https://github.com/pandas-dev/pandas/runs/4101565310?check_suite_focus=true
>>>-------------------------------------------------------------------------
Exception in /home/runner/work/pandas/pandas/doc/source/user_guide/io.rst at block ending on line 3032
Specify :okexcept: as an option in the ipython:: block to suppress this message
---------------------------------------------------------------------------
AttributeError Traceback (most recent call last)
<ipython-input-331-4c4d77530df1> in <module>
----> 1 df = pd.read_xml(
2 "s3://irs-form-990/201923199349319487_public.xml",
3 xpath=".//irs:Form990PartVIISectionAGrp",
4 namespaces={"irs": "http://www.irs.gov/efile"}
5 )
~/work/pandas/pandas/pandas/io/xml.py in read_xml(path_or_buffer, xpath, namespaces, elems_only, attrs_only, names, encoding, parser, stylesheet, compression, storage_options)
921 """
922
--> 923 return _parse(
924 path_or_buffer=path_or_buffer,
925 xpath=xpath,
~/work/pandas/pandas/pandas/io/xml.py in _parse(path_or_buffer, xpath, namespaces, elems_only, attrs_only, names, encoding, parser, stylesheet, compression, storage_options, **kwargs)
722 raise ValueError("Values for parser can only be lxml or etree.")
723
--> 724 data_dicts = p.parse_data()
725
726 return _data_to_frame(data=data_dicts, **kwargs)
~/work/pandas/pandas/pandas/io/xml.py in parse_data(self)
387 from lxml.etree import XML
388
--> 389 self.xml_doc = XML(self._parse_doc(self.path_or_buffer))
390
391 if self.stylesheet is not None:
~/work/pandas/pandas/pandas/io/xml.py in _parse_doc(self, raw_doc)
536 )
537
--> 538 handle_data = get_data_from_filepath(
539 filepath_or_buffer=raw_doc,
540 encoding=self.encoding,
~/work/pandas/pandas/pandas/io/xml.py in get_data_from_filepath(filepath_or_buffer, encoding, compression, storage_options)
599 or file_exists(filepath_or_buffer)
600 ):
--> 601 with get_handle(
602 filepath_or_buffer,
603 "r",
~/work/pandas/pandas/pandas/io/common.py in get_handle(path_or_buf, mode, encoding, compression, memory_map, is_text, errors, storage_options)
606
607 # open URLs
--> 608 ioargs = _get_filepath_or_buffer(
609 path_or_buf,
610 encoding=encoding,
~/work/pandas/pandas/pandas/io/common.py in _get_filepath_or_buffer(filepath_or_buffer, encoding, compression, mode, storage_options)
354
355 try:
--> 356 file_obj = fsspec.open(
357 filepath_or_buffer, mode=fsspec_mode, **(storage_options or {})
358 ).open()
~/miniconda3/envs/pandas-dev/lib/python3.8/site-packages/fsspec/core.py in open(self)
133 been deleted; but a with-context is better style.
134 """
--> 135 out = self.__enter__()
136 closer = out.close
137 fobjects = self.fobjects.copy()[:-1]
~/miniconda3/envs/pandas-dev/lib/python3.8/site-packages/fsspec/core.py in __enter__(self)
100 mode = self.mode.replace("t", "").replace("b", "") + "b"
101
--> 102 f = self.fs.open(self.path, mode=mode)
103
104 self.fobjects = [f]
~/miniconda3/envs/pandas-dev/lib/python3.8/site-packages/fsspec/spec.py in open(self, path, mode, block_size, cache_options, **kwargs)
974 else:
975 ac = kwargs.pop("autocommit", not self._intrans)
--> 976 f = self._open(
977 path,
978 mode=mode,
~/miniconda3/envs/pandas-dev/lib/python3.8/site-packages/s3fs/core.py in _open(self, path, mode, block_size, acl, version_id, fill_cache, cache_type, autocommit, requester_pays, **kwargs)
532 cache_type = self.default_cache_type
533
--> 534 return S3File(
535 self,
536 path,
~/miniconda3/envs/pandas-dev/lib/python3.8/site-packages/s3fs/core.py in __init__(self, s3, path, mode, block_size, acl, version_id, fill_cache, s3_additional_kwargs, autocommit, cache_type, requester_pays)
1821 self.details = s3.info(path)
1822 self.version_id = self.details.get("VersionId")
-> 1823 super().__init__(
