/jobsearch/search_result.php?fromJs=1&jobarea=010000,020000,030200,040000,080200,00&district=000000&funtype=0000&industrytype=00&issuedate=9&providesalary=99&keyword=python&keywordtype=2&curr_page=1&lang=c&stype=1&postchannel=0000&workyear=99&cotype=99°reefrom=99&jobterm=99&companysize=99&lonlat=0,0&radius=-1&ord_field=0&list_type=0&dibiaoid=0&confirmdate=9','http://search.51job.com/jobsearch/search_result.php?fromJs=1&jobarea=010000,020000,030200,040000,080200,00&district=000000&funtype=0000&industrytype=00&issuedate=9&providesalary=99&keyword=java&keywordtype=2&curr_page=1&lang=c&stype=1&postchannel=0000&workyear=99&cotype=99°reefrom=99&jobterm=99&companysize=99&lonlat=0,0&radius=-1&ord_field=0&list_type=0&dibiaoid=0&confirmdate=9','http://search.51job.com/jobsearch/search_result.php?fromJs=1&jobarea=010000,020000,030200,040000,080200,00&district=000000&funtype=0000&industrytype=00&issuedate=9&providesalary=99&keyword=php&keywordtype=2&curr_page=1&lang=c&stype=1&postchannel=0000&workyear=99&cotype=99°reefrom=99&jobterm=99&companysize=99&lonlat=0,0&radius=-1&ord_field=0&list_type=0&dibiaoid=0&confirmdate=9'] # 请求发送成功并返回响应后，会自动调用parse这个函数 def parse(self, response): # 先找到所有的divs，包裹职位信息的标签 divs = response.xpath('//div[@id="resultList"]/div[@class="el"]') for div in divs: # 找到职位名称 zwmc = div.xpath('p/span/a/text()').extract_first('未知') # 去除职位名称中的空格 zwmc = zwmc.strip() zwmc = zwmc.strip('\n\r') # 找到公司名称 gsmc = div.xpath('span[@class="t2"]//text()').extract_first('未知') # 找到工作地点 gzdd = div.xpath('span[@class="t3"]/text()').extract_first('未知') # 找到职位月薪 zwyx = div.xpath('span[@class="t4"]/text()').extract_first('面议') # 找到发布日期 fbrq = div.xpath('span[@class="t5"]/text()').extract_first('未知') # 创建JobSpidererItem对象，保存找到的数据 item = JobSpidererItem() item['zwmc'] = zwmc item['gsmc'] = gsmc item['zwyx'] = zwyx item['gzdd'] = gzdd item['fbrq'] = fbrq # yield 传递item yield item # 找到下一页的链接地址 next_href = response.xpath('//div[@class="p_in"]/ul/li[last()]/a/@href').extract_first('') # 判断是否有下一页 if next_href: # yield 请求对象 yield scrapy.Request(next_href)

items.py

# -*- 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 # item数据模型 class JobSpidererItem(scrapy.Item): # define the fields for your item here like: # name = scrapy.Field() zwmc = scrapy.Field() # 职位名称 gsmc = scrapy.Field() # 公司名称 zwyx = scrapy.Field() # 职位月薪 gzdd = scrapy.Field() # 工作地点 fbrq = scrapy.Field() # 发布日期

pipelines.py

# -*- 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 import xlwt # 写入excel表格 class JobSpidererPipeline(object): def __init__(self): # 初始化xls表格 self.workbook = xlwt.Workbook(encoding='utf-8') self.sheet = self.workbook.add_sheet(u'51job职位数据') self.sheet.write(0, 0, '职位名称') self.sheet.write(0, 1, '公司名称') self.sheet.write(0, 2, '工作地点') self.sheet.write(0, 3, '职位月薪') self.sheet.write(0, 4, '发布日期') # 定义一个属性记录处理的个数 self.count = 1 # 当爬虫关闭的时候 def close_spider(self,spider): # 保存职位信息 self.workbook.save(u'51job职位信息.xls') # 销毁对象的时候执行 def __del__(self): print '对象被销毁了.......' def process_item(self, item, spider): # 处理item数据 self.sheet.write(self.count, 0, item['zwmc']) self.sheet.write(self.count, 1, item['gsmc']) self.sheet.write(self.count, 2, item['gzdd']) self.sheet.write(self.count, 3, item['zwyx']) self.sheet.write(self.count, 4, item['fbrq']) # 行号+1 self.count += 1 print self.count return item

settings.py

# -*- coding: utf-8 -*- # Scrapy settings for Job_Spiderer 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 = 'Job_Spiderer' SPIDER_MODULES = ['Job_Spiderer.spiders'] NEWSPIDER_MODULE = 'Job_Spiderer.spiders' # Crawl responsibly by identifying yourself (and your website) on the user-agent #USER_AGENT = 'Job_Spiderer (+http://www.yourdomain.com)' # Obey robots.txt rules ROBOTSTXT_OBEY = False # 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 = 1 # 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', 'User-Agent':"Mozilla/5.0 (Windows NT 10.0; WOW64; rv:52.0) Gecko/20100101 Firefox/52.0", } # Enable or disable spider middlewares # See https://doc.scrapy.org/en/latest/topics/spider-middleware.html #SPIDER_MIDDLEWARES = { # 'Job_Spiderer.middlewares.JobSpidererSpiderMiddleware': 543, #} # Enable or disable downloader middlewares # See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html #DOWNLOADER_MIDDLEWARES = { # 'Job_Spiderer.middlewares.JobSpidererDownloaderMiddleware': 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 = { 'Job_Spiderer.pipelines.JobSpidererPipeline': 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'

debug.py

# coding: utf-8 # 引入execute函数 from scrapy.cmdline import execute # 执行命令 execute(['scrapy', 'crawl', 'jobs'])

middlewares.py

# -*- 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 JobSpidererSpiderMiddleware(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 JobSpidererDownloaderMiddleware(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)