def read_html(io,
match='.+',
flavor=None,
header=None,
index_col=None,
skiprows=None,
attrs=None,
parse_dates=False,
tupleize_cols=False,
thousands=',',
encoding=None,
decimal='.',
converters=None,
na_values=None,
keep_default_na=True):
r"""Read HTML tables into a ``list`` of ``DataFrame`` objects.
Parameters
----------
io : str or file-like
A URL, a file-like object, or a raw string containing HTML. Note that
lxml only accepts the http, ftp and file url protocols. If you have a
URL that starts with ``'https'`` you might try removing the ``'s'``.
match : str or compiled regular expression, optional
The set of tables containing text matching this regex or string will be
returned. Unless the HTML is extremely simple you will probably need to
pass a non-empty string here. Defaults to '.+' (match any non-empty
string). The default value will return all tables contained on a page.
This value is converted to a regular expression so that there is
consistent behavior between Beautiful Soup and lxml.
flavor : str or None, container of strings
The parsing engine to use. 'bs4' and 'html5lib' are synonymous with
each other, they are both there for backwards compatibility. The
default of ``None`` tries to use ``lxml`` to parse and if that fails it
falls back on ``bs4`` + ``html5lib``.
header : int or list-like or None, optional
The row (or list of rows for a :class:`~pandas.MultiIndex`) to use to
make the columns headers.
index_col : int or list-like or None, optional
The column (or list of columns) to use to create the index.
skiprows : int or list-like or slice or None, optional
0-based. Number of rows to skip after parsing the column integer. If a
sequence of integers or a slice is given, will skip the rows indexed by
that sequence. Note that a single element sequence means 'skip the nth
row' whereas an integer means 'skip n rows'.
attrs : dict or None, optional
This is a dictionary of attributes that you can pass to use to identify
the table in the HTML. These are not checked for validity before being
passed to lxml or Beautiful Soup. However, these attributes must be
valid HTML table attributes to work correctly. For example, ::
attrs = {'id': 'table'}
is a valid attribute dictionary because the 'id' HTML tag attribute is
a valid HTML attribute for *any* HTML tag as per `this document
<http://www.w3.org/TR/html-markup/global-attributes.html>`__. ::
attrs = {'asdf': 'table'}
is *not* a valid attribute dictionary because 'asdf' is not a valid
HTML attribute even if it is a valid XML attribute. Valid HTML 4.01
table attributes can be found `here
<http://www.w3.org/TR/REC-html40/struct/tables.html#h-11.2>`__. A
working draft of the HTML 5 spec can be found `here
<http://www.w3.org/TR/html-markup/table.html>`__. It contains the
latest information on table attributes for the modern web.
parse_dates : bool, optional
See :func:`~pandas.read_csv` for more details.
tupleize_cols : bool, optional
If ``False`` try to parse multiple header rows into a
:class:`~pandas.MultiIndex`, otherwise return raw tuples. Defaults to
``False``.
thousands : str, optional
Separator to use to parse thousands. Defaults to ``','``.
encoding : str or None, optional
The encoding used to decode the web page. Defaults to ``None``.``None``
preserves the previous encoding behavior, which depends on the
underlying parser library (e.g., the parser library will try to use
the encoding provided by the document).
decimal : str, default '.'
Character to recognize as decimal point (e.g. use ',' for European
data).
.. versionadded:: 0.19.0
converters : dict, default None
Dict of functions for converting values in certain columns. Keys can
either be integers or column labels, values are functions that take one
input argument, the cell (not column) content, and return the
transformed content.
.. versionadded:: 0.19.0
na_values : iterable, default None
Custom NA values
.. versionadded:: 0.19.0
keep_default_na : bool, default True
If na_values are specified and keep_default_na is False the default NaN
values are overridden, otherwise they're appended to
.. versionadded:: 0.19.0
Returns
-------
dfs : list of DataFrames
Notes
-----
Before using this function you should read the :ref:`gotchas about the
HTML parsing libraries <io.html.gotchas>`.
