密钥错误： "None of [Index(['URL'], dtype='object')] are in the [columns]"

Question

我试图使用谷歌索引API通过python索引我的网站url。我不太懂编码，所以我从一个网站复制了这段代码。

当我搜索这个错误代码之前，似乎有什么问题与csv格式可能?

我的csv格式是这样的"url，"然后新建一行(第二列为空)。

代码如下:

from oauth2client.service_account import ServiceAccountCredentials
import httplib2
import json
import pandas as pd
# https://developers.google.com/search/apis/indexing-api/v3/prereqs#header_2
JSON_KEY_FILE = "/content/astute-tractor-329613-1baed60ec1c0.json"
SCOPES = ["https://www.googleapis.com/auth/indexing"]
credentials = ServiceAccountCredentials.from_json_keyfile_name(JSON_KEY_FILE, scopes=SCOPES)
http = credentials.authorize(httplib2.Http())
def indexURL(urls, http):
# print(type(url)); print("URL: {}".format(url));return;
ENDPOINT = "https://indexing.googleapis.com/v3/urlNotifications:publish"

for u in urls:
# print("U: {} type: {}".format(u, type(u)))

content = {}
content['url'] = u.strip()
content['type'] = "URL_UPDATED"
json_ctn = json.dumps(content)    
# print(json_ctn);return

response, content = http.request(ENDPOINT, method="POST", body=json_ctn)
result = json.loads(content.decode())
# For debug purpose only
if("error" in result):
print("Error({} - {}): {}".format(result["error"]["code"], result["error"]["status"], result["error"]["message"]))
else:
print("urlNotificationMetadata.url: {}".format(result["urlNotificationMetadata"]["url"]))
print("urlNotificationMetadata.latestUpdate.url: {}".format(result["urlNotificationMetadata"]["latestUpdate"]["url"]))
print("urlNotificationMetadata.latestUpdate.type: {}".format(result["urlNotificationMetadata"]["latestUpdate"]["type"]))
print("urlNotificationMetadata.latestUpdate.notifyTime: {}".format(result["urlNotificationMetadata"]["latestUpdate"]["notifyTime"]))
"""
data.csv has 2 columns: URL and date.
I just need the URL column.
"""
csv = pd.read_csv("/content/indekseerida-1.csv")
csv[["URL"]].apply(lambda x: indexURL(x, http))

它给了我这些错误:

KeyError                                  Traceback (most recent call last)
<ipython-input-8-f2bea693a148> in <module>()
44 """
45 csv = pd.read_csv("/content/indekseerida-1.csv")
---> 46 csv[["URL"]].apply(lambda x: indexURL(x, http))
/usr/local/lib/python3.7/dist-packages/pandas/core/frame.py in __getitem__(self, key)
2910             if is_iterator(key):
2911                 key = list(key)
-> 2912             indexer = self.loc._get_listlike_indexer(key, axis=1, raise_missing=True)[1]
2913 
2914         # take() does not accept boolean indexers
/usr/local/lib/python3.7/dist-packages/pandas/core/indexing.py in _get_listlike_indexer(self, key, axis, raise_missing)
1252             keyarr, indexer, new_indexer = ax._reindex_non_unique(keyarr)
1253 
-> 1254         self._validate_read_indexer(keyarr, indexer, axis, raise_missing=raise_missing)
1255         return keyarr, indexer
1256 
/usr/local/lib/python3.7/dist-packages/pandas/core/indexing.py in _validate_read_indexer(self, key, indexer, axis, raise_missing)
1296             if missing == len(indexer):
1297                 axis_name = self.obj._get_axis_name(axis)
-> 1298                 raise KeyError(f"None of [{key}] are in the [{axis_name}]")
1299 
1300             # We (temporarily) allow for some missing keys with .loc, except in
KeyError: "None of [Index(['URL'], dtype='object')] are in the [columns]"

Answer 1

为了修复这个错误，您可以替换

csv[["URL"]].apply(lambda x: indexURL(x, http))

indexURLNew = lambda x: indexURL(x, http)
result_iterator = map(indexURLNew, csv["URL"])
print(list(result_iterator))

result_iterator是一个迭代器，你可以从中得到结果