python之Scrapy爬虫案例：豆瓣

1. 运行命令创建项目：scrapy startproject scrapySpider
2. 进入项目目录：cd .\scrapySpider\
3. 运行命令创建爬虫：scrapy genspider douban movie.douban.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
   |   |   |   |-- douban.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. 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())
   

6. 爬取豆瓣案例

• douban.py

  import scrapy
  from scrapy import cmdline
  from scrapy.http import HtmlResponse,Request
  from scrapySpider.items import DoubanItem
  
  class DoubanSpider(scrapy.Spider):
      name = 'douban'
      allowed_domains = ['movie.douban.com']
      start_urls = ['https://movie.douban.com/top250']
  
      def parse(self, response: HtmlResponse,**kwargs):
          video_list = response.xpath('//ol[@class="grid_view"]/li')
          for li in video_list:
              item = DoubanItem()
              item['title'] = li.xpath('.//div[@class="hd"]/a/span[1]/text()').extract_first()
              item['rating'] = li.xpath('.//div[@class="bd"]//span[@class="rating_num"]/text()').extract_first()
              item['quote'] = li.xpath('.//div[@class="bd"]//p[@class="quote"]/span/text()').extract_first()
              detail_url = li.xpath('.//div[@class="hd"]/a/@href').extract_first()
              yield Request(url=detail_url,callback=self.get_detail_info,meta={'item':item})
          #获取下一页数据
          next_page_url = response.xpath('//div[@class="paginator"]//link[@rel="next"]/@href').extract_first()
          if next_page_url:
              yield Request(url=response.urljoin(next_page_url),callback=self.parse)
  
      #重写start_requests获取多页数据
      # def start_requests(self):
      #     for i in range(0,2):
      #         yield Request(url=f'{self.start_urls[0]}?start={i*25}&filter=',dont_filter=True,callback=self.parse)
  
      def get_detail_info(self,response:HtmlResponse):
          item = response.meta['item']
          detail = response.xpath('//span[@class="all hidden"]/text()').extract_first()
          if not detail:
              detail = response.xpath('//div[@id="link-report-intra"]/span[1]/text()').extract_first()
          item['intro'] = detail.strip()
          request item
  
  if __name__ == '__main__':
      cmdline.execute('scrapy crawl douban'.split())
  

• settings.py

  # Scrapy settings for scrapySpider 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 = "scrapySpider"
  
  SPIDER_MODULES = ["scrapySpider.spiders"]
  NEWSPIDER_MODULE = "scrapySpider.spiders"
  
  
  # Crawl responsibly by identifying yourself (and your website) on the user-agent
  # 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"
  
  # 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 = {
  #    "scrapySpider.middlewares.ScrapyspiderSpiderMiddleware": 543,
  #}
  
  # Enable or disable downloader middlewares
  # See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
  DOWNLOADER_MIDDLEWARES = {
     "scrapySpider.middlewares.DoubanDownloaderMiddleware": 543,
  }
  
  # 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 = {
     "scrapySpider.pipelines.MysqlPipeLine": 300,
     "scrapySpider.pipelines.MongoPipeLine": 301,
  }
  
  # 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 DoubanItem(scrapy.Item):
      # define the fields for your item here like:
      # name = scrapy.Field()
      title = scrapy.Field()
      rating = scrapy.Field()
      quote = scrapy.Field()
      intro = 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 pymongo
  
  video_spider = ['douban']
  
  class DoubanPipeline:
      def process_item(self, item, spider):
          print(item)
          return item
  
  
  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()
          # 创建video数据库和相关爬虫表
          if self.spider.name in video_spider:
              self.create_db('video')
  
      '''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)
               if self.spider.name == 'douban':
                   self.create_douban_table()
           except Exception as e:
              print(f'创建{db_name}数据库失败：{e}')
  
      '''创建表douban'''
      def create_douban_table(self):
          sql = f'''
          CREATE TABLE IF NOT EXISTS {self.spider.name}(
          id INT AUTO_INCREMENT,
          title VARCHAR(255),
          rating FLOAT,
          quote VARCHAR(255),
          intro TEXT,
          PRIMARY KEY(id)
          )
          '''
          try:
              self.cursor.execute(sql)
          except Exception as e:
              print(f'创建douban表失败：{e}')
  
      def process_item(self, item, spider):
          if spider.name == 'douban':
              sql = f'''INSERT INTO {spider.name}(title,rating,quote,intro) VALUES(%(title)s,%(rating)s,%(quote)s,%(intro)s)'''
              try:
                  item['rating'] = float(item['rating'])
                  self.cursor.execute(sql,dict(item))
                  self.mysql.commit()
              except Exception as e:
                  print(f'”{item["title"]}”插入失败：{e}')
                  self.mysql.rollback()
          return item
  
      def close_spider(self,spider):
          self.mysql.close()
  
  
  class MongoPipeLine:
  
      def open_spider(self, spider):
          self.spider = spider
          self.mongo = pymongo.MongoClient(host='localhost',port=27017)
          # 创建video数据库和相关爬虫表
          if self.spider.name in video_spider:
              self.cursor = self.mongo['video'][self.spider.name]
  
      def process_item(self, item, spider):
          try:
              self.cursor.insert_one(dict(item))
          except Exception as e:
              print(f'”{item["title"]}”插入失败：{e}')
  
          return item
  
      def close_spider(self, spider):
          self.mongo.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 fake_useragent import UserAgent
  from scrapy.http import Request,HtmlResponse
  from scrapySpider.kuaidaili import Kuaidaili
  
  # useful for handling different item types with a single interface
  from itemadapter import is_item, ItemAdapter
  
  class DoubanDownloaderMiddleware:
  
      def __init__(self):
          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):
          s = cls()
          crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)
          return s
  
      def process_request(self, request: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
          spider.logger.info(f'ip：{request.meta["proxy"]}')
          return None
  
      def process_response(self, request, response:HtmlResponse, spider):
          spider.logger.info(f'ip：{request.meta["proxy"]}')
          if response.status == 200:
              return response
          #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 spider_opened(self, spider):
          spider.logger.info(f'"{spider.name}"Spide')