Expect to do some cleanup after you call this function. For example, you
might need to manually assign column names if the column names are
converted to NaN when you pass the `header=0` argument. We try to assume as
little as possible about the structure of the table and push the
idiosyncrasies of the HTML contained in the table to the user.
This function searches for ``<table>`` elements and only for ``<tr>``
and ``<th>`` rows and ``<td>`` elements within each ``<tr>`` or ``<th>``
element in the table. ``<td>`` stands for "table data".
Similar to :func:`~pandas.read_csv` the `header` argument is applied
**after** `skiprows` is applied.
This function will *always* return a list of :class:`DataFrame` *or*
it will fail, e.g., it will *not* return an empty list.
Examples
--------
See the :ref:`read_html documentation in the IO section of the docs
<io.read_html>` for some examples of reading in HTML tables.
See Also
--------
pandas.read_csv
"""
_importers()
# Type check here. We don't want to parse only to fail because of an
# invalid value of an integer skiprows.
if isinstance(skiprows, numbers.Integral) and skiprows < 0:
raise ValueError('cannot skip rows starting from the end of the '
'data (you passed a negative value)')
_validate_header_arg(header)
return _parse(flavor=flavor,
io=io,
match=match,
header=header,
index_col=index_col,
skiprows=skiprows,
parse_dates=parse_dates,
tupleize_cols=tupleize_cols,
thousands=thousands,
attrs=attrs,
encoding=encoding,
decimal=decimal,
converters=converters,
na_values=na_values,
keep_default_na=keep_default_na)
def read_html(io, match='.+', flavor=None, header=None, index_col=None,
skiprows=None, attrs=None, parse_dates=False,
tupleize_cols=False, thousands=',', encoding=None,
decimal='.', converters=None, na_values=None,
keep_default_na=True):
r"""Read HTML tables into a ``list`` of ``DataFrame`` objects.
Parameters
----------
io : str or file-like
A URL, a file-like object, or a raw string containing HTML. Note that
lxml only accepts the http, ftp and file url protocols. If you have a
URL that starts with ``'https'`` you might try removing the ``'s'``.
match : str or compiled regular expression, optional
The set of tables containing text matching this regex or string will be
returned. Unless the HTML is extremely simple you will probably need to
pass a non-empty string here. Defaults to '.+' (match any non-empty
string). The default value will return all tables contained on a page.
This value is converted to a regular expression so that there is
consistent behavior between Beautiful Soup and lxml.
flavor : str or None, container of strings
The parsing engine to use. 'bs4' and 'html5lib' are synonymous with
each other, they are both there for backwards compatibility. The
default of ``None`` tries to use ``lxml`` to parse and if that fails it
falls back on ``bs4`` + ``html5lib``.
header : int or list-like or None, optional
The row (or list of rows for a :class:`~pandas.MultiIndex`) to use to
make the columns headers.
index_col : int or list-like or None, optional
The column (or list of columns) to use to create the index.
skiprows : int or list-like or slice or None, optional
0-based. Number of rows to skip after parsing the column integer. If a
sequence of integers or a slice is given, will skip the rows indexed by
that sequence. Note that a single element sequence means 'skip the nth
row' whereas an integer means 'skip n rows'.
attrs : dict or None, optional
This is a dictionary of attributes that you can pass to use to identify
the table in the HTML. These are not checked for validity before being
passed to lxml or Beautiful Soup. However, these attributes must be
valid HTML table attributes to work correctly. For example, ::
attrs = {'id': 'table'}
is a valid attribute dictionary because the 'id' HTML tag attribute is
a valid HTML attribute for *any* HTML tag as per `this document
<http://www.w3.org/TR/html-markup/global-attributes.html>`__. ::
attrs = {'asdf': 'table'}
is *not* a valid attribute dictionary because 'asdf' is not a valid
HTML attribute even if it is a valid XML attribute. Valid HTML 4.01
table attributes can be found `here
<http://www.w3.org/TR/REC-html40/struct/tables.html#h-11.2>`__. A
working draft of the HTML 5 spec can be found `here
<http://www.w3.org/TR/html-markup/table.html>`__. It contains the
latest information on table attributes for the modern web.
