好久没有用爬虫了,手有点生,找了一段代码,但是发现有BUG,还得自己修复。
import requests
import browsercookie
import random,time
from copyheaders import headers_raw_to_dict
headers_raw = b'''
authority: qun.qq.com
method: POST
path: /cgi-bin/qun_mgr/search_group_members
'''
headers = headers_raw_to_dict(headers_raw)
class QQ(object):
def __init__(self,gc,bkn,num,headers):
= headers
= gc
= bkn
= num//40 + 1
= ';
def qqs(self):
qqs = []
for i in range():
num1 = i * 40
num2 = (i + 1) * 40
data = {'gc': ,
'st': '{}'.format(num1),
'end': '{}'.format(num2),
'sort': '0',
'bkn':
}
res = reque(, data=data, headers=, cookies = cookies).json()
print(res)
(2, 3.5))
members = res['mems']
for line in members:
qq = line.get('uin', 85***7)
nick = line.get('nick','未知')
qq_data = '{}\t{}'.format(nick,qq)
print(qq_data)
qqs.append(qq_data)
return qqs
def save_qqs(self):
qqs = ()
with open('qqs.txt','w',encoding='utf-8-sig') as f:
f.writelines([qq+'\n' for qq in qqs])
# 三个参数,即QQ群号gc,bkn值,群成员个数,请求头;其中gc、bkn在荷载中可以查到
qq = QQ('60***5','20***103',1945,headers)
qq.save_qqs()
可以看到QQ号,昵称、加入群时间,最后发言时间,这4个数据有用!
在一个项目做种子用户的时候,QQ群仍是一个有利的工具。