Scrapy项目 - 项目源码 - 实现腾讯网站社会招聘信息爬取的爬虫设计
1.tencentSpider.py
# -*- coding: utf-8 -*- import scrapy from Tencent.items import TencentItem #创建爬虫类 class TencentspiderSpider(scrapy.Spider): name = 'tencentSpider'#爬虫名字 allowed_domains = ['tencent.com']#容许爬虫的作用范围 # 定义开始的URL offset = 0 url = 'https://hr.tencent.com/position.php?&start=' #urll='#a' start_urls = [url + str(offset)] # 爬虫开始的URL def parse(self, response): # 继承 item = TencentItem() # 根节点 movies = response.xpath("//tr[@class='odd']|//tr[@class='even']") for each in movies: item['zhiwei']=each.xpath(".//td[@class='l square']/a/text()").extract()[0] item['lianjie'] = each.xpath(".//td[@class='l square']/a/@href").extract()[0] #item['leibie'] = each.xpath("//tr[@class='odd']/td[2]/text()|//tr[@class='even']/td[2]/text()").extract()[0] item['leibie'] = each.xpath("//tr[@class='odd']/td[2]/text()|//tr[@class='even']/td[2]/text()").extract()[0] #data = response.xpath(".//tr[@class='odd']/td[2]|//tr[@class='even']/td[2][descendant-or-self::text()]") #item['leibie'] = data.xpath('string(.)').extract() item['renshu'] = each.xpath("//tr[@class='odd']/td[3]/text()|//tr[@class='even']/td[3]/text()").extract()[0] item['didian'] = each.xpath("//tr[@class='odd']/td[4]/text()|//tr[@class='even']/td[4]/text()").extract()[0] item['shijian'] = each.xpath("//tr[@class='odd']/td[5]/text()|//tr[@class='even']/td[5]/text()").extract()[0] # 异常处理 #if len(quote) != 0: #item['quote'] = quote[0] print(item) yield item if self.offset < 2840: self.offset += 10 # 每次处理完一页之后，重新发送下一页请求 # self offset 自增25，同时拼接为新的URL并调用回调函数，self parse 处理response yield scrapy.Request(self.url + str(self.offset),callback=self.parse)
2.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 class TencentItem(scrapy.Item): # define the fields for your item here like: # name = scrapy.Field() zhiwei = scrapy.Field() lianjie = scrapy.Field() leibie = scrapy.Field() renshu = scrapy.Field() didian = scrapy.Field() shijian = scrapy.Field()
3.main.py
from scrapy import cmdline # cmdline.execute("scrapy crawl tencentSpider".split())
4.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 TencentSpiderMiddleware(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 TencentDownloaderMiddleware(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)
5.pipelines.py
# -*- coding: utf-8 -*- # Define your item pipelines here #Tencent.json #class TencentPipeline(object): # Don't forget to add your pipeline to the ITEM_PIPELINES setting # See: https://doc.scrapy.org/en/latest/topics/item-pipeline.html import json from openpyxl import Workbook class TencentPipeline(object): wb = Workbook() ws = wb.active # 设置表头 ws.append(['职位', '链接', '类型', '人数', '地点', '时间']) def process_item(self, item, spider): # 添加数据 line = [item['zhiwei'],item['lianjie'],item['leibie'],item['renshu'],item['didian'],item['shijian']] self.ws.append(line) # 按行添加 self.wb.save('tencentSpider.xlsx') return item
6.settings.py
# -*- coding: utf-8 -*- # Scrapy settings for Tencent 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 = 'Tencent' SPIDER_MODULES = ['Tencent.spiders'] NEWSPIDER_MODULE = 'Tencent.spiders' # Crawl responsibly by identifying yourself (and your website) on the user-agent USER_AGENT = 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/71.0.3578.98 Safari/537.36' # 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 = { # 'Tencent.middlewares.TencentSpiderMiddleware': 543, #} # Enable or disable downloader middlewares # See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html #DOWNLOADER_MIDDLEWARES = { # 'Tencent.middlewares.TencentDownloaderMiddleware': 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 = { 'Tencent.pipelines.TencentPipeline': 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'
