我正在寻找一种漂亮的打印表格的方法：
=======================
| column 1 | column 2 |
=======================
| value1 | value2 |
| value3 | value4 |
=======================
我已经找到了ASCII库，但它不做边框等。我不需要任何复杂的数据项格式，它们只是字符串。我确实需要它来自动调整列的大小。
是否存在其他库或方法，或者我是否需要花几分钟时间编写自己的库或方法？
我很久以前就读过这个问题，并完成了我自己漂亮的表打印机tabulate的编写。
我的用例是：
- 我大部分时间都想要一条班轮
- 哪个足够聪明，可以为我找到最好的格式
- 并且可以输出不同的纯文本格式
举个例子，grid可能是最相似的输出格式：
from tabulate import tabulate
print tabulate([["value1", "value2"], ["value3", "value4"]], ["column 1", "column 2"], tablefmt="grid")
+------------+------------+
| column 1 | column 2 |
+============+============+
| value1 | value2 |
+------------+------------+
| value3 | value4 |
+------------+------------+
其他支持的格式有plain(无行(、simple(Pandoc简单表(、pipe(类似于PHP Markdown Extra中的表(、orgtbl(类似于Emacs的组织模式下的表(和rst(类似于reStructuredText中的简单表(。CCD_ 8和CCD_。
就性能而言，tabulate比asciitable稍慢，但比PrettyTable和texttable快得多。
附言：我也非常喜欢用小数列对齐数字。因此，这是数字的默认对齐方式(如果有((可重写(。
下面是我编写的一个快速而肮脏的小函数，用于显示SQL查询的结果，我只能通过SOAP API进行查询。它期望一个或多个namedtuples序列的输入作为表行。如果只有一张唱片，它会以不同的方式打印出来。
它对我来说很方便，可能是你的起点：
def pprinttable(rows):
if len(rows) > 1:
headers = rows[0]._fields
lens = []
for i in range(len(rows[0])):
lens.append(len(max([x[i] for x in rows] + [headers[i]],key=lambda x:len(str(x)))))
formats = []
hformats = []
for i in range(len(rows[0])):
if isinstance(rows[0][i], int):
formats.append("%%%dd" % lens[i])
else:
formats.append("%%-%ds" % lens[i])
hformats.append("%%-%ds" % lens[i])
pattern = " | ".join(formats)
hpattern = " | ".join(hformats)
separator = "-+-".join(['-' * n for n in lens])
print hpattern % tuple(headers)
print separator
_u = lambda t: t.decode('UTF-8', 'replace') if isinstance(t, str) else t
for line in rows:
print pattern % tuple(_u(t) for t in line)
elif len(rows) == 1:
row = rows[0]
hwidth = len(max(row._fields,key=lambda x: len(x)))
for i in range(len(row)):
print "%*s = %s" % (hwidth,row._fields[i],row[i])
样本输出：
pkid|fkn|npi-------------------------------------+--------------------------------------+----405fd665-0a2f-4f69-7320-be01201752ec|8c9949b9-552e-e448-64e2-7492834c73e|05b517507-2a42-ad2e-98dc-8c9ac6152afa |f972bee7-f5a4-8532-c4e5-2e82897b10f6|02f960dfc-b67a-26be-d1b3-9b105535e0a8|ec3e1058-8840-c9f2-3b25-2488f8b3a8af|1c71b28a3-5299-7f4d-f27a-7ad8aeadafe0|72d25703-4735-310b-2e06-ff76af1e45ed|03b0a5021-a52b-9ba0-1439-d5afcf348e7|d81bb78a-d984-e957-034d-87434acb4e97|196c36bb7-c4f4-27787-ada8-aadc17d1123|c171fe85-33e2-6481-0791-2922267e8777|195d0f85f-71da-bb9a-2d80-fe27f7c02fe2|226f964c-028d-d6de-bf6c-688d2908c5ae|1132aa774-42e5-3d3f-498b-50b44a89d401|44e31f89-d089-8afc-f4b1-ada051c01474|1ff91641a-5802-be02-ece-79bca993fdbc|33d8294a-053d-6ab4-94d4-890b47fcf70d|1f3196e15-5b61-e92d-e717-f00ed93fe8ae|62fa4566-5ca2-4a36-f872-4d00f7abadcf|1
