数据采集第四次作业

作业一

熟练掌握 scrapy 中 Item、Pipeline 数据的序列化输出方法；Scrapy+Xpath+MySQL数据库存储技术路线爬取当当网站图书数据
代码部分

items.py
`

  import scrapy


  class DdbooksItem(scrapy.Item):
      # define the fields for your item here like:
      # name = scrapy.Field()
      title = scrapy.Field()
      author = scrapy.Field()
      date = scrapy.Field()
      publisher = scrapy.Field()
      detail = scrapy.Field()
      price = scrapy.Field()

`

pipelines.py
`

  import pymysql


  class DdbooksPipeline(object):
      def open_spider(self, spider):
          print("opened")
          try:
              self.con = pymysql.connect(host="127.0.0.1", port=3306, user="root", passwd="123456", db="mydb",
                                   charset="utf8")
              self.cursor = self.con.cursor(pymysql.cursors.DictCursor)
              self.cursor.execute("delete from books")
              self.opened = True
              self.count = 0
          except Exception as err:
              print(err)
              self.opened = False

def close_spider(self, spider):
    if self.opened:
        self.con.commit()
        self.con.close()
        self.opened = False
    print("closed")
    print("总共爬取", self.count, "本书籍")

def process_item(self, item, spider):
    try:
        print(item["title"])
        print(item["author"])
        print(item["publisher"])
        print(item["date"])
        print(item["price"])
        print(item["detail"])
        print()
        if self.opened:
            self.cursor.execute(
                "insert into books(bTitle, bAuthor, bPublisher, bDate, bPrice, bDetail)values( % s, % s, % s, "
                "% s, % s, % s)",
                (item["title"], item["author"], item["publisher"], item["date"], item["price"], item["detail"]))
            self.count += 1
    except Exception as err:
        print(err)
    return item

`

settings.py
`

  BOT_NAME = 'DDBooks'

  SPIDER_MODULES = ['DDBooks.spiders']
  NEWSPIDER_MODULE = 'DDBooks.spiders'
  ITEM_PIPELINES = {
     'DDBooks.pipelines.DdbooksPipeline': 300,
  }

`

Books.py

`

  import scrapy
  from bs4 import UnicodeDammit

  from DDBooks.items import DdbooksItem


  class BooksSpider(scrapy.Spider):
      name = 'Books'
      # allowed_domains = ['search.dangdang.com']
      key = 'java'
      source_url = 'http://search.dangdang.com/'

def start_requests(self):
    url = BooksSpider.source_url + '?key=' + BooksSpider.key
    yield scrapy.Request(url=url, callback=self.parse)

def parse(self, response):
    try:
        dammit = UnicodeDammit(response.body, ["utf-8", "gbk"])
        data = dammit.unicode_markup
        selector = scrapy.Selector(text=data)
        lis = selector.xpath("//li['@ddt-pit'][starts-with(@class,'line')]")
        for li in lis:
            title = li.xpath("./a[position()=1]/@title").extract_first()
            price = li.xpath("./p[@class='price']/span[@class='search_now_price']/text()").extract_first()
            author = li.xpath("./p[@class='search_book_author']/span[position()=1]/a/@title").extract_first()
            date = li.xpath(
                "./p[@class='search_book_author']/span[position()=last()-1] / text()").extract_first()
            publisher = li.xpath(
                "./p[@class='search_book_author']/span[position()=last()]/a/@title").extract_first()
            detail = li.xpath("./p[@class='detail']/text()").extract_first()
            # detail有时没有，结果None
            item = DdbooksItem()
            item["title"] = title.strip() if title else ""
            item["author"] = author.strip() if author else ""
            item["date"] = date.strip()[1:] if date else ""
            item["publisher"] = publisher.strip() if publisher else ""
            item["price"] = price.strip() if price else ""
            item["detail"] = detail.strip() if detail else ""
            yield item
        # 最后一页时link为None
        link = selector.xpath(
            "//div[@class='paging']/ul[@name='Fy']/li[@class='next'] / a / @ href").extract_first()
        if link:
            url = response.urljoin(link)
        yield scrapy.Request(url=url, callback=self.parse)
    except Exception as err:
        print(err)

