数据采集与融合技术实践作业3

作业要求

码云仓库链接

一.内容，代码和结果

管道代码如下：

# 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
import threading
from itemadapter import ItemAdapter
import urllib.request
import os
import pathlib
import pymysql
from Practical_work3.items import work1_Item
from Practical_work3.items import work2_Item
from Practical_work3.items import work3_Item

class work1_Pipeline:
    count = 0
    desktopDir = str(pathlib.Path.home()).replace('\\','\\\\') + '\\Desktop'
    threads = []
    def open_spider(self,spider):
        picture_path=self.desktopDir+'\\images'
        if os.path.exists(picture_path):  # 判断文件夹是否存在
            for root, dirs, files in os.walk(picture_path, topdown=False):
                for name in files:
                    os.remove(os.path.join(root, name))  # 删除文件
                for name in dirs:
                    os.rmdir(os.path.join(root, name))  # 删除文件夹
            os.rmdir(picture_path)  # 删除文件夹
        os.mkdir(picture_path)  # 创建文件夹

    def process_item(self, item, spider):
        if isinstance(item,work1_Item):
            url = item['img_url']
            print(url)
            T=threading.Thread(target=self.download_img,args=(url,))
            T.setDaemon(False)
            T.start() 
            self.threads.append(T)
        return item

    def download_img(self,url):
        img_data = urllib.request.urlopen(url=url).read()
        img_path = self.desktopDir + '\\images\\' + str(self.count)+'.jpg'
        with open(img_path, 'wb') as fp:
            fp.write(img_data)
        self.count = self.count + 1
    
    def close_spider(self,spider):
        for t in self.threads:
            t.join() 

class work2_Pipeline:
    def open_spider(self,spider):
        try:
            self.db = pymysql.connect(host='127.0.0.1', user='root', passwd='1a2345678', port=3306,charset='utf8',database='zrc')
            self.cursor = self.db.cursor()
            self.cursor.execute('DROP TABLE IF EXISTS stocktable')
            sql = """CREATE TABLE stocktable(Latest_quotation Double,Chg Double,up_down_amount Double,turnover Double,transaction_volume Double,
            amplitude Double,id varchar(11) PRIMARY KEY,name varchar(32),highest Double, lowest Double,today Double,yesterday Double)"""
            self.cursor.execute(sql)
        except Exception as e:
            print(e)
        
    def process_item(self, item, spider):
        if isinstance(item,work2_Item):
            sql = """INSERT INTO stocktable VALUES (%f,%f,%f,%f,%f,%f,"%s","%s",%f,%f,%f,%f)""" % (item['f2'],item['f3'],item['f4'],item['f5'],item['f6'],
                                                            item['f7'],item['f12'],item['f14'],item['f15'],item['f16'],item['f17'],item['f18'])
            self.cursor.execute(sql)
            self.db.commit()
        return item

    def close_spider(self,spider):
        self.cursor.close()
        self.db.close()


class work3_Pipeline:

    def open_spider(self,spider):
        try:
            self.db = pymysql.connect(host='127.0.0.1', user='root', passwd='1a2345678', port=3306,charset='utf8',database='zrc')
            self.cursor = self.db.cursor()
            self.cursor.execute('DROP TABLE IF EXISTS money')
            sql = """CREATE TABLE money(Currency varchar(32),p1 varchar(18),p2 varchar(18),p3 varchar(18),p4 varchar(18),p5 varchar(18),Time varchar(32))"""
            self.cursor.execute(sql)
        except Exception as e:
            print(e)

    def process_item(self, item, spider):
        if isinstance(item,work3_Item):
            sql = 'INSERT INTO money VALUES ("%s","%s","%s","%s","%s","%s","%s")' % (item['name'],item['price1'],item['price2'],
                                                                                                    item['price3'],item['price4'],item['price5'],item['date'])
            self.cursor.execute(sql)
            self.db.commit()
        return item
    
    def close_spider(self,spider):
        self.cursor.close()
        self.db.close()

上第一题图片是多线程下载，第一题的单线程class如下：

    # 单线程
      def process_item(self, item, spider):
          url = item['img_url']
          print(url)
          img_data = urllib.request.urlopen(url=url).read()
          img_path = self.desktopDir + '\\images\\' + str(self.count)+'.jpg'
          with open(img_path, 'wb') as fp:
              fp.write(img_data)
         self.count = self.count + 1
         return item

第一题的items如下：

import scrapy

class work1_Item(scrapy.Item):
    img_url = scrapy.Field()

