[VK] Парсер документов из перепискок

[stax_bern]

config.py

vk_tokens = '1234'

main.py

import vk_api
import os
import requests
from config import vk_tokens

vk_session = vk_api.VkApi(token=vk_tokens)
vk = vk_session.get_api()

dialogs = vk.messages.getConversations(count=200)['items']

supported_media_types = ['photo', 'video', 'doc', 'audio']

print("Выберите вариант скачивания:")
for i, media_type in enumerate(supported_media_types):
    print(f"{i+1}. {media_type}")
print(f"{len(supported_media_types)+1}. Скачать все файлы поочередно")

choice = int(input("Введите номер: "))

if choice < 1 or choice > len(supported_media_types) + 1:
    print("Некорректный выбор.")
else:
    if choice != len(supported_media_types) + 1:
        media_type = supported_media_types[choice - 1]

    for dialog in dialogs:
        dialog_info = dialog['conversation']['peer']
        if dialog_info['type'] == 'user':
            dialog_id = dialog_info['id']
            user_info = vk.users.get(user_ids=dialog_id)[0]
            first_name = user_info['first_name']
            last_name = user_info['last_name']

            dialog_dir = f"{first_name}_{last_name}"
            if not os.path.exists(dialog_dir):
                os.makedirs(dialog_dir)

            response = vk.messages.getHistoryAttachments(peer_id=dialog_id, media_type=media_type, count=200)
            attachments = response['items']
            while 'next_from' in response:
                response = vk.messages.getHistoryAttachments(
                    peer_id=dialog_id, media_type=media_type, count=200, start_from=response['next_from'])
                attachments.extend(response['items'])

            save_dir = os.path.join(dialog_dir, media_type)
            if not os.path.exists(save_dir):
                os.makedirs(save_dir)

            for attachment in attachments:
                attachment_type = attachment['attachment']['type']
                media = attachment['attachment'][attachment_type]
                if attachment_type == 'photo':
                    photo_url = media['sizes'][-1]['url']
                    file_name = f"{media['id']}.jpg"
                    file_path = os.path.join(save_dir, file_name)
                    response = requests.get(photo_url)
                    with open(file_path, 'wb') as f:
                        f.write(response.content)
                    print(f"Сохранено: {file_path}")
                elif attachment_type == 'video':
                    video_url = media['player']
                    file_name = f"{media['id']}.mp4"
                    file_path = os.path.join(save_dir, file_name)
                    response = requests.get(video_url)
                    with open(file_path, 'wb') as f:
                        f.write(response.content)
                    print(f"Сохранено: {file_path}")
                elif attachment_type == 'doc':
                    doc_url = media['url']
                    file_name = f"{media['id']}_{media['title']}"
                    file_path = os.path.join(save_dir, file_name)
                    response = requests.get(doc_url)
                    with open(file_path, 'wb') as f:
                        f.write(response.content)
                    print(f"Сохранено: {file_path}")
                elif attachment_type == 'audio':
                    audio_url = media['url']
                    file_name = f"{media['id']}_{media['artist']} - {media['title']}.mp3"
                    file_path = os.path.join(save_dir, file_name)
                    response = requests.get(audio_url)
                    with open(file_path, 'wb') as f:
                        f.write(response.content)
                    print(f"Сохранено: {file_path}")