示例
>>> from collections import namedtuple
>>> Row = namedtuple('Row',['first','second','third'])
>>> data = Row(1,2,3)
>>> data
Row(first=1, second=2, third=3)
>>> pprinttable([data])
first = 1
second = 2
third = 3
>>> pprinttable([data,data])
first | second | third
------+--------+------
1 | 2 | 3
1 | 2 | 3
由于某种原因，当我在谷歌搜索中包含"docutils"时，我偶然发现了texttable，这似乎就是我想要的。
我也为此编写了自己的解决方案。我尽量保持简单。
https://github.com/Robpol86/terminaltables
from terminaltables import AsciiTable
table_data = [
['Heading1', 'Heading2'],
['row1 column1', 'row1 column2'],
['row2 column1', 'row2 column2']
]
table = AsciiTable(table_data)
print table.table
+--------------+--------------+
| Heading1 | Heading2 |
+--------------+--------------+
| row1 column1 | row1 column2 |
| row2 column1 | row2 column2 |
+--------------+--------------+
table.inner_heading_row_border = False
print table.table
+--------------+--------------+
| Heading1 | Heading2 |
| row1 column1 | row1 column2 |
| row2 column1 | row2 column2 |
+--------------+--------------+
table.inner_row_border = True
table.justify_columns[1] = 'right'
table.table_data[1][1] += 'nnewline'
print table.table
+--------------+--------------+
| Heading1 | Heading2 |
+--------------+--------------+
| row1 column1 | row1 column2 |
| | newline |
+--------------+--------------+
| row2 column1 | row2 column2 |
+--------------+--------------+
我刚刚为此发布了术语表。例如，这个
import termtables as tt
tt.print(
[[1, 2, 3], [613.23236243236, 613.23236243236, 613.23236243236]],
header=["a", "bb", "ccc"],
style=tt.styles.ascii_thin_double,
padding=(0, 1),
alignment="lcr"
)
给你
+-----------------+-----------------+-----------------+
| a | bb | ccc |
+=================+=================+=================+
| 1 | 2 | 3 |
+-----------------+-----------------+-----------------+
| 613.23236243236 | 613.23236243236 | 613.23236243236 |
+-----------------+-----------------+-----------------+
默认情况下，该表使用Unicode方框图字符进行渲染
┌─────────────────┬─────────────────┬─────────────────┐
│ a │ bb │ ccc │
╞═════════════════╪═════════════════╪═════════════════╡
│ 1 │ 2 │ 3 │
├─────────────────┼─────────────────┼─────────────────┤
│ 613.23236243236 │ 613.23236243236 │ 613.23236243236 │
└─────────────────┴─────────────────┴─────────────────┘
术语表是非常可配置的；查看测试以获取更多示例。
如果您想要一个具有列和行跨度的表，请尝试我的库dashtable
from dashtable import data2rst
table = [
["Header 1", "Header 2", "Header3", "Header 4"],
["row 1", "column 2", "column 3", "column 4"],
["row 2", "Cells span columns.", "", ""],
["row 3", "Cellsnspan rows.", "- Cellsn- containn- blocks", ""],
["row 4", "", "", ""]
]
# [Row, Column] pairs of merged cells
span0 = ([2, 1], [2, 2], [2, 3])
span1 = ([3, 1], [4, 1])
