唯品会数据抓取 | 爬虫

import requests
import re
import json
import time

class WPHSpider(object):
    """
    抓取唯品会列表页产品名称以及图片
    """
    def __init__(self):
        # 伪造请求头
        self.headers = {
            "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/66.0.3359.181 Safari/537.36",
        }
        # ip代理
        self.proxies = {
            "https:": "https://36.248.129.249:26392",
        }
        self.start_param = {
            "q": "3|29970||",
            "rp": "30073|30079",
        }

    def get_page(self, url, data_for_get):
        response = requests.get(url, params=data_for_get,
                                headers=self.headers, proxies=self.proxies)
        return response.text

    def run(self):
        i = 1
        while True:
            # 指定抓取５页
            if i == 5:
                break
            start_url = "https://category.vip.com/search-2-0-%s.html?q=3|29970||&rp=30073|30079" % i
            # 1.请求列表页
            res_content = self.get_page(start_url, self.start_param)
            # 2.从静态相应中解析出产品id
            com = re.compile(""".*productIds":(.*),"cateName".*""")

            data_by_re = com.findall(res_content)[0][3:-3].split(‘","‘)
            for n, pro_id in enumerate(data_by_re):
                if n == 50:
                    break
                # 3.构造ajax请求所需参数
                query_data = {
                    "service": "product_info",
                    "callback": "categoryMerchandiseInfo1",
                    "productIds": pro_id,
                    "functions": "brandShowName,surprisePrice,pcExtra",
                    "warehouse": "VIP_SH",
                    "mobile_platform": "1",
                    "app_name": "shop_pc",
                    "app_version": "4.0",
                    "mars_cid": "1526974867740_7faa89da4de8a00c3547899d727a48f4",
                    "fdc_area_id": "103103101",
                    "_": "1527053746100",
                }
                # 4.发起请求,获取产品数据
                dest_url = "https://category.vip.com/ajax/mapi.php"
                res_content = self.get_page(dest_url, query_data)
                # 5.解析所需数据
                com_second = re.compile(""".*"data":(.*)""")
                try:
                    temp_dict = com_second.findall(res_content)[0][13:-4]
                    # 6.将json字符串转换成python的字典数据类型
                    temp_dict = json.loads(temp_dict)
                except:
                    pass
                else:
                    # 7.构造文件名,以及获取图片数据源
                    productName = temp_dict["productName"] + ".jpg"
                    smallImage = temp_dict["smallImage"]
                    vipshopPrice = temp_dict["vipshopPrice"]
                    print(productName, smallImage, vipshopPrice)
                i += 1

if __name__ == "__main__":
    wph_spider = WPHSpider()
    wph_spider.run()

# -*- coding: utf-8 -*-
import scrapy
import re
import json
import time

class WphSpiderSpider(scrapy.Spider):
    name = ‘wph_spider‘
    allowed_domains = [‘vip.com‘]
    start_urls = [
        "https://category.vip.com/search-2-0-%s.html?q=3|29970||&rp=30073|30079" % i for i in range(5)]

    def parse(self, response):
        res_content = response.text
        com = re.compile(r""".*productIds":(.*),"cateName".*""")
        data_by_re = com.findall(res_content)[0][3:-3].split(‘","‘)
        for n, pro_id in enumerate(data_by_re):
            query_data = {
                "service": "product_info",
                "callback": "categoryMerchandiseInfo1",
                "productIds": pro_id,
                "functions": "brandShowName,surprisePrice,pcExtra",
                "warehouse": "VIP_SH",
                "mobile_platform": "1",
                "app_name": "shop_pc",
                "app_version": "4.0",
                "mars_cid": "1526974867740_7faa89da4de8a00c3547899d727a48f4",
                "fdc_area_id": "103103101",
            }
            param = ""
            i = 1
            for key,value in query_data.items():
                if i == 1:
                    param01 = key + "=" + value
                else:
                    param01 = "&" + key + "=" + value
                param += param01
                i += 1
            temp_url = "https://category.vip.com/ajax/mapi.php?" + param
            yield scrapy.Request(temp_url, callback=self.parse_detail)

    def parse_detail(self, response):
        com_second = re.compile(r""".*"data":(.*)""")

        temp_dict = com_second.findall(response.text)[0][13:-4]
        temp_dict = json.loads(temp_dict)

        productName = temp_dict["productName"] + ".jpg"
        smallImage = temp_dict["smallImage"]
        vipshopPrice = temp_dict["vipshopPrice"]
        with open("data.json", "a+") as f:
            f.write(json.dumps({
                    "productName": productName,
                    "smallImage": smallImage,
                    "vipshopPrice": vipshopPrice,
                }, ensure_ascii=False))
        print(productName, smallImage, vipshopPrice)

scrapy实现抓取

原文地址：https://www.cnblogs.com/pymkl/p/9089780.html