# -*- coding: utf-8 -*-
import scrapyclass ChoutiSpider(scrapy.Spider):#爬虫文件的名称：可以指定某一个具体的爬虫文件name = 'chouti'#允许的域名：#allowed_domains = ['www.chouti.com']#起始url列表：工程被执行后就可以获取该列表中url所对应的页面数据start_urls = ['https://dig.chouti.com/']#该方法作用:就是讲起始url列表中指定url对应的页面数据进行解析操作#response参数：就是对起始url发起请求后对应的响应对象def parse(self, response):print(response)

# -*- coding: utf-8 -*-
import scrapyclass QiubaiSpider(scrapy.Spider):name = 'qiubai'#allowed_domains = ['www.fdsfds.com']start_urls = ['https://www.qiushibaike.com/text/']def parse(self, response):#xpath返回的列表元素类型为Selecor类型div_list = response.xpath('//div[@id="content-left"]/div')#声明一个用于存储解析到数据的列表all_data = []for div in div_list:#extract()可以将selector对象中存储的文本内容获取#author = div.xpath('./div[1]/a[2]/h2/text()')[0].extract()author = div.xpath('./div[1]/a[2]/h2/text()').extract_first() #取出第一个元素，不用[0]了--意义同上行content = div.xpath('.//div[@class="content"]/span//text()').extract() #//text获取的内容不止一个，extract()获取多个列表内容content = "".join(content) #将列表转化成字符串dict = {'author':author,'content':content}all_data.append(dict)return all_data#持久化存储方式：#1.基于终端指令：必须保证parse方法有一个可迭代类型对象的返回#2.基于管道

import scrapyclass PipelineproItem(scrapy.Item):# define the fields for your item here like:# name = scrapy.Field()author = scrapy.Field()content = scrapy.Field()

# -*- coding: utf-8 -*-# Scrapy settings for pipeLinePro 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 = 'pipeLinePro'SPIDER_MODULES = ['pipeLinePro.spiders']
NEWSPIDER_MODULE = 'pipeLinePro.spiders'# Crawl responsibly by identifying yourself (and your website) on the user-agent
#USER_AGENT = 'pipeLinePro (+http://www.yourdomain.com)'
USER_AGENT = 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.77 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://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 = {
#    'pipeLinePro.middlewares.PipelineproSpiderMiddleware': 543,
#}# Enable or disable downloader middlewares
# See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
#DOWNLOADER_MIDDLEWARES = {
#    'pipeLinePro.middlewares.PipelineproDownloaderMiddleware': 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 = {'pipeLinePro.pipelines.PipelineproPipeline': 300,'pipeLinePro.pipelines.MyPipeline': 301,
}# 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'

# -*- coding: utf-8 -*-
import scrapy
from pipeLinePro.items import PipelineproItemclass QiubaiSpider(scrapy.Spider):name = 'qiubai'#allowed_domains = ['www.ds.com']start_urls = ['https://www.qiushibaike.com/text/']def parse(self, response):# xpath返回的列表元素类型为Selecor类型div_list = response.xpath('//div[@id="content-left"]/div')# 声明一个用于存储解析到数据的列表all_data = []for div in div_list:# extract()可以将selector对象中存储的文本内容获取# author = div.xpath('./div[1]/a[2]/h2/text()')[0].extract()author = div.xpath('./div[1]/a[2]/h2/text()').extract_first()content = div.xpath('.//div[@class="content"]/span//text()').extract()content = "".join(content)#实例化item对象item = PipelineproItem()#将解析到的数据值存储到item对象中item['author'] = authoritem['content'] = content#将item对象提交给管道yield item# 持久化存储方式：# 1.基于终端指令：必须保证parse方法有一个可迭代类型对象的返回# 2.基于管道:#1.items.py:对该文件中的类进行实例化操作（item对象：存储解析到的数据值）。#2.pipeline.py:管道，作用就是接受爬虫文件提交的item对象，然后将该对象中的数据值进行持久化存储操作

# -*- coding: utf-8 -*-import pymysqlclass PipelineproPipeline(object):#作用：每当爬虫文件向管道提交一次item，该方法就会被调用一次。item参数就是接受到爬虫文件给提交过来的item对象#该方法只有在开始爬虫的时候被调用一次fp = Nonedef open_spider(self,spider): #父类的方法print('开始爬虫')self.fp = open('./qiubai_data.txt', 'w', encoding='utf-8')def process_item(self, item, spider): #父类的方法author = item['author']content = item['content']self.fp.write(author+":"+content)return item#该方法只有在爬虫结束后被调用一次def close_spider(self,spider):  #父类的方法print('爬虫结束')self.fp.close()class MyPipeline(object):conn = Nonecursor = None# 作用：每当爬虫文件向管道提交一次item，该方法就会被调用一次。item参数就是接受到爬虫文件给提交过来的item对象def open_spider(self,spider):self.conn = pymysql.Connect(host="192.168.12.65", port=3306, db="scrapyDB", charset="utf8", user="root")self.cursor = self.conn.cursor()print('mysql')def process_item(self, item, spider):author = item['author']content = item['content']sql = "insert into qiubai values('%s','%s')" % (author,content)  #qiubai是表名try:self.cursor.execute(sql) #执行sqlself.conn.commit() #事务的处理，没有问题提交，有问题回滚except Exception as e:print(e)self.conn.rollback()return item