span2 = ([3, 3], [3, 2], [4, 2], [4, 3])
my_spans = [span0, span1, span2]
print(data2rst(table, spans=my_spans, use_headers=True))
哪个输出：
+----------+------------+----------+----------+
| Header 1 | Header 2 | Header3 | Header 4 |
+==========+============+==========+==========+
| row 1 | column 2 | column 3 | column 4 |
+----------+------------+----------+----------+
| row 2 | Cells span columns. |
+----------+----------------------------------+
| row 3 | Cells | - Cells |
+----------+ span rows. | - contain |
| row 4 | | - blocks |
+----------+------------+---------------------+
使用w3m的版本，旨在处理MattH版本接受的类型：
import subprocess
import tempfile
import html
def pprinttable(rows):
esc = lambda x: html.escape(str(x))
sour = "<table border=1>"
if len(rows) == 1:
for i in range(len(rows[0]._fields)):
sour += "<tr><th>%s<td>%s" % (esc(rows[0]._fields[i]), esc(rows[0][i]))
else:
sour += "<tr>" + "".join(["<th>%s" % esc(x) for x in rows[0]._fields])
sour += "".join(["<tr>%s" % "".join(["<td>%s" % esc(y) for y in x]) for x in rows])
with tempfile.NamedTemporaryFile(suffix=".html") as f:
f.write(sour.encode("utf-8"))
f.flush()
print(
subprocess
.Popen(["w3m","-dump",f.name], stdout=subprocess.PIPE)
.communicate()[0].decode("utf-8").strip()
)
from collections import namedtuple
Row = namedtuple('Row',['first','second','third'])
data1 = Row(1,2,3)
data2 = Row(4,5,6)
pprinttable([data1])
pprinttable([data1,data2])
结果在：
┌───────┬─┐
│ first │1│
├───────┼─┤
│second │2│
├───────┼─┤
│ third │3│
└───────┴─┘
┌─────┬───────┬─────┐
│first│second │third│
├─────┼───────┼─────┤
│1 │2 │3 │
├─────┼───────┼─────┤
│4 │5 │6 │
└─────┴───────┴─────┘
您可以尝试BeautifulTable。它做你想做的事
>>> from beautifultable import BeautifulTable
>>> table = BeautifulTable()
>>> table.columns.header = ["name", "rank", "gender"]
>>> table.rows.append(["Jacob", 1, "boy"])
>>> table.rows.append(["Isabella", 1, "girl"])
>>> table.rows.append(["Ethan", 2, "boy"])
>>> table.rows.append(["Sophia", 2, "girl"])
>>> table.rows.append(["Michael", 3, "boy"])
>>> print(table)
+----------+------+--------+
| name | rank | gender |
+----------+------+--------+
| Jacob | 1 | boy |
+----------+------+--------+
| Isabella | 1 | girl |
+----------+------+--------+
| Ethan | 2 | boy |
+----------+------+--------+
| Sophia | 2 | girl |
+----------+------+--------+
| Michael | 3 | boy |
+----------+------+--------+
from sys import stderr, stdout
def create_table(table: dict, full_row: bool = False) -> None:
min_len = len(min((v for v in table.values()), key=lambda q: len(q)))
max_len = len(max((v for v in table.values()), key=lambda q: len(q)))
if min_len < max_len:
stderr.write("Table is out of shape, please make sure all columns have the same length.")
