使用 shell 或批处理命令行将 Python Pretty table 转换为 CSV
Convert Python Pretty table to CSV using shell or batch command line
有什么简单的方法可以将 Python Pretty table 的输出转换为语法上可用的格式,例如 CSV。
输出如下所示:
C:\test> nova 列表
spu+--------------------------------------+--------+--------+------------+-------------+-----------------------------------+
| ID | Name | Status | Task State | Power State | Networks |
+--------------------------------------+--------+--------+------------+-------------+-----------------------------------+
| 6bca09f8-a320-44d4-a11f-647dcec0aaa1 | tester | ACTIVE | - | Running | OpenStack-net=10.0.0.1, 10.0.0.3 |
+--------------------------------------+--------+--------+------------+-------------+-----------------------------------+
也许这会让你接近:
nova list | grep -v '\-\-\-\-' | sed 's/^[^|]\+|//g' | sed 's/|\(.\)/,/g' | tr '|' '\n'
这将删除 --- 行
删除前导 |
替换除最后一个以外的所有 |和 ,
替换最后一个 |与 \n
这是一个真正丑陋的单线
import csv
s = """\
spu+--------------------------------------+--------+--------+------------+-------------+-----------------------------------+
| ID | Name | Status | Task State | Power State | Networks |
+--------------------------------------+--------+--------+------------+-------------+-----------------------------------+
| 6bca09f8-a320-44d4-a11f-647dcec0aaa1 | tester | ACTIVE | - | Running | OpenStack-net=10.0.0.1, 10.0.0.3 |
+--------------------------------------+--------+--------+------------+-------------+-----------------------------------+"""
result = [tuple(filter(None, map(str.strip, splitline))) for line in s.splitlines() for splitline in [line.split("|")] if len(splitline) > 1]
with open('output.csv', 'wb') as outcsv:
writer = csv.writer(outcsv)
writer.writerows(result)
我可以把它拆开一点,让它看起来更漂亮:
splitlines = s.splitlines()
splitdata = line.split("|")
splitdata = filter(lambda line: len(line) > 1, data)
# toss the lines that don't have any data in them -- pure separator lines
header, *data = [[field.strip() for field in line if field.strip()] for line in splitdata]
result = [header] + data
# I'm really just separating these, then re-joining them, but sometimes having
# the headers separately is an important thing!
或者可能更有帮助:
result = []
for line in s.splitlines():
splitdata = line.split("|")
if len(splitdata) == 1:
continue # skip lines with no separators
linedata = []
for field in splitdata:
field = field.strip()
if field:
linedata.append(field)
result.append(linedata)
这是一个使用正则表达式的解决方案。它也适用于任意数量的列(列数通过计算第一行中加号的数量来确定)。
input_string = """spu+--------------------------------------+--------+--------+------------+-------------+-----------------------------------+
| ID | Name | Status | Task State | Power State | Networks |
+--------------------------------------+--------+--------+------------+-------------+-----------------------------------+
| 6bca09f8-a320-44d4-a11f-647dcec0aaa1 | tester | ACTIVE | - | Running | OpenStack-net=10.0.0.1, 10.0.0.3 |
+--------------------------------------+--------+--------+------------+-------------+-----------------------------------+"""
import re, csv, sys
def pretty_table_to_tuples(input_str):
lines = input_str.split("\n")
num_columns = len(re.findall("\+", lines[0])) - 1
line_regex = r"\|" + (r" +(.*?) +\|"*num_columns)
for line in lines:
m = re.match(line_regex, line.strip())
if m:
yield m.groups()
w = csv.writer(sys.stdout)
w.writerows(pretty_table_to_tuples(input_string))
@AdamSmith 的回答有一个很好的方法来解析原始 table 字符串。这里有一些添加以将其变成通用函数(我选择不使用 csv
模块,因此没有额外的依赖项)
def ptable_to_csv(table, filename, headers=True):
"""Save PrettyTable results to a CSV file.
Adapted from @AdamSmith
:param PrettyTable table: Table object to get data from.
:param str filename: Filepath for the output CSV.
:param bool headers: Whether to include the header row in the CSV.
