python-爬虫：取qq号中各分组成员信息存入数据库，并将qq头像下载保存到文件夹，图片命名为qq号（实例3）

标签：res   cgi   接口   srm   def   __init__   bin   requests   数据库   

import requests
import pymongo
import requests
import os

class QqGroup:
#三个接口url 获取 qq组号  获取每组成员信息  获取qq头像下载地址
   group_url = "https://qun.qq.com/cgi-bin/qun_mgr/get_group_list"
   member_url = "https://qun.qq.com/cgi-bin/qun_mgr/search_group_members"
   pic_url = "http://q4.qlogo.cn/g?b=qq&nk={%s}&s=140"
#一般将cookie与链接数据库代码写在构造函数
   def __init__(self,cookie):
      self.cookie = cookie
      self.client = pymongo.MongoClient(host=‘118.24.3.40‘,port=27017)
      self.db = self.client[‘qq_group‘] #数据库名称
      self.table = self.db[‘qq_group‘]   #表名称
#获取 qq组号
   def get_all_group(self):
      data = {‘bkn‘:2039193070}
      res = requests.post(self.group_url,data,headers={‘cookie‘:self.cookie}).json()
#新方法 1、对于返回值为多个list合并，如果返回为空，增加默认值为空 2、对于字典取值用get方法
      all_groups = res.get(‘join‘, []) + res.get(‘create‘, []) + res.get(‘manage‘, [])

      all_gc=[i.get(‘gc‘) for i in all_groups]

      return all_gc
#获取每组成员信息 
   def get_group_info(self,num):
      data = {"gc":num,"st":0,"end":200,"sort":0,"bkn":2039193070}
      res = requests.post(url=self.member_url, data=data, headers={‘Cookie‘:self.cookie})
      mems = res.json().get("mems")  
      for i in mems:
         mem = {
            "qq": i.get("uin"),
            "gender": i.get("g"),
            "nick": i.get("nick"),
            "card": i.get("card"),
            "qage": i.get("qage")
            }
         if mem.get("gender") == 0:
            mem[‘gender‘] = "男"
         elif mem.get("gender") == 1:
            mem[‘gender‘] = "女"
         else:
            mem[‘gender‘] = "未知"
         if mem.get("card") == "":
            mem[‘card‘] = "没有群名片"
         self.save_mongo(mem)
         self.down_pic(i.get("uin"))
#存入mogodb数据库
   def save_mongo(self,data):
      self.table.insert(data)

#下载qq头像
   def down_pic(self,qq_num):
      real_url=self.pic_url %qq_num
      res=requests.get(real_url).content
      pathnew = os.path.dirname(os.path.abspath(__file__))
      pathnew = os.path.join(pathnew, ‘imgs‘)
      if not os.path.isdir(‘imgs‘):
         os.makedirs(‘imgs‘)
      with open(os.path.join(pathnew, str(qq_num) + ‘.jpg‘), ‘wb‘) as fw:
         fw.write(res)
         print(‘%s头像下载完成‘ % qq_num)
#main函数用于将各过程统一到一个函数，便于实例化后调用
   def mian(self):
      all_group=self.get_all_group()
      for i in all_group:
         self.get_group_info(i)
#实例化类 参数传递为cookie
Q=QqGroup(‘pgv_pvid=1745803612; pgv_pvi=9485686784; RK=vRZxXdy1Y7; _qpsvr_localtk=0.8876927078641847; pgv_si=s3971407872; ptisp=cnc; ptcz=e42f943c39b23e3d7a94d9deac0de69388506bbb9b09000f197b8681624f70ac; uin=o0106148088; skey=@pH5b3tYaY; pt2gguin=o0106148088; p_uin=o0106148088; pt4_token=Vrwh5LwXxUAe0OaJi5DR-XEt8F13T5OheqfWVI3CJjQ_; p_skey=SPaNeBpdwjMfAGplMvT-msRMptEYPnPykjrJo80kXqY_‘)
Q.mian()

python-爬虫：取qq号中各分组成员信息存入数据库，并将qq头像下载保存到文件夹，图片命名为qq号（实例3）

标签：res   cgi   接口   srm   def   __init__   bin   requests   数据库   

原文地址：https://www.cnblogs.com/wenchengqingfeng/p/9396291.html