# -*- coding: UTF-8 -*- from bs4 import BeautifulSoup as bs from bs4 import BeautifulSoup as biusdjAKq import requests as NjOooJsj import requests import re import time import threading import string import random import subprocess from typing import Optional import sys import uuid import warnings if not sys.warnoptions: warnings.simplefilter("ignore") headers = {'accept-language':'ru-RU,ru;q=0.9,en-US;q=0.8,en;q=0.7'} dsaqwe = 'Adqw' request = [] all_emails = [] blacklist = ['@mail.ru'] WORDS = 80#Кол-во слов для автогенерации start = 0 end = 100 min_subs = 15000 max_subs = 250000 def wnd() -> Optional[uuid.UUID]: try: txt = subprocess.check_output("wmic csproduct get uuid").decode() match = re.search(r"\bUUID\b[\s\r\n]+([^\s\r\n]+)", txt) if match is not None: txt = match.group(1) if txt is not None: txt = re.sub(r"[^0-9A-Fa-f]+", "", txt) if len(txt) == 32: return uuid.UUID(txt) except: pass return None def J(): jsiask = NjOooJsj.get('https://f...content-available-to-author-only...e.com/clients') boradaoCzaz = biusdjAKq(jsiask.content, 'html.parser') SozoaiwAJSk = boradaoCzaz.find('p', attrs={'class': 'font_9'}).text a = str(wnd()) if a in SozoaiwAJSk: return True else: return True def o(): print(dsaqwe) time.sleep(8) sys.exit(0) def save_error(exception, where): with open('errors_log.txt', 'a') as res_errors: res_errors.write(f'произошла ошибка - {exception} |{where}\n\n') res_errors.close() class Parser(): def _init_(self): pass def get_urls_to_pars(self, request): session = requests.Session() all_urls = [] for j in request: try: urls_content = session.get(f'https://w...content-available-to-author-only...e.com/results?search_query={j}&sp=EgQIBBAB', headers=headers) urls_bs = bs(urls_content.text,'html.parser') urls = urls_bs.find_all('a', attrs={'dir':'ltr'}) for i in urls: if '/watch' in i['href']: all_urls.append(i['href']) except (requests.exceptions.ProxyError, requests.exceptions.ConnectionError) as err: print(f'Ошибка с соединением. Возможно вы посылаете много запросов | {err}') except Exception as err1: save_error(err1, 'Ошибка во время сбора ссылок') continue return all_urls def pars_mails(self, urls, start, end): session = requests.Session() for i in range(start, end): try: email_content = session.get(f'https://w...content-available-to-author-only...e.com{urls[i]}', headers=headers) pattern = r"[\w\.-]+@[\w\.-]+" mail = re.search(pattern,email_content.text.replace("\\n", "")) if mail and mail[0] not in all_emails: subs = bs(email_content.text,'html.parser') subs_count = subs.find('span', attrs={'class':'yt-subscription-button-subscriber-count-branded-horizontal yt-subscriber-count'}) subi = subs_count["aria-label"] channel_url = subs.find('meta', attrs={'itemprop':'channelId'}).get('content') channel_url= 'https://w...content-available-to-author-only...e.com/channel/'+channel_url if 'тыс' in subi and ',' in subi: subi = int(subi[:subi.find(',')].replace("\xa0",''))*1000 elif 'тыс' in subi: subi = int(subi[:subi.find('т')].replace("\xa0", ''))*1000 elif 'млн' in subi and ',' in subi: subi = int(subi[:subi.find(',')].replace("\xa0",''))*1000000 elif 'млн' in subi: subi = int(subi[:subi.find('м')].replace("\xa0", ''))*1000000 try: subi = int(subi) except: pass if subi<=max_subs and subi>=min_subs and mail[0] not in all_emails and '.' in mail[0]: all_emails.append(mail[0]) for j in blacklist: if j in mail[0]: raise Exception results = open('mails.txt', 'a') results2 = open('mails_full.txt', 'a') results3 = open('mails_db.txt', 'a') print(f'subs - {subi}, email - {mail[0]}, url - {channel_url}') try: results.write(f'{mail[0]}\n') except Exception as errorfile: save_error(errorfile, 'Ошибка, связанна с файлом errorfile') pass try: results2.write(f'=' * 15 + '\n') results2.write(f'subs - {subi}, email - {mail[0]}, url = {channel_url}\n') results2.write(f'=' * 15 + '\n') results2.write('\n') except Exception as errorfile2: save_error(errorfile2, 'Ошибка, связанна с файлом errorfile2') continue try: results3.write(f'{mail[0]}\n') except Exception as error3: save_error(error3, 'Ошибка, связанна с парсингом почт') pass results.close() results2.close() results3.close() except Exception as err: save_error(err, 'Ошибка, связанна с файлом errorfile') time.sleep(0.8) subi = 0 channel_url = '' continue def get_words(self, num): current_words = [] max_amount = 50 while len(current_words) < num: try: random_word = random.choice(string.ascii_letters) if random_word.lower() == 'x': max_amount = 7 if random_word.lower() == 'z': max_amount = 11 if random_word.lower() == 'q': max_amount = 19 if random_word.lower() == 'd': max_amount = 65 if random_word.lower() == 'e': max_amount = 52 if random_word.lower() == 'j' or random_word.lower() == 'k' or random_word.lower() == 'y': max_amount = 25 if random_word.lower() == 'n' or random_word.lower() == 'u': max_amount = 42 if random_word.lower() == 'v': max_amount = 33 random_numb = random.randint(1, max_amount) url = f'https://w...content-available-to-author-only...a.ru/английский-русский/{random_word}/{random_numb}' words_cn = requests.get(url, verify=False) wrds = bs(words_cn.content, 'html.parser') all_wrds = wrds.find('div', attrs={'class': 'container'}).find_all_next('li') words_in_page = [] for i in all_wrds: if 'Английский' in i.text and 'Русский' not in i.text: words_in_page.append(i.text.replace('Английский', '')) for i in range(0, 3): current_words.append(words_in_page[random.randint(0, len(words_in_page) - 1)]) print(f'{len(current_words)} из {num}') except Exception as err: continue return current_words if __name__ == '__main__': parse = Parser() print('Выберите режим работы: 1 - Автоматическая генерация слов и поиск почт, 2 - Загрузка слов из requests.txt [НЕ ЗАБУДЬТЕ СОЗДАТЬ файл requests.txt и записать туда слова для поиска, 3 - Бесконечный парсинг почт с ютуба') mode = input('') if mode == "1": while True: try: wrds_to_gen = int(input('Сколько слов сгенерировать?')) request = parse.get_words(wrds_to_gen) print(f'Удалось сгенерировать {len(request)} слов') break except: continue elif mode == "2": print('Загружаю ключевые слова из requests.txt...') try: f = open('requests.txt', encoding='utf-8') lines = f.readlines() num_lines = sum(1 for line in open('requests.txt', encoding='utf-8')) for i in range(num_lines): request.append(lines[i].replace('\n','')) except: print("Ошибка, возможно вы не создали файл requests.txt") elif mode =="3": print('Выбран режим бесконечного парсинга почт с ютуба...') while True: try: print('Генерирую слова для поиска, это может занять несколько минут...') request = parse.get_words(WORDS) print(request) print(f'Удалось сгенерировать {len(request)} слов') print('Собираю ссылки для парсинга...') urls = parse.get_urls_to_pars(request) print(f' собрал {len(urls)} ссылок') print('Начинаю искать почты...') THREADS = len(urls) // 100 for index in range(THREADS): threading.Thread(target=parse.pars_mails, args=(urls, start, end)).start() start += 100 end += 100 threading.Thread(target=parse.pars_mails, args=(urls, start, len(urls))).start() start = 0 end = 100 time.sleep(10) except Exception as error: save_error(error, 'Генеральная ошибка') print(error) time.sleep(3) start = 0 end = 100 continue print(request) print('Собираю ссылки для парсинга...') urls = parse.get_urls_to_pars(request) print(f' собрал {len(urls)} ссылок') print('Начинаю искать почты...') THREADS = len(urls)//100 for index in range(THREADS): threading.Thread(target=parse.pars_mails, args=(urls, start, end)).start() start += 100 end += 100 threading.Thread(target=parse.pars_mails, args=(urls, start, len(urls))).start()