綜合大作業
第一步：愛奇藝《青春有你2》評論數據爬取(參考鏈接：https://www.iqiyi.com/v_19ryfkiv8w.html#curid=15068699100_9f9bab7e0d1e30c494622af777f4ba39)
- 爬取任意一期正片視頻下評論
- 評論條數不少於1000條
第二步：詞頻統計並可視化展示
- 數據預處理：清理清洗評論中特殊字符（如：@#￥%、emoji表情符）,清洗後結果存儲爲txt文檔
- 中文分詞：添加新增詞（如：青你、奧利給、衝鴨），去除停用詞（如：哦、因此、不然、也好、但是）
- 統計top10高頻詞
- 可視化展示高頻詞
第三步：繪製詞雲
- 根據詞頻生成詞雲
- 可選項-添加背景圖片，根據背景圖片輪廓生成詞雲
第四步：結合PaddleHub，對評論進行內容審覈
需要的配置和準備
- 中文分詞需要jieba
- 詞雲繪製需要wordcloud
- 可視化展示中需要的中文字體
- 網上公開資源中找一箇中文停用詞表
- 根據分詞結果自己製作新增詞表
- 準備一張詞雲背景圖（附加項，不做要求，可用hub摳圖實現）
- paddlehub配置
!pip install jieba
!pip install wordcloud
Looking in indexes: https://pypi.mirrors.ustc.edu.cn/simple/
Requirement already satisfied: jieba in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (0.42.1)
Looking in indexes: https://pypi.mirrors.ustc.edu.cn/simple/
Collecting wordcloud
[?25l Downloading https://mirrors.tuna.tsinghua.edu.cn/pypi/web/packages/d6/af/55c7f2aa0997147943b474a74bab8deb17e7cf935b9abb8798d724c57721/wordcloud-1.6.0-cp37-cp37m-manylinux1_x86_64.whl (361kB)
[K |████████████████████████████████| 368kB 9.8MB/s eta 0:00:01
[?25hRequirement already satisfied: matplotlib in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from wordcloud) (2.2.3)
Requirement already satisfied: pillow in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from wordcloud) (6.2.0)
Requirement already satisfied: numpy>=1.6.1 in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from wordcloud) (1.16.4)
Requirement already satisfied: python-dateutil>=2.1 in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from matplotlib->wordcloud) (2.8.0)
Requirement already satisfied: pytz in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from matplotlib->wordcloud) (2019.3)
Requirement already satisfied: pyparsing!=2.0.4,!=2.1.2,!=2.1.6,>=2.0.1 in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from matplotlib->wordcloud) (2.4.2)
Requirement already satisfied: cycler>=0.10 in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from matplotlib->wordcloud) (0.10.0)
Requirement already satisfied: six>=1.10 in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from matplotlib->wordcloud) (1.12.0)
Requirement already satisfied: kiwisolver>=1.0.1 in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from matplotlib->wordcloud) (1.1.0)
Requirement already satisfied: setuptools in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from kiwisolver>=1.0.1->matplotlib->wordcloud) (41.4.0)
Installing collected packages: wordcloud
Successfully installed wordcloud-1.6.0
# Linux系統默認字體文件路徑
# !ls /usr/share/fonts/
# 查看系統可用的ttf格式中文字體
!fc-list :lang=zh | grep ".ttf"
# !wget https://mydueros.cdn.bcebos.com/font/simhei.ttf # 下載中文字體
# #創建字體目錄fonts
!mkdir .fonts
# # 複製字體文件到該路徑
!cp simhei.ttf .fonts/
#安裝模型
!hub install porn_detection_lstm==1.1.0
!pip install --upgrade paddlehub
Downloading porn_detection_lstm
[==================================================] 100.00%
Uncompress /home/aistudio/.paddlehub/tmp/tmpai7vxso2/porn_detection_lstm
[==================================================] 100.00%
Successfully installed porn_detection_lstm-1.1.0
Looking in indexes: https://pypi.mirrors.ustc.edu.cn/simple/
[33mWARNING: Retrying (Retry(total=4, connect=None, read=None, redirect=None, status=None)) after connection broken by 'ReadTimeoutError("HTTPSConnectionPool(host='pypi.mirrors.ustc.edu.cn', port=443): Read timed out. (read timeout=15)")': /simple/paddlehub/[0m
Requirement already up-to-date: paddlehub in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (1.6.1)
Requirement already satisfied, skipping upgrade: colorlog in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from paddlehub) (4.1.0)
