eBay 商品数据采集实战：Python 调用网页抓取 API 接入方案

2. 配置关键参数

• Token：API 认证令牌，必须正确填写。
• 抓取方式：选择按链接或按关键词等形式。
• URL/关键词：填入目标商品链接或搜索词。
• 名称：设置结果文件命名规则。

3. 接入示例代码

配置好参数后，可选择对应编程语言（如 Python）的示例代码进行接入。

import requests
import json

def main():
    client = requests.Session()
    target_url = "https://scraper.ipidea.net/builder"
    spider_parameters = [
        {
            "url": "https://www.ebay.com/itm/187538926483?_skw=Apple&itmmeta=01K4KYKPQW7M913YDTWF9EJKQ4&hash=item2baa30eb93:g:VbMAAeSwtSRot5L8&itmprp=enc%3AAQAKAAAA4MHg7L1Zz0LA5DYYmRTS30kFPVExlz%2FTbUuctB71Yk%2FfQV0aiX%2BN2ICzGj8BIeYBUa7tIGv3VKEgsvuXC0PvIFFvjxEBfsALP5m0Rkcclb576wHpV5%2FGunXNmnt9grpWOipLuKMA0RDkORHa96xYJy8rg%2BYGIi2l2d0Iw2K%2FcLiqP7TlRBd1LsXAjnXShdLOq%2BFxcbaNCarcoIJ%2Fp5DgBLl5UK3WHBVGnpUQZqOMSz1JX0axUzL%2BxlVrnBGK0wekqYG6ShKyf5iRg5%2BY%2F35FueGxIeViMX5ZU5%2B8nFwIGsMl%7Ctkp%3ABFBMjOzO_qRm"
        },
        {
            "url": "https://www.ebay.com/itm/134042783029?_trkparms=amclksrc%3DITM%26aid%3D777008%26algo%3DPERSONAL.TOPIC%26ao%3D1%26asc%3D20230823115209%26meid%3Dab2275e853cd4322bf89abeadb8059b6%26pid%3D101800%26rk%3D1%26rkt%3D1%26itm%3D134042783029%26pmt%3D1%26noa%3D1%26pg%3D4375194%26algv%3DRecentlyViewedItemsV2SignedOut&_trksid=p4375194.c101800.m5481&_trkparms=parentrq%3A384b525a18e0a8d34d3f1e79fffe9de5%7Cpageci%3A11d381b5-e149-11ee-846f-7e8c3c878a6e%7Ciid%3A1%7Cvlpname%3Avlp_homepage"
        }
    ]
    spider_parameters_json = json.dumps(spider_parameters)
    form_data = {
        "spider_name": "ebay.com",
        "spider_id": "ebay_ebay_by-url",
        "spider_parameters": spider_parameters_json,
        "spider_errors": "true",
        "file_name": "{{TasksID}}"
    }
    headers = {
        "Authorization": "Bearer YOUR_API_TOKEN",
        "Content-Type": "application/x-www-form-urlencoded"
    }
    try:
        resp = client.post(target_url, data=form_data, headers=headers)
        resp.raise_for_status()
        print(f"Status Code: {resp.status_code}")
        print(f"Response Body: {resp.text}")
    except requests.exceptions.RequestException as e:
        print(f"Error sending request: {e}")

if __name__ == "__main__":
    main()

4. 提交请求与查看任务

提交请求后，可在后台查看抓取任务状态。抓取成功后，可选择多种结构化格式下载数据，支持 JSON、CSV、XLSX 三种文件类型。

5. 本地 PyCharm 调用接口

使用本地环境运行代码示例，基于 requests 库调用抓取 API。配置 API 令牌、目标链接等参数，通过 POST 请求提交任务，设置超时时间并捕获异常。

import requests
import json

# -------------------------- 可配置参数 --------------------------
API_TOKEN = "YOUR_API_TOKEN"
TARGET_URL = "https://scraper.ipidea.net/builder"
EBAY_SPIDER_NAME = "ebay.com"
EBAY_SPIDER_ID = "ebay_ebay_by-url"

SPIDER_PARAMS = [
    {
        "url": "https://www.ebay.com/itm/134042783029?_trkparms=amclksrc%3DITM%26aid%3D777008%26algo%3DPERSONAL.TOPIC%26ao%3D1%26asc%3D20230823115209%26meid%3Dab2275e853cd4322bf89abeadb8059b6%26pid%3D101800%26rk%3D1%26rkt%3D1%26itm%3D134042783029%26pmt%3D1%26noa%3D1%26pg%3D4375194%26algv%3DRecentlyViewedItemsV2SignedOut&_trksid=p4375194.c101800.m5481&_trkparms=parentrq%3A384b525a18e0a8d34d3f1e79fffe9de5%7Cpageci%3A11d381b5-e149-11ee-846f-7e8c3c878a6e%7Ciid%3A1%7Cvlpname%3Avlp_homepage"
    }
]
REQUEST_TIMEOUT = 30

