def read(self):
self.read_manifest()
self.read_strings()
self.read_workbook()
self.read_properties()
self.read_theme()
apply_stylesheet(self.archive, self.wb)
self.read_worksheets()
self.parser.assign_names()
self.archive.close()
def load_workbook(filename, read_only=False, keep_vba=KEEP_VBA,
data_only=False, guess_types=False, keep_links=True):
"""Open the given filename and return the workbook
:param filename: the path to open or a file-like object
:type filename: string or a file-like object open in binary mode c.f., :class:`zipfile.ZipFile`
:param read_only: optimised for reading, content cannot be edited
:type read_only: bool
:param keep_vba: preseve vba content (this does NOT mean you can use it)
:type keep_vba: bool
:param guess_types: guess cell content type and do not read it from the file
:type guess_types: bool
:param data_only: controls whether cells with formulae have either the formula (default) or the value stored the last time Excel read the sheet
:type data_only: bool
:param keep_links: whether links to external workbooks should be preserved. The default is True
:type keep_links: bool
:rtype: :class:`openpyxl.workbook.Workbook`
.. note::
When using lazy load, all worksheets will be :class:`openpyxl.worksheet.iter_worksheet.IterableWorksheet`
and the returned workbook will be read-only.
"""
archive = _validate_archive(filename)
read_only = read_only
src = archive.read(ARC_CONTENT_TYPES)
root = fromstring(src)
package = Manifest.from_tree(root)
wb_part = _find_workbook_part(package)
parser = WorkbookParser(archive, wb_part.PartName[1:])
wb = parser.wb
wb._data_only = data_only
wb._read_only = read_only
wb._keep_links = keep_links
wb.guess_types = guess_types
wb.template = wb_part.ContentType in (XLTX, XLTM)
parser.parse()
wb._sheets = []
if read_only and guess_types:
warnings.warn('Data types are not guessed when using iterator reader')
valid_files = archive.namelist()
# If are going to preserve the vba then attach a copy of the archive to the
# workbook so that is available for the save.
if keep_vba:
wb.vba_archive = ZipFile(BytesIO(), 'a', ZIP_DEFLATED)
for name in archive.namelist():
wb.vba_archive.writestr(name, archive.read(name))
if read_only:
wb._archive = ZipFile(filename)
# get workbook-level information
if ARC_CORE in valid_files:
src = fromstring(archive.read(ARC_CORE))
wb.properties = DocumentProperties.from_tree(src)
shared_strings = []
ct = package.find(SHARED_STRINGS)
if ct is not None:
strings_path = ct.PartName[1:]
shared_strings = read_string_table(archive.read(strings_path))
if ARC_THEME in valid_files:
wb.loaded_theme = archive.read(ARC_THEME)
apply_stylesheet(archive, wb) # bind styles to workbook
pivot_caches = parser.pivot_caches
# get worksheets
for sheet, rel in parser.find_sheets():
sheet_name = sheet.name
worksheet_path = rel.target
rels_path = get_rels_path(worksheet_path)
rels = []
if rels_path in valid_files:
rels = get_dependents(archive, rels_path)
if not worksheet_path in valid_files:
continue
if read_only:
ws = ReadOnlyWorksheet(wb, sheet_name, worksheet_path, None,
shared_strings)
wb._sheets.append(ws)
else:
fh = archive.open(worksheet_path)
ws = wb.create_sheet(sheet_name)
ws._rels = rels
ws_parser = WorkSheetParser(ws, fh, shared_strings)
ws_parser.parse()
if rels:
# assign any comments to cells
for r in rels.find(COMMENTS_NS):
src = archive.read(r.target)
comment_sheet = CommentSheet.from_tree(fromstring(src))
for ref, comment in comment_sheet.comments:
ws[ref].comment = comment
# preserve link to VML file if VBA
if (
wb.vba_archive is not None
and ws.legacy_drawing is not None
):
ws.legacy_drawing = rels[ws.legacy_drawing].target
for t in ws_parser.tables:
src = archive.read(t)
xml = fromstring(src)
table = Table.from_tree(xml)
