使用Python从Google Drive/Workspace下载电子表格

Question

你能给我一个Python的例子，教我怎么根据Google Sheets的关键字和工作表ID（gid）下载一个电子表格吗？我搞不定。

我查了API的1、2和3版本，但都没找到解决办法。我搞不懂他们复杂的类似ATOM的API，gdata.docs.service.DocsService._DownloadFile这个私有方法还说我没有权限，我也不想自己写一个完整的Google登录认证系统。真是让我快崩溃了。

我有几个电子表格，想这样访问它们：

username = 'mygooglelogin@gmail.com'
password = getpass.getpass()

def get_spreadsheet(key, gid=0):
    ... (help!) ...

for row in get_spreadsheet('5a3c7f7dcee4b4f'):
    cell1, cell2, cell3 = row
    ...

求你帮帮我。

---

更新 1：我试过以下方法，但无论是Download()还是Export()都没用。（关于DocsService的文档可以在这里找到）

import gdata.docs.service
import getpass
import os
import tempfile
import csv

def get_csv(file_path):
  return csv.reader(file(file_path).readlines())

def get_spreadsheet(key, gid=0):
  gd_client = gdata.docs.service.DocsService()
  gd_client.email = 'xxxxxxxxx@gmail.com'
  gd_client.password = getpass.getpass()
  gd_client.ssl = False
  gd_client.source = "My Fancy Spreadsheet Downloader"
  gd_client.ProgrammaticLogin()

  file_path = tempfile.mktemp(suffix='.csv')
  uri = 'http://docs.google.com/feeds/documents/private/full/%s' % key
  try:
    entry = gd_client.GetDocumentListEntry(uri)

    # XXXX - The following dies with RequestError "Unauthorized"
    gd_client.Download(entry, file_path)

    return get_csv(file_path)
  finally:
    try:
      os.remove(file_path)
    except OSError:
      pass

Answer 1

你可以试试文档中提到的AuthSub方法，具体在导出电子表格的部分。

为电子表格服务获取一个单独的登录令牌，然后用这个令牌来替代导出时使用的。把这个添加到get_spreadsheet的代码里对我来说是有效的：

import gdata.spreadsheet.service

def get_spreadsheet(key, gid=0):
    # ...
    spreadsheets_client = gdata.spreadsheet.service.SpreadsheetsService()
    spreadsheets_client.email = gd_client.email
    spreadsheets_client.password = gd_client.password
    spreadsheets_client.source = "My Fancy Spreadsheet Downloader"
    spreadsheets_client.ProgrammaticLogin()

    # ...
    entry = gd_client.GetDocumentListEntry(uri)
    docs_auth_token = gd_client.GetClientLoginToken()
    gd_client.SetClientLoginToken(spreadsheets_client.GetClientLoginToken())
    gd_client.Export(entry, file_path)
    gd_client.SetClientLoginToken(docs_auth_token) # reset the DocList auth token

注意我还用了Export，因为Download似乎只会下载PDF文件。

Answer 2

gspread这个库是一个更新、更简单的方法来与Google表格进行互动。相比之下，之前的解决方案推荐使用gdata库，但这个库不仅太底层，而且还复杂得让人头疼。

你还需要创建并下载一个服务账户密钥，格式为JSON。可以在这里找到：https://console.developers.google.com/apis/credentials/serviceaccountkey

下面是一个使用它的例子：

import csv
import gspread
from oauth2client.service_account import ServiceAccountCredentials

scope = ['https://spreadsheets.google.com/feeds']
credentials = ServiceAccountCredentials.from_json_keyfile_name('credentials.json', scope)

docid = "0zjVQXjJixf-SdGpLKnJtcmQhNjVUTk1hNTRpc0x5b9c"

client = gspread.authorize(credentials)
spreadsheet = client.open_by_key(docid)
for i, worksheet in enumerate(spreadsheet.worksheets()):
    filename = docid + '-worksheet' + str(i) + '.csv'
    with open(filename, 'wb') as f:
        writer = csv.writer(f)
        writer.writerows(worksheet.get_all_values())

Answer 3

如果有人遇到这个问题想找个快速解决办法，这里有一个目前有效的解决方案，它不依赖于gdata客户端库：

#!/usr/bin/python

import re, urllib, urllib2

class Spreadsheet(object):
    def __init__(self, key):
        super(Spreadsheet, self).__init__()
        self.key = key

class Client(object):
    def __init__(self, email, password):
        super(Client, self).__init__()
        self.email = email
        self.password = password

    def _get_auth_token(self, email, password, source, service):
        url = "https://www.google.com/accounts/ClientLogin"
        params = {
            "Email": email, "Passwd": password,
            "service": service,
            "accountType": "HOSTED_OR_GOOGLE",
            "source": source
        }
        req = urllib2.Request(url, urllib.urlencode(params))
        return re.findall(r"Auth=(.*)", urllib2.urlopen(req).read())[0]

    def get_auth_token(self):
        source = type(self).__name__
        return self._get_auth_token(self.email, self.password, source, service="wise")

    def download(self, spreadsheet, gid=0, format="csv"):
        url_format = "https://spreadsheets.google.com/feeds/download/spreadsheets/Export?key=%s&exportFormat=%s&gid=%i"
        headers = {
            "Authorization": "GoogleLogin auth=" + self.get_auth_token(),
            "GData-Version": "3.0"
        }
        req = urllib2.Request(url_format % (spreadsheet.key, format, gid), headers=headers)
        return urllib2.urlopen(req)

if __name__ == "__main__":
    import getpass
    import csv

    email = "" # (your email here)
    password = getpass.getpass()
    spreadsheet_id = "" # (spreadsheet id here)

    # Create client and spreadsheet objects
    gs = Client(email, password)
    ss = Spreadsheet(spreadsheet_id)

    # Request a file-like object containing the spreadsheet's contents
    csv_file = gs.download(ss)

    # Parse as CSV and print the rows
    for row in csv.reader(csv_file):
        print ", ".join(row)