parse_dates : bool, optional
See :func:`~pandas.read_csv` for more details.
tupleize_cols : bool, optional
If ``False`` try to parse multiple header rows into a
:class:`~pandas.MultiIndex`, otherwise return raw tuples. Defaults to
``False``.
thousands : str, optional
Separator to use to parse thousands. Defaults to ``','``.
encoding : str or None, optional
The encoding used to decode the web page. Defaults to ``None``.``None``
preserves the previous encoding behavior, which depends on the
underlying parser library (e.g., the parser library will try to use
the encoding provided by the document).
decimal : str, default '.'
Character to recognize as decimal point (e.g. use ',' for European
data).
.. versionadded:: 0.19.0
converters : dict, default None
Dict of functions for converting values in certain columns. Keys can
either be integers or column labels, values are functions that take one
input argument, the cell (not column) content, and return the
transformed content.
.. versionadded:: 0.19.0
na_values : iterable, default None
Custom NA values
.. versionadded:: 0.19.0
keep_default_na : bool, default True
If na_values are specified and keep_default_na is False the default NaN
values are overridden, otherwise they're appended to
.. versionadded:: 0.19.0
Returns
-------
dfs : list of DataFrames
Notes
-----
Before using this function you should read the :ref:`gotchas about the
HTML parsing libraries <html-gotchas>`.
Expect to do some cleanup after you call this function. For example, you
might need to manually assign column names if the column names are
converted to NaN when you pass the `header=0` argument. We try to assume as
little as possible about the structure of the table and push the
idiosyncrasies of the HTML contained in the table to the user.
This function searches for ``<table>`` elements and only for ``<tr>``
and ``<th>`` rows and ``<td>`` elements within each ``<tr>`` or ``<th>``
element in the table. ``<td>`` stands for "table data".
Similar to :func:`~pandas.read_csv` the `header` argument is applied
**after** `skiprows` is applied.
This function will *always* return a list of :class:`DataFrame` *or*
it will fail, e.g., it will *not* return an empty list.
Examples
--------
See the :ref:`read_html documentation in the IO section of the docs
<io.read_html>` for some examples of reading in HTML tables.
See Also
--------
pandas.read_csv
"""
_importers()
# Type check here. We don't want to parse only to fail because of an
# invalid value of an integer skiprows.
if isinstance(skiprows, numbers.Integral) and skiprows < 0:
raise ValueError('cannot skip rows starting from the end of the '
'data (you passed a negative value)')
_validate_header_arg(header)
return _parse(flavor=flavor, io=io, match=match, header=header,
index_col=index_col, skiprows=skiprows,
parse_dates=parse_dates, tupleize_cols=tupleize_cols,
thousands=thousands, attrs=attrs, encoding=encoding,
decimal=decimal, converters=converters, na_values=na_values,
keep_default_na=keep_default_na)
def parse(self,
sheet_name=0,
header=0,
names=None,
index_col=None,
usecols=None,
squeeze=False,
dtype=None,
true_values=None,
false_values=None,
skiprows=None,
nrows=None,
na_values=None,
verbose=False,
parse_dates=False,
date_parser=None,
thousands=None,
comment=None,
skipfooter=0,
convert_float=True,
mangle_dupe_cols=True,
**kwds):
_validate_header_arg(header)
ret_dict = False
# Keep sheetname to maintain backwards compatibility.
if isinstance(sheet_name, list):
sheets = sheet_name
ret_dict = True
elif sheet_name is None:
sheets = self.sheet_names
ret_dict = True
else:
sheets = [sheet_name]
