You can use groupby
to group the data using the empty lines as delimiters, use a defaultdict
for repeated keys extending the rest of the values from each val returned from groupby after extracting the key/first element.
from itertools import groupby
from collections import defaultdict
d = defaultdict(list)
with open("file.txt") as f:
for k, val in groupby(f, lambda x: x.strip() != ""):
# if k is True we have a section
if k:
# get key "k" which is the first line
# from each section, val will be the remaining lines
k,*v = val
# add or add to the existing key/value pairing
d[k].extend(map(str.rstrip,v))
from pprint import pprint as pp
pp(d)
Output:
{'Bob Dylan\n': ['1966 Blonde on Blonde',
'-Rainy Day Women #12 & 35',
'-Pledging My Time',
'-Visions of Johanna',
'-One of Us Must Know (Sooner or Later)',
'-I Want You',
'-Stuck Inside of Mobile with the Memphis Blues Again',
'-Leopard-Skin Pill-Box Hat',
'-Just Like a Woman',
"-Most Likely You Go Your Way (And I'll Go Mine)",
'-Temporary Like Achilles',
'-Absolutely Sweet Marie',
'-4th Time Around',
'-Obviously 5 Believers',
'-Sad Eyed Lady of the Lowlands'],
'Led Zeppelin\n': ['1979 In Through the Outdoor',
'-In the Evening',
'-South Bound Saurez',
'-Fool in the Rain',
'-Hot Dog',
'-Carouselambra',
'-All My Love',
"-I'm Gonna Crawl",
'1969 II',
'-Whole Lotta Love',
'-What Is and What Should Never Be',
'-The Lemon Song',
'-Thank You',
'-Heartbreaker',
"-Living Loving Maid (She's Just a Woman)",
'-Ramble On',
'-Moby Dick',
'-Bring It on Home']}
For python2 the unpack syntax is slightly different:
with open("file.txt") as f:
for k, val in groupby(f, lambda x: x.strip() != ""):
if k:
k, v = next(val), val
d[k].extend(map(str.rstrip, v))
If you want to keep the newlines remove the map(str.rstrip..
If you want the album and songs separately for each artist:
from itertools import groupby
from collections import defaultdict
d = defaultdict(lambda: defaultdict(list))
with open("file.txt") as f:
for k, val in groupby(f, lambda x: x.strip() != ""):
if k:
k, alb, songs = next(val),next(val), val
d[k.rstrip()][alb.rstrip()] = list(map(str.rstrip, songs))
from pprint import pprint as pp
pp(d)
{'Bob Dylan': {'1966 Blonde on Blonde': ['-Rainy Day Women #12 & 35',
'-Pledging My Time',
'-Visions of Johanna',
'-One of Us Must Know (Sooner or '
'Later)',
'-I Want You',
'-Stuck Inside of Mobile with the '
'Memphis Blues Again',
'-Leopard-Skin Pill-Box Hat',
'-Just Like a Woman',
'-Most Likely You Go Your Way '
"(And I'll Go Mine)",
'-Temporary Like Achilles',
'-Absolutely Sweet Marie',
'-4th Time Around',
'-Obviously 5 Believers',
'-Sad Eyed Lady of the Lowlands']},
'Led Zeppelin': {'1969 II': ['-Whole Lotta Love',
'-What Is and What Should Never Be',
'-The Lemon Song',
'-Thank You',
'-Heartbreaker',
"-Living Loving Maid (She's Just a Woman)",
'-Ramble On',
'-Moby Dick',
'-Bring It on Home'],
'1979 In Through the Outdoor': ['-In the Evening',
'-South Bound Saurez',
'-Fool in the Rain',
'-Hot Dog',
'-Carouselambra',
'-All My Love',
"-I'm Gonna Crawl"]}}