我想用Telethon API抓取一个Telegram组。但这段代码会刮伤组中的所有用户。但我只想在网上和最近一次看到的用户。怎么做?
from telethon.sync import TelegramClient
from telethon.tl.functions.messages import GetDialogsRequest
from telethon.tl.types import InputPeerEmpty
import csv
api_id = 123456
api_hash = 'YOUR_API_HASH'
phone = '+111111111111'
client = TelegramClient(phone, api_id, api_hash)
client.connect()
if not client.is_user_authorized():
client.send_code_request(phone)
client.sign_in(phone, input('Enter the code: '))
chats = []
last_date = None
chunk_size = 200
groups=[]
result = client(GetDialogsRequest(
offset_date=last_date,
offset_id=0,
offset_peer=InputPeerEmpty(),
limit=chunk_size,
hash = 0
))
chats.extend(result.chats)
for chat in chats:
try:
if chat.megagroup== True:
groups.append(chat)
except:
continue
print('Choose a group to scrape members from:')
i=0
for g in groups:
print(str(i) + '- ' + g.title)
i+=1
g_index = input("Enter a Number: ")
target_group=groups[int(g_index)]
print('Fetching Members...')
all_participants = []
all_participants = client.get_participants(target_group, aggressive=True)
print('Saving In file...')
with open("members.csv","w",encoding='UTF-8') as f:
writer = csv.writer(f,delimiter=",",lineterminator="n")
writer.writerow(['username','user id', 'access hash','name','group', 'group id'])
for user in all_participants:
if user.username:
username= user.username
else:
username= ""
if user.first_name:
first_name= user.first_name
else:
first_name= ""
if user.last_name:
last_name= user.last_name
else:
last_name= ""
name= (first_name + ' ' + last_name).strip()
writer.writerow([username,user.id,user.access_hash,name,target_group.title, target_group.id])
print('Members scraped successfully.')
希望这有帮助:
...
for user in all_participants:
if not user.user.status in ['online','recently']: continue
if user.username:
username= user.username
...
我尝试了这个代码和另一个具有num.date
条件的代码,但向我显示了一个成员,甚至什么都不显示,但我认为最好更改一个简单的东西,最后使用Excel的过滤器来获得答案。最近最后一次看到是在上线前1到2或3天。。。
with open("members.csv","w",encoding='UTF-8') as f:
writer = csv.writer(f,delimiter=",",lineterminator="n")
writer.writerow(['username','user id', 'access hash','name','group', 'group id','status'])
for user in all_participants:
if user.username:
username= user.username
else:
username= ""
if user.first_name:
first_name= user.first_name
else:
first_name= ""
if user.last_name:
last_name= user.last_name
else:
last_name= ""
name= (first_name + ' ' + last_name).strip()
writer.writerow([username,user.id,user.access_hash,name,target_group.title, target_group.id,user.status])
print('Members scraped successfully.')
你可以在最后添加user.status
,它工作得很好。