python 爬取京东数据 python基于scrapy爬取京东笔记本电脑数据并进行简单处理和分析

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

virtualenv .venv

scrapy startproject 项目名称

scrapy genspider 爬虫名称 url

import re
import scrapy


from lianjia.items import jd_detailItem


class 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_sku
        computer_title = response.xpath('//div[@class="sku-name"]/text()').extract_first().strip()
        computer_title = ''.join(re.findall('\S', computer_title))
        item['computer_title'] = computer_title
        computer_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_detail
        yield 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()

import random


from fake_useragent import UserAgent
ua = UserAgent()
USER_AGENT = ua.random
ROBOTSTXT_OBEY = False
DOWNLOAD_DELAY = random.uniform(0.5, 1)
DOWNLOADER_MIDDLEWARES = {
    'lianjia.middlewares.jdDownloaderMiddleware': 543
}
ITEM_PIPELINES = {
    'lianjia.pipelines.jd_csv_Pipeline': 300
}

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_sku\tcomputer_title\tcomputer_p_shop\tcomputer_price\tcomputer_commit\tcomputer_detail\n')

    def process_item(self, item, spider):
        # 写入文件
        try:
            line = '\t'.join(list(item.values())) + '\n'
            self.fp.write(line)
            return item
        except:
            pass

    def close_spider(self, spider):
        # 关闭文件
        self.fp.close()

class jdDownloaderMiddleware:
    def process_request(self, request, spider):
        # 判断是否是ji_computer_detail的爬虫
        # 判断是否是首页
        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

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

import re
import os
import jieba
import wordcloud
import pandas as pd
import numpy as np
from PIL import Image
import seaborn as sns
from docx import Document
from docx.shared import Inches
import matplotlib.pyplot as plt
from pandas import DataFrame,Series

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

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

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)

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)

def convert_three(s):
    if re.findall(f'(\d+)万+', str(s)) != []:
        number = int(re.findall(f'(\d+)万+', str(s))[0]) * 10000
        return number
    elif re.findall(f'(\d+)+', str(s)) != []:
        number = re.findall(f'(\d+)+', str(s))[0]
        return number
df_jp['computer_commit'] = df_jp['computer_commit'].map(convert_three)

def find_computer(name, s):
    sr = re.findall(f'.*({name}).*', str(s))[0]
    return sr
def convert(s):
    if re.findall(f'.*(联想).*', str(s)) != []:
        return find_computer('联想', s)
    elif re.findall(f'.*(惠普).*', str(s)) != []:
        return find_computer('惠普', s)
    elif re.findall(f'.*(华为).*', str(s)) != []:
        return find_computer('华为', s)
    elif re.findall(f'.*(戴尔).*', str(s)) != []:
        return find_computer('戴尔', s)
    elif re.findall(f'.*(华硕).*', str(s)) != []:
        return find_computer('华硕', s)
    elif re.findall(f'.*(小米).*', str(s)) != []:
        return find_computer('小米', s)
    elif re.findall(f'.*(荣耀).*', str(s)) != []:
        return find_computer('荣耀', 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)

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)

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('平均价格')
ax.set_title('各品牌平均价格')
boxplot_fig = ax.get_figure()
boxplot_fig.savefig('各品牌平均价格.png', dpi=400)

plt.figure(figsize=(10, 8), dpi=100)
ax = sns.boxenplot(x='computer_p_shop', y='computer_price', data=df_jp.query('computer_price>500'))
ax.set_xlabel('品牌')
ax.set_ylabel('价格区间')
ax.set_title('各品牌价格区间')
boxplot_fig = ax.get_figure()
boxplot_fig.savefig('各品牌价格区间.png', dpi=400)

df_jp['computer_commit'] = df_jp['computer_commit'].astype('int64')
ax = sns.jointplot(x="computer_commit", y="computer_price", data=df_jp, kind="reg", truncate=False,color="m", height=10)
ax.fig.savefig('评论数与价格的关系.png')

