# -*- coding: utf-8 -*-
import scrapy
from moviePro.items import MovieproItem class MovieSpider(scrapy.Spider): name = 'movie' allowed_domains = ['www.id97.com'] start_urls = ['http://www.id97.com/'] def parse(self, response): div_list = response.xpath('//div[@class="col-xs-1-5 movie-item"]') for div in div_list: item = MovieproItem() item['name'] = div.xpath('.//h1/a/text()').extract_first() item['score'] = div.xpath('.//h1/em/text()').extract_first() #xpath(string(.))表示提取当前节点下所有子节点中的数据值（.）表示当前节点 item['kind'] = div.xpath('.//div[@class="otherinfo"]').xpath('string(.)').extract_first() item['detail_url'] = div.xpath('./div/a/@href').extract_first() #请求二级详情页面，解析二级页面中的相应内容,通过meta参数进行Request的数据传递 yield scrapy.Request(url=item['detail_url'],callback=self.parse_detail,meta={'item':item}) def parse_detail(self,response): #通过response获取item item = response.meta['item'] item['actor'] = response.xpath('//div[@class="row"]//table/tr[1]/a/text()').extract_first() item['time'] = response.xpath('//div[@class="row"]//table/tr[7]/td[2]/text()').extract_first() item['long'] = response.xpath('//div[@class="row"]//table/tr[8]/td[2]/text()').extract_first() #提交item到管道 yield item

# -*- coding: utf-8 -*-# Define here the models for your scraped items
# # See documentation in: # https://doc.scrapy.org/en/latest/topics/items.html import scrapy class MovieproItem(scrapy.Item): # define the fields for your item here like: name = scrapy.Field() score = scrapy.Field() time = scrapy.Field() long = scrapy.Field() actor = scrapy.Field() kind = scrapy.Field() detail_url = scrapy.Field()

# -*- coding: utf-8 -*-# Define your item pipelines here
# # Don't forget to add your pipeline to the ITEM_PIPELINES setting # See: https://doc.scrapy.org/en/latest/topics/item-pipeline.html import json class MovieproPipeline(object): def __init__(self): self.fp = open('data.txt','w') def process_item(self, item, spider): dic = dict(item) print(dic) json.dump(dic,self.fp,ensure_ascii=False) return item def close_spider(self,spider): self.fp.close()

增加并发：默认scrapy开启的并发线程为32个，可以适当进行增加。在settings配置文件中修改CONCURRENT_REQUESTS = 100值为100,并发设置成了为100。降低日志级别：在运行scrapy时，会有大量日志信息的输出，为了减少CPU的使用率。可以设置log输出信息为INFO或者ERROR即可。在配置文件中编写：LOG_LEVEL = ‘INFO’ 禁止cookie： 如果不是真的需要cookie，则在scrapy爬取数据时可以进制cookie从而减少CPU的使用率，提升爬取效率。在配置文件中编写：COOKIES_ENABLED = False 禁止重试： 对失败的HTTP进行重新请求（重试）会减慢爬取速度，因此可以禁止重试。在配置文件中编写：RETRY_ENABLED = False 减少下载超时： 如果对一个非常慢的链接进行爬取，减少下载超时可以能让卡住的链接快速被放弃，从而提升效率。在配置文件中进行编写：DOWNLOAD_TIMEOUT = 10 超时时间为10s 

# -*- coding: utf-8 -*-
import scrapy
from xiaohua.items import XiaohuaItem class XiahuaSpider(scrapy.Spider): name = 'xiaohua' allowed_domains = ['www.521609.com'] start_urls = ['http://www.521609.com/daxuemeinv/'] pageNum = 1 url = 'http://www.521609.com/daxuemeinv/list8%d.html' def parse(self, response): li_list = response.xpath('//div[@class="index_img list_center"]/ul/li') for li in li_list: school = li.xpath('./a/img/@alt').extract_first() img_url = li.xpath('./a/img/@src').extract_first() item = XiaohuaItem() item['school'] = school item['img_url'] = 'http://www.521609.com' + img_url yield item if self.pageNum < 10: self.pageNum += 1 url = format(self.url % self.pageNum) #print(url) yield scrapy.Request(url=url,callback=self.parse) 

# -*- coding: utf-8 -*-# Define here the models for your scraped items
# # See documentation in: # https://doc.scrapy.org/en/latest/topics/items.html import scrapy class XiaohuaItem(scrapy.Item): # define the fields for your item here like: # name = scrapy.Field() school=scrapy.Field() img_url=scrapy.Field() 

# -*- coding: utf-8 -*-# Define your item pipelines here
# # Don't forget to add your pipeline to the ITEM_PIPELINES setting # See: https://doc.scrapy.org/en/latest/topics/item-pipeline.html import json import os import urllib.request class XiaohuaPipeline(object): def __init__(self): self.fp = None def open_spider(self,spider): print('开始爬虫') self.fp = open('./xiaohua.txt','w') def download_img(self,item): url = item['img_url'] fileName = item['school']+'.jpg' if not os.path.exists('./xiaohualib'): os.mkdir('./xiaohualib') filepath = os.path.join('./xiaohualib',fileName) urllib.request.urlretrieve(url,filepath) print(fileName+"下载成功") def process_item(self, item, spider): obj = dict(item) json_str = json.dumps(obj,ensure_ascii=False) self.fp.write(json_str+'\n') #下载图片 self.download_img(item) return item def close_spider(self,spider): print('结束爬虫') self.fp.close() 

USER_AGENT = 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.106 Safari/537.36'# Obey robots.txt rules
ROBOTSTXT_OBEY = False # Configure maximum concurrent requests performed by Scrapy (default: 16) CONCURRENT_REQUESTS = 100 COOKIES_ENABLED = False LOG_LEVEL = 'ERROR' RETRY_ENABLED = False DOWNLOAD_TIMEOUT = 3 # Configure a delay for requests for the same website (default: 0) # See https://doc.scrapy.org/en/latest/topics/settings.html#download-delay # See also autothrottle settings and docs # The download delay setting will honor only one of: #CONCURRENT_REQUESTS_PER_DOMAIN = 16 #CONCURRENT_REQUESTS_PER_IP = 16 DOWNLOAD_DELAY = 3