Created
December 29, 2021 14:37
-
-
Save yumechi/578e987919252af0d02b92df613a66c0 to your computer and use it in GitHub Desktop.
tweet_idをtweet.jsから引っ張るやつ
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import json | |
from pprint import pprint | |
from datetime import datetime, timezone | |
from dataclasses import dataclass | |
def date_reformat(s: str) -> datetime: | |
""" | |
reforemat dateformat | |
example: | |
Fri May 25 08:35:41 +0000 2018 -> 2018-05-25 08:35:41 | |
Args: | |
s (string): US format datetime | |
Returns: | |
datetime: my format datetime | |
""" | |
return datetime.strptime(s, '%a %b %d %H:%M:%S %z %Y') | |
@dataclass | |
class TweetData: | |
tweet_id: int | |
created_at: datetime | |
full_text: str | |
status: bool = False | |
def __str__(self) -> str: | |
""" | |
debug時はツイートコンテンツを出していていたが、csvとして出すときにめんどくさくなったので消しました。 | |
""" | |
return ",".join([ | |
str(self.tweet_id), | |
self.date_str(self.created_at), | |
str(self.status).lower(), | |
]) | |
def __gt__(self, __o: object) -> bool: | |
return self.created_at > __o.created_at | |
def date_str(target_time: datetime) -> str: | |
return datetime.strftime(target_time, '%Y-%m-%d %H:%M:%S') | |
def solve() -> None: | |
output = [] | |
# tweet.js から最初の変数名を消してjsonとして読み込めるようにする | |
with open('tweet.json') as f: | |
df = json.load(f) | |
for f in df: | |
try: | |
tweet = f['tweet'] | |
tweet_id = int(tweet['id']) | |
created_at = date_reformat(str(tweet['created_at'])) | |
full_text = str(tweet['full_text']).replace("\n", "\\n") | |
output.append(TweetData( | |
tweet_id=tweet_id, | |
created_at=created_at, | |
full_text=full_text, | |
)) | |
except Exception as e: | |
print(f"error: {e}") | |
pprint(f) | |
output.sort(reverse=True) | |
# これより後のデータは黒歴史クリーナーなり、takanahikoさんのツールで消せたためフィルタ用 | |
threshold_date = datetime(year=2020, month=10, day=30, tzinfo=timezone.utc) | |
# 後でjqでいろいろやってたけどcsv→jqにする作業をjqでやらずにpython側で出したほうがよさそう | |
header = [','.join(['tweet_id', 'created_at', 'status'])] | |
data = [str(line) for line in output | |
if threshold_date > line.created_at] | |
contents = header + data | |
print('\n'.join(contents)) | |
if __name__ == '__main__': | |
solve() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
statusは後作業で必要だったので入れてます。
後はこんな感じで
手で一番最初のjsonを消すとjsonとして扱いやすいかも。