import imageio

# 将特征转换为列表
ls = df_jp['computer_title'].to_list()
# 替换非中英文的字符
feature_points = [re.sub(r'[^a-zA-Z\u4E00-\u9FA5]+',' ',str(feature)) for feature in ls]
# 读取停用词
stop_world = list(pd.read_csv('./百度停用词表.txt', engine='python', encoding='utf-8', names=['stopwords'])['stopwords'])
feature_points2 = []
for feature in feature_points:  # 遍历每一条评论
    words = jieba.lcut(feature) # 精确模式，没有冗余.对每一条评论进行jieba分词
    ind1 = np.array([len(word) > 1 for word in words])  # 判断每个分词的长度是否大于1
    ser1 = pd.Series(words)
    ser2 = ser1[ind1] # 筛选分词长度大于1的分词留下
    ind2 = ~ser2.isin(stop_world)  # 注意取反负号
    ser3 = ser2[ind2].unique()  # 筛选出不在停用词表的分词留下,并去重
    if len(ser3) > 0:
        feature_points2.append(list(ser3))
# 将所有分词存储到一个列表中
wordlist = [word for feature in feature_points2 for word in feature]
# 将列表中所有的分词拼接成一个字符串
feature_str =  ' '.join(wordlist)   
# 标题分析
font_path = r'./simhei.ttf'
shoes_box_jpg = imageio.imread('./home.jpg')
wc=wordcloud.WordCloud(
    background_color='black',
    mask=shoes_box_jpg,
    font_path = font_path,
    min_font_size=5,
    max_font_size=50,
    width=260,
    height=260,
)
wc.generate(feature_str)
plt.figure(figsize=(10, 8), dpi=100)
plt.imshow(wc)
plt.axis('off')
plt.savefig('标题提取关键词')

df_jd_query = df_jp.loc[(df_jp['computer_price'] <=5000) & (df_jp['computer_price']>=4000) & (df_jp['computer_p_shop']=="联想") & (df_jp['computer_intel']=="i5") & (df_jp['computer_in']=="15.0英寸-15.9英寸"), :].copy()
plt.figure(figsize=(20, 10), dpi=100)
ax = sns.barplot(x='computer_sku', y='computer_price', data=df_jd_query)
ax.set_xlabel('联想品牌SKU')
ax.set_ylabel('价格')
ax.set_title('酷睿i5处理器屏幕15寸以上各SKU的价格')
boxplot_fig = ax.get_figure()
boxplot_fig.savefig('酷睿i5处理器屏幕15寸以上各SKU的价格.png', dpi=400)

df_jp_daier = df_jp.loc[(df_jp['computer_price'] <=5000) & (df_jp['computer_price']>=4000) & (df_jp['computer_p_shop']=="戴尔") & (df_jp['computer_intel']=="i7") & (df_jp['computer_in']=="15.0英寸-15.9英寸"), :].copy()
plt.figure(figsize=(10, 8), dpi=100)
ax = sns.barplot(x='computer_sku', y='computer_price', data=df_jp_daier)
ax.set_xlabel('戴尔品牌SKU')
ax.set_ylabel('价格')
ax.set_title('酷睿i7处理器屏幕15寸以上各SKU的价格')
boxplot_fig = ax.get_figure()
boxplot_fig.savefig('酷睿i7处理器屏幕15寸以上各SKU的价格.png', dpi=400)

plt.figure(figsize=(10, 8), dpi=100)
ax = sns.barplot(x='computer_p_shop', y='computer_price', data=df_jp, hue='computer_intel')
ax.set_xlabel('品牌')
ax.set_ylabel('价格')
ax.set_title('不同酷睿处理器品牌的价格')
boxplot_fig = ax.get_figure()
boxplot_fig.savefig('不同酷睿处理器品牌的价格.png', dpi=400)

plt.figure(figsize=(10, 8), dpi=100)
ax = sns.barplot(x='computer_p_shop', y='computer_price', data=df_jp, hue='computer_in')
ax.set_xlabel('品牌')
ax.set_ylabel('价格')
ax.set_title('不同尺寸品牌的价格')
boxplot_fig = ax.get_figure()
boxplot_fig.savefig('不同尺寸品牌的价格.png', dpi=400)