第二题：

import scrapy

class work2_Item(scrapy.Item):
    f2 = scrapy.Field()
    f3 = scrapy.Field()
    f4 = scrapy.Field()
    f5 = scrapy.Field()
    f6 = scrapy.Field()
    f7 = scrapy.Field()
    f12 = scrapy.Field()
    f14 = scrapy.Field()
    f15 = scrapy.Field()
    f16 = scrapy.Field()
    f17 = scrapy.Field()
    f18 = scrapy.Field()

第三题：

import scrapy

class work3_Item(scrapy.Item):
    name = scrapy.Field()
    price1 = scrapy.Field()
    price2 = scrapy.Field()
    price3 = scrapy.Field()
    price4 = scrapy.Field()
    price5 = scrapy.Field()
    date = scrapy.Field()

settings:

BOT_NAME = 'Practical_work3'

SPIDER_MODULES = ['Practical_work3.spiders']
NEWSPIDER_MODULE = 'Practical_work3.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/118.0.0.0 Safari/537.36 Edg/118.0.2088.76'
# Obey robots.txt rules
ROBOTSTXT_OBEY = False

LOG_LEVEL = 'ERROR'

ITEM_PIPELINES = {
   'Practical_work3.pipelines.work1_Pipeline': 250,
   'Practical_work3.pipelines.work2_Pipeline': 520,
   'Practical_work3.pipelines.work3_Pipeline': 1314
}

work1:

import scrapy
from Practical_work3.items import work1_Item

class Work1Spider(scrapy.Spider):
    name = 'work1'
    # allowed_domains = ['www.weather.com.cn']
    start_urls = ['http://www.weather.com.cn/']

    def parse(self, response):
        data = response.body.decode()
        selector=scrapy.Selector(text=data) 
        img_datas = selector.xpath('//a/img/@src')
        for img_data in img_datas:
            item = work1_Item()
            item['img_url'] = img_data.extract()
            yield item

work2:

import scrapy
import re
import json
from Practical_work3.items import work2_Item

class Work2Spider(scrapy.Spider):
    name = 'work2'
    # allowed_domains = ['25.push2.eastmoney.com']

    start_urls = ['http://25.push2.eastmoney.com/api/qt/clist/get?cb=jQuery1124021313927342030325_1696658971596&pn=1&pz=20&po=1&np=1&ut=bd1d9ddb04089700cf9c27f6f7426281&fltt=2&invt=2&wbp2u=|0|0|0|web&fid=f3&fs=m:0+t:6,m:0+t:80,m:1+t:2,m:1+t:23,m:0+t:81+s:2048&fields=f2,f3,f4,f5,f6,f7,f12,f14,f15,f16,f17,f18&_=1696658971636']
    def parse(self, response):
        data = response.body.decode()
        item = work2_Item()
        data = re.compile('"diff":\[(.*?)\]',re.S).findall(data)
        columns={'f2':'最新价','f3':'涨跌幅(%)','f4':'涨跌额','f5':'成交量','f6':'成交额','f7':'振幅(%)','f12':'代码','f14':'名称','f15':'最高',
        'f16':'最低','f17':'今开','f18':'昨收'}
        for one_data in re.compile('\{(.*?)\}',re.S).findall(data[0]):
            data_dic = json.loads('{' + one_data + '}')
            for k,v in data_dic.items():
                item[k] = v
            yield item

work3:

import scrapy
from Practical_work3.items import work3_Item

class Work3Spider(scrapy.Spider):
    name = 'work3'
    # allowed_domains = ['www.boc.cn']
    start_urls = ['https://www.boc.cn/sourcedb/whpj/']

    def parse(self, response):
        data = response.body.decode()
        selector=scrapy.Selector(text=data) 
        data_lists = selector.xpath('//table[@align="left"]/tr')
        for data_list in data_lists:
            datas = data_list.xpath('.//td')
            if datas != []:
                item = work3_Item()
                keys = ['name','price1','price2','price3','price4','price5','date']
                str_lists = datas.extract()
                for i in range(len(str_lists)-1):
                    item[keys[i]] = str_lists[i].strip('<td class="pjrq"></td>').strip()
                yield item

第一二三题的运行结果如下，连接mysql在终端上查看：

二.心得

在爬取动态信息时Xpath的使用要注意，在电脑上安装mysql并连接到数据库，刚开始运行时没有到sql的bin目录下运行导致一致报错，可以使用后，由于初始代码需要手动删除表格不然再次运行就会报错，于是加入了表格删除的功能，每次创建前先删除即可，通过本次案例，熟悉了scrapy框架并且学习了把获得的数据存储到数据库中