Question

我试图改编the following script。我已经获得了所遵循的内容。

#!/usr/bin/python3

import re
import csv

import urllib.request, urllib.parse

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 = urllib.request.Request(url, urllib.parse.urlencode(params))
        return re.findall(r"Auth=(.*)", urllib.request.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 = urllib.request.Request(url_format % (spreadsheet.key, format, gid), headers=headers)
        return urllib.request.urlopen(req)

if __name__ == "__main__":
    email = "xxx" # (your email here)
    password = "yyyy"
    spreadsheet_id = "zzz" # (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
    print(gs.download(ss).read())

我的问题是我有以下错误。

Traceback (most recent call last):
  File "/Users/test.py", line 54, in <module>
    print(gs.download(ss).read())
  File "/Users/test.py", line 38, in download
    "Authorization": "GoogleLogin auth=" + self.get_auth_token(),
  File "/Users/test.py", line 33, in get_auth_token
    return self._get_auth_token(self.email, self.password, source, service="wise")
  File "/Users/test.py", line 29, in _get_auth_token
    return re.findall(r"Auth=(.*)", urllib.request.urlopen(req).read())[0]
  File "/Library/Frameworks/Python.framework/Versions/3.2/lib/python3.2/urllib/request.py", line 138, in urlopen
    return opener.open(url, data, timeout)
  File "/Library/Frameworks/Python.framework/Versions/3.2/lib/python3.2/urllib/request.py", line 364, in open
    req = meth(req)
  File "/Library/Frameworks/Python.framework/Versions/3.2/lib/python3.2/urllib/request.py", line 1052, in do_request_
    raise TypeError("POST data should be bytes"
TypeError: POST data should be bytes or an iterable of bytes. It cannot be str.

麻烦来自方法urllib.request.urlopen(req)中的_get_auth_token。有办法解决这个问题吗？

Answer 1

是的，在发布之前将数据编码为字节：

req = urllib.request.Request(url, urllib.parse.urlencode(params).encode('ASCII'))

我在这里假设您的数据仅限ASCII（通常是电子邮件地址，大概是您的密码）。

urllib - 从Python2更新到Python3

1 个答案: