使用playwright代替akshare爬指数数据

Dockerfile_base

@@ -3,6 +3,41 @@ FROM python:3.12-slim
 # 设置工作目录
 WORKDIR /app
 
+# 安装系统依赖
+RUN apt-get update && apt-get install -y \
+    wget \
+    gnupg \
+    && rm -rf /var/lib/apt/lists/*
+
+# 安装Playwright的依赖
+RUN apt-get update && apt-get install -y \
+    libnss3 \
+    libnspr4 \
+    libatk1.0-0 \
+    libatk-bridge2.0-0 \
+    libcups2 \
+    libdrm2 \
+    libdbus-1-3 \
+    libxkbcommon0 \
+    libxcomposite1 \
+    libxdamage1 \
+    libxfixes3 \
+    libxrandr2 \
+    libgbm1 \
+    libasound2 \
+    libpango-1.0-0 \
+    libpangocairo-1.0-0 \
+    && rm -rf /var/lib/apt/lists/*
+
+# 配置pip源
+RUN mkdir -p /root/.pip && \
+    echo "[global]" > /root/.pip/pip.conf && \
+    echo "index-url = https://pypi.tuna.tsinghua.edu.cn/simple" >> /root/.pip/pip.conf && \
+    echo "trusted-host = pypi.tuna.tsinghua.edu.cn" >> /root/.pip/pip.conf
+
+# 更新pip
+RUN python -m pip install --upgrade pip
+
 RUN apt-get update && \
     apt-get install -y --no-install-recommends tzdata && \
     ln -sf /usr/share/zoneinfo/Asia/Shanghai /etc/localtime && \
@@ -23,6 +58,16 @@ COPY requirements.txt .
 
 RUN uv pip install --system -r requirements.txt
 
+# 预先安装 Playwright 的系统依赖
+RUN apt-get update && apt-get install -y \
+    xvfb \
+    libopengl0 \
+    && rm -rf /var/lib/apt/lists/*
+
+# 安装Playwright浏览器
+RUN playwright install chromium
+RUN playwright install-deps
+
 
 # 暴露端口
 EXPOSE 80

em_browser_state.json

@@ -0,0 +1 @@
+{"cookies": [{"name": "fullscreengg", "value": "1", "domain": ".eastmoney.com", "path": "/", "expires": -1, "httpOnly": false, "secure": false, "sameSite": "Lax"}, {"name": "fullscreengg2", "value": "1", "domain": ".eastmoney.com", "path": "/", "expires": -1, "httpOnly": false, "secure": false, "sameSite": "Lax"}, {"name": "qgqp_b_id", "value": "97fe41278894bed48362b5a789967a07", "domain": ".eastmoney.com", "path": "/", "expires": 1796300946.515741, "httpOnly": false, "secure": false, "sameSite": "Lax"}, {"name": "st_nvi", "value": "i2BBcnTi2AO9bsuYZ0j6d8247", "domain": ".eastmoney.com", "path": "/", "expires": 1793276946, "httpOnly": false, "secure": false, "sameSite": "Lax"}, {"name": "st_si", "value": "35941754435197", "domain": ".eastmoney.com", "path": "/", "expires": -1, "httpOnly": false, "secure": false, "sameSite": "Lax"}, {"name": "st_asi", "value": "delete", "domain": ".eastmoney.com", "path": "/", "expires": -1, "httpOnly": false, "secure": false, "sameSite": "Lax"}, {"name": "nid", "value": "0019f2c6f761ce5374eb765f94801d3e", "domain": ".eastmoney.com", "path": "/", "expires": 1769516947, "httpOnly": false, "secure": false, "sameSite": "Lax"}, {"name": "nid_create_time", "value": "1761740947152", "domain": ".eastmoney.com", "path": "/", "expires": 1769516947, "httpOnly": false, "secure": false, "sameSite": "Lax"}, {"name": "gvi", "value": "qLqK7zZ_mgPbeKzwrmP5z1c45", "domain": ".eastmoney.com", "path": "/", "expires": 1769516947, "httpOnly": false, "secure": false, "sameSite": "Lax"}, {"name": "gvi_create_time", "value": "1761740947153", "domain": ".eastmoney.com", "path": "/", "expires": 1769516947, "httpOnly": false, "secure": false, "sameSite": "Lax"}, {"name": "wsc_checkuser_ok", "value": "1", "domain": ".eastmoney.com", "path": "/", "expires": -1, "httpOnly": false, "secure": false, "sameSite": "Lax"}, {"name": "st_pvi", "value": "54550357370034", "domain": ".eastmoney.com", "path": "/", "expires": 1796300966.64546, "httpOnly": false, "secure": false, "sameSite": "Lax"}, {"name": "st_sp", "value": "2025-10-29%2020%3A29%3A06", "domain": ".eastmoney.com", "path": "/", "expires": 1796300966.645772, "httpOnly": false, "secure": false, "sameSite": "Lax"}, {"name": "st_inirUrl", "value": "", "domain": ".eastmoney.com", "path": "/", "expires": 1796300966.646048, "httpOnly": false, "secure": false, "sameSite": "Lax"}, {"name": "st_sn", "value": "3", "domain": ".eastmoney.com", "path": "/", "expires": -1, "httpOnly": false, "secure": false, "sameSite": "Lax"}, {"name": "st_psi", "value": "20251029202926644-113200313003-0775966632", "domain": ".eastmoney.com", "path": "/", "expires": -1, "httpOnly": false, "secure": false, "sameSite": "Lax"}], "origins": [{"origin": "https://quote.eastmoney.com", "localStorage": [{"name": "st_pvi", "value": "54550357370034"}, {"name": "st_sp", "value": "2025-10-29 20:29:06"}, {"name": "st_inirUrl", "value": ""}]}]}

em_index_sport.py

@@ -0,0 +1,102 @@
+import time
+from playwright.sync_api import sync_playwright
+from loguru import logger
+import datetime
+import re
+import json
+import pandas as pd
+
+
+def index_data_scraper(index_code: str, data_file_path: str):
+
+    with sync_playwright() as p:
+
+        def on_response(response):
+            if "push2.eastmoney.com/api/qt/clist/get" in response.url:
+                try:
+                    if response.request.failure is None and response.status == 200:
+                        data = response.text()
+                        # logger.info(f"最新数据: \n{data}")
+
+                        # 保存响应数据
+                        with open(data_file_path, "a", encoding="utf-8") as f:
+                            f.write(data)
+                            f.write("\n")
+                except Exception as e:
+                    logger.error(f"处理响应数据失败: {e}")
+
+        browser_state_file_path = "./em_browser_state.json"
+        browser = p.chromium.launch(args=["--start-maximized"], headless=True)
+        context = browser.new_context(
+            storage_state=browser_state_file_path, no_viewport=True
+        )
+        page = context.new_page()
+        page.on("response", on_response)
+        url = f"https://quote.eastmoney.com/center/gridlist.html#{index_code}"
+        page.goto(url)
+        # page.pause()
+        for i in range(1, 500):
+            logger.info(f"第{i}次点击")
+            try:
+                page.get_by_role("link", name=">", exact=True).click(timeout=30000)
+            except Exception as e:
+                break
+            time.sleep(10)
+
+
+def parse_data(data_file_path: str):
+    df_list = []
+    with open(data_file_path, "r", encoding="utf-8") as f:
+        for line in f:
+            match = re.search(r"\((\{.*\})\);?$", line)
+            json_str = match.group(1)
+            data = json.loads(json_str)
+            inner_temp_df = pd.DataFrame(data["data"]["diff"])
+            df_list.append(inner_temp_df)
+            logger.info(inner_temp_df)
+    temp_df = pd.concat(df_list, ignore_index=True)
+    temp_df["f3"] = pd.to_numeric(temp_df["f3"], errors="coerce")
+    temp_df.sort_values(by=["f3"], ascending=False, inplace=True, ignore_index=True)
+    temp_df.reset_index(inplace=True)
+    temp_df["index"] = temp_df["index"].astype(int) + 1
+    col_name_map = {
+        "index": "序号",
+        "f12": "代码",
+        "f14": "名称",
+        "f2": "最新价",
+        "f3": "涨跌幅",
+        "f4": "涨跌额",
+        "f5": "成交量",
+        "f6": "成交额",
+        "f7": "振幅",
+        "f15": "最高",
+        "f16": "最低",
+        "f17": "今开",
+        "f18": "昨收",
+        "f10": "量比",
+    }
+    temp_df.rename(
+        columns=col_name_map,
+        inplace=True,
+    )
+    new_cols = col_name_map.values()
+    temp_df = temp_df[new_cols]
+    for col in new_cols:
+        temp_df[col] = pd.to_numeric(temp_df[col], errors="coerce")
+    return temp_df
+
+
+def get_index_latest_data():
+    today = datetime.datetime.now().strftime("%Y%m%d")
+    data_file_path = f"./{today}.txt"
+    index_code = "index_sh"
+    index_code_list = ["index_sh", "index_sz", "index_components", "index_zzzs"]
+    for index_code in index_code_list:
+        logger.info(f"开始更新指数数据: {index_code}")
+        index_data_scraper(index_code=index_code, data_file_path=data_file_path)
+    df = parse_data(data_file_path)
+    return df
+
+
+if __name__ == "__main__":
+    get_index_latest_data()

requirements.txt

@@ -17,9 +17,12 @@ urllib3>=1.26.0
 # 进度条
 tqdm>=4.65.0
 
+
 # 时间处理
 python-dateutil>=2.8.0
 schedule
 akshare
 TA-Lib
 tabulate
+
+playwright>=1.45.1

update_data.py

@@ -3,7 +3,8 @@ from db_config import DatabaseManager, DatabaseConfig
 from loguru import logger
 from datetime import datetime
 import akshare as ak
-from index_downloader import get_all_stock_index
+# from index_downloader import get_all_stock_index
+from em_index_sport import get_index_latest_data
 import schedule
 import time
 import traceback
@@ -24,7 +25,8 @@ def get_latest_index_kline_date():
     #     "/Users/aszer/Documents/vscode/etf/data/index_history_data/000001.csv",
     #     encoding="utf-8-sig",
     # )
-    df = get_all_stock_index()
+    # df = get_all_stock_index()
+    df = get_index_latest_data()
     column_mapping = {
         "date": "date",
         "代码": "code",
@@ -74,7 +76,7 @@ def main():
         return
 
     try:
-        db_config = DatabaseConfig()
+        db_config = DatabaseConfig(env="daily")
         logger.info(f"数据库连接: {db_config.connection_string}")
 
         # 如果只是测试连接
@@ -104,6 +106,7 @@ def main():
 
 
 if __name__ == "__main__":
+    # main()
     logger.info(datetime.now())
     PULL_SCHEDULE: str = os.getenv("PULL_SCHEDULE", "16:00")
     logger.info(f"PULL_SCHEDULE: {PULL_SCHEDULE}")