fz0x1/HPI
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

use more-itertools; merge tweets

Browse source
This commit is contained in:
Dima Gerasimov 2020-04-14 22:15:35 +01:00
parent 30b6918a8d
commit 69a1624f8f
1 changed files with 15 additions and 3 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

18
my/twitter/all.py
View file

@ -1,17 +1,29 @@
""" """
Unified Twitter data (merged from the archive and periodic updates) Unified Twitter data (merged from the archive and periodic updates)
""" """
from itertools import chain
from . import twint from . import twint
from . import archive from . import archive
from more_itertools import unique_everseen
def merge_tweets(*sources):
yield from unique_everseen(
chain(*sources),
key=lambda t: t.id_str,
)
def tweets(): def tweets():
yield from archive.tweets() # NOTE order matters.. twint seems to contain better data
yield from twint.tweets() # todo probably, worthy an investigation..
yield from merge_tweets(twint.tweets(), archive.tweets())
# TODO not sure, likes vs favoites?? # TODO not sure, likes vs favoites??
def likes(): def likes():
yield from archive.likes() yield from merge_tweets(archive.likes())
# yield from twint # yield from twint