詳解Python之Scrapy爬蟲教程NBA球員數(shù)據(jù)存放到Mysql數(shù)據(jù)庫

# Define here the models for your scraped items
#
# See documentation in:
# https://docs.scrapy.org/en/latest/topics/items.html

import scrapy


class NbaprojectItem(scrapy.Item):
  # define the fields for your item here like:
  # name = scrapy.Field()
  # pass
  # 創(chuàng)建字段的固定格式-->scrapy.Field()
  # 英文名
  engName = scrapy.Field()
  # 中文名
  chName = scrapy.Field()
  # 身高
  height = scrapy.Field()
  # 體重
  weight = scrapy.Field()
  # 國家英文名
  contryEn = scrapy.Field()
  # 國家中文名
  contryCh = scrapy.Field()
  # NBA球齡
  experience = scrapy.Field()
  # 球衣號碼
  jerseyNo = scrapy.Field()
  # 入選年
  draftYear = scrapy.Field()
  # 隊伍英文名
  engTeam = scrapy.Field()
  # 隊伍中文名
  chTeam = scrapy.Field()
  # 位置
  position = scrapy.Field()
  # 東南部
  displayConference = scrapy.Field()
  # 分區(qū)
  division = scrapy.Field()

import scrapy
import json
from nbaProject.items import NbaprojectItem

class NbaspiderSpider(scrapy.Spider):
  name = 'nbaSpider'
  allowed_domains = ['nba.com']
  # 第一次爬取的網(wǎng)址,可以寫多個網(wǎng)址
  # start_urls = ['http://nba.com/']
  start_urls = ['https://china.nba.com/static/data/league/playerlist.json']
  # 處理網(wǎng)址的response
  def parse(self, response):
    # 因為訪問的網(wǎng)站返回的是json格式,首先用第三方包處理json數(shù)據(jù)
    data = json.loads(response.text)['payload']['players']
    # 以下列表用來存放不同的字段
    # 英文名
    engName = []
    # 中文名
    chName = []
    # 身高
    height = []
    # 體重
    weight = []
    # 國家英文名
    contryEn = []
    # 國家中文名
    contryCh = []
    # NBA球齡
    experience = []
    # 球衣號碼
    jerseyNo = []
    # 入選年
    draftYear = []
    # 隊伍英文名
    engTeam = []
    # 隊伍中文名
    chTeam = []
    # 位置
    position = []
    # 東南部
    displayConference = []
    # 分區(qū)
    division = []
    # 計數(shù)
    count = 1
    for i in data:
      # 英文名
      engName.append(str(i['playerProfile']['firstNameEn'] + i['playerProfile']['lastNameEn']))
      # 中文名
      chName.append(str(i['playerProfile']['firstName'] + i['playerProfile']['lastName']))
      # 國家英文名
      contryEn.append(str(i['playerProfile']['countryEn']))
      # 國家中文
      contryCh.append(str(i['playerProfile']['country']))
      # 身高
      height.append(str(i['playerProfile']['height']))
      # 體重
      weight.append(str(i['playerProfile']['weight']))
      # NBA球齡
      experience.append(str(i['playerProfile']['experience']))
      # 球衣號碼
      jerseyNo.append(str(i['playerProfile']['jerseyNo']))
      # 入選年
      draftYear.append(str(i['playerProfile']['draftYear']))
      # 隊伍英文名
      engTeam.append(str(i['teamProfile']['code']))
      # 隊伍中文名
      chTeam.append(str(i['teamProfile']['displayAbbr']))
      # 位置
      position.append(str(i['playerProfile']['position']))
      # 東南部
      displayConference.append(str(i['teamProfile']['displayConference']))
      # 分區(qū)
      division.append(str(i['teamProfile']['division']))

