问将所有名称与末尾的5位数字完全匹配。

EN

>>> import re
>>> re.match('\w*', '12345')
<_sre.SRE_Match object at 0x021241E0>
>>> re.match('\w*', '12345').group()
'12345'
>>>

matches = re.findall(r'[A-Za-z]*\d{5}:',filetext2)

import re
# Dictionary to hold the results
results = {}
# Break-up the file text to get the names and their associated data.
# filetext2.split('\n\n') breaks it up into individual data blocks (one per person).
# Mapping to str.splitlines breaks each data block into single lines.
for name, *data in map(str.splitlines, filetext2.split('\n\n')):
    # See if the name matches our pattern.
    if re.match('[A-Za-z]*\d{5}:', name):
        # Add the name and the relevant data to the file.
        # [:-1] gets rid of the colon on the end of the name.
        # The list comprehension gets only the file names from the data.
        results[name[:-1]] = [x for x in data if x.endswith('.zip')]

import re
results = {}
for name, *data in map(str.splitlines, filetext2.split('\n\n')):
    if re.match('[A-Za-z]*\d{5}:', name):
        results[name[:-1]] = [x for x in data if x.endswith('.zip')]

>>> import re
>> filetext2 = '''\
... john123:
... 1
... 2
... coconut_rum.zip
...
... bob234513253:
... 0
... jackdaniels.zip
... nowater.zip
... 3
...
... judy88009:
... dontdrink.zip
... 9
...
... tommi54321:
... dontdrinkalso.zip
... 92
... '''
>>> results = {}
>>> for name, *data in map(str.splitlines, filetext2.split('\n\n')):
...     if re.match('[A-Za-z]*\d{5}:', name):
...         results[name[:-1]] = [x for x in data if x.endswith('.zip')]
...
>>> results
{'tommi54321': ['dontdrinkalso.zip'], 'judy88009': ['dontdrink.zip']}
>>>

import re

results = {}

with open('datazip') as f:
    records = f.read().split('\n\n')

for record in records:
    lines = record.split()
    header = lines[0]

    # note that you need a raw string
    if re.match(r"[^\d]\d{5}:", header[-7:]):

        # in general multiple hits are possible, so put them into a list
        results[header] = [l for l in lines[1:] if l[-3:]=="zip"]

print results

{'tommi54321:': ['dontdrinkalso.zip'], 'judy88009:': ['dontdrink.zip']}

import re

def records(f):
    record = []
    for l in f:
        l = l.strip()
        if l:
            record.append(l)
        else:
            yield record
            record = []
    yield record

results = {}
for record in records(open('datazip')):
    head = record[0]
    if re.match(r"[^\d]\d{5}:", head[-7:]):
        results[head] = [ r for r in record[1:] if r[-3:]=="zip"]
print results

[a-zA-Z]+\d{5}\b

judy88009:

tommi54321:

>>> re.findall(r'[a-zA-Z]+\d{5}\b', x)
['judy88009', 'tommi54321']