Andrey Dugin

import pandas as pd

pd.read_csv('input.txt', sep='|', header=None).drop_duplicates(0).to_csv('output.txt', sep='|', header=False, index=False)

matrix[np.diag_indices_from(matrix)] = diagonal[-min(matrix.shape):]

def __init__(self, a=0, b=0, c=0):
    self.a, self.b, self.c = sorted([a, b, c])

def days_till_warming(T):
    counts = []
    for i, curr_temp in enumerate(T):
        for j, next_temp in enumerate(T[i+1:], i + 1):
            if next_temp > curr_temp:
                delta = j - i
                break
        else:
             delta = 0
        counts.append(delta)
    return counts

re.sub('a', lambda c: random.choice(sm), 'aabbbaccddaaadde')

from collections import ChainMap
from itertools import groupby
from operator import itemgetter

ig = itemgetter('user_id')

[{**ChainMap(*dicts)} for _, dicts in groupby(sorted(list1 + list2, key=ig), key=ig)]

#!/usr/bin/env python
# coding: utf-8

import asyncio
import aiohttp
import xml.etree.ElementTree as ET

from zipfile import ZipFile
from collections import Counter
from pathlib import Path
from itertools import islice

TARGET = 'plate_number_image_url'
# TARGET = 'photo_url'

def url_to_filename(url, base_dir=TARGET, last_n_parts=3) -> Path:
    path = Path(base_dir).joinpath(*url.strip().split('/')[-last_n_parts:])
    path.parent.mkdir(parents=True, exist_ok=True)
    return path

async def download_content_as_bytes(url: str) -> bytes:
    content = None
    try:
        async with aiohttp.ClientSession() as session:
            async with session.get(url) as response:
                content = await response.read()
    except aiohttp.client_exceptions.ClientConnectorError:
        # await asyncio.sleep(60)
        pass
    finally:
        return content

async def write_bytes_to_file(content: bytes, filename: str) -> None:
    if content:
        with open(filename, 'wb') as file:
            file.write(content)
            print(f'SAVED {filename}')

async def file_download_task(url: str) -> None:
    filename = url_to_filename(url)
    if not filename.exists():
        content = await download_content_as_bytes(url)
        await write_bytes_to_file(content, filename)
    else:
        pass
        # print(f'SKIPPED {filename}')

async def main(batch_size=1000) -> None:
    with open(f'{TARGET}.txt') as f:
        urls = [line.strip() for line in f]
        print(f'TOTAL: {len(urls)}')
    while urls:
        tasks = map(file_download_task, urls[:batch_size])
        await asyncio.wait(tasks)
        del urls[:batch_size]

if __name__ == '__main__':
    while True:
        asyncio.run(main())

#!/usr/bin/env python
# coding: utf-8

import cv2
import requests
from PIL import Image
from pathlib import Path

for root in ['photo_url', 'plate_number_image_url']:
    for path in Path(root).glob('**/*.*'):
        if path.stat().st_size > 0:
            try:
                if any(Image.open(path).size):
                    image = cv2.imread(str(path))
            except:
                pass
            else:
                continue
        url = list(path.parts)
        url[0] = 'http://img03.platesmania.com'
        url = '/'.join(url)
        response = requests.get(url)
        if response.ok:
            with open(path, 'wb') as fo:
                fo.write(response.content)
                print(f'LOADED {path}')
        else:
            # Повреждённый или отсутствующий файл
            print(path)

def update(d1, d2):
    for key, value in d2.items():
        if isinstance(value, dict):
            d1.setdefault(key, {}).update(value)
        else:
            d1[key] = value
            
update(default, overridden)