ws.add_table(table)
pivot_rel = rels.find(TableDefinition.rel_type)
for r in pivot_rel:
pivot_path = r.Target
src = archive.read(pivot_path)
tree = fromstring(src)
pivot = TableDefinition.from_tree(tree)
pivot.cache = pivot_caches[pivot.cacheId]
ws.add_pivot(pivot)
ws.sheet_state = sheet.state
ws._rels = [] # reset
parser.assign_names()
#wb._differential_styles.styles = [] # tables may depened upon dxf
archive.close()
return wb
def load_workbook(filename, read_only=False, keep_vba=KEEP_VBA,
data_only=False, guess_types=False, keep_links=True):
"""Open the given filename and return the workbook
:param filename: the path to open or a file-like object
:type filename: string or a file-like object open in binary mode c.f., :class:`zipfile.ZipFile`
:param read_only: optimised for reading, content cannot be edited
:type read_only: bool
:param keep_vba: preseve vba content (this does NOT mean you can use it)
:type keep_vba: bool
:param guess_types: guess cell content type and do not read it from the file
:type guess_types: bool
:param data_only: controls whether cells with formulae have either the formula (default) or the value stored the last time Excel read the sheet
:type data_only: bool
:param keep_links: whether links to external workbooks should be preserved. The default is True
:type keep_links: bool
:rtype: :class:`openpyxl.workbook.Workbook`
.. note::
When using lazy load, all worksheets will be :class:`openpyxl.worksheet.iter_worksheet.IterableWorksheet`
and the returned workbook will be read-only.
"""
archive = _validate_archive(filename)
read_only = read_only
parser = WorkbookParser(archive)
wb = parser.wb
wb._data_only = data_only
wb._read_only = read_only
wb._keep_links = keep_links
wb.guess_types = guess_types
parser.parse()
wb._sheets = []
if read_only and guess_types:
warnings.warn('Data types are not guessed when using iterator reader')
valid_files = archive.namelist()
# If are going to preserve the vba then attach a copy of the archive to the
# workbook so that is available for the save.
if keep_vba:
wb.vba_archive = ZipFile(BytesIO(), 'a', ZIP_DEFLATED)
for name in archive.namelist():
wb.vba_archive.writestr(name, archive.read(name))
if read_only:
wb._archive = ZipFile(filename)
# get workbook-level information
if ARC_CORE in valid_files:
src = fromstring(archive.read(ARC_CORE))
wb.properties = DocumentProperties.from_tree(src)
# is workbook a template or note
src = archive.read(ARC_CONTENT_TYPES)
root = fromstring(src)
package = Manifest.from_tree(root)
wb.template = XLTX in package or XLTM in package
shared_strings = []
ct = package.find(SHARED_STRINGS)
if ct is not None:
strings_path = ct.PartName[1:]
shared_strings = read_string_table(archive.read(strings_path))
if ARC_THEME in valid_files:
wb.loaded_theme = archive.read(ARC_THEME)
apply_stylesheet(archive, wb) # bind styles to workbook
# get worksheets
for sheet, rel in parser.find_sheets():
sheet_name = sheet.name
worksheet_path = rel.target
rels_path = get_rels_path(worksheet_path)
rels = []
if rels_path in valid_files:
rels = get_dependents(archive, rels_path)
if not worksheet_path in valid_files:
continue
if read_only:
ws = ReadOnlyWorksheet(wb, sheet_name, worksheet_path, None,
shared_strings)
wb._sheets.append(ws)
else:
fh = archive.open(worksheet_path)
ws = wb.create_sheet(sheet_name)
ws._rels = rels
ws_parser = WorkSheetParser(ws, fh, shared_strings)
ws_parser.parse()
if rels:
# assign any comments to cells
for r in rels.find(COMMENTS_NS):
src = archive.read(r.target)
comment_sheet = CommentSheet.from_tree(fromstring(src))
for ref, comment in comment_sheet.comments:
ws[ref].comment = comment
# preserve link to VML file if VBA
if (
wb.vba_archive is not None
and ws.legacy_drawing is not None
):
ws.legacy_drawing = rels[ws.legacy_drawing].target
