test3_sb

# -Либо получить список участников групп сайта ВКонтакте, чтоб в названии/описании группы
# фигурировала информация о крипте.
# Цель чтоб получить как можно лучшую информацию по клиенту(фио, др, или телефон)
# чтоб дальше можно было понять кто это

#from bs4 import BeautifulSoup

print('\nimpotring libs...\n')
import requests as req
import pandas
from pathlib import Path
from datetime import datetime
import csv
import math

vk_api_version = '5.131'
vk_api_method = 'groups.getMembers'
print('Hello, and welcome to vk parcer for test task(3*).\nThis script is working on vk\'s api version=',vk_api_version)
print('For working with this script u should make service-token.',
'\n fyi: https://dev.vk.com/api/access-token/getting-started \n\n')

group_link = input('Input link on vk-community. example: https://vk.com/free_nft\nInput link: ')
#check for right link providing
try:
    main_link = req.get(group_link)
except:
    print('wrong link')
    exit()

#check for private settings
try:
    gr_id = ((main_link.text.split('owner_id=-'))[1].split('&'))[0]
except:
    print('it\' private group. impossible to parse')
    exit()
group_name = ((main_link.text.split('data-post-owner-type="group">'))[1].split('</a> </div>'))[0]

#making output folder
base_path = str(Path.cwd())+'/output_folder/'
base_p = Path(base_path)
base_p.mkdir(exist_ok=True)

#creating csv
csv_path = base_path+gr_id+'_'+str(datetime.now().strftime("%Y-%m-%d-%H-%M-%S"))+'.csv'
csv_result_ids = open(csv_path, "x")
csv_result_ids.write('id_of_subs\n')
csv_result_ids.close()

#creating and checking for group's readme
try:
    readme = open(base_path+gr_id+'.txt','x')
    readme.write('Group name: '+group_name+'\npermanent link: https://vk.com/club'+gr_id+'\nDescription:'+str(((main_link.text.split('<meta name="description" content="'))[1].split('" />'))[0]))
except:
    print('readme for',group_name,'already created')

#run through subs
main_link = req.get('https://vk.com/search?c[section]=people&c[group]='+gr_id)

# а тут я вспомнил про три буквы - A P I
#user's own service-token for api requests
ur_service_token = input('input ur vk-api\'s service token.\nInput s-token:')

#counts of subs
api_q = req.get('https://api.vk.com/method/groups.getMembers?access_token='+ur_service_token+'&v='+vk_api_version+'&group_id='+gr_id+'&count=0')
amount_of_subs = ((str(api_q.json()).split('\'count\': '))[1].split(','))[0]

#saving subs ids
offset_help = 0
csv_result_ids = open(csv_path,'a')#,newline='')
for i in range(int(math.ceil(int(amount_of_subs)/1000))):
    api_q = req.get('https://api.vk.com/method/groups.getMembers?access_token='+ur_service_token+'&v='+vk_api_version+'&group_id='+gr_id+'&offset='+str(offset_help))
    array_of_ids=((str(api_q.json()).split('['))[1].split(']'))[0].split(',')
    for j in array_of_ids:
        (csv.writer(csv_result_ids)).writerow([j])
    offset_help +=1000
csv_result_ids.close()

#adding other info: publicity of profile, id, name, city, phone | берем айдишники, идем к апи-запросу
#primerno zdes' nachinaetsya kasha s bol'shim kolichestvom bottle neck'ov i kostiley
n=0
csv_path_finale = base_path+gr_id+'-'+str(datetime.now().strftime("%Y-%m-%d-%H-%M-%S"))+'.csv'
csv_result = open(csv_path_finale,encoding='utf-16',mode='a')
csv_result.write('id,is_closed,name,bday,sex,country,city,mobile_phone,home_phone\n')
# sex: 1-female, 2-male, 0-none

print('\nparcing in progress...\n')

csv_result_ids=open(csv_path,'r')
read_csv=csv.reader(csv_result_ids)
next(read_csv)
for i in range(int(math.ceil(int(amount_of_subs)/100))):
    users_ids=[]
    users_ids_no_spaces=''
    for j in range(n,99+n):
        try:
            users_ids+=next(read_csv)
        except:
            continue
    for k in range(len(users_ids)):
        users_ids_no_spaces+=users_ids[k].replace(' ','')+','
    api_q = req.get('https://api.vk.com/method/users.get?access_token='+ur_service_token+'&v='+vk_api_version+'&user_ids='+users_ids_no_spaces+'&fields=country,city,contacts,sex,bdate')
    users_info = (str(api_q.json()).split('['))[1].split('}, {')

    for j in range(100):
        try:
            user = users_info[j]
            u_id = user.split('id\':')[1].split(',')[0]+','
            u_private =  user.split('is_closed\':')[1].replace('}]}','')+','
            u_name=(user.split('last_name\':')[1].split(',')[0]+'_'+user.split('first_name\':')[1].split(',')[0]).replace('\'','')+','
            u_bday=','
            u_sex=','
            u_country=','
            u_city=','
            u_mobile_phone=','
            u_home_pnohe=''

            if 'bdate' in user:
                u_bday = user.split('bdate\':')[1].split(',')[0].replace('\'','')+','
            if 'sex' in user:
                u_sex =  user.split('sex\':')[1].split(',')[0]+','
            if 'mobile_phone' in user:
                u_mobile_phone=(user.split('mobile_phone\':')[1].split(',')[0]).replace('\'','')+','
            if 'home_phone' in user:
                u_home_pnohe=user.split('home_phone\':')[1].split(',')[0].replace('\'','')
            if 'country' in user:
                u_country=user.split('country\': {')[1].split(',')[0].replace('\'id\': ','')+'|'+user.split('country\': {')[1].split('title\':')[1].split('}')[0].replace(' ','').replace('\'','')+','
            if 'city' in user:
                u_city=user.split('city\': {')[1].split(',')[0].replace('\'id\': ','')+'|'+user.split('city\': {')[1].split('title\':')[1].split('}')[0].replace(' ','').replace('\'','')+','

            u_result=(u_id+u_private+u_name+u_bday+u_sex+u_country+u_city+u_mobile_phone+u_home_pnohe).replace(' ','')
            csv_result.write(u_result+'\n')
        except:
            continue
    n+=100

print('result file was created by path:',csv_path_finale)
Path.unlink(csv_path)