python怎么爬取京東商品評論

本篇內容介紹了“python怎么爬取京東商品評論”的有關知識，在實際案例的操作過程中，不少人都會遇到這樣的困境，接下來就讓小編帶領大家學習一下如何處理這些情況吧！希望大家仔細閱讀，能夠學有所成！

#!/usr/bin/python
# -*- coding: UTF-8 -*-
import requests
import re
import json
import time
import xlwt
import random

#
#
#配置表格
#不需要明白是干啥的
#有下面4行代碼就可以往表格寫中文了
#
style=xlwt.XFStyle()
font=xlwt.Font()
font.name='SimSun'
style.font=font

#創建一個表格
w=xlwt.Workbook(encoding='utf-8')
#添加個sheet
ws=w.add_sheet('sheet 1',cell_overwrite_ok=True)
#當前寫入表格到第 row行
row=1
#
#寫入表格頭
#
ws.write(0,0,'content')
ws.write(0,1,'userClientShow')
ws.write(0,2,'creationTime')
ws.write(0,3,'userLevelName')
ws.write(0,4,'productColor')
ws.write(0,5,'userLevelId')
ws.write(0,6,'score')
ws.write(0,7,'referenceName')
ws.write(0,8,'referenceTime')
ws.write(0,9,'isMobile')
ws.write(0,10,'nickname')

#
#接受一個json對象
#將內容寫進表格
#一次一頁評論
#
def write_json_to_xls(dat):

    global row
    for comment in dat['comments']:
        ws.write(row,0,comment['content'])
        ws.write(row,1,comment['userClientShow'])
        ws.write(row,2,comment['creationTime'])
        ws.write(row,3,comment['userLevelName'])
        ws.write(row,4,comment['productColor'])
        ws.write(row,5,comment['userLevelId'])
        ws.write(row,6,comment['score'])
        ws.write(row,7,comment['referenceName'])
        ws.write(row,8,comment['referenceTime'])
        ws.write(row,9,comment['isMobile'])
        ws.write(row,10,comment['nickname'])
        row+=1

#
#
# 循環獲取數據
#
#
hearders = {"Referer": "https://item.jd.hk/2990360.html",
"User-Agent": "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.110 Safari/537.36'"}
auto_jquery = 8809536
for i in range(1,10+1):
    #url='https://club.jd.com/comment/productPageComments.action?productId=1475512465&score=0&sortType=5&page=%d&pageSize=100&isShadowSku=0&fold=' % i
    #url = 'https://sclub.jd.com/comment/productPageComments.action?callback=jQuery2663266&productId=2990360&score=2&sortType=5&page=%d&pageSize=10&pin=null&_=1563330030798' % i
    url = 'https://sclub.jd.com/comment/productPageComments.action'
    #print(url)
    try:

        auto_jquery = auto_jquery+1
        jquery = 'jQuery%d' % auto_jquery
        times = random.randint(100,999)
        print times
        auto_tims = int(time.time())
        true_string = '%d%d' %(auto_tims, times)
        print true_string


        params = {'callback':jquery,'productId':'2990360','sortType':'5','page':i,'pageSize':'10','pin':'null','_':true_string,'score':'2'}
        json_req = requests.get(url,params=params,headers=hearders)
        print('11111111111111111111111')
        print (json_req.url)
        print (json_req.text)
        print('22222222222222222222222')

        flag = json_req.text.split('(')
        flag_two = flag[1].split(')')
        print flag_two[0];
        print ('666666666666666666')
        json_flag = json.loads((flag_two[0]))
        print json_flag['comments']
        #dat = json_req.json()
        write_json_to_xls(json_flag)
        print(u'寫入第%d頁數據'%i)
    except Exception as e:
       print(u'獲取數據失敗數據',e)
    time.sleep(0.5)


#將數據存進表格
w.save('result.xls')

“python怎么爬取京東商品評論”的內容就介紹到這里了，感謝大家的閱讀。如果想了解更多行業相關的知識可以關注億速云網站，小編將為大家輸出更多高質量的實用文章！