ws.sheet_state = sheet.state
ws._rels = [] # reset
parser.assign_names()
wb._differential_styles.styles = []
archive.close()
return wb
def load_workbook(filename, read_only=False, use_iterators=False, keep_vba=KEEP_VBA, guess_types=False, data_only=False):
"""Open the given filename and return the workbook
:param filename: the path to open or a file-like object
:type filename: string or a file-like object open in binary mode c.f., :class:`zipfile.ZipFile`
:param read_only: optimised for reading, content cannot be edited
:type read_only: bool
:param use_iterators: use lazy load for cells
:type use_iterators: bool
:param keep_vba: preseve vba content (this does NOT mean you can use it)
:type keep_vba: bool
:param guess_types: guess cell content type and do not read it from the file
:type guess_types: bool
:param data_only: controls whether cells with formulae have either the formula (default) or the value stored the last time Excel read the sheet
:type data_only: bool
:rtype: :class:`openpyxl.workbook.Workbook`
.. note::
When using lazy load, all worksheets will be :class:`openpyxl.worksheet.iter_worksheet.IterableWorksheet`
and the returned workbook will be read-only.
"""
archive = _validate_archive(filename)
read_only = read_only or use_iterators
wb = Workbook(guess_types=guess_types, data_only=data_only, read_only=read_only)
if read_only and guess_types:
warnings.warn('Data types are not guessed when using iterator reader')
valid_files = archive.namelist()
# If are going to preserve the vba then attach a copy of the archive to the
# workbook so that is available for the save.
if keep_vba:
try:
f = open(filename, 'rb')
s = f.read()
f.close()
except:
pos = filename.tell()
filename.seek(0)
s = filename.read()
filename.seek(pos)
wb.vba_archive = ZipFile(BytesIO(s), 'r')
if read_only:
wb._archive = ZipFile(filename)
# get workbook-level information
try:
src = fromstring(archive.read(ARC_CORE))
wb.properties = DocumentProperties.from_tree(src)
except KeyError:
wb.properties = DocumentProperties()
wb.active = read_workbook_settings(archive.read(ARC_WORKBOOK)) or 0
# what content types do we have?
cts = dict(read_content_types(archive))
strings_path = cts.get(SHARED_STRINGS)
if strings_path is not None:
if strings_path.startswith("/"):
strings_path = strings_path[1:]
shared_strings = read_string_table(archive.read(strings_path))
else:
shared_strings = []
wb.is_template = XLTX in cts or XLTM in cts
try:
wb.loaded_theme = archive.read(ARC_THEME) # some writers don't output a theme, live with it (fixes #160)
except KeyError:
pass
apply_stylesheet(archive, wb) # bind styles to workbook
wb.excel_base_date = read_excel_base_date(archive)
# get worksheets
wb._sheets = [] # remove preset worksheet
for sheet in detect_worksheets(archive):
sheet_name = sheet['title']
worksheet_path = sheet['path']
if not worksheet_path in valid_files:
continue
if read_only:
new_ws = ReadOnlyWorksheet(wb, sheet_name, worksheet_path, None,
shared_strings)
wb._add_sheet(new_ws)
else:
fh = archive.open(worksheet_path)
parser = WorkSheetParser(wb, sheet_name, fh, shared_strings)
parser.parse()
new_ws = wb[sheet_name]
new_ws.sheet_state = sheet['state']
if not read_only:
# load comments into the worksheet cells
comments_file = get_comments_file(worksheet_path, archive, valid_files)
if comments_file is not None:
read_comments(new_ws, archive.read(comments_file))
wb._differential_styles = [] # reset
wb._named_ranges = list(read_named_ranges(archive.read(ARC_WORKBOOK), wb))
wb.code_name = read_workbook_code_name(archive.read(ARC_WORKBOOK))
if EXTERNAL_LINK in cts:
rels = read_rels(archive)
wb._external_links = {book.link_index: book for book in detect_external_links(rels, archive)}
archive.close()
return wb