Requirement already satisfied, skipping upgrade: pre-commit in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from paddlehub) (1.21.0)
Requirement already satisfied, skipping upgrade: gunicorn>=19.10.0; sys_platform != "win32" in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from paddlehub) (20.0.4)
Requirement already satisfied, skipping upgrade: protobuf>=3.6.0 in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from paddlehub) (3.10.0)
Requirement already satisfied, skipping upgrade: pyyaml in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from paddlehub) (5.1.2)
Requirement already satisfied, skipping upgrade: flask>=1.1.0 in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from paddlehub) (1.1.1)
Requirement already satisfied, skipping upgrade: tb-paddle in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from paddlehub) (0.3.6)
Requirement already satisfied, skipping upgrade: cma==2.7.0 in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from paddlehub) (2.7.0)
Requirement already satisfied, skipping upgrade: chardet==3.0.4 in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from paddlehub) (3.0.4)
Requirement already satisfied, skipping upgrade: flake8 in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from paddlehub) (3.7.9)
Requirement already satisfied, skipping upgrade: six>=1.10.0 in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from paddlehub) (1.12.0)
Requirement already satisfied, skipping upgrade: sentencepiece in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from paddlehub) (0.1.85)
Requirement already satisfied, skipping upgrade: Pillow in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from paddlehub) (6.2.0)
Requirement already satisfied, skipping upgrade: yapf==0.26.0 in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from paddlehub) (0.26.0)
Requirement already satisfied, skipping upgrade: tensorboard>=1.15 in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from paddlehub) (2.1.0)
Requirement already satisfied, skipping upgrade: opencv-python in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from paddlehub) (4.1.1.26)
Requirement already satisfied, skipping upgrade: numpy; python_version >= "3" in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from paddlehub) (1.16.4)
Requirement already satisfied, skipping upgrade: requests in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from paddlehub) (2.22.0)
Requirement already satisfied, skipping upgrade: pandas; python_version >= "3" in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from paddlehub) (0.23.4)
Requirement already satisfied, skipping upgrade: nltk in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from paddlehub) (3.4.5)
Requirement already satisfied, skipping upgrade: cfgv>=2.0.0 in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from pre-commit->paddlehub) (2.0.1)
Requirement already satisfied, skipping upgrade: nodeenv>=0.11.1 in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from pre-commit->paddlehub) (1.3.4)
Requirement already satisfied, skipping upgrade: virtualenv>=15.2 in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from pre-commit->paddlehub) (16.7.9)
Requirement already satisfied, skipping upgrade: identify>=1.0.0 in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from pre-commit->paddlehub) (1.4.10)
Requirement already satisfied, skipping upgrade: toml in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from pre-commit->paddlehub) (0.10.0)
Requirement already satisfied, skipping upgrade: aspy.yaml in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from pre-commit->paddlehub) (1.3.0)
