文章詳情頁

python基于scrapy爬取京東筆記本電腦數(shù)據(jù)并進行簡單處理和分析

瀏覽：270日期：2022-06-22 14:32:32

一、環(huán)境準備 python3.8.3 pycharm 項目所需第三方包

pip install scrapy fake-useragent requests selenium virtualenv -i https://pypi.douban.com/simple

1.1 創(chuàng)建虛擬環(huán)境

切換到指定目錄創(chuàng)建

virtualenv .venv

創(chuàng)建完記得激活虛擬環(huán)境

1.2 創(chuàng)建項目

scrapy startproject 項目名稱

1.3 使用pycharm打開項目，將創(chuàng)建的虛擬環(huán)境配置到項目中來1.4 創(chuàng)建京東spider

scrapy genspider 爬蟲名稱 url

1.5 修改允許訪問的域名，刪除https：

二、問題分析

爬取數(shù)據(jù)的思路是先獲取首頁的基本信息，在獲取詳情頁商品詳細信息；爬取京東數(shù)據(jù)時，只返回40條數(shù)據(jù)，這里，作者使用selenium，在scrapy框架中編寫下載器中間件，返回頁面所有數(shù)據(jù)。爬取的字段分別是：

商品價格

商品評數(shù)

商品店家

商品SKU（京東可直接搜索到對應的產(chǎn)品）

商品標題

商品詳細信息

三、spider

import reimport scrapyfrom lianjia.items import jd_detailItemclass JiComputerDetailSpider(scrapy.Spider): name = ’ji_computer_detail’ allowed_domains = [’search.jd.com’, ’item.jd.com’] start_urls = [’https://search.jd.com/Search?keyword=%E7%AC%94%E8%AE%B0%E6%9C%AC%E7%94%B5%E8%84%91&suggest=1.def.0.base&wq=%E7%AC%94%E8%AE%B0%E6%9C%AC%E7%94%B5%E8%84%91&page=1&s=1&click=0’] def parse(self, response):lls = response.xpath(’//ul[@class='gl-warp clearfix']/li’)for ll in lls: item = jd_detailItem() computer_price = ll.xpath(’.//div[@class='p-price']/strong/i/text()’).extract_first() computer_commit = ll.xpath(’.//div[@class='p-commit']/strong/a/text()’).extract_first() computer_p_shop = ll.xpath(’.//div[@class='p-shop']/span/a/text()’).extract_first() item[’computer_price’] = computer_price item[’computer_commit’] = computer_commit item[’computer_p_shop’] = computer_p_shop meta = {’item’: item } shop_detail_url = ll.xpath(’.//div[@class='p-img']/a/@href’).extract_first() shop_detail_url = ’https:’ + shop_detail_url yield scrapy.Request(url=shop_detail_url, callback=self.detail_parse, meta=meta)for i in range(2, 200, 2): next_page_url = f’https://search.jd.com/Search?keyword=%E7%AC%94%E8%AE%B0%E6%9C%AC%E7%94%B5%E8%84%91&suggest=1.def.0.base&wq=%E7%AC%94%E8%AE%B0%E6%9C%AC%E7%94%B5%E8%84%91&page={i}&s=116&click=0’ yield scrapy.Request(url=next_page_url, callback=self.parse) def detail_parse(self, response):item = response.meta.get(’item’)computer_sku = response.xpath(’//a[@class='notice J-notify-sale']/@data-sku’).extract_first()item[’computer_sku’] = computer_skucomputer_title = response.xpath(’//div[@class='sku-name']/text()’).extract_first().strip()computer_title = ’’.join(re.findall(’S’, computer_title))item[’computer_title’] = computer_titlecomputer_detail = response.xpath(’string(//ul[@class='parameter2 p-parameter-list'])’).extract_first().strip()computer_detail = ’’.join(re.findall(’S’, computer_detail))item[’computer_detail’] = computer_detailyield item四、item

class jd_detailItem(scrapy.Item): # define the fields for your item here like: computer_sku = scrapy.Field() computer_price = scrapy.Field() computer_title = scrapy.Field() computer_commit = scrapy.Field() computer_p_shop = scrapy.Field() computer_detail = scrapy.Field()五、setting

import randomfrom fake_useragent import UserAgentua = UserAgent()USER_AGENT = ua.randomROBOTSTXT_OBEY = FalseDOWNLOAD_DELAY = random.uniform(0.5, 1)DOWNLOADER_MIDDLEWARES = { ’lianjia.middlewares.jdDownloaderMiddleware’: 543}ITEM_PIPELINES = { ’lianjia.pipelines.jd_csv_Pipeline’: 300}六、pipelines

class jd_csv_Pipeline: # def process_item(self, item, spider): # return item def open_spider(self, spider):self.fp = open(’./jd_computer_message.xlsx’, mode=’w+’, encoding=’utf-8’)self.fp.write(’computer_skutcomputer_titletcomputer_p_shoptcomputer_pricetcomputer_committcomputer_detailn’) def process_item(self, item, spider):# 寫入文件try: line = ’t’.join(list(item.values())) + ’n’ self.fp.write(line) return itemexcept: pass def close_spider(self, spider):# 關(guān)閉文件self.fp.close()七、middlewares

class jdDownloaderMiddleware: def process_request(self, request, spider):# 判斷是否是ji_computer_detail的爬蟲# 判斷是否是首頁if spider.name == ’ji_computer_detail’ and re.findall(f’.*(item.jd.com).*’, request.url) == []: options = ChromeOptions() options.add_argument('--headless') driver = webdriver.Chrome(options=options) driver.get(request.url) for i in range(0, 15000, 5000):driver.execute_script(f’window.scrollTo(0, {i})’)time.sleep(0.5) body = driver.page_source.encode() time.sleep(1) return HtmlResponse(url=request.url, body=body, request=request)return None八、使用jupyter進行簡單的處理和分析