:return: None
"""
raw = table.get_string()
data = [tuple(filter(None, map(str.strip, splitline)))
for line in raw.splitlines()
for splitline in [line.split('|')] if len(splitline) > 1]
if table.title is not None:
data = data[1:]
if not headers:
data = data[1:]
with open(filename, 'w') as f:
for d in data:
f.write('{}\n'.format(','.join(d)))
有什么简单的方法可以将 Python Pretty table 的输出转换为语法上可用的格式,例如 CSV。
输出如下所示:
C:\test> nova 列表
spu+--------------------------------------+--------+--------+------------+-------------+-----------------------------------+
| ID | Name | Status | Task State | Power State | Networks |
+--------------------------------------+--------+--------+------------+-------------+-----------------------------------+
| 6bca09f8-a320-44d4-a11f-647dcec0aaa1 | tester | ACTIVE | - | Running | OpenStack-net=10.0.0.1, 10.0.0.3 |
+--------------------------------------+--------+--------+------------+-------------+-----------------------------------+
也许这会让你接近:
nova list | grep -v '\-\-\-\-' | sed 's/^[^|]\+|//g' | sed 's/|\(.\)/,/g' | tr '|' '\n'
这将删除 --- 行 删除前导 | 替换除最后一个以外的所有 |和 , 替换最后一个 |与 \n
这是一个真正丑陋的单线
import csv
s = """\
spu+--------------------------------------+--------+--------+------------+-------------+-----------------------------------+
| ID | Name | Status | Task State | Power State | Networks |
+--------------------------------------+--------+--------+------------+-------------+-----------------------------------+
| 6bca09f8-a320-44d4-a11f-647dcec0aaa1 | tester | ACTIVE | - | Running | OpenStack-net=10.0.0.1, 10.0.0.3 |
+--------------------------------------+--------+--------+------------+-------------+-----------------------------------+"""
result = [tuple(filter(None, map(str.strip, splitline))) for line in s.splitlines() for splitline in [line.split("|")] if len(splitline) > 1]
with open('output.csv', 'wb') as outcsv:
writer = csv.writer(outcsv)
writer.writerows(result)
我可以把它拆开一点,让它看起来更漂亮:
splitlines = s.splitlines()
splitdata = line.split("|")
splitdata = filter(lambda line: len(line) > 1, data)
# toss the lines that don't have any data in them -- pure separator lines
header, *data = [[field.strip() for field in line if field.strip()] for line in splitdata]
result = [header] + data
# I'm really just separating these, then re-joining them, but sometimes having
# the headers separately is an important thing!
或者可能更有帮助:
result = []
for line in s.splitlines():
splitdata = line.split("|")
if len(splitdata) == 1:
continue # skip lines with no separators
linedata = []
for field in splitdata:
field = field.strip()
if field:
linedata.append(field)
result.append(linedata)
这是一个使用正则表达式的解决方案。它也适用于任意数量的列(列数通过计算第一行中加号的数量来确定)。
input_string = """spu+--------------------------------------+--------+--------+------------+-------------+-----------------------------------+
| ID | Name | Status | Task State | Power State | Networks |
+--------------------------------------+--------+--------+------------+-------------+-----------------------------------+
| 6bca09f8-a320-44d4-a11f-647dcec0aaa1 | tester | ACTIVE | - | Running | OpenStack-net=10.0.0.1, 10.0.0.3 |
+--------------------------------------+--------+--------+------------+-------------+-----------------------------------+"""
import re, csv, sys
def pretty_table_to_tuples(input_str):
lines = input_str.split("\n")
num_columns = len(re.findall("\+", lines[0])) - 1
line_regex = r"\|" + (r" +(.*?) +\|"*num_columns)
for line in lines:
m = re.match(line_regex, line.strip())
if m:
yield m.groups()
w = csv.writer(sys.stdout)
w.writerows(pretty_table_to_tuples(input_string))
@AdamSmith 的回答有一个很好的方法来解析原始 table 字符串。这里有一些添加以将其变成通用函数(我选择不使用 csv
模块,因此没有额外的依赖项)
def ptable_to_csv(table, filename, headers=True):
"""Save PrettyTable results to a CSV file.
Adapted from @AdamSmith
:param PrettyTable table: Table object to get data from.
:param str filename: Filepath for the output CSV.
:param bool headers: Whether to include the header row in the CSV.
:return: None
"""
raw = table.get_string()
data = [tuple(filter(None, map(str.strip, splitline)))
for line in raw.splitlines()
for splitline in [line.split('|')] if len(splitline) > 1]
if table.title is not None:
data = data[1:]
if not headers:
data = data[1:]
with open(filename, 'w') as f:
for d in data:
f.write('{}\n'.format(','.join(d)))