Requirement already satisfied, skipping upgrade: importlib-metadata; python_version < "3.8" in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from pre-commit->paddlehub) (0.23)
Requirement already satisfied, skipping upgrade: setuptools>=3.0 in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from gunicorn>=19.10.0; sys_platform != "win32"->paddlehub) (41.4.0)
Requirement already satisfied, skipping upgrade: click>=5.1 in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from flask>=1.1.0->paddlehub) (7.0)
Requirement already satisfied, skipping upgrade: Jinja2>=2.10.1 in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from flask>=1.1.0->paddlehub) (2.10.1)
Requirement already satisfied, skipping upgrade: Werkzeug>=0.15 in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from flask>=1.1.0->paddlehub) (0.16.0)
Requirement already satisfied, skipping upgrade: itsdangerous>=0.24 in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from flask>=1.1.0->paddlehub) (1.1.0)
Requirement already satisfied, skipping upgrade: moviepy in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from tb-paddle->paddlehub) (1.0.1)
Requirement already satisfied, skipping upgrade: mccabe<0.7.0,>=0.6.0 in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from flake8->paddlehub) (0.6.1)
Requirement already satisfied, skipping upgrade: entrypoints<0.4.0,>=0.3.0 in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from flake8->paddlehub) (0.3)
Requirement already satisfied, skipping upgrade: pyflakes<2.2.0,>=2.1.0 in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from flake8->paddlehub) (2.1.1)
Requirement already satisfied, skipping upgrade: pycodestyle<2.6.0,>=2.5.0 in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from flake8->paddlehub) (2.5.0)
Requirement already satisfied, skipping upgrade: absl-py>=0.4 in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from tensorboard>=1.15->paddlehub) (0.8.1)
Requirement already satisfied, skipping upgrade: google-auth<2,>=1.6.3 in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from tensorboard>=1.15->paddlehub) (1.10.0)
Requirement already satisfied, skipping upgrade: wheel>=0.26; python_version >= "3" in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from tensorboard>=1.15->paddlehub) (0.33.6)
Requirement already satisfied, skipping upgrade: google-auth-oauthlib<0.5,>=0.4.1 in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from tensorboard>=1.15->paddlehub) (0.4.1)
Requirement already satisfied, skipping upgrade: markdown>=2.6.8 in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from tensorboard>=1.15->paddlehub) (3.1.1)
Requirement already satisfied, skipping upgrade: grpcio>=1.24.3 in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from tensorboard>=1.15->paddlehub) (1.26.0)
Requirement already satisfied, skipping upgrade: idna<2.9,>=2.5 in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from requests->paddlehub) (2.8)
Requirement already satisfied, skipping upgrade: urllib3!=1.25.0,!=1.25.1,<1.26,>=1.21.1 in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from requests->paddlehub) (1.25.6)
Requirement already satisfied, skipping upgrade: certifi>=2017.4.17 in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from requests->paddlehub) (2019.9.11)
Requirement already satisfied, skipping upgrade: python-dateutil>=2.5.0 in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from pandas; python_version >= "3"->paddlehub) (2.8.0)
Requirement already satisfied, skipping upgrade: pytz>=2011k in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from pandas; python_version >= "3"->paddlehub) (2019.3)
