python - Pandas 中的 read_excel 错误 ('ElementTree' 对象没有属性 'getiterator' )

Question

我什么都试过了。我是一个完全的初学者。所以非常感谢帮助。

这是我要运行的代码。

import pandas as pd

filepath = r'/Users/vignesh/Desktop/Python/test2.xlsx'
df = pd.read_excel(filepath)
print(df)

这在 Jupyterlabs 上不断抛出以下错误。有人知道我该如何解决吗？我已经安装并更新了 xlrd、openpyxl。我在 YT 上看了一些视频，看看其他人是怎么做的。他们似乎可以毫不费力地使用这些相同的代码行。

---------------------------------------------------------------------------
AttributeError                            Traceback (most recent call last)
<ipython-input-3-fa10276656c9> in <module>
----> 1 pd.read_excel('test2.xlsx')

/Library/Frameworks/Python.framework/Versions/3.9/lib/python3.9/site-packages/pandas/util/_decorators.py in wrapper(*args, **kwargs)
    294                 )
    295                 warnings.warn(msg, FutureWarning, stacklevel=stacklevel)
--> 296             return func(*args, **kwargs)
    297 
    298         return wrapper

/Library/Frameworks/Python.framework/Versions/3.9/lib/python3.9/site-packages/pandas/io/excel/_base.py in read_excel(io, sheet_name, header, names, index_col, usecols, squeeze, dtype, engine, converters, true_values, false_values, skiprows, nrows, na_values, keep_default_na, na_filter, verbose, parse_dates, date_parser, thousands, comment, skipfooter, convert_float, mangle_dupe_cols)
    302 
    303     if not isinstance(io, ExcelFile):
--> 304         io = ExcelFile(io, engine=engine)
    305     elif engine and engine != io.engine:
    306         raise ValueError(

/Library/Frameworks/Python.framework/Versions/3.9/lib/python3.9/site-packages/pandas/io/excel/_base.py in __init__(self, path_or_buffer, engine)
    865         self._io = stringify_path(path_or_buffer)
    866 
--> 867         self._reader = self._engines[engine](self._io)
    868 
    869     def __fspath__(self):

/Library/Frameworks/Python.framework/Versions/3.9/lib/python3.9/site-packages/pandas/io/excel/_xlrd.py in __init__(self, filepath_or_buffer)
     20         err_msg = "Install xlrd >= 1.0.0 for Excel support"
     21         import_optional_dependency("xlrd", extra=err_msg)
---> 22         super().__init__(filepath_or_buffer)
     23 
     24     @property

/Library/Frameworks/Python.framework/Versions/3.9/lib/python3.9/site-packages/pandas/io/excel/_base.py in __init__(self, filepath_or_buffer)
    351             self.book = self.load_workbook(filepath_or_buffer)
    352         elif isinstance(filepath_or_buffer, str):
--> 353             self.book = self.load_workbook(filepath_or_buffer)
    354         elif isinstance(filepath_or_buffer, bytes):
    355             self.book = self.load_workbook(BytesIO(filepath_or_buffer))

/Library/Frameworks/Python.framework/Versions/3.9/lib/python3.9/site-packages/pandas/io/excel/_xlrd.py in load_workbook(self, filepath_or_buffer)
     35             return open_workbook(file_contents=data)
     36         else:
---> 37             return open_workbook(filepath_or_buffer)
     38 
     39     @property

/Library/Frameworks/Python.framework/Versions/3.9/lib/python3.9/site-packages/xlrd/__init__.py in open_workbook(filename, logfile, verbosity, use_mmap, file_contents, encoding_override, formatting_info, on_demand, ragged_rows)
    128         if 'xl/workbook.xml' in component_names:
    129             from . import xlsx
--> 130             bk = xlsx.open_workbook_2007_xml(
    131                 zf,
    132                 component_names,

/Library/Frameworks/Python.framework/Versions/3.9/lib/python3.9/site-packages/xlrd/xlsx.py in open_workbook_2007_xml(zf, component_names, logfile, verbosity, use_mmap, formatting_info, on_demand, ragged_rows)
    810     del zflo
    811     zflo = zf.open(component_names['xl/workbook.xml'])
--> 812     x12book.process_stream(zflo, 'Workbook')
    813     del zflo
    814     props_name = 'docprops/core.xml'

/Library/Frameworks/Python.framework/Versions/3.9/lib/python3.9/site-packages/xlrd/xlsx.py in process_stream(self, stream, heading)
    264         self.tree = ET.parse(stream)
    265         getmethod = self.tag2meth.get
--> 266         for elem in self.tree.iter() if Element_has_iter else self.tree.getiterator():
    267             if self.verbosity >= 3:
    268                 self.dump_elem(elem)

AttributeError: 'ElementTree' object has no attribute 'getiterator'

Answer 1

您正在使用带有 xldr 的 Python 3.9，此错误是由于从 xldr 中删除了 getiterator 方法。 (NB 不指定引擎，默认使用 xldr 根据 pandas documentation )

您可以使用 Python < 3.9 的版本或使用不同的引擎来解析您的 excel 文件。像这样:

import pandas as pd

filepath = r'/Users/vignesh/Desktop/Python/test2.xlsx'
df = pd.read_excel(filepath, engine='openpyxl')
print(df)