      # 創(chuàng)建item字段對象,用來存儲信息 這里的item就是對應(yīng)上面導(dǎo)的NbaprojectItem
      item = NbaprojectItem()
      item['engName'] = str(i['playerProfile']['firstNameEn'] + i['playerProfile']['lastNameEn'])
      item['chName'] = str(i['playerProfile']['firstName'] + i['playerProfile']['lastName'])
      item['contryEn'] = str(i['playerProfile']['countryEn'])
      item['contryCh'] = str(i['playerProfile']['country'])
      item['height'] = str(i['playerProfile']['height'])
      item['weight'] = str(i['playerProfile']['weight'])
      item['experience'] = str(i['playerProfile']['experience'])
      item['jerseyNo'] = str(i['playerProfile']['jerseyNo'])
      item['draftYear'] = str(i['playerProfile']['draftYear'])
      item['engTeam'] = str(i['teamProfile']['code'])
      item['chTeam'] = str(i['teamProfile']['displayAbbr'])
      item['position'] = str(i['playerProfile']['position'])
      item['displayConference'] = str(i['teamProfile']['displayConference'])
      item['division'] = str(i['teamProfile']['division'])
      # 打印爬取信息
      print("傳輸了",count,"條字段")
      count += 1
      # 將字段交回給引擎 -> 管道文件
      yield item

# Scrapy settings for nbaProject 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
# ----------不做修改部分---------
BOT_NAME = 'nbaProject'

SPIDER_MODULES = ['nbaProject.spiders']
NEWSPIDER_MODULE = 'nbaProject.spiders'
# ----------不做修改部分---------

# Crawl responsibly by identifying yourself (and your website) on the user-agent
#USER_AGENT = 'nbaProject (+http://www.yourdomain.com)'

# Obey robots.txt rules
# ----------修改部分(可以自行查這是啥東西)---------
# ROBOTSTXT_OBEY = True
# ----------修改部分---------

# 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 = {
#  'nbaProject.middlewares.NbaprojectSpiderMiddleware': 543,
#}

# Enable or disable downloader middlewares
# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
#DOWNLOADER_MIDDLEWARES = {
#  'nbaProject.middlewares.NbaprojectDownloaderMiddleware': 543,
#}

# Enable or disable extensions
# See https://docs.scrapy.org/en/latest/topics/extensions.html
#EXTENSIONS = {
#  'scrapy.extensions.telnet.TelnetConsole': None,
#}

# Configure item pipelines
# See https://docs.scrapy.org/en/latest/topics/item-pipeline.html
# 開啟管道文件
# ----------修改部分---------
ITEM_PIPELINES = {
  'nbaProject.pipelines.NbaprojectPipeline': 300,
}
# ----------修改部分---------
# 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'

# 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
class NbaprojectPipeline:
	# 初始化函數(shù)
  def __init__(self):
    # 連接數(shù)據(jù)庫 注意修改數(shù)據(jù)庫信息
    self.connect = pymysql.connect(host='域名', user='用戶名', passwd='密碼',
                    db='數(shù)據(jù)庫', port=端口號) 
    # 獲取游標(biāo)
    self.cursor = self.connect.cursor()
    # 創(chuàng)建一個表用于存放item字段的數(shù)據(jù)
    createTableSql = """
              create table if not exists `nbaPlayer`(
              playerId INT UNSIGNED AUTO_INCREMENT,
              engName varchar(80),
              chName varchar(20),
              height varchar(20),
              weight varchar(20),
              contryEn varchar(50),
              contryCh varchar(20),
              experience int,
              jerseyNo int,
              draftYear int,
              engTeam varchar(50),
              chTeam varchar(50),
              position varchar(50),
              displayConference varchar(50),
              division varchar(50),
              primary key(playerId)
              )charset=utf8;
              """
    # 執(zhí)行sql語句
    self.cursor.execute(createTableSql)
    self.connect.commit()
    print("完成了創(chuàng)建表的工作")
	#每次yield回來的字段會在這里做處理
  def process_item(self, item, spider):
  	# 打印item增加觀賞性
  	print(item)
    # sql語句
    insert_sql = """
    insert into nbaPlayer(
    playerId, engName, 
    chName,height,
    weight,contryEn,
    contryCh,experience,
    jerseyNo,draftYear
    ,engTeam,chTeam,
    position,displayConference,
    division
    ) VALUES (null,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s)
    """
    # 執(zhí)行插入數(shù)據(jù)到數(shù)據(jù)庫操作
    # 參數(shù)(sql語句,用item字段里的內(nèi)容替換sql語句的占位符)
    self.cursor.execute(insert_sql, (item['engName'], item['chName'], item['height'], item['weight']
                     , item['contryEn'], item['contryCh'], item['experience'], item['jerseyNo'],
                     item['draftYear'], item['engTeam'], item['chTeam'], item['position'],
                     item['displayConference'], item['division']))
    # 提交，不進(jìn)行提交無法保存到數(shù)據(jù)庫
    self.connect.commit()
    print("數(shù)據(jù)提交成功!")