其他文件：百度停用詞庫、簡體字文件下載第三方包

!pip install seaborn jieba wordcloud PIL -i https://pypi.douban.com/simple

8.1導入第三方包

import reimport osimport jiebaimport wordcloudimport pandas as pdimport numpy as npfrom PIL import Imageimport seaborn as snsfrom docx import Documentfrom docx.shared import Inchesimport matplotlib.pyplot as pltfrom pandas import DataFrame,Series

8.2設置可視化的默認字體和seaborn的樣式

sns.set_style(’darkgrid’)plt.rcParams[’font.sans-serif’] = [’SimHei’]plt.rcParams[’axes.unicode_minus’] = False

8.3讀取數(shù)據(jù)

df_jp = pd.read_excel(’./jd_shop.xlsx’)

8.4篩選Inteli5、i7、i9處理器數(shù)據(jù)

def convert_one(s): if re.findall(f’.*?(i5).*’, str(s)) != []:return re.findall(f’.*?(i5).*’, str(s))[0] elif re.findall(f’.*?(i7).*’, str(s)) != []:return re.findall(f’.*?(i7).*’, str(s))[0] elif re.findall(f’.*?(i9).*’, str(s)) != []:return re.findall(f’.*?(i9).*’, str(s))[0]df_jp[’computer_intel’] = df_jp[’computer_detail’].map(convert_one)

8.5篩選筆記本電腦的屏幕尺寸范圍

def convert_two(s): if re.findall(f’.*?(d+.d+英寸-d+.d+英寸).*’, str(s)) != []:return re.findall(f’.*?(d+.d+英寸-d+.d+英寸).*’, str(s))[0]df_jp[’computer_in’] = df_jp[’computer_detail’].map(convert_two)

8.6將評論數(shù)轉(zhuǎn)化為整形

def convert_three(s): if re.findall(f’(d+)萬+’, str(s)) != []:number = int(re.findall(f’(d+)萬+’, str(s))[0]) * 10000return number elif re.findall(f’(d+)+’, str(s)) != []:number = re.findall(f’(d+)+’, str(s))[0]return numberdf_jp[’computer_commit’] = df_jp[’computer_commit’].map(convert_three)

8.7篩選出需要分析的品牌

def find_computer(name, s): sr = re.findall(f’.*({name}).*’, str(s))[0] return srdef convert(s): if re.findall(f’.*(聯(lián)想).*’, str(s)) != []:return find_computer(’聯(lián)想’, s) elif re.findall(f’.*(惠普).*’, str(s)) != []:return find_computer(’惠普’, s) elif re.findall(f’.*(華為).*’, str(s)) != []:return find_computer(’華為’, s) elif re.findall(f’.*(戴爾).*’, str(s)) != []:return find_computer(’戴爾’, s) elif re.findall(f’.*(華碩).*’, str(s)) != []:return find_computer(’華碩’, s) elif re.findall(f’.*(小米).*’, str(s)) != []:return find_computer(’小米’, s) elif re.findall(f’.*(榮耀).*’, str(s)) != []:return find_computer(’榮耀’, s) elif re.findall(f’.*(神舟).*’, str(s)) != []:return find_computer(’神舟’, s) elif re.findall(f’.*(外星人).*’, str(s)) != []:return find_computer(’外星人’, s)df_jp[’computer_p_shop’] = df_jp[’computer_p_shop’].map(convert)

8.8刪除指定字段為空值的數(shù)據(jù)

for n in [’computer_price’, ’computer_commit’, ’computer_p_shop’, ’computer_sku’, ’computer_detail’, ’computer_intel’, ’computer_in’]: index_ls = df_jp[df_jp[[n]].isnull().any(axis=1)==True].index df_jp.drop(index=index_ls, inplace=True)

8.9查看各品牌的平均價格

plt.figure(figsize=(10, 8), dpi=100)ax = sns.barplot(x=’computer_p_shop’, y=’computer_price’, data=df_jp.groupby(by=’computer_p_shop’)[[’computer_price’]].mean().reset_index())for index,row in df_jp.groupby(by=’computer_p_shop’)[[’computer_price’]].mean().reset_index().iterrows(): ax.text(row.name,row[’computer_price’] + 2,round(row[’computer_price’],2),color='black',ha='center')ax.set_xlabel(’品牌’)ax.set_ylabel(’平均價格’)ax.set_title(’各品牌平均價格’)boxplot_fig = ax.get_figure()boxplot_fig.savefig(’各品牌平均價格.png’, dpi=400)