scrapy爬虫天猫笔记本电脑销量前60的商品
程序员文章站
2022-04-11 08:40:03
# 抓取内容:商品名称,商品价格,商品链接,店铺名称,店铺链接 # 爬取的时候之前返回了多次302,301 但是html网页还是被爬取下来了 抓取的首页: start_urls = ['https://list.tmall.com/search_product.htm?spm=a220m.10008 ......
# 抓取内容:商品名称,商品价格,商品链接,店铺名称,店铺链接
# 爬取的时候之前返回了多次302,301 但是html网页还是被爬取下来了
抓取的首页:
start_urls = ['https://list.tmall.com/search_product.htm?spm=a220m.1000858.1000724.4.4b3df937tMXU1S&cat=50024399&sort=d&style=g&active=1&industryCatId=50024399&theme=663']
第一步:item.py编写
相信刚开始的准备工作不需要讲了(cmd---scrapy startproject tianmao-----scrapy genspider topgood tmall.com)
1 import scrapy 2 3 4 class TianmaoItem(scrapy.Item): 5 # define the fields for your item here like: 6 # name = scrapy.Field() 7 GOODS_PRICE = scrapy.Field() # 价格 8 GOODS_NAME = scrapy.Field() # 名称 9 GOODS_URL = scrapy.Field() # 商品链接 10 SHOP_NAME = scrapy.Field() # 商店名称 11 SHOP_URL = scrapy.Field() # 商店链接
注释:主要是介绍从一个网页获取商品价格名称链接,再通过链接爬取商店名称链接。所以挑了几个具有代表性的数据。
第二步:编写spiders
1 # -*- coding: utf-8 -*- 2 import scrapy 3 from tianmao.items import TianmaoItem 4 5 6 class TopgoodSpider(scrapy.Spider): 7 name = 'topgood' 8 allowed_domains = ['list.tmall.com', 'detail.tmall.com'] # 二级域名 9 10 start_urls = ['https://list.tmall.com/search_product.htm?spm=a220m.1000858.1000724.4.4b3df937tMXU1S&cat=50024399&sort=d&style=g&active=1&industryCatId=50024399&theme=663'] 11 12 def parse(self, response): 13 divs = response.xpath("//div[@id='J_ItemList']/div[@class='product item-1111 ']/div") # 有的时候会出现标签变化的情况,需要自行修改 14 print(divs) 15 16 for div in divs: 17 item = TianmaoItem() 18 # 价格 19 item['GOODS_PRICE'] = div.xpath("p[@class='productPrice']/em/@title")[0].extract() # 序列化该节点为unicode字符串并返回list 20 print(item) 21 # 名称//*[@id="J_ItemList"]/div[3]/div/div[2]/a[1] 22 item['GOODS_NAME'] = div.xpath("div[@class='productTitle productTitle-spu']/a[1]/@title")[0].extract() 23 print(item) 24 pre_Product_Url = div.xpath("div[@class='productTitle productTitle-spu']/a[1]/@href").extract_first() 25 26 if 'http' not in pre_Product_Url: 27 pre_Product_Url = response.urljoin(pre_Product_Url) 28 29 item['GOODS_URL'] = pre_Product_Url 30 print(item) 31 yield scrapy.Request(url=pre_Product_Url, meta={'item': item}, callback=self.parse_detail,dont_filter=True) 32 33 def parse_detail(self, response): 34 divs = response.xpath("//div[@class='extend']/ul") 35 36 if len(divs) == 0: 37 self.log("Detail Page error --%s"%response.url) 38 39 div = divs[0] 40 item = response.meta['item'] 41 item['SHOP_NAME'] = div.xpath("li[1]/div[1]/a/text()")[0].extract().strip() 42 item['SHOP_URL'] = div.xpath("li[1]/div[1]/a/@href")[0].extract() 43 44 yield item 45 # 要保存为csv的格式 scrapy crawl topgood -o result.csv
第三步:setting.py编写
BOT_NAME = 'tianmao' SPIDER_MODULES = ['tianmao.spiders'] NEWSPIDER_MODULE = 'tianmao.spiders' LOG_FILE = 'topgood.log' LOG_STDOUT=True DEPTH_LIMIT = 2 # Crawl responsibly by identifying yourself (and your website) on the user-agent USER_AGENT = "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.87 Safari/537.36" # Output .csv FEED_URI = u'goods.csv' FEED_FORMAT = 'CSV' DOWNLOAD_DELAY = 5 # Obey robots.txt rules ROBOTSTXT_OBEY = False # Override the default request headers: DEFAULT_REQUEST_HEADERS = { 'Accept': 'text/html,application/xhtml+xm…plication/xml;q=0.9,*/*;q=0.8', 'Accept-Encoding': 'gzip, deflate, br', 'Accept-Language': 'zh-CN,zh;q=0.8', "Cookie":"自己访问该网站时候的cookie", "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.87 Safari/537.36" } ITEM_PIPELINES = { 'tianmao.pipelines.TianmaoPipeline': 300, }
注:参数详解
# BOT_NAME ---项目名称 # DEFAULT_REQUEST_HEADERS ---默认请求头 # DEPTH_LIMIT ---爬取网页的深度,默认零 # ITEM_PIPELINES ---保存项目中启用的pipeline及其顺序的字典。该字典默认为空,值(value)任意。 不过值(value)习惯设定在0-1000范围内。 # LOG_ENABLED ---是否启动logging # LOG_ENCODING ---logging的编码 # LOG_FILE ---日志文件的文件名 # LOG_LEVEL ---日志记录的级别 (CRITICAL、 ERROR、WARNING、INFO、DEBUG) # (关键, 错误, 警告, 信息,调试) # LOG_STDOUT --- 默认: False # 如果为 True ,进程所有的标准输出(及错误)将会被重定向到log中。 # 例如, 执行 print 'hello' ,其将会在Scrapy log中显示。 # RANDOMIZE_DOWNLOAD_DELAY ---默认为True,在相同网站获取数据时随机暂停 # DOWNLOAD_DELAY 默认为0 # ROBOTSTXT_OBEY 默认False,是否遵守robots.txt策咯 # FEED_FORMAT --- 设置数据保存的形式 # FEED_URI --- 保存数据的路径和文件名