1824 s3, path, mode, block_size, autocommit=autocommit, cache_type=cache_type
1825 )
~/miniconda3/envs/pandas-dev/lib/python3.8/site-packages/fsspec/spec.py in __init__(self, fs, path, mode, block_size, autocommit, cache_type, cache_options, **kwargs)
1302 if mode == "rb":
1303 if not hasattr(self, "details"):
-> 1304 self.details = fs.info(path)
1305 self.size = self.details["size"]
1306 self.cache = caches[cache_type](
~/miniconda3/envs/pandas-dev/lib/python3.8/site-packages/fsspec/asyn.py in wrapper(*args, **kwargs)
86 def wrapper(*args, **kwargs):
87 self = obj or args[0]
---> 88 return sync(self.loop, func, *args, **kwargs)
89
90 return wrapper
~/miniconda3/envs/pandas-dev/lib/python3.8/site-packages/fsspec/asyn.py in sync(loop, func, timeout, *args, **kwargs)
67 raise FSTimeoutError
68 if isinstance(result[0], BaseException):
---> 69 raise result[0]
70 return result[0]
71
~/miniconda3/envs/pandas-dev/lib/python3.8/site-packages/fsspec/asyn.py in _runner(event, coro, result, timeout)
23 coro = asyncio.wait_for(coro, timeout=timeout)
24 try:
---> 25 result[0] = await coro
26 except Exception as ex:
27 result[0] = ex
~/miniconda3/envs/pandas-dev/lib/python3.8/site-packages/s3fs/core.py in _info(self, path, bucket, key, refresh, version_id)
1062 else:
1063 try:
-> 1064 out = await self._simple_info(path)
1065 except PermissionError:
1066 # If the permissions aren't enough for scanning a prefix
~/miniconda3/envs/pandas-dev/lib/python3.8/site-packages/s3fs/core.py in _simple_info(self, path)
975 prefix = key.strip("/")
976
--> 977 out = await self._call_s3(
978 "list_objects_v2",
979 self.kwargs,
~/miniconda3/envs/pandas-dev/lib/python3.8/site-packages/s3fs/core.py in _call_s3(self, method, *akwarglist, **kwargs)
235
236 async def _call_s3(self, method, *akwarglist, **kwargs):
--> 237 await self.set_session()
238 s3 = await self.get_s3(kwargs.get("Bucket"))
239 method = getattr(s3, method)
~/miniconda3/envs/pandas-dev/lib/python3.8/site-packages/s3fs/core.py in set_session(self, refresh, kwargs)
376
377 conf = AioConfig(**config_kwargs)
--> 378 self.session = aiobotocore.AioSession(**self.kwargs)
379
380 for parameters in (config_kwargs, self.kwargs, init_kwargs, client_kwargs):
AttributeError: module 'aiobotocore' has no attribute 'AioSession'
cc @pandas-dev/pandas-core
Comment From: jreback
I guess s3fs changed or incompatible with new aiobotocore.
cc @martindurant if any ideas.
Comment From: phofl
Probably incompatible. aiobotocore deprecated the AioSession object a few weeks ago, probably removed now.
Release Note of 2.0:
turn off default AIOBOTOCORE_DEPRECATED_1_4_0_APIS env var to match botocore module. See notes in 1.4.0.
Pinning to < 2.0 in s3fs should help
Comment From: jorisvandenbossche
It seems a fix for this was already released a while ago: https://github.com/fsspec/s3fs/issues/514 (so the question might then be why those builds don't get the latest s3fs version)
Comment From: phofl
Looks like s3fs requires aiobotocore~=1.4.1, which references 1.4.2 in this case and not 2.0. Looks like aiobotocore 2.0 is installed first and searches for the latest s3fs release without this clause, which seems to be 2021.07
Comment From: rhshadrach
Looks like docs build is now green, okay to close?
Comment From: phofl
No aiobotocore is pinned to lower than 2.0
Comment From: simonjayhawkins
Removing milestone here as not critical to fix for 1.3.x (or backport unpin).
Comment From: ParfaitG
I see this issue involves a read_xml run in IO tools docs to demonstrate an S3 bucket call. An :okwarning: was added to its ipython block. If resolved, should we close this issue? If needed, I can convert ipython block to code-block.
Comment From: phofl
We can close when we can unpin aiobotocore