Last active
March 31, 2022 15:56
-
-
Save Axeltherabbit/d91624739392a59d48c5e8282e7811ab to your computer and use it in GitHub Desktop.
Messy code but it creates a list with user's messages stats from a telegram group's exported json file
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 collections import namedtuple | |
class person: | |
def __init__(self, _id, username): | |
self.id = _id | |
self.username = username | |
self.msgs_len = [] | |
def add_msg(self, msg): | |
m = [] | |
def recmsg2text(raw): | |
if isinstance(raw, str): | |
m.append(raw) | |
if isinstance(raw, list): | |
for item in raw: | |
recmsg2text(item) | |
if isinstance(raw, dict): | |
for key in raw: | |
if key == "text": | |
m.append(raw[key]) | |
recmsg2text(msg) | |
self.msgs_len.append(len(" ".join(m))) | |
def __hash__(self): | |
return self.id | |
def id2int(_id): | |
return int(_id.replace("user", "").replace("channel", "")) | |
def main(): | |
people = {} | |
with open("result.json", "r") as f: | |
js = json.load(f) | |
for msg in js["messages"]: | |
if msg["type"] == "message": | |
_id = id2int(msg["from_id"]) | |
if not people.get(_id, False): | |
p = person(_id, msg["from"]) | |
people[_id] = p | |
people[_id].add_msg(msg["text"]) | |
prsn = namedtuple("person", ["username", "messages", "average_len", "median_len"]) | |
res = [ | |
prsn( | |
person.username, | |
len(person.msgs_len), | |
int(sum(person.msgs_len) / len(person.msgs_len)), | |
sorted(person.msgs_len)[len(person.msgs_len) // 2], | |
) | |
for _id, person in people.items() | |
] | |
st = sorted(res, key=lambda o: o.messages) | |
print(*st, sep="\n") | |
if __name__ == "__main__": | |
main() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment