we-analysis/main.py

import os
import json
import asyncio
import datetime
import pandas as pd
from playwright.async_api import async_playwright

from applications import check_account, get_info, Mysql

platform_name = None
data_frame = []
lock = asyncio.Lock()


async def handle_download(download):
    global platform_name
    global data_frame

    async with lock:
        today = datetime.datetime.today().__str__().split(" ")[0].replace("-", "")
        temp = [platform_name]

        download_path = await download.path()
        # 指定新文件名
        new_file_path = r"temp_file\temp.xlsx"
        # 重命名文件
        if os.path.exists(new_file_path):
            os.remove(new_file_path)
        os.rename(download_path, new_file_path)
        if os.path.exists(download_path):
            os.remove(download_path)
        df = pd.read_excel(new_file_path)
        df = df.values.tolist()
        # 实验名称
        task_name = df[0][1]
        temp.append(task_name)
        # 数据指标
        task_index = df[5][1]
        temp.append(task_index)
        title_row = df[8]
        data_line = df[-1]
        # if data_line[0] != today:
        #     print("Not today")
        # else:
        temp += data_line
        w = {temp: data_line[index] for index, temp in enumerate(title_row)}
        print(platform_name, "\t", task_name, "\t", task_index)
        print(json.dumps(w, ensure_ascii=False, indent=4))
        while len(temp) < 29:
            temp.append("NULL")
        Mysql().insert_line(data=temp)
        data_frame.append(temp)
        os.remove(new_file_path)


async def run(playwright):
    """
    小程序：
        -1 票圈内容精选   ok
        -2 票圈 l 3亿人喜欢的视频平台  ok
        -3 票圈 l 视频精选
        -4 票圈 l 祝福
        -5 票圈 l 福年
        -6 票圈 l 信仰之路    ok
        -7 票圈视频  ok
        -8 票圈短视频
        -9 老好看视频    ok
        -10 票圈最惊奇   ok
        -11 票圈视频+
    """
    global platform_name
    global data_frame

    # 初始化浏览器
    browser = await playwright.chromium.launch(
        headless=False,
        downloads_path="temp_file",
    )
    context = await browser.new_context(accept_downloads=True)
    page = await context.new_page()
    await page.set_viewport_size({"width": 1680, "height": 1080})

    page.on("download", handle_download)

    # 登陆，需要扫码
    await page.goto("https://wedata.weixin.qq.com/mp2/login")
    await page.goto("https://wedata.weixin.qq.com/mp2/?source=0")
    await page.goto("https://wedata.weixin.qq.com/mp2/basic-data/core-data?source=0")

    # # 默认先进入票圈内容精选
    platform_name = '票圈内容精选'
    await get_info(page, platform_name)

    # 票圈 ｜ 3亿人喜欢的视频平台
    platform_name = "票圈 l 3亿人喜欢的视频平台"
    await check_account(page, platform_name)
    await asyncio.sleep(3)
    await get_info(page, platform_name)

    # 票圈 ｜ 视频精选
    platform_name = "票圈 l 视频精选"
    await check_account(page, platform_name)
    await get_info(page, platform_name)

    # 票圈 l 祝福
    platform_name = "票圈 l 祝福"
    await check_account(page, platform_name)
    await get_info(page, platform_name)

    # 票圈 l 福年 1
    platform_name = "票圈 I 福年"
    await check_account(page, platform_name)
    await get_info(page, platform_name)

    # 票圈 l 信仰之路 1
    platform_name = "票圈 l 信仰之路"
    await check_account(page, platform_name)
    await get_info(page, platform_name)

    # 票圈视频
    platform_name = "票圈视频"
    await check_account(page, platform_name)
    await get_info(page, platform_name)

    # 票圈短视频 1
    platform_name = "票圈短视频"
    await check_account(page, platform_name)
    await get_info(page, platform_name)

    # 老好看视频
    platform_name = "老好看视频"
    await check_account(page, platform_name)
    await get_info(page, platform_name)

    # 票圈最惊奇
    platform_name = "票圈最惊奇"
    await check_account(page, platform_name)
    await get_info(page, platform_name)

    # 票圈视频+
    platform_name = "票圈视频+"
    await check_account(page, platform_name)
    await get_info(page, platform_name)

    # columns = ["小程序", "实验", "指标", "日期", "对照组"] + [
    #     "实验组{}".format(i) for i in range(1, 25)
    # ]
    # print(len(columns))
    # out_df = DataFrame(data_frame, columns=columns)
    # out_df.to_excel("{}.xlsx".format("2024-01-02-result"), index=False)

    # await asyncio.sleep(100)

    # 关闭浏览器上下文和浏览器
    await context.close()
    await browser.close()


async def main():
    async with async_playwright() as playwright:
        await run(playwright)


asyncio.run(main())