pythonz之Scrapy+selenium爬取腾讯招聘案例

1. 运行命令创建项目：scrapy startproject seleniumScrapySpider
2. 进入项目目录：cd .\seleniumScrapySpider\
3. 运行命令创建爬虫：scrapy genspider seleniumTxWork careers.tencent.com
4. 目录结构说明

   |-- scrapySpider 项目目录
   |   |-- scrapySpider 项目目录
   |   |   |-- spiders 爬虫文件目录
   |   |   |   |-- seleniumTxWork.py 爬虫文件
   |   |   |-- items.py 定义数据模型文件，类似于数据库表的模式或数据结构的定义
   |   |   |-- middlewares.py 定义中间件文件，用于对请求和响应进行处理和修改
   |   |   |-- pipelines.py 定义数据处理管道（Pipeline）文件，用于处理爬取到的数据的组件
   |   |   |-- settings.py 定义配置文件，用于配置 Scrapy 项目的各种设置选项和参数
   |   |-- scrapy.cfg 框架中的配置文件，用于指定项目的结构和元数据信息
   

5. 设置全局chrome驱动，把chrome驱动文件复制到miniconda根目录，不设置驱动运行程序会报“‘chromedriver’ executable needs to be in PATH”错误
6. 创建快代理文件scrapySpider>kuaidaili.py：https://www.kuaidaili.com/

   import requests
   
   
   class Kuaidaili():
       request_url = {
           # 获取代理ip前面
           'getIpSignature': 'https://auth.kdlapi.com/api/get_secret_token',
           # 获取代理ip
           'getIp': 'https://dps.kdlapi.com/api/getdps?secret_id=oy2q5xu76k4s8olx59et&num=1&signature={}'
       }
   
       headers = {
           'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/116.0.0.0 Safari/537.36'
       }
   
       ip_use = '购买代理用户名'
       ip_password = '购买代理密码'
   
       def __init__(self):
           '''创建request会话对象'''
           self.request_session = requests.Session()
           self.request_session.headers.update(self.headers)
   
       # 获取代理ip签名
       @classmethod
       def get_ip_url(cls):
           par = {
               'secret_id': 'oy2q5xu76k4s8olx59et',
               'secret_key': '5xg6gvouc0vszfw0kxs1a8vrw1r6ity7'
           }
           response = requests.post(cls.request_url['getIpSignature'],data=par)
           response_data = response.json()
           return cls.request_url['getIp'].format(response_data['data']['secret_token'])
   
       @classmethod
       def get_ip(cls):
           url = cls.get_ip_url()
           response = requests.get(url)
           return f'http://{cls.ip_use}:{cls.ip_password}@{response.text}/'
   
   if __name__ == '__main__':
       kuaidaili = Kuaidaili()
       print(kuaidaili.get_ip())
   

7. 爬取腾讯招聘案例

• seleniumTxWork.py

  import scrapy
  import scrapy.cmdline
  from scrapy.http import HtmlResponse, Request
  from seleniumScrapySpider.items import SeleniumScrapySpiderItem
  import loguru
  import re
  
  
  class SeleniumTxWorkSpider(scrapy.Spider):
      name = "seleniumTxWork"
      allowed_domains = ["careers.tencent.com"]
      start_urls = ["https://careers.tencent.com/search.html?index={}&keyword=python"]
  
      def parse(self, response: HtmlResponse, **kwargs):
          work_list = response.xpath('//div[@class="recruit-list"]')
          reg = re.compile(r'\n|\s')
          for work in work_list:
              work_item = SeleniumScrapySpiderItem()
              work_item['workName'] = re.sub(reg, '',
                                             work.xpath('.//span[@class="job-recruit-title"]/text()').extract_first())
              work_item['workAddress'] = re.sub(reg, '', work.xpath(
                  './/span[@class="job-recruit-location"]/text()').extract_first())
              work_item['workResponsibility'] = re.sub(reg, '',
                                                       work.xpath('.//p[@class="recruit-text"]/text()').extract_first())
              work_item['workYearsName'] = re.sub(reg, '', work.xpath(
                  './/p[@class="recruit-tips"]/span[5]/text()').extract_first())
              yield work_item
          '''根据分页总数获取其他页数据'''
          page_total = int(response.xpath('//ul[@class="page-list"]/li[last() - 1]/span/text()').extract_first())
          active_page = int(
              response.xpath('//ul[@class="page-list"]/li[@class="page-li active"]/span/text()').extract_first())
          if page_total != active_page:
              active_page += 1
              loguru.logger.info(f'******************总页数{page_total}，开始抓取第 {active_page} 页数据******************')
              yield Request(url=self.start_urls[0].format(active_page))
          else:
              loguru.logger.info('******************数据已全部抓取完毕******************')
  
