python爬虫抓取天猫商品评论模板，有详细教程

最新推荐文章于 2024-09-02 14:50:26 发布

置顶我心心念的爬虫啊

最新推荐文章于 2024-09-02 14:50:26 发布

阅读量2.7k

点赞数 3

分类专栏： python爬虫个人测试项目分享文章标签： python 经验分享

本文链接：https://blog.csdn.net/JJ_BoY/article/details/103801648

版权

python爬虫个人测试项目分享专栏收录该内容

10 篇文章 2 订阅

订阅专栏

详细教程，天猫和淘宝是一样的，在我主页里有淘宝的，在这发下天猫的

import requests
import re
import time
#需要修改的参数
#url_1
#a和b
#cookie不能用时重新修改

def set_up():
#打开商品的主页面链接
    url_1 = 'https://detail.tmall.com/item.htm?id=548071255763&ali_trackid=2:mm_28347190_2425761_109058700251:1577888365_191_532209995&spm=a231o.7712113/g.1004.1&pvid=200_11.27.33.24_345_1577888359041'
#找到评论接口,构造相应页数的接口
    url_2 = []
    for i in range(int(page)):
        a='https://rate.tmall.com/list_detail_rate.htm?itemId=548071255763&spuId=929590581&sellerId=1986899349&order=3&currentPage='
        b='&append=0&content=1&tagId=&posi=&picture=&groupId=&ua=098%23E1hvMpvRvP%2BvUvCkvvvvvjiPRsS9gjnjPs5ysjrCPmPO0jEmRsd9tjlEPLcZgjlP9phv2nQwwx6rzYswzjqx7u6CvvyvmCvmCvpvRVpEvpCWvVEHvvaSIExrl8TZfvDrQjc6%2BulgEfsUln97%2B3%2B%2BaNLUACAxEcqWafmxdXIaUExrQjZL%2B3%2B%2BafmxfXkKf3qxs4V9%2Bull88oQD76OddyCvmFMMQ2GS6vvtQvvvQCvpvLEvvv2vhCv2UhvvvWvphvWmpvvvQavpv1Cuphvmvvv9bw37srSkphvC9QvvOCzB9hCvvOvUvvvphvPvpvhvv2MMsyCvvpvvvvviQhvCvvv9U8jvpvhvvpvv86CvvyvmvWmlnpvUvGtvpvhvvvvv86CvvyvmW%2BmyXhvORI%3D&needFold=0&_ksTS=1577888442636_496&callback=jsonp497'
        url_2.append(a+str(i)+b)
#找到cookie
    cookie=''

    headers={
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:71.0) Gecko/20100101 Firefox/71.0',
        'Host': 'rate.tmall.com',
        'Accept': '*/*',
        'Accept-Language': 'zh-CN,zh;q=0.8,zh-TW;q=0.7,zh-HK;q=0.5,en-US;q=0.3,en;q=0.2',
        'Accept-Encoding': 'gzip, deflate, br',
        'Referer': url_1,
        'Connection': 'keep-alive',
        'Cookie' : cookie ,
        'TE': 'Trailers'
    }
    spider(url_2,headers)

def spider(url_2,headers):
    for y in range(len(url_2)):
        response = requests.get(url_2[y],headers=headers,timeout=30).content.decode()
        #初次评价
        evaluate = re.findall(',"rateContent":"(.*?)"',response)
        #分类
        kinds = re.findall('"auctionSku":"(.*?)",',response)
        for i in range(len(evaluate)):
            #将每一页的评论添加到总评论里面
            Evaluate.append({'商品的种类为：': kinds[i],'商品的初次评价为：': evaluate[i],})
        print('第'+str(y+1)+'页的评论获取成功')
        #延时，防止检测
        time.sleep(5)

    print('一共获取了'+str(len(Evaluate))+'评论')
    for i in Evaluate:
        print(i)


if __name__ == '__main__':
    page = input('输入想获取多少页的评论：')
#存放评价的列表
    Evaluate =[]
    set_up()