stderr.flush()
return
additional_spacing = 1
heading_separator = '| '
horizontal_split = '| '
rc_separator = ''
key_list = list(table.keys())
rc_len_values = []
for key in key_list:
rc_len = len(max((v for v in table[key]), key=lambda q: len(str(q))))
rc_len_values += ([rc_len, [key]] for n in range(len(table[key])))
heading_line = (key + (" " * (rc_len + (additional_spacing + 1)))) + heading_separator
stdout.write(heading_line)
rc_separator += ("-" * (len(key) + (rc_len + (additional_spacing + 1)))) + '+-'
if key is key_list[-1]:
stdout.flush()
stdout.write('n' + rc_separator + 'n')
value_list = [v for vl in table.values() for v in vl]
aligned_data_offset = max_len
row_count = len(key_list)
next_idx = 0
newline_indicator = 0
iterations = 0
for n in range(len(value_list)):
key = rc_len_values[next_idx][1][0]
rc_len = rc_len_values[next_idx][0]
line = ('{:{}} ' + " " * len(key)).format(value_list[next_idx], str(rc_len + additional_spacing)) + horizontal_split
if next_idx >= (len(value_list) - aligned_data_offset):
next_idx = iterations + 1
iterations += 1
else:
next_idx += aligned_data_offset
if newline_indicator >= row_count:
if full_row:
stdout.flush()
stdout.write('n' + rc_separator + 'n')
else:
stdout.flush()
stdout.write('n')
newline_indicator = 0
stdout.write(line)
newline_indicator += 1
stdout.write('n' + rc_separator + 'n')
stdout.flush()
示例：
table = {
"uid": ["0", "1", "2", "3"],
"name": ["Jon", "Doe", "Lemma", "Hemma"]
}
create_table(table)
输出：
uid | name |
------+------------+-
0 | Jon |
1 | Doe |
2 | Lemma |
3 | Hemma |
------+------------+-
我知道这个问题有点老了，但下面是我的尝试：
https://gist.github.com/lonetwin/4721748
它的可读性更强(尽管它不像@MattH的解决方案那样区分单行/多行，也不使用NamedTuples(。
这是我的解决方案：
def make_table(columns, data):
"""Create an ASCII table and return it as a string.
Pass a list of strings to use as columns in the table and a list of
dicts. The strings in 'columns' will be used as the keys to the dicts in
'data.'
Not all column values have to be present in each data dict.
>>> print(make_table(["a", "b"], [{"a": "1", "b": "test"}]))
| a | b |
|----------|
| 1 | test |
"""
# Calculate how wide each cell needs to be
cell_widths = {}
for c in columns:
values = [str(d.get(c, "")) for d in data]
cell_widths[c] = len(max(values + [c]))
# Used for formatting rows of data
row_template = "|" + " {} |" * len(columns)
# CONSTRUCT THE TABLE
# The top row with the column titles
justified_column_heads = [c.ljust(cell_widths[c]) for c in columns]
header = row_template.format(*justified_column_heads)
# The second row contains separators
sep = "|" + "-" * (len(header) - 2) + "|"
# Rows of data
rows = []
for d in data:
fields = [str(d.get(c, "")).ljust(cell_widths[c]) for c in columns]
row = row_template.format(*fields)
rows.append(row)
return "n".join([header, sep] + rows)
我使用这个小实用程序函数。
def get_pretty_table(iterable, header):
max_len = [len(x) for x in header]
for row in iterable:
row = [row] if type(row) not in (list, tuple) else row
for index, col in enumerate(row):
if max_len[index] < len(str(col)):
max_len[index] = len(str(col))
output = '-' * (sum(max_len) + 1) + 'n'
output += '|' + ''.join([h + ' ' * (l - len(h)) + '|' for h, l in zip(header, max_len)]) + 'n'
output += '-' * (sum(max_len) + 1) + 'n'
for row in iterable:
row = [row] if type(row) not in (list, tuple) else row
output += '|' + ''.join([str(c) + ' ' * (l - len(str(c))) + '|' for c, l in zip(row, max_len)]) + 'n'
output += '-' * (sum(max_len) + 1) + 'n'
return output
print get_pretty_table([[1, 2], [3, 4]], ['header 1', 'header 2'])
输出
-----------------
|header 1|header 2|
-----------------
|1 |2 |
|3 |4 |
-----------------
只有使用列表和字符串理解的内置模块才能做到这一点。接受所有格式相同的词典列表。。。
def tableit(dictlist):
lengths = [ max(map(lambda x:len(x.get(k)), dictlist) + [len(k)]) for k in dictlist[0].keys() ]
lenstr = " | ".join("{:<%s}" % m for m in lengths)
lenstr += "n"
outmsg = lenstr.format(*dictlist[0].keys())
outmsg += "-" * (sum(lengths) + 3*len(lengths))
outmsg += "n"
outmsg += "".join(
lenstr.format(*v) for v in [ item.values() for item in dictlist ]
)
return outmsg