scrapy 爬取淘宝商品评论信息

深碍√TFBOYSˉ_ 2022-05-09 02:10 400阅读 0赞

爬虫最后要达到的效果，是将某分类下，第一页的所有商品的评论保存至mysql中。  
具体会保存评论日期、评论id、评论内容、商品链接和商品id。  
![在这里插入图片描述][70]

爬虫部分代码

# -*- coding: utf-8 -*-
    import scrapy
    import re
    import requests
    import math
    import json
    from scrapy.loader import ItemLoader
    from taobao_test.items import GoodsItem
    
    
    
    class LianyiqunSpider(scrapy.Spider):
        name = 'lianyiqun'
        allowed_domains = ['item.taobao.com',
                           'rate.taobao.com',
                           's.taobao.com'
                           ]
        start_urls = [
            '这里填写要抓取的商品分类主页链接'
        ]
    
        # 解析"连衣裙"分类页面（第一页商品）
        def parse(self, response):
    
            # 获取储存列表用的script标签
            js_script = response.css('script::text')[4].extract()
    
            # 获取储存列表用的json
            g_page_config = re.findall('g_page_config = ([\s\S]*)g_srp_loadCss', js_script)[0]
            g_page_config_json = json.loads(g_page_config.strip()[0:-1])
    
            # 访问商品链接
            auctions = g_page_config_json['mods']['itemlist']['data']['auctions']
            for a in auctions:
                yield scrapy.Request(url="http://" + a['detail_url'], callback=self.goods_detail)
    
        # 解析商品信息
        def goods_detail(self, response):
            # 获取到页面渲染的第一个脚本的数据结构
            first_js_script = response.css('script::text')[0].extract()
    
            # 正则匹配到g_config字段
            g_config = re.findall('var g_config = ([\s\S]*)g_config\.tadInfo', first_js_script)[0]
    
            # 正则匹配，拿到页面的评论url
            rate_counter_api = re.findall("rateCounterApi   : '//(.*)',", g_config)[0]
    
            # 访问获取评论的url
            rate_count_response = requests.get("http://" + rate_counter_api)
    
            # 获取评论数量
            rate_count = re.findall('"count":(.*)}', rate_count_response.text)[0]
    
            # 拿到data_list_api_url，这个能够匹配到域名
            data_list_api_url = response.css('#reviews::attr(data-listapi)').extract()[0]
    
            # 获取到评论的url
            feed_rate_list_url = re.findall('//(.*)\?', data_list_api_url)[0]
    
            # 宝贝id
            auttion_num_id = re.findall('auctionNumId=([\d]*)&', data_list_api_url)[0]
    
            # 设置一个值，一页获取的评论数量
            page_size = 20
    
            # 计算一共有多少页的评论
            pages = math.ceil(int(rate_count) / page_size)
    
            # 迭代一共有多少页，然后分别请求每一页评论
            for current_page_number in range(1, pages):
                yield scrapy.Request(url="http://" + feed_rate_list_url
                                         + "?auctionNumId=" + auttion_num_id
                                         + "&currentPageNum=" + str(current_page_number)
                                         + "&pageSize=" + str(page_size),
                                     callback=self.parse_rate_list)
    
        # 解析具体的评论
        def parse_rate_list(self, response):
    
            # 将响应信息转换成json格式
            goods_rate_data_json = json.loads(response.text.strip()[1:-1])
    
            # 获取到具体的评论信息，就是json信息获取
            comments = goods_rate_data_json['comments']
    
            for comment in comments:
    
                # ItemLoader方式
                goods_item_loader = ItemLoader(item=GoodsItem(), response=response)
    
                # 评论时间
                goods_item_loader.add_value('date', comment['date'])
                # 评论id
                goods_item_loader.add_value('rate_id', comment['rateId'])
                # 评论内容
                goods_item_loader.add_value('content', comment['content'])
                auction = comment['auction']
                # 商品的链接地址
                goods_item_loader.add_value('link', auction['link'])
                # 商品id
                goods_item_loader.add_value('auc_num_id', auction['aucNumId'])
    
                yield goods_item_loader.load_item()

items代码

# -*- coding: utf-8 -*-
    
    import scrapy
    from scrapy.loader.processors import MapCompose
    from scrapy.loader.processors import Join
    
    def parse_field(text):
        return str(text).strip()
    
    class TaobaoTestItem(scrapy.Item):
        # define the fields for your item here like:
        # name = scrapy.Field()
        pass
    
    class GoodsItem(scrapy.Item):
    
        # 评论时间
        date = scrapy.Field(
            input_processor=MapCompose(parse_field),
            output_processor=Join(),
        )
    
        # 评论id
        rate_id = scrapy.Field(
            input_processor=MapCompose(parse_field),
            output_processor=Join(),
        )
    
        # 评论内容
        content = scrapy.Field(
            input_processor=MapCompose(parse_field),
            output_processor=Join(),
        )
    
        # 商品链接
        link = scrapy.Field(
            input_processor=MapCompose(parse_field),
            output_processor=Join(),
        )
    
        # 商品id
        auc_num_id = scrapy.Field(
            input_processor=MapCompose(parse_field),
            output_processor=Join(),
        )
    
        def get_insert_sql(self):
            insert_sql = """
                insert into rate(date,rate_id,content,link,auc_num_id)
                values (%s,%s,%s,%s,%s)
            """
    
            params = (self["date"], self["rate_id"], self["content"], self["link"], self["auc_num_id"])
    
            return insert_sql, params

main代码

#coding:utf-8
    from scrapy.cmdline import execute
    
    import sys
    import os
    
    sys.path.append(os.path.dirname(os.path.abspath(__file__)))
    
    execute(["scrapy", "crawl", "lianyiqun"])

pipelines代码

# -*- coding: utf-8 -*-
    
    # Define your item pipelines here
    #
    # Don't forget to add your pipeline to the ITEM_PIPELINES setting
    # See: https://doc.scrapy.org/en/latest/topics/item-pipeline.html
    import codecs
    import json
    import MySQLdb.cursors
    from twisted.enterprise import adbapi
    import pymysql
    
    
    class TaobaoTestPipeline(object):
        def process_item(self, item, spider):
            return item
    
    
    class JsonPipeline(object):
    
        def __init__(self):
            self.file = codecs.open("jsondata.json", "w", encoding="utf-8")
    
        def process_item(self, item, spider):
            lines = json.dumps(dict(item), ensure_ascii=False) + "\n"
            self.file.write(lines)
            return item
    
        def spider_close(self):
            self.file.close()
    
    class writeMysql(object):
        def __init__(self):
            self.client = pymysql.connect(
                host='localhost',
                port=3306,
                user='root',
                passwd='123456',
                db='new_model',
                charset='utf8'
            )
            self.cur = self.client.cursor()
    
        def process_item(self, item, spider):
            insert_sql, params = item.get_insert_sql()
            self.cur.execute(insert_sql, params)
            self.client.commit()
            return item
    
        def handle_error(self, failure, item, spider):
            print(failure)

源码以上传至git，可点击直接[查看git地址][git]，有疑问的同学可提Issues或在博客下方留言~

[70]: /images/20220509/040eb7dce7934b0ea97d75b92576a4f4.png
[git]: https://github.com/Maginaaa/taobaoGoodsCommentsSpider