# ---------------------------------------------------------------------------
def main():
    client = requests.Session()
    form_data = {
        "spider_name": EBAY_SPIDER_NAME,
        "spider_id": EBAY_SPIDER_ID,
        "spider_parameters": json.dumps(SPIDER_PARAMS, ensure_ascii=False),
        "spider_errors": "true",
        "file_name": "{{TasksID}}"
    }
    headers = {
        "Authorization": f"Bearer {API_TOKEN}",
        "Content-Type": "application/x-www-form-urlencoded"
    }
    try:
        resp = client.post(
            url=TARGET_URL,
            data=form_data,
            headers=headers,
            timeout=REQUEST_TIMEOUT
        )
        resp.raise_for_status()
        resp_json = resp.json()
        print(f"请求成功 | 状态码：{resp.status_code}")
        print(f"返回数据：{json.dumps(resp_json, indent=2, ensure_ascii=False)}")
    except requests.exceptions.HTTPError as e:
        print(f"HTTP 请求错误：{e}")
    except requests.exceptions.Timeout:
        print(f"请求超时（超过{REQUEST_TIMEOUT}秒），请检查网络或接口状态")
    except json.JSONDecodeError:
        print(f"接口返回非 JSON 格式，原始内容：{resp.text}")
    except requests.exceptions.RequestException as e:
        print(f"请求失败：{e}")

if __name__ == "__main__":
    main()

电商类目数据抓取：关键词案例分析

1. 选择关键词抓取方式

2. 添加抓取关键词

关键词可覆盖数码、美妆、服饰等多电商类目，支撑跨品类趋势、细分人群偏好分析。

3. 接入示例代码

复制接入示例代码至本地运行。

import requests
import json

def main():
    client = requests.Session()
    target_url = "https://scraper.ipidea.net/builder"
    spider_parameters = [
        {"keywords": "wireless headphones"},
        {"keywords": "laptop accessories"},
        {"keywords": "skincare set"},
        {"keywords": "2025 trending gadgets"},
        {"keywords": "summer dresses 2025"},
        {"keywords": "home office desk"},
        {"keywords": "outdoor camping gear"},
        {"keywords": "kids toys for 3-5 years"},
        {"keywords": "plus size women clothing"},
        {"keywords": "long battery life power bank"}
    ]
    spider_parameters_json = json.dumps(spider_parameters)
    form_data = {
        "spider_name": "ebay.com",
        "spider_id": "ebay_ebay_by-keywords",
        "spider_parameters": spider_parameters_json,
        "spider_errors": "true",
        "file_name": "{{TasksID}}"
    }
    headers = {
        "Authorization": "Bearer YOUR_API_TOKEN",
        "Content-Type": "application/x-www-form-urlencoded"
    }
    try:
        resp = client.post(target_url, data=form_data, headers=headers)
        resp.raise_for_status()
        print(f"Status Code: {resp.status_code}")
        print(f"Response Body: {resp.text}")
    except requests.exceptions.RequestException as e:
        print(f"Error sending request: {e}")

if __name__ == "__main__":
    main()

4. 查看任务与数据分析

查看后台任务是否运行，等待加载完成后下载数据。根据抓取信息可分析商品核心数据，如价格区间、销量、库存及配送情况。

抓取流程解析

整体流程清晰：在控制台选择平台抓取工具，填写 Token、抓取方式和目标 URL 等基础参数，系统自动生成示例代码。将代码复制到本地运行后，后台自动完成代理调度、页面渲染、数据结构化提取，以 JSON 或 CSV 方式返回可直接使用的商品详情数据。

• 选择目标抓取工具
• 填写 Token、抓取方式和目标 URL
• 复制系统生成的示例代码到本地运行
• 自动完成代理、渲染与抓取处理
• 返回 JSON 或 CSV 格式的结构化抓取结果

总结

网页抓取 API 通过全球合规住宅 IP、智能抓取、自动验证码跳过及多格式结构化解析，解决了跨境电商数据采集中的 IP 限制、合规难与开发成本高的问题。依托可视化配置 + 一行代码接入的方式，可实现稳定、高成功率、低成本的数据获取。本次实战以 eBay 商品采集为例，从配置、抓取到结果下载完整复现，展示了如何快速构建一个可直接投入业务的全球电商数据采集工具。