Requirement already satisfied, skipping upgrade: zipp>=0.5 in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from importlib-metadata; python_version < "3.8"->pre-commit->paddlehub) (0.6.0)
Requirement already satisfied, skipping upgrade: MarkupSafe>=0.23 in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from Jinja2>=2.10.1->flask>=1.1.0->paddlehub) (1.1.1)
Requirement already satisfied, skipping upgrade: tqdm<5.0,>=4.11.2 in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from moviepy->tb-paddle->paddlehub) (4.36.1)
Requirement already satisfied, skipping upgrade: imageio<3.0,>=2.5; python_version >= "3.4" in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from moviepy->tb-paddle->paddlehub) (2.6.1)
Requirement already satisfied, skipping upgrade: imageio-ffmpeg>=0.2.0; python_version >= "3.4" in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from moviepy->tb-paddle->paddlehub) (0.3.0)
Requirement already satisfied, skipping upgrade: proglog<=1.0.0 in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from moviepy->tb-paddle->paddlehub) (0.1.9)
Requirement already satisfied, skipping upgrade: decorator<5.0,>=4.0.2 in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from moviepy->tb-paddle->paddlehub) (4.4.0)
Requirement already satisfied, skipping upgrade: cachetools<5.0,>=2.0.0 in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from google-auth<2,>=1.6.3->tensorboard>=1.15->paddlehub) (4.0.0)
Requirement already satisfied, skipping upgrade: pyasn1-modules>=0.2.1 in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from google-auth<2,>=1.6.3->tensorboard>=1.15->paddlehub) (0.2.7)
Requirement already satisfied, skipping upgrade: rsa<4.1,>=3.1.4 in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from google-auth<2,>=1.6.3->tensorboard>=1.15->paddlehub) (4.0)
Requirement already satisfied, skipping upgrade: requests-oauthlib>=0.7.0 in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from google-auth-oauthlib<0.5,>=0.4.1->tensorboard>=1.15->paddlehub) (1.3.0)
Requirement already satisfied, skipping upgrade: more-itertools in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from zipp>=0.5->importlib-metadata; python_version < "3.8"->pre-commit->paddlehub) (7.2.0)
Requirement already satisfied, skipping upgrade: pyasn1<0.5.0,>=0.4.6 in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from pyasn1-modules>=0.2.1->google-auth<2,>=1.6.3->tensorboard>=1.15->paddlehub) (0.4.8)
Requirement already satisfied, skipping upgrade: oauthlib>=3.0.0 in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from requests-oauthlib>=0.7.0->google-auth-oauthlib<0.5,>=0.4.1->tensorboard>=1.15->paddlehub) (3.1.0)
from __future__ import print_function
import requests
import json
import re #正則匹配
import time #時間處理模塊
import jieba #中文分詞
import numpy as np
import matplotlib
import matplotlib.pyplot as plt
import matplotlib.font_manager as font_manager
from PIL import Image
from wordcloud import WordCloud #繪製詞雲模塊
import paddlehub as hub
# 獲取接口
def getMoveinfo(url):
session = requests.Session()
headers = {
"User-Agent": "Mozilla/5.0 (iPhone; CPU iPhone OS 11_0 like Mac OS X) AppleWebKit/604.1.38 (KHTML, like Gecko) Version/11.0 Mobile/15A372 Safari/604.1",
"Accept": "application/json",
"Referer": "http://m.iqiyi.com/v_19rqriflzg.html",
"Origin": "http://m.iqiyi.com",
"Host": "sns-comment.iqiyi.com",
"Connection": "keep-alive",
"Accept-Language": "en-US,en;q=0.9,zh-CN;q=0.8,zh;q=0.7,zh-TW;q=0.6",
"Accept-Encoding": "gzip, deflate"
}
response = session.get(url, headers=headers)
if response.status_code == 200:
return response.text
return None
def saveMovieInfoToFile(lastId, arr):
