电商API接口数据与市场趋势分析的深度融合

import requests
import json

# 代理服务器配置
proxyHost = "www.16yun.cn"
proxyPort = "5445"
proxyUser = "16QMSOML"
proxyPass = "280651"

# 构造代理信息
proxies = {
    "http": f"http://{proxyUser}:{proxyPass}@{proxyHost}:{proxyPort}",
    "https": f"http://{proxyUser}:{proxyPass}@{proxyHost}:{proxyPort}"
}

# 假设API接口的URL和认证信息
API_URL = "https://api.example.com/sales"
API_KEY = "your_api_key"
HEADERS = {"Authorization": f"Bearer {API_KEY}", "Content-Type": "application/json"}

def fetch_sales_data(start_date, end_date):
    """
    获取指定日期范围内的销售数据
    """
    params = {
        "start_date": start_date,
        "end_date": end_date
    }
    try:
        # 使用代理发送请求
        response = requests.get(API_URL, headers=HEADERS, params=params, proxies=proxies, timeout=10)
        if response.status_code == 200:
            return json.loads(response.text)
        else:
            raise Exception(f"Failed to fetch data: HTTP {response.status_code}")
    except requests.exceptions.ProxyError:
        print("代理服务器配置可能有问题，请检查代理信息是否正确。")
    except requests.exceptions.ConnectionError:
        print("网络连接失败，请检查网络状态或API链接的合法性。")
    except requests.exceptions.Timeout:
        print("请求超时，请检查网络状态或稍后重试。")
    except Exception as e:
        print(f"发生错误：{e}")

# 示例：获取2024年1月的销售数据
sales_data = fetch_sales_data("2024-01-01", "2024-01-31")
if sales_data:
    print(sales_data)
else:
    print("未能成功获取数据，请检查API链接或网络状态。")

import pandas as pd

def preprocess_data(data):
    """
    将API返回的JSON数据转换为Pandas DataFrame，并进行清洗
    """
    df = pd.json_normalize(data)
    df["order_date"] = pd.to_datetime(df["order_date"])
    df["sales_amount"] = pd.to_numeric(df["sales_amount"])
    df.dropna(inplace=True)  # 删除缺失值
    return df

# 示例：预处理销售数据
cleaned_sales_data = preprocess_data(sales_data)
print(cleaned_sales_data.head())

import matplotlib.pyplot as plt

def analyze_sales_trend(data):
    """
    分析销售趋势并绘制图表
    """
    data["order_date"] = pd.to_datetime(data["order_date"])
    daily_sales = data.groupby(data["order_date"].dt.date).sum()["sales_amount"]
    
    plt.figure(figsize=(12, 6))
    plt.plot(daily_sales.index, daily_sales.values, marker="o", linestyle="-", color="blue")
    plt.title("Daily Sales Trend")
    plt.xlabel("Date")
    plt.ylabel("Sales Amount")
    plt.grid(True)
    plt.show()

# 示例：分析销售趋势
analyze_sales_trend(cleaned_sales_data)

def fetch_user_behavior_data(start_date, end_date):
    """
    获取指定日期范围内的用户行为数据
    """
    params = {
        "start_date": start_date,
        "end_date": end_date
    }
    response = requests.get("https://api.example.com/user_behavior", headers=HEADERS, params=params)
    if response.status_code == 200:
        return json.loads(response.text)
    else:
        raise Exception(f"Failed to fetch data: {response.status_code}")

# 示例：获取用户行为数据
user_behavior_data = fetch_user_behavior_data("2024-01-01", "2024-01-31")
cleaned_user_behavior_data = preprocess_data(user_behavior_data)

def analyze_user_behavior(data):
    """
    分析用户行为并绘制图表
    """
    page_views = data.groupby("page_url").count()["user_id"]
    top_pages = page_views.nlargest(10)
    
    plt.figure(figsize=(12, 6))
    top_pages.plot(kind="bar", color="green")
    plt.title("Top 10 Pages by Page Views")
    plt.xlabel("Page URL")
    plt.ylabel("Page Views")
    plt.show()

# 示例：分析用户行为
analyze_user_behavior(cleaned_user_behavior_data)