scrapy 分布式爬取数据同步写入数据库
spider文件
继承RedisCrawlSpider，实现全站爬取数据
import scrapy from scrapy.linkextractors import LinkExtractor from scrapy.spiders import CrawlSpider, Rule from houseBjPro.items import HousebjproItem from scrapy_redis.spiders import RedisCrawlSpider import re """" 爬取58同城北京二手房数据 """ class HousebjSpider(RedisCrawlSpider): name = 'houseBj' # # allowed_domains = ['https://bj.58.com/ershoufang/'] # start_urls = ['https://bj.58.com/ershoufang/'] # 调度器队列的名称 redis_key = 'houseBjurl' rules = ( Rule(LinkExtractor(allow=r'ershoufang/pn\d+/'), callback='parse_item', follow=True), # 爬取分页信息 ) def parse_item(self, response): i = {} house_list = response.xpath('//ul[@class="house-list-wrap"]/li') # 得到房产列表 for h_item in house_list: sum_price = h_item.xpath('./div[@class="price"]/p[1]/b/text()').extract_first() unit_price = h_item.xpath('./div[@class="price"]/p[2]/text()').extract_first() title = h_item.xpath('./div[@class="list-info"]/h2/a/text()').extract_first() house_info = h_item.xpath('./div[@class="list-info"]/p[1]//text()').extract() house_loc = h_item.xpath('./div[@class="list-info"]/p[2]/span//text()').extract() house_info = re.sub(r'\s+',',',"".join(house_info).replace('-','').strip()) house_loc = re.sub(r'\s+',',',"".join(house_loc).replace('-','').strip()) item = HousebjproItem() print(sum_price) print(unit_price) print(house_loc) print(title) print(house_info) item['sum_price'] = sum_price+'万' # 总价 item['unit_price'] =unit_price # 单价 item['title'] = title # 标题 item['house_info'] = house_info # 户型面积信息 item['house_loc'] = house_loc # 地段信息 # print('new_title:{}'.format(new_title)) yield item
pipeline文件
同步写入mysql数据库
import json from twisted.enterprise import adbapi import pymysql class HousebjproPipeline(object): """ 同步写入数据库 """ def __init__(self, conn): self.conn = conn self.cursor = self.conn.cursor() @classmethod def from_settings(cls, settings): # 先将setting中连接数据库所需内容取出，构造一个地点 dbparms = dict( host=settings["MYSQL_HOST"], db=settings["MYSQL_DBNAME"], port=3306, user=settings["MYSQL_USER"], password=settings["MYSQL_PASSWORD"], charset='utf8mb4', # 游标设置 cursorclass=pymysql.cursors.DictCursor, # 设置编码是否使用Unicode use_unicode=True ) conn = pymysql.connect(**dbparms) return cls(conn) def process_item(self, item, spider): insert_sql = """ insert ignore into tongcheng_content(title,sum_price,unit_price,house_info,house_loc ) VALUES(%s,%s,%s,%s,%s) """ try: self.cursor.execute(insert_sql, (item["title"], item["sum_price"], item["unit_price"], item["house_info"], item["house_loc"])) self.conn.commit() except Exception as e: print(e) self.conn.rollback() return item def close_spider(self, spider): self.cursor.close() self.conn.close()
middleware文件
使用ua池
from scrapy import signals import time from scrapy.contrib.downloadermiddleware.useragent import UserAgentMiddleware import random #UA池代码的编写（单独给UA池封装一个下载中间件的一个类） #1，导包UserAgentMiddlware类 class RandomUserAgent(UserAgentMiddleware): def process_request(self, request, spider): #从列表中随机抽选出一个ua值 ua = random.choice(user_agent_list) #ua值进行当前拦截到请求的ua的写入操作 request.headers.setdefault('User-Agent',ua) #批量对拦截到的请求进行ip更换 # class Proxy(object): # def process_request(self, request, spider): # #对拦截到请求的url进行判断（协议头到底是http还是https） # #request.url返回值：http://www.xxx.com # h = request.url.split(':')[0] #请求的协议头 # if h == 'https': # ip = random.choice(PROXY_https) # request.meta['proxy'] = 'https://'+ip # PROXY_https = [ # '120.83.49.90:9000', # '95.189.112.214:35508', # ] user_agent_list = [ "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 " "(KHTML, like Gecko) Chrome/22.0.1207.1 Safari/537.1", "Mozilla/5.0 (X11; CrOS i686 2268.111.0) AppleWebKit/536.11 " "(KHTML, like Gecko) Chrome/20.0.1132.57 