import requests

from lxml import etree

import re

import xlwt

from openpyxl import workbook # 寫入Excel表所用

from openpyxl import load_workbook # 讀取excel

# import matplotlib.pylab as plt

from xlrd import book

headers = {

'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:70.0) Gecko/20100101 Firefox/70.0',

'Cookie': 'x-wl-uid=1DVw4k4T/jAduWIfwW2jvf029Ha4Bgv/AJGjP/yRfJTdq26dr7oDdeEBdb6zOPUl0ByfsaKJ3GUY=; session-id-time=2082729601l; session-id=457-7649276-4174543; csm-hit=tb:DAHATSQRZZBWHWD4ZXYP+s-T61YJHRDEC6Y6S2VMTVZ|1573355007668&t:1573355007668&adb:adblk_no; ubid-acbcn=459-2457809-1906210; session-token="4sZGQQPKw9CJUOzJFLsTdS3FtlpqIyp0hyvhXL6RMOchbDf7p7YLDEL90YFps2Hl80fBT6uPmzQ00meCLYxsrjuoabX3+kz7OB+CLw8GaAYZB8J9oBBcJLBUsGs6LLm/EHQht5Tm0IpOKR0hz0GGtATgcpJXDfRoEdvNol+CUc3mXOMA5KmEfFWstdV+KwyzSGrGW+DdrAftisgZMl2stffIdhcOLh53B4tJwsR5awKqPrOqZF8uJg=="; lc-acbcn=zh_CN; i18n-prefs=CNY'

} #添加headers模擬瀏覽器防止被發現

hao = []

zhong = []

cha = [] #獲取到的評論數存入里面

all_info_list = []

def parge_page(url):

response = requests.get(url=url,headers=headers)

#print(response) #測試一下看看也沒有請求到網頁

text = response.text

html = etree.HTML(text)

quan = html.xpath('//div[@id="cm_cr-review_list"]/div') #獲取到每個人的評論

for i in quan:

pinfen1 = i.xpath('.//span[@class="a-icon-alt"]/text()') #獲取到每個人的評分幾顆星

pinlun = i.xpath('.//span[@data-hook="review-body"]/span/text()') #獲取到每個人評論的字

time = i.xpath('.//span[@data-hook="review-date"]/text()')

color = i.xpath('.//a[@ data-hook="format-strip"]/text()')

# size = i.xpath('.//i[@ class="a-icon-text-separator"]/text()')

#print(pinlun)

for pinfen in pinfen1:

#print(pinlun)

a = re.sub('顆星','',pinfen) #使用正則把后面不用的字符串替換為空，顯得好看

#print(a)

list = {'評論':pinlun,'顏色和尺寸':color,'評分': a,'日期':time}

print(list)

info_list = [pinlun, color, a,time]

all_info_list.append(info_list)

# if a < str(2.0): #判斷，小于3顆星就存入差評

# cha.append(a)

# elif a < str(4.0): #小于4顆星就存入中評

# zhong.append(a)

# else:

# hao.append(a) #否則都是好評

def main():

# url = 'https://www.amazon.cn/product-reviews/B074MFRPWL'

# parge_page(url)

for x in range(10): #獲取100條評論，一頁10條

url = 'https://www.amazon.com/product-reviews/B07XGK5QXD/?pageNumber='+ str(x) #網站：

if __name__ == '__main__':

main() # 調用main方法

book = xlwt.Workbook(encoding='utf-8')

sheet = book.add_sheet('sheet1')

head = ['評論', '顏色和尺寸', '評分', '日期'] # 表頭

for h in range(len(head)):

sheet.write(0, h, head[h]) # 寫入表頭

i = 1

for list in all_info_list:

j = 0

for data in list:

sheet.write(i, j, data)

j += 1

i += 1

book.save('評論信息.xlsx')

print('完成',book)

總結

以上是生活随笔為你收集整理的python商品评论分析_亚马逊产品情感评论分析的全部內容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網站內容還不錯，歡迎將生活随笔推薦給好友。