      def start_requests(self):
          loguru.logger.info('******************开始抓取第 1 页数据******************')
          yield Request(url=self.start_urls[0].format(1))
          '''获取固定页数数据'''
          # for i in range(1,6):
          #     loguru.logger.info(f'******************开始抓取第 {i} 页数据******************')
          #     yield Request(url=self.start_urls[0].format(i))
  
  
  if __name__ == '__main__':
      scrapy.cmdline.execute('scrapy crawl seleniumTxWork'.split())
  
  

• settings.py

  # Scrapy settings for seleniumScrapySpider project
  #
  # For simplicity, this file contains only settings considered important or
  # commonly used. You can find more settings consulting the documentation:
  #
  #     https://docs.scrapy.org/en/latest/topics/settings.html
  #     https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
  #     https://docs.scrapy.org/en/latest/topics/spider-middleware.html
  
  BOT_NAME = "seleniumScrapySpider"
  
  SPIDER_MODULES = ["seleniumScrapySpider.spiders"]
  NEWSPIDER_MODULE = "seleniumScrapySpider.spiders"
  #需要换上自己SCRAPEOPS中的key
  SCRAPEOPS_API_KEY = 'b0a936d4-762b-4270-9e87-a2883c2a683e'
  
  # Crawl responsibly by identifying yourself (and your website) on the user-agent
  # USER_AGENT = "seleniumScrapySpider (+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://docs.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://docs.scrapy.org/en/latest/topics/spider-middleware.html
  # SPIDER_MIDDLEWARES = {
  #    "seleniumScrapySpider.middlewares.SeleniumscrapyspiderSpiderMiddleware": 543,
  # }
  
  # Enable or disable downloader middlewares
  # See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
  DOWNLOADER_MIDDLEWARES = {
      "seleniumScrapySpider.middlewares.SeleniumDownloaderMiddleware": 543,
      'scrapeops_scrapy.middleware.retry.RetryMiddleware': 550,
  }
  
  # Enable or disable extensions
  # See https://docs.scrapy.org/en/latest/topics/extensions.html
  EXTENSIONS = {
      'scrapeops_scrapy.extension.ScrapeOpsMonitor': 500,
  }
  
  # Configure item pipelines
  # See https://docs.scrapy.org/en/latest/topics/item-pipeline.html
  ITEM_PIPELINES = {
      "seleniumScrapySpider.pipelines.MysqlPipeLine": 300,
  }
  
  # Enable and configure the AutoThrottle extension (disabled by default)
  # See https://docs.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://docs.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"
  
  # Set settings whose default value is deprecated to a future-proof value
  REQUEST_FINGERPRINTER_IMPLEMENTATION = "2.7"
  TWISTED_REACTOR = "twisted.internet.asyncioreactor.AsyncioSelectorReactor"
  FEED_EXPORT_ENCODING = "utf-8"
  
  # 日志配置
  LOG_FILE = 'log.log'
  LOG_FILE_APPEND = False
  LOG_LEVEL = 'INFO'
  
  

• items.py

  # Define here the models for your scraped items
  #
  # See documentation in:
  # https://docs.scrapy.org/en/latest/topics/items.html
  
  import scrapy
  
  
  class SeleniumScrapySpiderItem(scrapy.Item):
     workName = scrapy.Field()
     workAddress = scrapy.Field()
     workResponsibility = scrapy.Field()
     workYearsName = scrapy.Field()
  
  

• pipelines.py

  # Define your item pipelines here
  #
  # Don't forget to add your pipeline to the ITEM_PIPELINES setting
  # See: https://docs.scrapy.org/en/latest/topics/item-pipeline.html
  
  
  # useful for handling different item types with a single interface
  from itemadapter import ItemAdapter
  import pymysql
  import loguru
  
  class MysqlPipeLine:
  
      def open_spider(self, spider):
          self.spider = spider
          self.mysql = pymysql.connect(host='localhost',port=3306,user='root',password='root')
          self.cursor = self.mysql.cursor()
          self.create_db('job')
  
      '''创建数据库'''
      def create_db(self,db_name):
           sql = f'''CREATE DATABASE IF NOT EXISTS {db_name}'''
           try:
               self.cursor.execute(sql)
               self.mysql.select_db(db_name)
               self.create_job_table()
           except Exception as e:
               loguru.logger.info(f'创建{db_name}数据库失败：{e}')
  
      '''创建表'''
      def create_job_table(self):
          sql = '''
               CREATE TABLE IF NOT EXISTS txWork(
                      workId INT AUTO_INCREMENT,
                      workName VARCHAR(255),
                      workAddress VARCHAR(255),
                      workResponsibility TEXT,
                      workYearsName VARCHAR(255),
                      PRIMARY KEY(workId)        
              )
             '''
          try:
              self.cursor.execute(sql)
          except Exception as e:
              loguru.logger.info(f'创建TxWork表失败：{e}')
  
      def process_item(self, item, spider):
          sql = f'''INSERT INTO txWork(workName,workAddress,workResponsibility,workYearsName) VALUES(%(workName)s,%(workAddress)s,%(workResponsibility)s,%(workYearsName)s)'''
          try:
              self.cursor.execute(sql, dict(item))
              self.mysql.commit()
              loguru.logger.info(f'”{item["workName"]}”插入成功')
          except Exception as e:
              loguru.logger.info(f'”{item["workName"]}”插入失败：{e}')
              self.mysql.rollback()
          return item
  
      def close_spider(self,spider):
          self.mysql.close()
  
  

• middlewares.py

  # Define here the models for your spider middleware
  #
  # See documentation in:
  # https://docs.scrapy.org/en/latest/topics/spider-middleware.html
  
  from scrapy import signals
  from scrapy.http import HtmlResponse
  from selenium.webdriver import Chrome,ChromeOptions
  from selenium.webdriver.support.wait import WebDriverWait
  from selenium.webdriver.support import expected_conditions
  from selenium.webdriver.common.by import By
  from fake_useragent import UserAgent
  from seleniumScrapySpider.kuaidaili import Kuaidaili
  import loguru
  
  # useful for handling different item types with a single interface
  from itemadapter import is_item, ItemAdapter
  
  
  class SeleniumDownloaderMiddleware:
  
      def __init__(self):
          chrome_options = ChromeOptions()
          chrome_options.add_experimental_option('detach', True)  # 不自动关闭浏览器
          chrome_options.add_experimental_option('excludeSwitches',['enable-automation'])  # 以开发者模式启动调试chrome，可以去掉提示受到自动软件控制
          chrome_options.add_experimental_option('useAutomationExtension', False)  # 去掉提示以开发者模式调用
          chrome_options.add_argument('--start-maximized')  # 最大化运行（全屏窗口）
          self.browser = Chrome(options=chrome_options)
          self.ua = UserAgent()
          self.kuaidaili = Kuaidaili()
          #初始化一个代理ip
          self.first_ip = self.kuaidaili.get_ip()
  
      @classmethod
      def from_crawler(cls, crawler):
          # This method is used by Scrapy to create your spiders.
          s = cls()
          crawler.signals.connect(s.spider_closed, signal=signals.spider_closed)
          return s
  
      def process_request(self, request, spider):
          # 设置UA
          request.headers['User-Agent'] = self.ua.random
          # 设置代理
          request.meta['proxy'] = self.first_ip
          request.meta['download_timeout'] = 5
          return None
  
      def process_response(self, request, response, spider):
          loguru.logger.info(f'代理ip：{request.meta["proxy"]}')
          if response.status == 200:
              self.browser.get(request.url)
              wait = WebDriverWait(self.browser, 10)  # 设置等待时间10s
              wait.until(expected_conditions.presence_of_element_located((By.CLASS_NAME,'recruit-list')))  # 设置判断条件：等待id='kw'的元素加载完成
              return HtmlResponse(url=request.url,body=self.browser.page_source,encoding='utf-8',request=request)
  
          # 代理失效小重新设置代理，并返回request重新请求
          request.meta['proxy'] = self.kuaidaili.get_ip()
          request.meta['download_timeout'] = 2
          return request
  
      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_closed(self, spider):
          self.browser.close()