JD京东商品详情及评论数据获取|JD电商API数据接口

京东获得JD商品详情 API 返回值说明

item_get-获得JD商品详情 [查看演示]  API注册测试

公共参数

请求参数

请求参数：num_iid=10335871600

参数说明：num_iid:JD商品ID

响应参数

Version: Date:

​​​​​​​

​​​​​代码实例

# -*- endoding: utf-8 -*-# @ModuleName:run# @Function(功能):# @Author : 苏穆冰白月晨# @Time : 2021/5/14 13:28import requestsimport pypinyinimport reimport randomimport timeimport json
url_data_pinyin = ''num = 0
headers = {
      'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/90.0.4430.212 Safari/537.36',    'accept-language': 'zh-CN,zh;q=0.9'}def request_data(url, id, url_data ,pageeee1):    response = requests.get(url, headers = headers).text    data = re.findall("<li title='.*?'>(.*?)</li>", response)
    for i in data:        if '<' in i :            i = re.findall('<.*?>(.*?)</a>', i)[0]        print(i)    for i in range(1, pageeee1):        url = 'https://club.jd.com/comment/productPageComments.action?'
        data = {'callback': 'fetchJSON_comment98',  # 调整页数page                'productId': str(id),  # 商品id                'score': 3,  # 好评score3，中评2，差评1,0代表全部评论                'sortType': 5,  # 推荐排序                'page': i,  # 第几页评论                'pageSize': 10,  # 一页10条                'isShadowSku': 0,                'fold': 1                }        brand = url_data        html = requests.get(url, params=data, headers=headers).text
        i = json.dumps(html)  # 将页面内容编码成json数据，（无论什么格式的数据编码后都变成了字符串类型str）        j = json.loads(i)  # 解码，将json数据解码为Python对象        comment = re.findall(r'{"productAttr":.*}', j)  # 对网页内容筛选找到我们想要的数据，得到值为字典的字符串即'{a:1,b:2}'        comm_dict = json.loads(comment[0])  # 将json对象obj解码为对应的字典dict        commentSummary = comm_dict['comments']  # 得到包含评论的字典组成的列表        for comment in commentSummary:  # 遍历每个包含评论的字典，获得评论和打分颜色版本时间            c_content = ''.join(comment['content'].split())  # 获得评论,split（）去空格并用join（）连接起一整段评论，便于存储            color = comment['productColor']            name = comment['referenceName']            time1 = comment['referenceTime']            # productColor: "黑色"；productSize: "128GB"；creationTime: "2020-06-08 17:53:53"；            print([brand], [color], [name], [time1], c_content)        sleeptime = random.randint(1, 4)        time.sleep(sleeptime)
    sleeptime = random.randint(1, 4)    time.sleep(sleeptime)

def request_url(url, url_data ,pageeee1,num1 = 0 ):    print('请求连接获取成功，链接为 ：', url)
    sleeptime = random.randint(1, 4)    time.sleep(sleeptime)
    response = requests.get(url, headers = headers).text
    url_zi_data = re.findall(r'href="(.*?)"\s+.*?>\s+<em>(.*?)</em>', response)    data_jiage = re.findall(r'<em>￥</em><i>(.*?)</i>', response)
    for i in url_zi_data:        name = i[1]        jiage = data_jiage[num1] + '￥'        num1 += 1
        if '<font class="skcolor_ljg">' in name:            name = name.replace('<font class="skcolor_ljg">', '')        if '</font>' in name:            name = name.replace('</font>', '')
        url_zi = 'https:' + i[0]        data_id = re.findall('m/(.*?).html', url_zi)[0]
        url_pinglunshu = f'https://club.jd.com/comment/productCommentSummaries.action?referenceIds={data_id}&callback=jQuery4573443&_=1616473554889'        headers1 = {
              'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/89.0.4389.82 Safari/537.36'        }
        comments = requests.get(url_pinglunshu, headers=headers1).text        comments = re.findall(r'"DefaultGoodCountStr":"(.*?)"', comments)[0]        print('\n')        print('---------------------------------------------------------------------')        print('主题:', name, '价格:', jiage, '评论数:', comments, '详情页面:',  url_zi)        request_data(url_zi, data_id, url_data ,pageeee1)

if __name__ == '__main__':    url_data = input('请输入关键字: ')    pageeee = int(input('请输入商品页面页数: '))    pageeee1 = int(input('请输入商品详情评论数据页数: '))    pageeee = pageeee * 2    url_data_pinyin_list = pypinyin.pinyin(url_data, style=pypinyin.NORMAL)    for i in url_data_pinyin_list:        url_data_pinyin += i[0]    for i in range(1,pageeee,2):        num += 1        url = f'https://search.jd.com/Search?keyword={url_data}&wq={url_data}&page={i}&s={num*61}&click=0'        request_url(url, url_data ,pageeee1)        sleeptime = random.randint(1, 4)        time.sleep(sleeptime)