url='https://sns-comment.iqiyi.com/v3/comment/get_comments.action?agent_type=118&agent_version=9.11.5&authcookie=null&business_type=17&content_id=15068699100&page=&page_size=10&types=time&last_id='
url+=str(lastId)
responseTxt = getMoveinfo(url)
responseJson=json.loads(responseTxt)
comments=responseJson['data']['comments']
for val in comments:
# print(val.keys())
if 'content' in val.keys():
print(val['content'])
arr.append(val['content'])
lastId = str(val['id'])
return lastId
#去除文本中特殊字符
def clear_special_char(content):
'''
正則處理特殊字符
參數 content:原文本
return: 清除後的文本
'''
comp = re.compile('[^A-Z^a-z^0-9^\u4e00-\u9fa5]')
return comp.sub('', content)
# text_zh = '$你好！我是個程序猿，標註碼農￥'
# print(clear_special_char(text_zh))
def fenci(text):
'''
利用jieba進行分詞
參數 text:需要分詞的句子或文本
return：分詞結果
'''
# 添加自定義字典 add_words.txt
# jieba.load_userdict('')
seg=jieba.lcut(text)
return seg
def stopwordslist(file_path):
'''
創建停用詞表
參數 file_path:停用詞文本路徑
return：停用詞list
'''
# f= open(file_path, 'r')
# my_data = [i.strip('\n') for i in f]
stopwords= [line.strip() for line in open(file_path,encoding='UTF-8').readline()]
return stopwords
# file_path=r'/home/aistudio/stopwords/中文停用詞表.txt'
# list=stopwordslist(file_path)
# print(list)
def movestopwords(sentence, stopwords, counts):
'''
去除停用詞,統計詞頻
參數 file_path:停用詞文本路徑 stopwords:停用詞list counts: 詞頻統計結果
return：None
'''
# out=[]
for word in sentence:
if word not in stopwords:
if len(word) !=1:
counts[word]=counts.get(word,0)+1
return None
def drawcounts(counts, num):
'''
繪製詞頻統計表
參數 counts: 詞頻統計結果 num:繪製topN
return：none
'''
x_aixs=[]
y_aixs=[]
c_order=sorted(counts.items(), key=lambda x:x[1],reverse=True)
for c in c_order[:num]:
x_aixs.append(c[0])
y_aixs.append(c[1])
matplotlib.rcParams['font.sans-serif']=['SimHei']
matplotlib.rcParams['axes.unicode_minus']=False
plt.bar(x_aixs, y_aixs)
plt.title('詞頻統計結果')
plt.show()
def drawcloud(word_f):
'''
根據詞頻繪製詞雲圖
參數 word_f:統計出的詞頻結果
return：none
'''
cloud_mask=np.array(Image.open('cloud.jpg'))
st=set(['東西', '這是'])
wc=WordCloud(background_color='white',
mask=cloud_mask,
max_words=150,
font_path='simhei.ttf',
min_font_size=10,
max_font_size=100,
width=400,
relative_scaling=0.3,
stopwords=st)
wc.fit_words(word_f)
wc.to_file('pic.png')
def text_detection(text, file_path):
'''
使用hub對評論進行內容分析
return：分析結果
'''
porn_detection_lstm=hub.Module(name='porn_detection_lstm')
f=open('aqy.txt', 'r', encoding='utf-8')
for line in f:
if len(line.strip())==1:
continue
else:
test_text.append(line)
f.close()
input_dict={'text':test_text}
results=porn_detection_lstm.detection(data=input_dict,use_gpu=True,batch_size=1)
for index, item in enumerate(results):
if item['porn_detection_key'] =='porn':
print(item['text'],':', item['porn_probs'])
#評論是多分頁的，得多次請求愛奇藝的評論接口才能獲取多頁評論,有些評論含有表情、特殊字符之類的
#num 是頁數，一頁10條評論，假如爬取1000條評論，設置num=100
## 轉換數據
if __name__ == '__main__':
num=20
lastId='0'
arr=[]
with open('aqy.txt', 'a', encoding='utf-8') as f:
for i in range(num):
lastId=saveMovieInfoToFile(lastId, arr)
time.sleep(0.5)
for item in arr:
item=clear_special_char(item)
if item.strip()!='':
try:
f.write(item+'\n')
except e:
print('含有特殊字符')
print("共獲取評論：", len(arr))
f=open('aqy.txt', 'r', encoding='utf-8')
counts={}
for line in f:
words=fenci(line)
stopwords=stopwordslist(r'./stopwords/中文停用詞表.txt')
movestopwords(words, stopwords, counts)
drawcounts(counts, 10)
drawcloud(counts)
f.close()
file_path='aqy.txt'
test_text=[]
text_detection(test_text, file_path)
啊啊啊啊啊啊啊啊啊啊啊乃萬沖沖衝
金子
讓我康下我昕姐的粉在哪裏吖 劉總真的太🉑️了 好愛好愛[色]
陳珏的音色真的又特別又深得我心！
謝可寅，安琦，虞書欣，金子涵金子涵金子涵！！！！！🍃🍃🍃
劉雨欣劉雨欣劉雨欣劉雨欣劉雨欣劉雨欣劉雨欣劉雨欣劉雨欣劉雨欣劉雨欣劉雨欣劉雨欣劉雨欣劉雨欣劉雨欣劉雨欣劉雨欣劉雨欣
啊啊啊啊媽媽愛你嗷嗷嗷嗷嗷～麼麼噠[親親][親親][親親][親親]加油喔！！！！！
劉雨昕劉雨昕劉雨昕劉雨昕劉雨昕劉雨昕劉雨昕劉雨昕劉雨昕劉雨昕劉雨昕劉雨昕劉雨昕劉雨昕劉雨昕
虞書欣沖沖衝[微笑]
衝啊許佳琪！
王承渲，加油!
