python爬取商品评论

Wizard go

已于 2023-02-02 15:53:13 修改

阅读量497

点赞数

文章标签： python 开发语言

于 2023-02-01 11:40:37 首次发布

本文链接：https://blog.csdn.net/weixin_45774311/article/details/128831083

版权

该代码实现了一个简单的Python爬虫，用于抓取京东商品页面的用户评论。它使用requests库发送HTTP请求，通过随机选择的代理IP进行访问，以模拟不同用户。爬虫解析JSON响应，提取评论的详细信息如商品ID、用户昵称、评分、评论时间和内容，并将数据写入Excel文件。

摘要由CSDN通过智能技术生成

import pandas as pd
import random
import requests
ip_pool = [
    '119.98.44.192:8118',
    '111.198.219.151:8118',
    '101.86.86.101:8118',
]
def ip_proxy():
    ip = ip_pool[random.randrange(0,3)]
    proxy_ip = 'http://'+ip
    proxies = {'http':proxy_ip}
    return proxies
class Jdcomment_spider(object):
    # 请求头,标识用户
    USER_AGENT_LIST = [
    "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; AcooBrowser; .NET CLR 1.1.4322; .NET CLR 2.0.50727)",
    "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.0; Acoo Browser; SLCC1; .NET CLR 2.0.50727; Media Center PC 5.0; .NET CLR 3.0.04506)",
    "Mozilla/4.0 (compatible; MSIE 7.0; AOL 9.5; AOLBuild 4337.35; Windows NT 5.1; .NET CLR 1.1.4322; .NET CLR 2.0.50727)",
    "Mozilla/5.0 (Windows; U; MSIE 9.0; Windows NT 9.0; en-US)",
    "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Win64; x64; Trident/5.0; .NET CLR 3.5.30729; .NET CLR 3.0.30729; .NET CLR 2.0.50727; Media Center PC 6.0)",
    "Mozilla/5.0 (compatible; MSIE 8.0; Windows NT 6.0; Trident/4.0; WOW64; Trident/4.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; .NET CLR 1.0.3705; .NET CLR 1.1.4322)",
    "Mozilla/4.0 (compatible; MSIE 7.0b; Windows NT 5.2; .NET CLR 1.1.4322; .NET CLR 2.0.50727; InfoPath.2; .NET CLR 3.0.04506.30)",
    "Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN) AppleWebKit/523.15 (KHTML, like Gecko, Safari/419.3) Arora/0.3 (Change: 287 c9dfb30)",
    "Mozilla/5.0 (X11; U; Linux; en-US) AppleWebKit/527+ (KHTML, like Gecko, Safari/419.3) Arora/0.6",
    "Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.8.1.2pre) Gecko/20070215 K-Ninja/2.1.1",
    "Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN; rv:1.9) Gecko/20080705 Firefox/3.0 Kapiko/3.0",
    "Mozilla/5.0 (X11; Linux i686; U;) Gecko/20070322 Kazehakase/0.4.5",
    "Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.9.0.8) Gecko Fedora/1.9.0.8-1.fc10 Kazehakase/0.5.6",
    "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11",
    "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_3) AppleWebKit/535.20 (KHTML, like Gecko) Chrome/19.0.1036.7 Safari/535.20",
    "Opera/9.80 (Macintosh; Intel Mac OS X 10.6.8; U; fr) Presto/2.9.168 Version/11.52",
    "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.11 (KHTML, like Gecko) Chrome/20.0.1132.11 TaoBrowser/2.0 Safari/536.11",
    "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/21.0.1180.71 Safari/537.1 LBBROWSER",
    "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; WOW64; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; .NET4.0E; LBBROWSER)",
    "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; QQDownload 732; .NET4.0C; .NET4.0E; LBBROWSER)",
    "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.84 Safari/535.11 LBBROWSER",
    "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.1; WOW64; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; .NET4.0E)",
    "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; WOW64; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; .NET4.0E; QQBrowser/7.0.3698.400)",
    "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; QQDownload 732; .NET4.0C; .NET4.0E)",
    "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Trident/4.0; SV1; QQDownload 732; .NET4.0C; .NET4.0E; 360SE)",
    "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; QQDownload 732; .NET4.0C; .NET4.0E)",
    "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.1; WOW64; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; .NET4.0E)",
    "Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/21.0.1180.89 Safari/537.1",
    "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/21.0.1180.89 Safari/537.1",
    "Mozilla/5.0 (iPad; U; CPU OS 4_2_1 like Mac OS X; zh-cn) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8C148 Safari/6533.18.5",
    "Mozilla/5.0 (Windows NT 6.1; Win64; x64; rv:2.0b13pre) Gecko/20110307 Firefox/4.0b13pre",
    "Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:16.0) Gecko/20100101 Firefox/16.0",
    "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.11 (KHTML, like Gecko) Chrome/23.0.1271.64 Safari/537.11",
    "Mozilla/5.0 (X11; U; Linux x86_64; zh-CN; rv:1.9.2.10) Gecko/20100922 Ubuntu/10.10 (maverick) Firefox/3.6.10",
    "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.36",
    ]
    USER_AGENT = random.choice(USER_AGENT_LIST)
    headers = {'user-agent': USER_AGENT}
   