`

运行截图：

心得体会
这次作业书上有实例，通过例子也加深了对MySQL数据库的理解。刚开始source_url不小心用了列表类型，加了[]之后就没有跑出来结果，经改正后才正常。

作业二

要求：熟练掌握 scrapy 中 Item、Pipeline 数据的序列化输出方法；Scrapy+Xpath+MySQL数据库存储技术路线爬取股票相关信息

候选网站：东方财富网：https://www.eastmoney.com/

​ 新浪股票：http://finance.sina.com.cn/stock/

代码部分

items.py
`

  import scrapy


  class MystocksItem(scrapy.Item):
      # define the fields for your item here like:
      # name = scrapy.Field()
      bNum = scrapy.Field()
      bNo = scrapy.Field()
      bName = scrapy.Field()
      bPrice = scrapy.Field()
      bUp = scrapy.Field()
      bUDN = scrapy.Field()
      bSum = scrapy.Field()
      bMoney = scrapy.Field()
      bAmp = scrapy.Field()

`

pipelines.py

`

  import pymysql
  from itemadapter import ItemAdapter


  class MystocksPipeline:
      def open_spider(self, spider):
          print("opened")
          try:
              self.con = pymysql.connect(host="127.0.0.1", port=3306, user="root", passwd="123456", db="mydb",
                                   charset="utf8")
              self.cursor = self.con.cursor(pymysql.cursors.DictCursor)
              self.cursor.execute("delete from books")
              self.opened = True
              self.count = 0
          except Exception as err:
              print(err)
              self.opened = False

def close_spider(self, spider):
    if self.opened:
        self.con.commit()
        self.con.close()
        self.opened = False
    print("closed")
    # 关闭连接

def process_item(self, item, spider):
    try:

        if self.opened:
            self.cursor.execute(
                "insert into stocks(bNum, bNo, bName, bPrice, bUp, bUDN,bSum,bMoney,bAmp)values( % s, % s, % s, "
                "% s, % s, % s, % s, % s, % s)",
                (item["bNum"], item["bNo"], item["bName"], item["bPrice"], item["bUp"], item["bUDN"], item["bSum"],
                 item["bMoney"], item["bAmp"]))  # 数据插入MySQL中的表
            self.count += 1
    except Exception as err:
        print(err)
    return item

`

sd.py

`

  import re

  import scrapy
  from bs4 import UnicodeDammit

  from mystocks.items import MystocksItem


  class SdSpider(scrapy.Spider):
      name = 'sd'
      #allowed_domains = ['www.eastmoney.com']
      #start_urls = ['http://www.eastmoney.com/']
      start_urls = ['http://49.push2.eastmoney.com/api/qt/clist/get?cb=jQuery112403706613772931069_1603890900421&pn=2&pz=20&po=1&np=1&ut=bd1d9ddb04089700cf9c27f6f7426281&fltt=2&invt=2&fid=f3&fs=m:0+t:6,m:0+t:13,m:0+t:80,m:1+t:2,m:1+t:23&fields=f1,f2,f3,f4,f5,f6,f7,f8,f9,f10,f12,f13,f14,f15,f16,f17,f18,f20,f21,f23,f24,f25,f22,f11,f62,f128,f136,f115,f152&_=1603890900433']

def parse(self, response):
    req = response.text
    pat = '"diff":[{(.*?)}]'
    data = re.compile(pat, re.S).findall(req)
    datas = data[0].split('},{')  # 对字符进行分片
    print("序号		股票代码		股票名称		最新报价		涨跌幅		涨跌额		成交量		成交额		振幅		")
    j = 0
    for i in range(len(datas)):
        item = MystocksItem()
        s = r'"(w)+":'
        line = re.sub(s, " ", datas[i]).split(",")
        item["bNum"] = str(j + 1)
        item["bNo"] = line[11]
        item["bName"] = line[13]
        item["bPrice"] = line[1]
        item["bUp"] = line[2]
        item["bUDN"] = line[3]
        item["bSum"] = line[4]
        item["bMoney"] = line[5]
        item["bAmp"] = line[6]
        j += 1
        print(item["bNum"] + "	", item['bNo'] + "	", item['bName'] + "	", item['bPrice'] + "	", item['bUp'] + "%	",
              item['bUDN'] + "	", item['bSum'] + "	", str(item['bMoney']) + "	", item['bAmp'])
        yield item