搞不懂虞書欣有什麼資格得第一。。。
喜歡寅
許佳琪衝啊！
劉雨昕我好愛他
劉雨昕最棒
劉雨昕
乃萬沖沖衝！！
乃萬！
3A女王才第四？！[流汗]什麼鬼
安琦真的值得最好的，舞臺爆發力超級強，配得上第一[害羞]
安崎真的怎麼可能不進前三，我哭，她配得上最好的，第一第一[色]出道第一，必須出道
我也叫孫芮
怎麼會沒有葛鑫怡[流淚][流淚][流淚]
許佳琪 孔雪兒高位出道吧
其實虞書欣真的很棒，每次都是第一名
投虞書欣，孔雪兒，趙小棠，她們值得
虞書欣一直在背後努力證明自己，證明她可以坐在c位
劉雨昕沖沖衝！
真的喜歡這些香香的女孩子呀[色]
趙小棠！！！我pick她！！！太棒啦嗚嗚嗚嗚嗚嗚嗚嗚嗚嗚嗚嗚嗚嗚嗚
劉雨昕加油
最近準備寫一篇關於噴子的論文，從其家庭背景，生活習慣，社交，與年紀，各個方面來進行簡述，大家支持我一下好嗎
謝可寅最棒了
衝鴨！加油[親親]
這個第一怎麼選的，太失望了，又作又沒實力[冷汗][冷汗][冷汗]我也是醉了！
爲什麼後期沒見到申家四姐妹？
kiki加油相信你自己,你要相信自己是最棒的!
欣欣好可愛，我愛死你了！
我投票給了虞書欣 趙小棠 王承渲 蔡卓宜 朱林雨 戴萌 胡馨尹 孔雪兒 秦牛正威牛姐
謝可寅給媽媽衝呀！！！
欣欣子加油你是最棒的小石榴們一直在你身後支持你所有人都以爲你很容易但你說對了自己吃過的苦只有自己知道
Pick虞書欣書欣書欣書欣書欣書欣書欣書欣書欣書欣書欣書欣書欣書欣書欣書欣
欣欣我們都會支持你哦，加油加油♡ 愛你麼麼噠
虞書欣加油！
書欣書欣書欣書欣書欣書欣愛你愛你愛你
欣欣子加油＾０＾~
虞書欣虞書欣虞書欣虞書欣虞書欣
書欣寶貝😊
虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣虞書欣。l like you♡
請大家投給書欣一票吧🙏🙏🙏🙏
虞書欣胖了[呲牙]支持
喻言衝呀
這個牛奶真難喝，還沒有真果粒好喝
難喝
難喝
難喝
劉雨欣
勾√小姐姐的vocal真不錯
金子涵沖沖衝
劉雨昕
劉雨昕
有6票未投，幫我投宋昭藝好嗎
劉雨昕超級棒的全能劉雨昕 加油 越努力越幸運
劉雨昕！！
劉雨欣很棒
欣欣加油♥
很喜歡劉雨昕 真的有顏值又有實力，期待小姐姐，和我們一起走花路叭
虞書欣
劉雨昕，你每次舞臺都給人不同的驚喜，太喜歡你了，十年的堅持，希望你的夢想成真！
我還有9票，誰需要
[微笑][微笑][微笑]
文哲這麼棒啊
姐妹們，康康NINEONE吧！
91差一點點就進前九了，
請大家手裏如果有多餘票的，
投給乃萬一票吧，蟹蟹🙏
