Скрипт на python для синхронизации списка Буду смотреть Кинопоиска между аккаунтами и добавления торрентов на TorrServer

kinopoisk_sync.py

from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.common.keys import Keys
from selenium.webdriver.support.wait import WebDriverWait
from selenium.webdriver.support import expected_conditions
import time
import os
import json
import sys
import requests
import re

# mode = 'SYNC_MOVIES_TO_WATCH'
mode = 'GET_MOVIES_DATA'

if mode == 'SYNC_MOVIES_TO_WATCH':
    GET_MOVIES_LIST = True
    DELETE_OLD_LIST = True
    AUTHORIZE = True
    PUT_LIKES = True
    GET_TORRENTS = False
elif mode == 'GET_MOVIES_DATA':
    GET_MOVIES_LIST = True
    DELETE_OLD_LIST = False
    AUTHORIZE = False
    PUT_LIKES = False
    GET_TORRENTS = True



driver = webdriver.Chrome()
wait = WebDriverWait(driver, timeout=120)

movies = []
if GET_MOVIES_LIST:
    movies_list = 'https://www.kinopoisk.ru/user/12345/movies/list/type/3575/sort/default/vector/desc/perpage/200/#list' # change to your user id

    print ('getting the page movies list...')
    driver.implicitly_wait(10)
    driver.get(movies_list)
    time.sleep(10)
    print ('starting to find movies...')
    movies_li = driver.find_elements(By.XPATH, '//li[starts-with(@id,"film_")]')
    if movies_li:
        for li in movies_li:
            url = None
            kinopoisk_id = None
            name = None
            name_orig = None
            year = None
            poster = None
            link = li.find_elements(By.CLASS_NAME, 'name')
            if link:
                url = link[0].get_attribute('href')
                kinopoisk_id = url.replace('https://www.kinopoisk.ru/film/','').replace('/','')
                name = link[0].text
                if '(сериал)' in name:
                    name = name.replace(' (сериал)', '')
                    mtype = 'series'
                else:
                    mtype = 'movie'
            data = li.find_elements(By.TAG_NAME, 'span')
            if data:
                for d in data:
                    if 'мин' in d.text:
                        pattern = r"(?P<text>.*?)?\s?\((\d{4})\)"
                        match = re.search(pattern, data[0].text)
                        if match:
                            name_orig = match.group('text').strip()
                            year = match.group(2)
                        break
            img = li.find_elements(By.TAG_NAME, 'img')
            if img and len(img)>0:
                poster = img[0].get_attribute('src')
                if poster == 'https://st.kp.yandex.net/images/spacer.gif':
                    poster = None


            movies.append({'url': url,
                'id': kinopoisk_id,
                'name': name,
                'name_orig': name_orig,
                'year': year,
                'type': mtype,
                'poster': poster})
    print('movies found: ' + str(len(movies)))
    if len(movies)>0: print('first movie: ' + str(movies[0]))

if AUTHORIZE:
    print('logging to account...')
    driver.implicitly_wait(5)
    driver.get('https://kinopoisk.ru')
    login_button = driver.find_element(By.XPATH, '//button[text()="Войти"]')
    login_button.click()
    wait.until(expected_conditions.title_is('Авторизация'))

    # timeouts are needed for proper login
    elem = driver.find_elements(By.NAME, 'login')[0]
    elem.send_keys('user-id') # change to your user id
    time.sleep(3)
    elem.send_keys(Keys.RETURN)
    time.sleep(3)
    elem = driver.find_elements(By.NAME, 'passwd')[0]
    elem.send_keys('password') # change to your password
    time.sleep(3)
    elem.send_keys(Keys.RETURN)
    time.sleep(3)

    print('check the browser to manually login...')
    wait.until(expected_conditions.title_is('Кинопоиск. Все фильмы планеты.'))

if DELETE_OLD_LIST and AUTHORIZE: # doesn't work without authorization
    print ('deleting old list...')
    driver.get('https://www.kinopoisk.ru/mykp/folders/3575/?limit=100')
    wait.until(expected_conditions.title_is('Кинопоиск — Все фильмы планеты'))
    select_all = driver.find_element(By.ID, 'selectAll_div')
    if select_all:
        select_all.click()
        delete_selected = driver.find_element(By.ID, 'delete_selected_upper_button')
        if delete_selected:
            delete_selected.click()
            alert = wait.until(expected_conditions.alert_is_present())
            alert.accept()

if PUT_LIKES and AUTHORIZE:
    driver.implicitly_wait(3)
    for m in movies:
        print('opening movie ' + m['url'])
        driver.get(m['url'])

        try:
            elem = driver.find_elements(By.CLASS_NAME, 'watch-online-button')
            if elem:
                print('... found online version')
                time.sleep(3)
                like_button = driver.find_element(By.XPATH, '//button[@title="Буду смотреть"]')
                if like_button:
                    like_button.click()
                    print('... liked')

        except Exception:
            pass

if GET_TORRENTS and GET_MOVIES_LIST:

    for m in movies:
        print('looking for torrents for '+m['name']+'...')
        url = 'https://jacred.ru/api/v1.0/torrents?search=%2B' + m['id']
        time.sleep(5)
        response = requests.get(url)
        if response.status_code == 200:
            data = response.json()
            if len(data)>0:
                filtered_data = [record for record in data if record['tracker'] in ['rutracker', 'nnmclub'] and
                 record['quality'] == 480 and
                 m['type'] in record['types'] and
                 m['year'] in record['title'] and
                 ('BDRip' in record['title'] or 'HDRip' in record['title'] or 'HDTVRip' in record['title'] or 'DVDRip' in record['title'])]
                if len(filtered_data)>0:
                    selected_record = max(filtered_data, key=lambda x: x['sid'])
                    magnet = selected_record.get('magnet')
                    title = selected_record.get('title')
                    print('... found magnet: ' + magnet)

                    print('adding torrent to TorrServer... ')
                    url = 'http://192.168.1.1:8090/torrents' # change to your TorrServer ip
                    data = {
                        'action': 'add',
                        'link': magnet,
                        'poster': m['poster'],
                        # 'data': title,
                        "save_to_db": True,
                        'title': m['name'] + ' (' + m['year'] + ')'
                    }

                    response = requests.post(url, data=json.dumps(data))
                    print('... result code: ' + str(response.status_code))
                else:
                    print('... no torrents with needed quality found')
            else:
                print('... no torrents found')
        elif response.status_code == 429:
            tine.sleep(10)
            print('... sleeping for 10 seconds')
        else:
            print('... failed to get torrents, result code: ' + str(response.status_code))


driver.close()