    #headers={
    #    'User-Agent':str(UserAgent().random)
    #}

    def __init__(self, file_name='test'):
        # 实例化类的时候运行初始化函数
        # 打开文件
        self.fp =open(f'./{file_name}.xls', 'w',encoding='utf-8')
        print(f'正在打开文件{file_name}.xls文件!')
    def parse_one_page(self,url):
        # 指定url
        # url = 'https://club.jd.com/comment/productPageComments.action?productId=10023108638660&score=0&sortType=5&page=0&pageSize=10&isShadowSku=0&rid=0&fold=1'
        # print(url)

        # 发起请求
        #time.sleep(5)
        response=requests.get(url,headers=self.headers,proxies=ip_proxy())
        # 获取响应
        js_data=response.json()

        # 提取评论列表
        comments_list=js_data['comments']

        for comment in comments_list:
            # 商品id
            goods_id=comment.get('id')
            # 用户昵称
            nickname=comment.get('nickname')
            # 评分
            score=comment.get('score')
            # 商品尺寸
            productSize=comment.get('productSize')
            # 商品颜色
            productColor=comment.get('productColor')
            # 评论时间
            creationTime=comment.get('creationTime')
            # 评论内容
            content=comment.get('content')
            content=' '.join(content.split('\n'))#处理换行符
            print(content)
            #循环写出数据
            self.fp.write(f'{goods_id}\t{nickname}\t{score}\t{productSize}\t{productColor}\t{creationTime}\t{content}\n')


    def parse_max_page(self):
        self.fp.write(f'"good_id"\t"nickname"\t"score"\t"productColor"\t"creationTime"\t"content"\n')
        #写入好评
        print("爬取好评")
        for page_num in range(100):#抓包获得最大页数
            #指定通用的url模板
            new_url = f'https://club.jd.com/comment/productPageComments.action?productId=100018079978&score=3&sortType=5&page={page_num}&pageSize=10&isShadowSku=0&fold=1'
            # 调用函数
            self.parse_one_page(url=new_url)
        #写入差评
        print("爬取差评")
        for page_num in range(100):#抓包获得最大页数
            # 指定通用的url模板
            new_url=f'https://club.jd.com/comment/productPageComments.action?productId=100018079978&score=1&sortType=5&page={page_num}&pageSize=10&isShadowSku=0&fold=1'
            #调用函数
            self.parse_one_page(url=new_url)

    def close_files(self):
        self.fp.close()
        print('爬虫结束，关闭文件！')
if __name__ == '__main__':

    # 实例对象
    jd_spider=Jdcomment_spider()
    # 开始爬虫
    jd_spider.parse_max_page()
    # 关闭文件
    jd_spider.close_files()