# -*- coding: utf-8 -*-
import urllib.request
import json
#定義要爬取的微博大V的微博ID
id='1259110474'
#設(shè)置代理IP
proxy_addr="122.241.72.191:808"
#定義頁(yè)面打開函數(shù)
def use_proxy(url,proxy_addr):
  req=urllib.request.Request(url)
  req.add_header("User-Agent","Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/49.0.2623.221 Safari/537.36 SE 2.X MetaSr 1.0")
  proxy=urllib.request.ProxyHandler({'http':proxy_addr})
  opener=urllib.request.build_opener(proxy,urllib.request.HTTPHandler)
  urllib.request.install_opener(opener)
  data=urllib.request.urlopen(req).read().decode('utf-8','ignore')
  return data
#獲取微博主頁(yè)的containerid，爬取微博內(nèi)容時(shí)需要此id
def get_containerid(url):
  data=use_proxy(url,proxy_addr)
  content=json.loads(data).get('data')
  for data in content.get('tabsInfo').get('tabs'):
    if(data.get('tab_type')=='weibo'):
      containerid=data.get('containerid')
  return containerid
#獲取微博大V賬號(hào)的用戶基本信息，如：微博昵稱、微博地址、微博頭像、關(guān)注人數(shù)、粉絲數(shù)、性別、等級(jí)等
def get_userInfo(id):
  url='https://m.weibo.cn/api/container/getIndex?type=uid&value='+id
  data=use_proxy(url,proxy_addr)
  content=json.loads(data).get('data')
  profile_image_url=content.get('userInfo').get('profile_image_url')
  description=content.get('userInfo').get('description')
  profile_url=content.get('userInfo').get('profile_url')
  verified=content.get('userInfo').get('verified')
  guanzhu=content.get('userInfo').get('follow_count')
  name=content.get('userInfo').get('screen_name')
  fensi=content.get('userInfo').get('followers_count')
  gender=content.get('userInfo').get('gender')
  urank=content.get('userInfo').get('urank')
  print("微博昵稱："+name+"\n"+"微博主頁(yè)地址："+profile_url+"\n"+"微博頭像地址："+profile_image_url+"\n"+"是否認(rèn)證："+str(verified)+"\n"+"微博說(shuō)明："+description+"\n"+"關(guān)注人數(shù)："+str(guanzhu)+"\n"+"粉絲數(shù)："+str(fensi)+"\n"+"性別："+gender+"\n"+"微博等級(jí)："+str(urank)+"\n")
#獲取微博內(nèi)容信息,并保存到文本中，內(nèi)容包括：每條微博的內(nèi)容、微博詳情頁(yè)面地址、點(diǎn)贊數(shù)、評(píng)論數(shù)、轉(zhuǎn)發(fā)數(shù)等
def get_weibo(id,file):
  i=1
  while True:
    url='https://m.weibo.cn/api/container/getIndex?type=uid&value='+id
    weibo_url='https://m.weibo.cn/api/container/getIndex?type=uid&value='+id+'&containerid='+get_containerid(url)+'&page='+str(i)
    try:
      data=use_proxy(weibo_url,proxy_addr)
      content=json.loads(data).get('data')
      cards=content.get('cards')
      if(len(cards)>0):
        for j in range(len(cards)):
          print("-----正在爬取第"+str(i)+"頁(yè)，第"+str(j)+"條微博------")
          card_type=cards[j].get('card_type')
          if(card_type==9):
            mblog=cards[j].get('mblog')
            attitudes_count=mblog.get('attitudes_count')
            comments_count=mblog.get('comments_count')
            created_at=mblog.get('created_at')
            reposts_count=mblog.get('reposts_count')
            scheme=cards[j].get('scheme')
            text=mblog.get('text')
            with open(file,'a',encoding='utf-8') as fh:
              fh.write("----第"+str(i)+"頁(yè)，第"+str(j)+"條微博----"+"\n")
              fh.write("微博地址："+str(scheme)+"\n"+"發(fā)布時(shí)間："+str(created_at)+"\n"+"微博內(nèi)容："+text+"\n"+"點(diǎn)贊數(shù)："+str(attitudes_count)+"\n"+"評(píng)論數(shù)："+str(comments_count)+"\n"+"轉(zhuǎn)發(fā)數(shù)："+str(reposts_count)+"\n")
        i+=1
      else:
        break
    except Exception as e:
      print(e)
      pass
if __name__=="__main__":
  file=id+".txt"
  get_userInfo(id)
  get_weibo(id,file)