#read.py

import scrapy
from readbook.items import ReadbookItem
from scrapy.linkextractors import LinkExtractor
from scrapy.spiders import CrawlSpider, Rule


class ReadSpider(CrawlSpider):
    name = 'read'
    allowed_domains = ['www.dushu.com']
    start_urls = ['https://www.dushu.com/book/1188_1.html']

    rules = (
        Rule(LinkExtractor(allow=r'/book/\d+/'), callback='parse_item', follow=True),
    )

    def parse_item(self, response):

        img_list=response.xpath('//div[@class="bookslist"]//img')
        for img in img_list:
            src=img.xpath('./@data-original').extract_first()
            name=img.xpath('./@alt').extract_first()
            book=ReadbookItem(name=name,src=src)
            yield book

#settings.py
DB_host='mysql主機地址'
DB_port=3306#埠號
DB_user='root'#使用者名稱
DB_password='1234'
DB_name='spider01'#資料庫名
#utf-8的-不允許寫，識別不了
DB_charset='utf-8'

BOT_NAME = 'readbook'

SPIDER_MODULES = ['readbook.spiders']
NEWSPIDER_MODULE = 'readbook.spiders'


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

# Obey robots.txt rules
ROBOTSTXT_OBEY = True

# 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 = {
#    'readbook.middlewares.ReadbookSpiderMiddleware': 543,
#}

# Enable or disable downloader middlewares
# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
#DOWNLOADER_MIDDLEWARES = {
#    'readbook.middlewares.ReadbookDownloaderMiddleware': 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
ITEM_PIPELINES = {
   'readbook.pipelines.ReadbookPipeline': 300,
   #MysqlPipline
   'readbook.pipelines.MysqlPipeline': 301,


}

# 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'

#piplines.py
# useful for handling different item types with a single interface
from itemadapter import ItemAdapter


class ReadbookPipeline:
    def open_spider(self,spider):
        self.fp=open('book.json','w',encoding='utf-8')
    def process_item(self, item, spider):
        self.fp.write(str(item))
        return item
    def close_spider(self,spider):
        self.fp.close()
#載入settings檔案
from scrapy.utils.project import get_project_settings
import pymysql

class MysqlPipline:
    def open_spider(self,spider):
        settings=get_project_settings()
        '''DB_host='mysql主機地址'
      DB_port=3306#埠號
      DB_user='root'#使用者名稱
      DB_password='1234'
      DB_name='spider01'#資料庫名
      DB_harset='utf-8'
        '''
        self.host=settings['DB_host']
        self.port=settings['DB_port']
        self.user=settings['DB_user']
        self.password=settings['DB_password']
        self.name=settings['DB_name']
        self.charest=settings['DB_charset']
        self.coonect()
    def connect(self):
        self.conn=pymysql.connect(
            host=self.host,
            port=self.port,
            user=self.user,
            password=self.password,
            db=self.name,
            charset=self.charest
        )
        self.cursor=self.conn.cursor()#執行sql語句
    def process_item(self,item,spider):
        sql='insert into book(name,src) values("{}","{}")'.format(item['name'],item['src'])
        self.cursor.execute(sql)#執行sql語句
        self.conn.commit()#提交


        return  item
    def close_spider(self,spider):
        self.cursor.close()
        self.conn.close()

#items.py
import scrapy


class ReadbookItem(scrapy.Item):
    # define the fields for your item here like:
    # name = scrapy.Field()
    name=scrapy.Field()
    src=scrapy.Field()