# handle same-type duplicates.
sheets = list(OrderedDict.fromkeys(sheets).keys())
output = OrderedDict()
for asheetname in sheets:
if verbose:
print("Reading sheet {sheet}".format(sheet=asheetname))
if isinstance(asheetname, compat.string_types):
sheet = self.get_sheet_by_name(asheetname)
else: # assume an integer if not a string
sheet = self.get_sheet_by_index(asheetname)
data = self.get_sheet_data(sheet, convert_float)
usecols = _maybe_convert_usecols(usecols)
if sheet.nrows == 0:
output[asheetname] = DataFrame()
continue
if is_list_like(header) and len(header) == 1:
header = header[0]
# forward fill and pull out names for MultiIndex column
header_names = None
if header is not None and is_list_like(header):
header_names = []
control_row = [True] * len(data[0])
for row in header:
if is_integer(skiprows):
row += skiprows
data[row], control_row = _fill_mi_header(data[row],
control_row)
if index_col is not None:
header_name, _ = _pop_header_name(data[row], index_col)
header_names.append(header_name)
if is_list_like(index_col):
# Forward fill values for MultiIndex index.
if not is_list_like(header):
offset = 1 + header
else:
offset = 1 + max(header)
# Check if we have an empty dataset
# before trying to collect data.
if offset < len(data):
for col in index_col:
last = data[offset][col]
for row in range(offset + 1, len(data)):
if data[row][col] == '' or data[row][col] is None:
data[row][col] = last
else:
last = data[row][col]
has_index_names = is_list_like(header) and len(header) > 1
# GH 12292 : error when read one empty column from excel file
try:
parser = TextParser(data,
names=names,
header=header,
index_col=index_col,
has_index_names=has_index_names,
squeeze=squeeze,
dtype=dtype,
true_values=true_values,
false_values=false_values,
skiprows=skiprows,
nrows=nrows,
na_values=na_values,
parse_dates=parse_dates,
date_parser=date_parser,
thousands=thousands,
comment=comment,
skipfooter=skipfooter,
usecols=usecols,
mangle_dupe_cols=mangle_dupe_cols,
**kwds)
output[asheetname] = parser.read(nrows=nrows)
if not squeeze or isinstance(output[asheetname], DataFrame):
if header_names:
output[asheetname].columns = output[
asheetname].columns.set_names(header_names)
elif compat.PY2:
output[asheetname].columns = _maybe_convert_to_string(
output[asheetname].columns)
except EmptyDataError:
# No Data, return an empty DataFrame
output[asheetname] = DataFrame()
if ret_dict:
return output
else:
return output[asheetname]
def parse(self,
sheet_name=0,
header=0,
names=None,
index_col=None,
usecols=None,
squeeze=False,
dtype=None,
true_values=None,
false_values=None,
skiprows=None,
nrows=None,
na_values=None,
verbose=False,
parse_dates=False,
date_parser=None,
thousands=None,
comment=None,
skipfooter=0,
convert_float=True,
mangle_dupe_cols=True,
**kwds):
_validate_header_arg(header)
ret_dict = False
# Keep sheetname to maintain backwards compatibility.
if isinstance(sheet_name, list):
sheets = sheet_name
ret_dict = True
elif sheet_name is None:
sheets = self.sheet_names
ret_dict = True
else:
sheets = [sheet_name]
# handle same-type duplicates.
sheets = list(OrderedDict.fromkeys(sheets).keys())
output = OrderedDict()
for asheetname in sheets:
if verbose:
print("Reading sheet {sheet}".format(sheet=asheetname))
if isinstance(asheetname, compat.string_types):
sheet = self.get_sheet_by_name(asheetname)
else: # assume an integer if not a string
sheet = self.get_sheet_by_index(asheetname)
data = self.get_sheet_data(sheet, convert_float)
usecols = _maybe_convert_usecols(usecols)
if sheet.nrows == 0:
output[asheetname] = DataFrame()
continue
if is_list_like(header) and len(header) == 1:
header = header[0]
# forward fill and pull out names for MultiIndex column
header_names = None
if header is not None and is_list_like(header):
header_names = []
control_row = [True] * len(data[0])
for row in header:
if is_integer(skiprows):
row += skiprows
data[row], control_row = _fill_mi_header(
data[row], control_row)
if index_col is not None:
header_name, _ = _pop_header_name(data[row], index_col)
header_names.append(header_name)
if is_list_like(index_col):