`

运行截图：

心得体会
这次我是在第三次作业基础上做的，遇到的问题就是在pycharm端序号能正常输出，但是导入数据库之后就没有按照序号排，不知道为什么。。。。

作业三

要求：熟练掌握 scrapy 中 Item、Pipeline 数据的序列化输出方法；使用scrapy框架+Xpath+MySQL数据库存储技术路线爬取外汇网站数据。

候选网站：招商银行网：http://fx.cmbchina.com/hq/

代码部分
items.py
`

  import scrapy


  class BankItem(scrapy.Item):
      # define the fields for your item here like:
      # name = scrapy.Field()
      id = scrapy.Field()
      Currency = scrapy.Field()
      TSP = scrapy.Field()
      CSP = scrapy.Field()
      TBP = scrapy.Field()
      CBP = scrapy.Field()
      Time = scrapy.Field()

`

pipelines.py

`

  import pymysql
  from itemadapter import ItemAdapter


  class BankPipeline:
      def open_spider(self, spider):
          print("opened")
          try:
              self.con = pymysql.connect(host="127.0.0.1", port=3306, user="root", passwd="123456", db="mydb",
                                   charset="utf8")
              self.cursor = self.con.cursor(pymysql.cursors.DictCursor)
              self.cursor.execute("delete from money")
              self.opened = True
              self.count = 1
          except Exception as err:
              print(err)
              self.opened = False

def close_spider(self, spider):
    if self.opened:
        self.con.commit()
        self.con.close()
        self.opened = False
    print("closed")
    #print("总共爬取", self.count, "本书籍")

def process_item(self, item, spider):

    try:

        print(item["id"])
        print(item["Currency"])
        print(item["TSP"])
        print(item["CSP"])
        print(item["TBP"])
        print(item["CBP"])
        print(item["Time"])
        print()
        if self.opened:
            self.cursor.execute(
                "insert into money(id, Currency, TSP, CSP, TBP, CBP, Time)values( % s, % s, % s, "
                "% s, % s, % s, % s)",
                (item["id"], item["Currency"], item["TSP"], item["CSP"], item["TBP"], item["CBP"], item["Time"]))
    except Exception as err:
        print(err)
    return item

`

currency.py

`

  import scrapy

  from bs4 import UnicodeDammit

  from Bank.items import BankItem


  class CurrencySpider(scrapy.Spider):
      name = 'currency'
      # allowed_domains = ['fx.cmbchina.com/hq/']
      start_urls = ['http://fx.cmbchina.com/hq//']

      def parse(self, response):
          i = 1
          try:
              dammit = UnicodeDammit(response.body, ["utf-8", "gbk"])
              data = dammit.unicode_markup
              selector = scrapy.Selector(text=data)
              trs = selector.xpath("//div[@id='realRateInfo']/table/tr")
              for tr in trs[1:]:  # 第一个tr是表头，略过
                  id = i
                  Currency = tr.xpath("./td[@class='fontbold'][position()=1]/text()").extract_first()
                  TSP = tr.xpath("./td[@class='numberright'][position()=1]/text()").extract_first()
                  CSP = tr.xpath("./td[@class='numberright'][position()=2]/text()").extract_first()
                  TBP = tr.xpath("./td[@class='numberright'][position()=3]/text()").extract_first()
                  CBP = tr.xpath("./td[@class='numberright'][position()=4]/text()").extract_first()
                  Time = tr.xpath("./td[@align='center'][position()=3]/text()").extract_first()
                  item = BankItem()
                  item["id"] = id
                  item["Currency"] = Currency.strip() if Currency else ""
                  item["TSP"] = TSP.strip() if TSP else ""
                  item["CSP"] = CSP.strip() if CSP else ""
                  item["TBP"] = TBP.strip() if TBP else ""
                  item["CBP"] = CBP.strip() if CBP else ""
                  item["Time"] = Time.strip() if Time else ""
                  i += 1
                  yield item

          except Exception as err:
              print(err)

`

运行截图：

心得体会：
有了前两次的经验这次就简单很多，而且网页也是规规矩矩的静态网页，实现起来就比较简单。