def parse(self, file):
excel_book = pyexcel.iget_book(file_type="xlsx",
file_content=file.read())
# Handle multiple sheets
for sheet_name in excel_book.sheet_names():
reader = excel_book[sheet_name].to_array()
yield from self.parse_excel_csv_reader(reader)
def test_get_sheet_from_dict(self):
adict = {"X": [1, 4], "Y": [2, 5], "Z": [3, 6]}
test_sheet_name = "custom_sheet"
book = pe.iget_book(adict=adict, sheet_name=test_sheet_name)
expected = [["X", "Y", "Z"], [1, 2, 3], [4, 5, 6]]
result = book.to_dict()
eq_(expected, list(result[test_sheet_name]))
def test_get_sheet_from_records(self):
records = [{"X": 1, "Y": 2, "Z": 3}, {"X": 4, "Y": 5, "Z": 6}]
test_sheet_name = "custom_sheet"
book = pe.iget_book(records=records, sheet_name=test_sheet_name)
expected = [["X", "Y", "Z"], [1, 2, 3], [4, 5, 6]]
result = book.to_dict()
eq_(expected, list(result[test_sheet_name]))
def test_get_book_from_memory(self):
content = _produce_ordered_dict()
io = pe.save_book_as(dest_file_type="xls", bookdict=content)
book_stream = pe.iget_book(file_content=io.getvalue(), file_type="xls")
assert book_stream.to_dict() != content
book = pe.Book(book_stream.to_dict())
eq_(book.to_dict(), content)
def test_look_at_sheet_names_without_incurring_further_memory_cost(self):
test_file = "test_get_book.xls"
content = _produce_ordered_dict()
book = pe.Book(content)
book.save_as(test_file)
book_stream = pe.iget_book(file_name=test_file)
eq_(book_stream.sheet_names(), ["Sheet1", "Sheet2", "Sheet3"])
assert isinstance(book_stream["Sheet1"].payload, GeneratorType)
os.unlink(test_file)
def test_look_at_sheet_names_decides_to_read_seond_one(self):
test_file = "test_get_book.xls"
content = _produce_ordered_dict()
book = pe.Book(content)
book.save_as(test_file)
book_stream = pe.iget_book(file_name=test_file)
data = pe.iget_array(sheet_stream=book_stream["Sheet1"])
assert isinstance(data, GeneratorType)
eq_(list(data), [[1, 1, 1, 1], [2, 2, 2, 2], [3, 3, 3, 3]])
os.unlink(test_file)
def test_get_book_from_file(self):
test_file = "test_get_book.xls"
content = _produce_ordered_dict()
book = pe.Book(content)
book.save_as(test_file)
book_stream = pe.iget_book(file_name=test_file)
assert book_stream.to_dict() != content
book3 = pe.Book(book_stream.to_dict())
eq_(book3.to_dict(), content)
os.unlink(test_file)
def _openbook(path):
"""Support function for 'filltables', iterator over an 'Excel' file.
ARGUMENTS:
- path : the file path
RETURNS:
- an iterator of tuples (sheet,key,metadata)"""
# We open the file
fil = pyexcel.iget_book(file_name=path)
# We get a dict of sheets
d_sheets = {}
for n_sheet in fil.sheets:
low = n_sheet.lower()
d_sheets[low] = n_sheet
# We get the 'languages' sheet first
d_langs = {}
sheet = d_sheets.get('languages')
if sheet:
sheet = fil.sheets[sheet].get_internal_array()
sheet = _readarray(0, sheet)
for code, metadata in sheet.items():
d_langs[code] = True
yield ('languages', code, metadata)
# We get 'editors' next
sheet = d_sheets.get('editors')
if sheet:
sheet = fil.sheets[sheet].get_internal_array()
sheet = _readarray(1, sheet)
for code, metadata in sheet.items():
yield ('editors', code, metadata)
# Followed by 'sources'
sheet = d_sheets.get('sources')
if sheet:
sheet = fil.sheets[sheet].get_internal_array()
sheet = _readarray(1, sheet)
for code, metadata in sheet.items():
yield ('sources', code, metadata)
# We finally get each language sheet
for code in d_langs:
sheet = fil.sheets.get(code, None)
if not sheet:
continue
sheet = sheet.get_internal_array()
sheet = _readarray(1, sheet)
for name, metadata in sheet.items():
yield (code, name, metadata)
pyexcel.free_resources()
def read_dict_sheet(xlsx_path: str, sheet_id_or_name=0) -> list:
"""
:param xlsx_path: xlsx文件路径
:param sheet_id_or_name: 标签页的id或名称
:return: 返回值
"""
book = p.iget_book(file_name=xlsx_path)
sheet = None
if type(sheet_id_or_name) == int:
# 输入的定位标是数字
if book.number_of_sheets() < sheet_id_or_name:
# 如果没有读取到数据，就返回空列表
pass
else:
name = book.sheet_names()[sheet_id_or_name]
sheet = book[name]
if type(sheet_id_or_name) == str:
# 输入的定位标是文本
sheet = book[sheet_id_or_name]
if sheet == None:
return []
ret = []
cache = sheet.array
if len(cache) < 1:
return []
keys = cache[0]
for i in range(1, len(cache)):
data = {}
for j in range(len(keys)):
if len(cache[i]) < j + 1:
data[keys[j]] = None
else:
data[keys[j]] = cache[i][j]
ret.append(data)
return ret
pass
def test_get_sheet_from_array(self):
data = [["X", "Y", "Z"], [1, 2, 3], [4, 5, 6]]
test_sheet_name = "custom_sheet"
book = pe.iget_book(array=data, sheet_name=test_sheet_name)
result = book.to_dict()
eq_(data, list(result[test_sheet_name]))
def test_get_book_from_memory_compatibility(self):
content = _produce_ordered_dict()
io = pe.save_book_as(dest_file_type="xls", bookdict=content)
pe.iget_book(content=io.getvalue(), file_type="xls")
def test_get_book_from_book_dict(self):
content = _produce_ordered_dict()
book = pe.iget_book(bookdict=content)
eq_(book.to_dict(), content)