# Forward fill values for MultiIndex index.
if not is_list_like(header):
offset = 1 + header
else:
offset = 1 + max(header)
# Check if we have an empty dataset
# before trying to collect data.
if offset < len(data):
for col in index_col:
last = data[offset][col]
for row in range(offset + 1, len(data)):
if data[row][col] == '' or data[row][col] is None:
data[row][col] = last
else:
last = data[row][col]
has_index_names = is_list_like(header) and len(header) > 1
# GH 12292 : error when read one empty column from excel file
try:
parser = TextParser(data,
names=names,
header=header,
index_col=index_col,
has_index_names=has_index_names,
squeeze=squeeze,
dtype=dtype,
true_values=true_values,
false_values=false_values,
skiprows=skiprows,
nrows=nrows,
na_values=na_values,
parse_dates=parse_dates,
date_parser=date_parser,
thousands=thousands,
comment=comment,
skipfooter=skipfooter,
usecols=usecols,
mangle_dupe_cols=mangle_dupe_cols,
**kwds)
output[asheetname] = parser.read(nrows=nrows)
if not squeeze or isinstance(output[asheetname], DataFrame):
if header_names:
output[asheetname].columns = output[
asheetname].columns.set_names(header_names)
except EmptyDataError:
# No Data, return an empty DataFrame
output[asheetname] = DataFrame()
if ret_dict:
return output
else:
return output[asheetname]
def _parse_excel(self,
sheetname=0,
header=0,
skiprows=None,
names=None,
skip_footer=0,
index_col=None,
has_index_names=None,
parse_cols=None,
parse_dates=False,
date_parser=None,
na_values=None,
thousands=None,
convert_float=True,
true_values=None,
false_values=None,
verbose=False,
dtype=None,
squeeze=False,
**kwds):
skipfooter = kwds.pop('skipfooter', None)
if skipfooter is not None:
skip_footer = skipfooter
_validate_header_arg(header)
if has_index_names is not None:
warn(
"\nThe has_index_names argument is deprecated; index names "
"will be automatically inferred based on index_col.\n"
"This argmument is still necessary if reading Excel output "
"from 0.16.2 or prior with index names.",
FutureWarning,
stacklevel=3)
if 'chunksize' in kwds:
raise NotImplementedError("chunksize keyword of read_excel "
"is not implemented")
if parse_dates is True and index_col is None:
warn("The 'parse_dates=True' keyword of read_excel was provided"
" without an 'index_col' keyword value.")
def _parse_cell(cell_contents, cell_typ):
"""converts the contents of the cell into a pandas
appropriate object"""
if cell_typ == XL_CELL_DATE:
if xlrd_0_9_3:
# Use the newer xlrd datetime handling.
try:
cell_contents = \
xldate.xldate_as_datetime(cell_contents,
epoch1904)
except OverflowError:
return cell_contents
# Excel doesn't distinguish between dates and time,
# so we treat dates on the epoch as times only.
# Also, Excel supports 1900 and 1904 epochs.
year = (cell_contents.timetuple())[0:3]
if ((not epoch1904 and year == (1899, 12, 31))
or (epoch1904 and year == (1904, 1, 1))):
cell_contents = time(cell_contents.hour,
cell_contents.minute,
cell_contents.second,
cell_contents.microsecond)
else:
