python - 解析具有重复 block 的文件中的垂直文本

Question

解析以下文件的最佳方法是什么？这些 block 重复多次。

预期结果输出到 CSV 文件:

{Place: REGION-1, Host: ABCD, Area: 44...}

我尝试了下面的代码，但它只迭代第一个 block 然后完成。

 with open('/tmp/t2.txt', 'r') as input_data:
   for line in input_data:

    if re.findall('(.*_RV)\n',line):
       myDict={}
       myDict['HOST'] = line[6:]
       continue

    elif re.findall('Interface(.*)\n',line):
       myDict['INTF'] = line[6:]
    elif len(line.strip()) == 0:
       print(myDict)

文本文件如下。

Instance REGION-1:
  ABCD_RV
    Interface: fastethernet01/01
    Last state change: 0h54m44s ago
    Sysid: 01441
    Speaks: IPv4
    Topologies:
      ipv4-unicast     
    SAPA: point-to-point
    Area Address(es):
      441
    IPv4 Address(es):
      1.1.1.1    

  EFGH_RV
    Interface: fastethernet01/01
    Last state change: 0h54m44s ago
    Sysid: 01442
    Speaks: IPv4
    Topologies:
      ipv4-unicast     
    SAPA: point-to-point
    Area Address(es):
      442
    IPv4 Address(es):
      1.1.1.2   

Instance REGION-2:
  IJKL_RV
    Interface: fastethernet01/01
    Last state change: 0h54m44s ago
    Sysid: 01443
    Speaks: IPv4
    Topologies:
      ipv4-unicast     
    SAPA: point-to-point
    Area Address(es):
      443
    IPv4 Address(es):
      1.1.1.3   

Answer 1

或者，如果您更喜欢丑陋的正则表达式路线:

import re

region_re = re.compile("^Instance\s+([^:]+):.*")
host_re = re.compile("^\s+(.*?)_RV.*")
interface_re = re.compile("^\s+Interface:\s+(.*?)\s+")
other_re = re.compile("^\s+([^\s]+).*?:\s+([^\s]*){0,1}")

myDict = {}
extra = None
with open('/tmp/t2.txt', 'r') as input_data:
   for line in input_data:
        if extra: # value on next line from key
            myDict[extra] = line.strip()
            extra = None
            continue

        region = region_re.match(line)
        if region:
            if len(myDict) > 1:
                print(myDict)
            myDict = {'Place': region.group(1)}
            continue

        host = host_re.match(line)
        if host:
            if len(myDict) > 1:
                print(myDict)
            myDict = {'Place': myDict['Place'], 'Host': host.group(1)}
            continue

        interface = interface_re.match(line)
        if interface:
            myDict['INTF'] = interface.group(1)
            continue

        other =  other_re.match(line)
        if other:
            groups = other.groups()
            if groups[1]:
                myDict[groups[0]] = groups[1]
            else:
                extra = groups[0]

# dump out final one
if len(myDict) > 1:
    print(myDict)

输出:

{'Place': 'REGION-1', 'Host': 'ABCD', 'INTF': 'fastethernet01/01', 'Last': '0h54m44s', 'Sysid': '01441', 'Speaks': 'IPv4', 'Topologies': 'ipv4-unicast', 'SAPA': 'point-to-point', 'Area': '441', 'IPv4': '1.1.1.1'}
{'Place': 'REGION-1', 'Host': 'EFGH', 'INTF': 'fastethernet01/01', 'Last': '0h54m44s', 'Sysid': '01442', 'Speaks': 'IPv4', 'Topologies': 'ipv4-unicast', 'SAPA': 'point-to-point', 'Area': '442', 'IPv4': '1.1.1.2'}
{'Place': 'REGION-2', 'Host': 'IJKL', 'INTF': 'fastethernet01/01', 'Last': '0h54m44s', 'Sysid': '01443', 'Speaks': 'IPv4', 'Topologies': 'ipv4-unicast', 'SAPA': 'point-to-point', 'Area': '443', 'IPv4': '1.1.1.3'}