Safari/536.11", "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.6 " "(KHTML, like Gecko) Chrome/20.0.1092.0 Safari/536.6", "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.6 " "(KHTML, like Gecko) Chrome/20.0.1090.0 Safari/536.6", "Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/537.1 " "(KHTML, like Gecko) Chrome/19.77.34.5 Safari/537.1", "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/536.5 " "(KHTML, like Gecko) Chrome/19.0.1084.9 Safari/536.5", "Mozilla/5.0 (Windows NT 6.0) AppleWebKit/536.5 " "(KHTML, like Gecko) Chrome/19.0.1084.36 Safari/536.5", "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 " "(KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3", "Mozilla/5.0 (Windows NT 5.1) AppleWebKit/536.3 " "(KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3", "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_8_0) AppleWebKit/536.3 " "(KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3", "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 " "(KHTML, like Gecko) Chrome/19.0.1062.0 Safari/536.3", "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 " "(KHTML, like Gecko) Chrome/19.0.1062.0 Safari/536.3", "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 " "(KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3", "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 " "(KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3", "Mozilla/5.0 (Windows NT 6.1) AppleWebKit/536.3 " "(KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3", "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 " "(KHTML, like Gecko) Chrome/19.0.1061.0 Safari/536.3", "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/535.24 " "(KHTML, like Gecko) Chrome/19.0.1055.1 Safari/535.24", "Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/535.24 " "(KHTML, like Gecko) Chrome/19.0.1055.1 Safari/535.24" ]
setting配置
BOT_NAME = 'houseBjPro' SPIDER_MODULES = ['houseBjPro.spiders'] NEWSPIDER_MODULE = 'houseBjPro.spiders' # Crawl responsibly by identifying yourself (and your website) on the user-agent USER_AGENT = 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.106 Safari/537.36' # 伪装请求载体身份 # Obey robots.txt rules # ROBOTSTXT_OBEY = True ROBOTSTXT_OBEY = False #可以忽略或者不遵守robots协议 #只显示指定类型的日志信息 LOG_LEVEL='ERROR' #开启访问频率限制 AUTOTHROTTLE_ENABLED = True #设置访问开始的延迟 AUTOTHROTTLE_START_DELAY = 5 #设置访问之间的最大延迟 AUTOTHROTTLE_MAX_DELAY = 60 #设置Scrapy 并行发给每台远程服务器的请求数量 AUTOTHROTTLE_TARGET_CONCURRENCY = 1.0 #设置下裁之后的自动延迟 DOWNLOAD_DELAY = 3 # 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 # 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', #} # Enable or disable spider middlewares # See https://doc.scrapy.org/en/latest/topics/spider-middleware.html #SPIDER_MIDDLEWARES = { # 'houseBjPro.middlewares.HousebjproSpiderMiddleware': 543, #} # Enable or disable downloader middlewares # See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html DOWNLOADER_MIDDLEWARES = { 'houseBjPro.middlewares.RandomUserAgent': 542, } # Enable or disable extensions # See https://doc.scrapy.org/en/latest/topics/extensions.html #EXTENSIONS = { # 'scrapy.extensions.telnet.TelnetConsole': None, #} ITEM_PIPELINES = { 'houseBjPro.pipelines.HousebjproPipeline': 300, 'scrapy_redis.pipelines.RedisPipeline': 400 } REDIS_HOST = '127.0.0.1' # 将这句注释掉 REDIS_PORT = 6379 REDIS_ENCODING = 'utf-8' MYSQL_HOST = '49.233.xx.xx' MYSQL_DBNAME = 'spider_db' MYSQL_USER = 'xx' MYSQL_PASSWORD = 'xx' # 增加了一个去重容器类的配置, 作用使用Redis的set集合来存储请求的指纹数据, 从而实现请求去重的持久化 DUPEFILTER_CLASS = "scrapy_redis.dupefilter.RFPDupeFilter" # 使用scrapy-redis组件自己的调度器 SCHEDULER = "scrapy_redis.scheduler.Scheduler" # 配置调度器是否要持久化, 也就是当爬虫结束了, 要不要清空Redis中请求队列和去重指纹的set。如果是True, 就表示要持久化存储, 就不清空数据, 否则清空数据 SCHEDULER_PERSIST = True