# Use the xlrd <= 0.9.2 date handling.
try:
dt = xldate.xldate_as_tuple(cell_contents, epoch1904)
except xldate.XLDateTooLarge:
return cell_contents
if dt[0] < MINYEAR:
cell_contents = time(*dt[3:])
else:
cell_contents = datetime(*dt)
elif cell_typ == XL_CELL_ERROR:
cell_contents = np.nan
elif cell_typ == XL_CELL_BOOLEAN:
cell_contents = bool(cell_contents)
elif convert_float and cell_typ == XL_CELL_NUMBER:
# GH5394 - Excel 'numbers' are always floats
# it's a minimal perf hit and less suprising
val = int(cell_contents)
if val == cell_contents:
cell_contents = val
return cell_contents
ret_dict = False
if isinstance(sheetname, list):
sheets = sheetname
ret_dict = True
elif sheetname is None:
sheets = self.sheet_names
ret_dict = True
else:
sheets = [sheetname]
# handle same-type duplicates.
sheets = list(OrderedDict.fromkeys(sheets).keys())
output = OrderedDict()
import xlrd
from xlrd import (xldate, XL_CELL_DATE, XL_CELL_ERROR, XL_CELL_BOOLEAN,
XL_CELL_NUMBER)
epoch1904 = self.book.datemode
# xlrd >= 0.9.3 can return datetime objects directly.
if LooseVersion(xlrd.__VERSION__) >= LooseVersion("0.9.3"):
xlrd_0_9_3 = True
else:
xlrd_0_9_3 = False
# Keep sheetname to maintain backwards compatibility.
for asheetname in sheets:
if verbose:
print("Reading sheet %s" % asheetname)
if isinstance(asheetname, compat.string_types):
sheet = self.book.sheet_by_name(asheetname)
else: # assume an integer if not a string
sheet = self.book.sheet_by_index(asheetname)
data = []
should_parse = {}
if sheet.nrows > 5000:
raise Exception(
"The raw file contains more than 5000 rows. Please check if it is correct or split the files (max: 5000 rows) for upload"
)
elif kwds.get('MaxTest'):
continue
for i in range(sheet.nrows):
row = []
for j, (value, typ) in enumerate(
zip(sheet.row_values(i), sheet.row_types(i))):
if parse_cols is not None and j not in should_parse:
should_parse[j] = self._should_parse(j, parse_cols)
if parse_cols is None or should_parse[j]:
row.append(_parse_cell(value, typ))
data.append(row)
# output[asheetname] = data
if sheet.nrows == 0:
output[asheetname] = DataFrame()
continue
if is_list_like(header) and len(header) == 1:
header = header[0]
# forward fill and pull out names for MultiIndex column
header_names = None
if header is not None:
if is_list_like(header):
header_names = []
control_row = [True for x in data[0]]
for row in header:
if is_integer(skiprows):
row += skiprows
data[row], control_row = _fill_mi_header(
data[row], control_row)
header_name, data[row] = _pop_header_name(
data[row], index_col)
header_names.append(header_name)
if is_list_like(index_col):
# forward fill values for MultiIndex index
if not is_list_like(header):
offset = 1 + header
else:
offset = 1 + max(header)
for col in index_col:
last = data[offset][col]
for row in range(offset + 1, len(data)):
if data[row][col] == '' or data[row][col] is None:
data[row][col] = last
else:
last = data[row][col]
if is_list_like(header) and len(header) > 1:
has_index_names = True
if kwds.get('parsed'):
try:
parser = TextParser(data,
header=header,
index_col=index_col,
has_index_names=has_index_names,
na_values=na_values,
thousands=thousands,
parse_dates=parse_dates,
date_parser=date_parser,
true_values=true_values,
false_values=false_values,
skiprows=skiprows,
skipfooter=skip_footer,
squeeze=squeeze,
dtype=dtype,
**kwds)
output[asheetname] = parser.read()
if names is not None:
output[asheetname].columns = names
if not squeeze or isinstance(output[asheetname],
DataFrame):
output[asheetname].columns = output[
asheetname].columns.set_names(header_names)
except EmptyDataError:
# No Data, return an empty DataFrame
output[asheetname] = DataFrame()
else:
output[asheetname] = data
if ret_dict or kwds.get('MaxTest'):
return output
else:
return output[asheetname]
