前言:
今天大家对“腾讯python”可能比较关心,小伙伴们都需要剖析一些“腾讯python”的相关知识。那么小编在网摘上汇集了一些有关“腾讯python””的相关资讯,希望同学们能喜欢,你们快快来学习一下吧!一、简介
本文讲述使用python下载腾讯文档中的Excel数据,下方有完整代码,方便食用。
1. 思路
腾讯文档导出流程如下
使用抓包工具获取导出接口,检测数据是否准备完成接口、下载excel接口,使用requests进行调用,即可完成下载
二、实现步骤数据准备
1.提供腾讯文档中excel文档地址,以便进行下载,首先需要进行登陆,获取excel文档地址
document_url =
2.获取文档localPadId,每份文档唯一。打开浏览器控制台,刷新页面,filter中输入doc_info,找到该请求的localPadId
local_pad_id = 300000000$TfQWCVvRALvN
cookie值获取,右键复制即可
cookie_value = ********
获取当前用户nowUserIndex
用户nowUserIndex字段为后续下载excel文件接口的u字段,这里通过调用接口document_url获取
def get_now_user_index(self): """ # 获取当前用户信息,供创建下载任务使用 :return: # nowUserIndex = '4883730fe8b94fbdb94da26a9a63b688' # uid = '144115225804776585' # utype = 'wx' """ response_body = requests.get(url=self.document_url, headers=self.headers, verify=False) parser = BeautifulSoup(response_body.content, 'html.parser') global_multi_user_list = re.findall(re.compile('window.global_multi_user=(.*?);'), str(parser)) if global_multi_user_list: user_dict = json.loads(global_multi_user_list[0]) print(user_dict) return user_dict['nowUserIndex'] return 'cookie过期,请重新输入'
创建导出任务
创建导出任务的接口通过点击导出按钮获取,其中u字段值即为nowUserIndex字段,创建导出任务接口会返回一个operationId字段,是检测数据准备进度的入参。
export_excel_url = f'{now_user_index}'
def export_excel_task(self, export_excel_url): """ 导出excel文件任务,供查询文件数据准备进度 :return: """ body = { 'docId': self.localPadId, 'version': '2' } res = requests.post(url=export_excel_url, headers=self.headers, data=body, verify=False) operation_id = res.json()['operationId'] return operation_id
检查数据准备进度,并下载
查询数据准备进度的接口为check_progress_url = f'{now_user_index}&operationId={operation_id}',在点击导出excel时会出现该接口信息,频繁调用该接口,当progress进度为100时,该接口返回值会出现file_url信息。然后requests调用file_url,就可以拿到文件流,写到excel文件中即可完成下载。
def download_excel(self, check_progress_url, file_name): """ 下载excel文件 :return: """ # 拿到下载excel文件的url start_time = time.time() file_url = '' while True: res = requests.get(url=check_progress_url, headers=self.headers, verify=False) progress = res.json()['progress'] if progress == 100: file_url = res.json()['file_url'] break elif time.time() - start_time > 30: print("数据准备超时,请排查") break if file_url: self.headers['content-type'] = 'application/octet-stream' res = requests.get(url=file_url, headers=self.headers, verify=False) with open(file_name, 'wb') as f: f.write(res.content) print('下载成功,文件名: ' + file_name) else: print("下载文件地址获取失败, 下载excel文件不成功")三、完整代码
# -*- coding: UTF-8 -*-"""@Project :small-tools @File :tengxun.py@Author :silen@Time :2022/5/26 15:42@Description : """import jsonimport osimport reimport timefrom datetime import datetimefrom time import sleepimport clickimport pandas as pdimport requestsfrom bs4 import BeautifulSoupclass TengXunDocument(): def __init__(self, document_url, local_pad_id, cookie_value): # excel文档地址 self.document_url = document_url # 此值每一份腾讯文档有一个,需要手动获取 self.localPadId = local_pad_id self.headers = { 'content-type': 'application/x-www-form-urlencoded', 'Cookie': cookie_value } def get_now_user_index(self): """ # 获取当前用户信息,供创建下载任务使用 :return: # nowUserIndex = '4883730fe8b94fbdb94da26a9a63b688' # uid = '144115225804776585' # utype = 'wx' """ response_body = requests.get(url=self.document_url, headers=self.headers, verify=False) parser = BeautifulSoup(response_body.content, 'html.parser') global_multi_user_list = re.findall(re.compile('window.global_multi_user=(.*?);'), str(parser)) if global_multi_user_list: user_dict = json.loads(global_multi_user_list[0]) print(user_dict) return user_dict['nowUserIndex'] return 'cookie过期,请重新输入' def export_excel_task(self, export_excel_url): """ 导出excel文件任务,供查询文件数据准备进度 :return: """ body = { 'docId': self.localPadId, 'version': '2' } res = requests.post(url=export_excel_url, headers=self.headers, data=body, verify=False) operation_id = res.json()['operationId'] return operation_id def download_excel(self, check_progress_url, file_name): """ 下载excel文件 :return: """ # 拿到下载excel文件的url start_time = time.time() file_url = '' while True: res = requests.get(url=check_progress_url, headers=self.headers, verify=False) progress = res.json()['progress'] if progress == 100: file_url = res.json()['file_url'] break elif time.time() - start_time > 30: print("数据准备超时,请排查") break if file_url: self.headers['content-type'] = 'application/octet-stream' res = requests.get(url=file_url, headers=self.headers, verify=False) with open(file_name, 'wb') as f: f.write(res.content) print('下载成功,文件名: ' + file_name) else: print("下载文件地址获取失败, 下载excel文件不成功")if __name__ == '__main__': # excel文档地址 document_url = '; # 此值每一份腾讯文档有一个,需要手动获取 local_pad_id = '300000000$JxGXTkhdsIxB' # 打开腾讯文档后,从抓到的接口中获取cookie信息 cookie_value = '******' tx = TengXunDocument(document_url, local_pad_id, cookie_value) now_user_index = tx.get_now_user_index() # 导出文件任务url export_excel_url = f'{now_user_index}' # 获取导出任务的操作id operation_id = tx.export_excel_task(export_excel_url) check_progress_url = f'{now_user_index}&operationId={operation_id}' current_datetime = datetime.strftime(datetime.now(), '%Y_%m_%d_%H_%M_%S') file_name = f'{current_datetime}.xlsx' tx.download_excel(check_progress_url, file_name)四、效果演示
成功下载的文档如下所示
如果我的文章对你有帮助,感谢你点的关注
标签: #腾讯python