python3下载腾讯文档

说明：

1、请记得修改四个参数，分别是：doc_url、local_padId、cookie_value、file_name。

2、通过按F12，查找到doc_info接口，然后复制：local_padId、cookie_value值。

3、执行文件即可下载腾讯在线文档到本地目录。

#! /usr/bin/python3
# -*- coding: utf-8 -*-

import json
import time
import requests
from lxml import etree

class TengXunDoc():
    def __init__(self, doc_url, local_padId, cookie_value):
        self.doc_url = doc_url
        self.local_padId = local_padId
        self.headers = {
            'content-type': 'application/x-www-form-urlencoded',
            'Cookie': cookie_value
        }
    # 获取当前用户信息
    def get_now_user(self):
        """
        # nowUserIndex = 'ec61dc70ef244cc0b771e772045092b6'
        # uid = '144115225804776585'
        # utype = 'wx'
        """
        req = requests.get(url=self.doc_url, headers=self.headers)
        req.encoding = req.apparent_encoding
        html = etree.HTML(req.text)
        user_list = html.xpath("/html/head/script[3]/text()")
        # 转换成字符串，再转换成json格式读取数据
        data = str(user_list[0])
        user_dict = json.loads(data.replace('window.global_multi_user=','').replace(';', ''))
        if user_dict.get("nowUserIndex") is not None:
            print(user_dict.get("nowUserIndex"))
            return user_dict['nowUserIndex']
        return 'cookie过期,请重新输入'

    # 获取当前用户ID号
    def export_task(self, export_url):
        body = {
            "docId": self.local_padId,
            "version": 2
        }
        req = requests.post(url=export_url, headers=self.headers, data=body)
        operat_id = req.json()["operationId"]
        return operat_id

    # 下载腾讯文档
    def downlowd_excel(self, check_url, file_name):
        start_time = time.time()
        file_url = ""
        while True:
            req = requests.get(url=check_url, headers=self.headers)
            progress = req.json()["progress"]

            if progress == 100:
                file_url = req.json()["file_url"]
                break
            elif time.time() - start_time > 60:
                print("数据下载超时，请检查")
                break
        if file_url:
            self.headers["content-type"] = "application/octet-stream"
            res = requests.get(url=file_url, headers=self.headers)
            with open(file_name,'wb') as fp:
                fp.write(res.content)
                print(f"文件下载成功，文件名：{file_name}")
        else:
            print("下载excel表格失败，请检查文件获取地址")

if __name__ == '__main__':
    # 腾讯文档在线地址
    doc_url = "https://docs.qq.com/sheet/DQ1RrcEhmaXJNZkJW?tab=xxx"

    # 查阅doc_info接口参数
    local_padId = "300000000$xxxx"
    cookie_value = ""

    html = TengXunDoc(doc_url, local_padId, cookie_value)
    now_user = html.get_now_user()

    # 导出文件
    export_url = f"https://docs.qq.com/v1/export/export_office?u={now_user}"

    operat_Id  = html.export_task(export_url)
    check_url = f"https://docs.qq.com/v1/export/query_progress?u={now_user}&operationId={operat_Id}"

    # 保存文件路径
    file_name = "fruit/产品运维xxxx应急演练管理.xlsx"
    html.downlowd_excel(check_url, file_name)