spider.py
import scrapy
from DD.items import DdItem
class DdSpider(scrapy.Spider):
name = 'dd'
allowed_domains = ['http://search.dangdang.com/']
start_urls = ['http://search.dangdang.com/?key=python&act=input&page_index=1']
def start_requests(self):
"""
爬虫请求之前
:return:
"""
for i in range(2,101):
url='http://search.dangdang.com/?key=python&act=input&page_index='+str(i)
yield scrapy.Request(url,self.parse)
def parse(self, response):
li_list=response.xpath('//div[@id="search_nature_rg"]/ul/li')
for book in li_list:
item=DdItem()
#书名
item["book_name"]=book.xpath('./a/@title').extract()
if len(book.xpath('./a/@title').extract()) > 0:
item["book_name"] = book.xpath('./a/@title').extract()
else:
item["book_name"]=["无简介信息"]
#价格
item["search_now_price"]=book.xpath('./p[3]/span[1]/text()').extract()
#作者
item["author"] = book.xpath('./p[5]/span[1]/a[1]/@title').extract()
if len(book.xpath('./p[5]/span[1]/a[1]/@title').extract()) > 0:
item["author"] = book.xpath('./p[5]/span[1]/a[1]/@title').extract()
else:
item["author"]=["无作者信息"]
#出版社
item["house"]=book.xpath('./p[5]/span[3]/a/@title').extract()
if len(book.xpath('./p[5]/span[3]/a/@title').extract())>0:
item["house"]=book.xpath('./p[5]/span[3]/a/@title').extract()
else:
item["house"]=["无出版社信息"]
#出版日期
item["data"]=book.xpath('./p[5]/span[2]/text()').extract()
if len(book.xpath('./p[5]/span[2]/text()').extract())>0:
item["data"] = book.xpath('./p[5]/span[2]/text()').extract()
else:
item["data"] =["无出版日期"]
#评论数量
item["review"]=book.xpath('./p[4]/a/text()').extract()
# print(item)
yield item
items.py
# Define here the models for your scraped items
#
# See documentation in:
# https://docs.scrapy.org/en/latest/topics/items.html
import scrapy
class DdItem(scrapy.Item):
# define the fields for your item here like:
#书名
book_name = scrapy.Field()
#价格
search_now_price=scrapy.Field()
#作者
author=scrapy.Field()
#出版社
house=scrapy.Field()
#出版日期
data=scrapy.Field()
#评论数量
review=scrapy.Field()
pipelines.py
# 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 DdPipeline:
def process_item(self, item, spider):
#连接数据库
conn=pymysql.connect(host="localhost",user="root",db="qu",passwd="123456",charset="utf8")
#定义游标
cur=conn.cursor()
# 书名
book_name = item["book_name"][0]
# 价格
search_now_price = item["search_now_price"][0]
# 作者
author = item["author"][0]
# 出版社
house = item["house"][0]
# 出版日期
data = item["data"][0]
# 评论数量
review = item["review"][0]
sql="insert into dd(book_name,search_now_price,author,house,data,review)values ('%s','%s','%s','%s','%s','%s')"%(book_name,search_now_price,author,house,data,review)
print(sql)
cur.execute(sql)
conn.commit()
cur.close()
conn.close()
return item
settings.py
# Scrapy settings for DD 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
BOT_NAME = 'DD'
SPIDER_MODULES = ['DD.spiders']
NEWSPIDER_MODULE = 'DD.spiders'
LOG_LEVEL="ERROR"
FEED_EXPROT_ENCODING="UTF-8"
# 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/89.0.4389.114 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://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 = {
# 'DD.middlewares.DdSpiderMiddleware': 543,
#}
# Enable or disable downloader middlewares
# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
#DOWNLOADER_MIDDLEWARES = {
# 'DD.middlewares.DdDownloaderMiddleware': 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 = {
'DD.pipelines.DdPipeline': 300,
}
# 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'