从Google Spreadsheet URL获取文件名称的Python教程

import pandas as pd
import requests
from urllib.parse import unquote

# 假设用户输入Google Spreadsheet的完整URL
# 例如: https://docs.google.com/spreadsheets/d/123abcDEF_GHIjKLM_NopQRS/edit#gid=0
link = input("请输入Google Spreadsheet的URL: ")

# 从URL中提取sheet_id
# 假设URL格式是标准的Google Sheets URL
try:
    link_parts = link.split('/')
    sheet_id = link_parts[5]
    print(f"提取到的Spreadsheet ID: {sheet_id}")
except IndexError:
    print("URL格式不正确，无法提取Sheet ID。请确保URL包含'/d/sheet_id/'。")
    exit()

# 构建导出URL
export_url = f"https://docs.google.com/spreadsheets/d/{sheet_id}/export?format=xlsx"

try:
    # 发送GET请求获取响应头
    r = requests.get(export_url)
    r.raise_for_status() # 检查请求是否成功

    # 打印完整的Content-Disposition头信息
    print(f"Content-Disposition: {r.headers.get('content-disposition')}")

    # 从Content-Disposition头中提取文件名
    content_disposition = r.headers.get('content-disposition')
    if content_disposition:
        # 查找 'filename*=UTF-8'' 后面的部分
        # 有些情况下可能是 filename="文件名.xlsx"
        if "filename*=UTF-8''" in content_disposition:
            # 提取并解码文件名，然后移除 .xlsx 后缀
            encoded_filename = content_disposition.split("filename*=UTF-8''")[1]
            filename_with_extension = unquote(encoded_filename)
            filename = filename_with_extension.replace(".xlsx", "")
        elif "filename=" in content_disposition:
            # 处理不带UTF-8编码的旧格式或不同格式
            filename_part = content_disposition.split("filename=")[1]
            # 移除双引号并解码（如果有的话）
            filename_with_extension = unquote(filename_part.strip('"'))
            filename = filename_with_extension.replace(".xlsx", "")
        else:
            filename = "未知文件"
            print("Content-Disposition头中未找到文件名信息。")
    else:
        filename = "未知文件"
        print("响应头中未找到Content-Disposition信息。")

    print(f"提取到的文件名称: {filename}")

    # 接下来可以使用这个文件名来保存数据
    # 例如：
    # sheet_data = pd.read_excel(export_url, header=0)
    # sheet_data.to_csv(f"{filename}.csv", index=False)
    # print(f"数据已成功保存为 {filename}.csv")

except requests.exceptions.RequestException as e:
    print(f"请求发生错误: {e}")
    print("请确保Google Spreadsheet已公开共享，或检查URL是否正确。")
except Exception as e:
    print(f"处理过程中发生错误: {e}")

import requests
import json

# 请替换为您的Google API Key
# 访问 Google Cloud Console (console.cloud.google.com) 创建项目并启用 Drive API，然后生成API Key
api_key = "YOUR_API_KEY" 

# 请替换为您的Google Spreadsheet ID
# 例如: https://docs.google.com/spreadsheets/d/YOUR_SPREADSHEET_ID/edit
spreadsheet_id = "YOUR_SPREADSHEET_ID" 

if api_key == "YOUR_API_KEY" or spreadsheet_id == "YOUR_SPREADSHEET_ID":
    print("请设置您的API Key和Spreadsheet ID。")
else:
    api_url = f"https://www.googleapis.com/drive/v3/files/{spreadsheet_id}?key={api_key}&fields=name"

    try:
        r = requests.get(api_url)
        r.raise_for_status() # 检查请求是否成功

        response_data = r.json()
        filename = response_data.get("name", "未知文件")
        print(f"通过Google Drive API获取到的文件名称: {filename}")

    except requests.exceptions.RequestException as e:
        print(f"API请求发生错误: {e}")
        print("请检查API Key是否有效，以及Spreadsheet ID是否正确。")
        print(f"API响应: {r.text if 'r' in locals() else '无响应'}")
    except json.JSONDecodeError:
        print("API响应不是有效的JSON格式。")
    except Exception as e:
        print(f"处理过程中发生错误: {e}")