精通python网络爬虫之自动爬取网页的爬虫 代码记录

items的编写

 # -*- 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 AutopjtItem(scrapy.Item):
     # define the fields for your item here like:
     # 用来存储商品名
     name = scrapy.Field()
     #用来存储商品价格
     price = scrapy.Field()
     # 用来存储商品链接
     link = scrapy.Field()
     # 用来存储商品评论数
     comnum = scrapy.Field()
     # 用来存储商品评论内容链接
     comnum_link = scrapy.Field()

piplines的编写

 # -*- coding: utf-8 -*-
 import codecs
 import json
 # 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
 
 class AutopjtPipeline(object):
     def __init__(self):
         self.file = codecs.open("D:/git/learn_scray/day11/1.json", "wb", encoding="utf-8")
 
     def process_item(self, item, spider):
         # 爬取当前页的所有信息
         for i in range(len(item["name"])):
             name = item["name"][i]
             price = item["price"][i]
             link = item["link"][i]
             comnum = item["comnum"][i]
             comnum_link = item["comnum_link"][i]
             current_conent = {"name":name,"price":price,"link":link,
                               "comnum":comnum,"comnum_link":comnum_link}
             j = json.dumps(dict(current_conent),ensure_ascii=False)
             # 为每条数据添加换行
             line = j + '\n'
             print(line)
             self.file.write(line)
         # for key,value in current_conent.items():
         #     print(key,value)
         return item
 
     def close_spider(self,spider):
         self.file.close()

自动爬虫编写实战

 # -*- coding: utf-8 -*-
 import scrapy
 from autopjt.items import AutopjtItem
 from scrapy.http import Request
 
 class AutospdSpider(scrapy.Spider):
     name = 'autospd'
     allowed_domains = ['dangdang.com']
     # 当当地方特产
     start_urls = ['http://category.dangdang.com/pg1-cid10010056.html']
 
     def parse(self, response):
         item = AutopjtItem()
         print("进入item")
         # print("获取标题:")
         # 获取标题
         item["name"] = response.xpath("//p[@class='name']/a/@title").extract()
         # print(title)
 
         # print("获取价格:")
         # 价格
         item["price"] = response.xpath("//span[@class='price_n']/text()").extract()
         # print(price)
 
         # print("获取商品链接:")
         # 获取商品链接
         item["link"] = response.xpath("//p[@class='name']/a/@href").extract()
         # print(link)
 
         # print("\n")
         # print("获取商品评论数:")
         # 获取商品评论数
         item["comnum"] = response.xpath("//a[@name='itemlist-review']/text()").extract()
         # comnum = response.xpath("//a[@name='itemlist-review']/text()").extract()
         # print(comnum)
 
         # print("获取商品评论数链接:")
         # 获取商品评论数链接
         item["comnum_link"] = response.xpath("//a[@name='itemlist-review']/@href").extract()
         # comnum_link = response.xpath("//a[@name='itemlist-review']/@href").extract()
         # print(comnum_link)
         yield item
         for i in range(1,79):
             # print(i)
             url = "http://category.dangdang.com/pg"+ str(i) + "-cid10010056.html"
             # print(url)
             yield Request(url, callback=self.parse)

yield详解:

　https://stackoverflow.com/questions/231767/what-does-the-yield-keyword-do

settings的设置:

 # -*- coding: utf-8 -*-
 
 # Scrapy settings for autopjt project
 #
 # For simplicity, this file contains only settings considered important or
 # commonly used. You can find more settings consulting the documentation:
 #
 #     https://doc.scrapy.org/en/latest/topics/settings.html
 #     https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
 #     https://doc.scrapy.org/en/latest/topics/spider-middleware.html
 
 BOT_NAME = 'autopjt'
 
 SPIDER_MODULES = ['autopjt.spiders']
 NEWSPIDER_MODULE = 'autopjt.spiders'
 
 # Crawl responsibly by identifying yourself (and your website) on the user-agent
 #USER_AGENT = 'autopjt (+http://www.yourdomain.com)'
 
 # Obey robots.txt rules
 # 默认为true遵守robots.txt协议 我试了一下能爬 为了保险设置为false
 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://doc.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://doc.scrapy.org/en/latest/topics/spider-middleware.html
 #SPIDER_MIDDLEWARES = {
 #    'autopjt.middlewares.AutopjtSpiderMiddleware': 543,
 #}
 
 # Enable or disable downloader middlewares
 # See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
 #DOWNLOADER_MIDDLEWARES = {
 #    'autopjt.middlewares.AutopjtDownloaderMiddleware': 543,
 #}
 
 # Enable or disable extensions
 # See https://doc.scrapy.org/en/latest/topics/extensions.html
 #EXTENSIONS = {
 #    'scrapy.extensions.telnet.TelnetConsole': None,
 #}
 
 # Configure item pipelines
 # See https://doc.scrapy.org/en/latest/topics/item-pipeline.html
 ITEM_PIPELINES = {
    'autopjt.pipelines.AutopjtPipeline': 300,
 }
 
 # Enable and configure the AutoThrottle extension (disabled by default)
 # See https://doc.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://doc.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'

最后的效果: