Python分析最近大火的网剧《隐秘的角落》

def get_data(tv_name,tv_id):
 url = https://cmts.iqiyi.com/bullet/{}/{}/{}_300_{}.z
 datas = pd.DataFrame(columns=[uid,contentsId,contents,likeCount])
 for i in range(1,20):
  myUrl = url.format(tv_id[-4:-2],tv_id[-2:],tv_id,i)
  print(myUrl)
  res = requests.get(myUrl)
  if res.status_code == 200:
   btArr = bytearray(res.content)
   xml=zlib.decompress(btArr).decode(utf-8)
   bs = BeautifulSoup(xml,"xml")
   data = pd.DataFrame(columns=[uid,contentsId,contents,likeCount])
   data[uid] = [i.text for i in bs.findAll(uid)]
   data[contentsId] = [i.text for i in bs.findAll(contentId)]
   data[contents] = [i.text for i in bs.findAll(content)]
   data[likeCount] = [i.text for i in bs.findAll(likeCount)]
  else:
   break
  datas = pd.concat([datas,data],ignore_index = True)
 datas[tv_name]= str(tv_name)
 return datas

#累计发送弹幕数的用户
danmu_counts = df.groupby(uid)[contentsId].count().sort_values(ascending = False).reset_index()
danmu_counts.columns = [用户id,累计发送弹幕数]
danmu_counts.head()

df_top1 = df[df[uid] == 1810351987].sort_values(by="likeCount",ascending = False).reset_index()
df_top1.head(10)

df_like = df[df.groupby([tv_name])[likeCount].rank(method="first", ascending=False)==1].reset_index()[[tv_name,contents,likeCount]]
df_like.columns = [剧集,弹幕,赞]
df_like