# coding:utf-8
from tasks.workers import app
from page_get import user as user_get
from db.seed_ids import get_seed_ids, get_seed_by_id, insert_seeds, set_seed_other_crawled
@app.task(ignore_result=True)
def crawl_follower_fans(uid):
  seed = get_seed_by_id(uid)
  if seed.other_crawled == 0:
    rs = user_get.get_fans_or_followers_ids(uid, 1

    rs.extend(user_get.get_fans_or_followers_ids(uid, 2))
    datas = set(rs)
    # 重復(fù)數(shù)據(jù)跳過插入
    if datas:
      insert_seeds(datas)
    set_seed_other_crawled(uid)
@app.task(ignore_result=True)
def crawl_person_infos(uid):
  ""
  根據(jù)用戶i來爬取用戶相關(guān)資料和用戶的關(guān)注數(shù)和粉絲數(shù)（由于微博服務(wù)端限制，默認(rèn)爬取前五頁，企業(yè)號(hào)的關(guān)注和粉絲也不能查看）
  :param uid: 用戶id
  :return:
  """
  if not uid:
    return
  # 由于與別的任務(wù)共享數(shù)據(jù)表，所以需要先判斷數(shù)據(jù)庫(kù)是否有該用戶信息，再進(jìn)行抓取
  user = user_get.get_profile(uid)
  # 不抓取企業(yè)號(hào)
  if user.verify_type == 2:
    set_seed_other_crawled(uid)
    return
  app.send_task('tasks.user.crawl_follower_fans', args=(uid,), queue='fans_followers',
         routing_key='for_fans_followers')
@app.task(ignore_result=True)
def excute_user_task():
  seeds = get_seed_ids()
  if seeds:
    for seed in seeds:
      # 在send_task的時(shí)候指定任務(wù)隊(duì)列
      app.send_task('tasks.user.crawl_person_infos', args=(seed.uid,), queue='user_crawler',
             routing_key='for_user_info')