拼夕夕买家订单数据提取_winform抓取拼多多订单

采用python + selenium + browsermobproxy抓包 提取拼多多订单数据，通过selenium模拟登录拼多多后到订单页提取订单数据。browsermob-proxy是一个代理工具，能抓取网页所有的访问细节。下载地址 使用还需要配置java环境 在python安装browsermobproxy

pip install browsermob-proxy
1

打开拼多多注意，查看network 发现存储数据的json文件

注意，这个只存储从第十一个订单开始的数据，下滑每十个刷新一次，前十个订单数据在源代码中window.rawData中，也在控制台输入即可看见。那么我们要做的就是selenium登录跳转到订单页面，从源代码中获取前十订单数据，从order_list_v3中获取剩余订单数据。
启动browsermob-proxy

from  browsermobproxy import Server
server = Server(r'D:\browsermob-proxy-2.1.4-bin\browsermob-proxy-2.1.4\bin\browsermob-proxy.bat')//添加browsermob-proxy路径
server.start()//启动
proxy = server.create_proxy()//创建
1
2
3
4

启动selenium

chrome_driver = r'C:\Users\dell\AppData\Local\Google\Chrome\Application\chromedriver.exe'
from selenium import webdriver
from selenium.webdriver.chrome.options import Options
chrome_options = Options()
chrome_options.add_argument('--ignore-certificate-errors')
# 解决你的链接不是私密问题
chrome_options.add_argument('--proxy-server={0}'.format(proxy.proxy))
driver = webdriver.Chrome(executable_path=chrome_driver,options=chrome_options)
driver.execute_cdp_cmd("Page.addScriptToEvaluateOnNewDocument", {
                "source": """
                Object.defineProperty(navigator, 'webdriver', {
                  get: () => Chrome
                })
              """
            })
driver.implicitly_wait(10)
driver.maximize_window()
driver.get("http://yangkeduo.com/")
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18

selenium登录评多多跳转到全订单页

driver.find_element_by_xpath('//*[@id="main"]/div/div[2]/div[4]/div/div[1]/div[5]').click()//点击订单跳转到登录页面
driver.find_element_by_class_name('phone-login').click()
driver.find_element_by_id('user-mobile').send_keys('手机号')
driver.find_element_by_id('code-button').click()
code = input('清输入验证码')
driver.find_element_by_id('input-code').send_keys(code)
driver.find_element_by_id('submit-button').click()//登录
1
2
3
4
5
6
7

启动监听，获取源代码数据

proxy.new_har('order',options={'captureContent': True})
driver.execute_script('return JSON.stringify(window.rawData)')//返回前十个订单数据，里面的json格式与order_list_v3中的不一样，需要单独存储提取==还有编码的坑
f = open('top_ten.json', 'a')
json.dump(data,f)
f.close()//保存数据
1
2
3
4
5

循环滚动到底

from selenium.common.exceptions import NoSuchElementException
def isElementPresent():
    try:
        element = driver.find_element_by_xpath('//*[@class = "loading-text"]')//到底不为空
    except NoSuchElementException as e:
        return False
    else:
        return True
while True:
    target = isElementPresent()//判断是否到底，如果没有，继续滚动
    if  target is False :
        driver.execute_script("window.scrollTo(0, document.body.scrollHeight)")
        time.sleep(2)
    else:
        break
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15

从代理的包提取包保存

        for entry in result['log']['entries']:
            # print(entry['request']['url'])
            url = entry['request']['url']
            # 根据URL找到数据接口
            if "order_list_v3" in url:
                response = entry['response']['content']
                content = response['text']
                f = open('data.json', 'a')
                f.write(content + '\n')
                f.close()
1
2
3
4
5
6
7
8
9
10

整体思路就是这样的，最后就是处理数据提取输出Excel表，欢迎指出错误。

    def get_data():
        detail_list = []
        with open(phone_number.get() + 'top_ten.json', 'r+', encoding='utf-8') as f1:
            data1 = json.load(f1)
            d = json.loads(data1)
            for order in d['ordersStore']['orders']:
                detail = {}
                detail['order_sn'] = order['orderSn']
                detail['order_amount'] = order['orderAmount']
                detail['goods_name'] = order['orderGoods'][0]['goodsName']
                detail['goods_price'] = order['orderGoods'][0]['goodsPrice']
                detail['goods_number'] = order['orderGoods'][0]['goodsNumber']
                detail['order_status_prompt'] = order['orderStatusPrompt']
                if not detail['order_status_prompt'] in ['交易已取消', '未发货，退款成功', '已发货，退款成功']:
                    detail_list.append(detail.copy())
        with open(phone_number.get() + 'data.json', 'r+')  as f:
            try:
                for item in jsonlines.Reader(f):
                    for order in item['orders']:
                        detail = {}
                        detail['order_sn'] = order['order_sn']
                        detail['order_amount'] = order['order_amount']
                        detail['goods_name'] = order['order_goods'][0]['goods_name']
                        detail['goods_price'] = order['order_goods'][0]['goods_price']
                        detail['goods_number'] = order['order_goods'][0]['goods_number']
                        detail['order_status_prompt'] = order['order_status_prompt']
                        if not detail['order_status_prompt'] in ['交易已取消', '未发货，退款成功', '已发货，退款成功']:
                            detail_list.append(detail.copy())
            except:
                print('没有更多订单了')
        return detail_list
    def export_excel(export):
        # 将字典列表转换为DataFrame
        pf = pd.DataFrame(list(export))
        # 指定字段顺序
        order = ['order_sn', 'order_amount', 'goods_name', 'goods_price', 'goods_number', 'order_status_prompt']
        pf = pf[order]
        # 将列名替换为中文
        columns_map = {
            'order_sn': '订单编号',
            'order_amount': '订单数额',
            'goods_name': '商品名称',
            'goods_price': '商品价格',
            'goods_number': '商品数量',
            'order_status_prompt': '订单状态',
        }
        pf.rename(columns=columns_map, inplace=True)
        file_path = pd.ExcelWriter(phone_number.get() + '.xlsx')
        pf.fillna(' ', inplace=True)
        pf.to_excel(file_path, encoding='utf-8', index=False)
        file_path.save()
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51

欢迎指正错误。