[色]
想看Lisa
虞書欣加油！[親親]
16票 有需要投的嘛
虞書欣
虞書欣
虞書欣衝
秦牛正威
孔雪兒！孔雪兒！
我發現有些人就是bb虞美人不配，就你能，就你最配！你行你上啊！不說好不好人家起碼會唱會跳，當時楊超越都不那麼會也照樣有人愛看，觀衆緣懂不懂，製作人懂不懂，不就是讓觀衆自己選自己喜歡的，要什麼都完美的人家就直接找幾個評委來評個等級了，作爲藝人你再好沒人看有什麼意思？！！
喻言喻言沖沖衝
葛鑫怡衝啊
Pick虞書欣書欣書欣書欣書欣書欣書欣書欣書欣書欣書欣書欣書欣書欣書欣書欣
虞書欣加油加油加油
虞書欣衝鴨！
虞書欣
虞書欣
乃萬啊啊啊啊衝呀
蔡徐坤:許佳琪可以喲
這輩子只愛許佳琪
許佳琪，神仙妹妹，你知道
許佳琪，我愛你
不是我說假，許佳琪要是上不了熱一前三，我倒立洗頭
許佳琪真的太棒了
有沒有姐妹可以幫王承渲投票，真心地謝謝每一個可以幫她投票的人，真的謝謝你們！
虞書欣 趙小棠 安崎 謝可寅 金子涵 葛鑫怡沖沖衝！！！
許佳琪小姐姐跳舞超級好的啊我好愛啊啊啊
大魚海棠頂配絕配第一配。
大虞海棠大虞海棠大虞海棠[害羞]
來晚了
劉雨昕！
我只投得一個票，還有八個票可投。有沒有需要幫人投的
虞書欣沖沖
虞書欣，我覺得你是最棒的，我很喜歡你，希望你繼續加油不管是拍戲還是表演都可以開開心心的我會一直支持你
安崎姐姐的“當然”真的令人着迷好嗎
評論裏都嘮美女，就讓我來挺張總
張總的妝發是怎麼了？？？害張總唱歌真的很好聽，嗓音絕了，連唱戲腔都超有內味，大家多看看這個有實力的張張總吧！
虞書欣給我說哭了，剛開始挺不喜歡她的，後面反而覺得挺可愛的，開心的人有時候並沒有看起來那麼快樂
今年最喜歡的只有劉雨昕了！！！雨昕加油！！！渲渲也很棒，有實力！！！！
今年最喜歡的只有劉雨昕了！！！雨昕加油！！！
喻言，劉雨欣，曾可妮，謝可寅，劉令姿，許佳琪。這幾個比較適合[色][色]
安崎 最棒，
kiki do you love me 我終於找到KIKI了
唯一人選，金子涵！
卓宜衝鴨
求求大家看看hhby的徐紫茵吧[快哭了]
許佳琪我意難平啊才第七
小宅衝啊！！！
我特別喜歡虞書欣 也就是爲了她來看這個節目的，對 你們是覺得她實力不夠，但有我們寵着！你們不喜歡她可以不看！但請不要黑她，她也是人也會傷心的。有時候自己還傷心着呢卻還想着安慰別人，我真的太愛欣欣了！
請投給陳珏謝謝謝謝謝謝謝謝
雪兒雪兒雪兒最棒
許佳琪！
加油
我的趙小棠呢
我真的愛了！許佳琪非常的溫柔，包容，親切。她待人真誠，沒有架子，從來都是以真心換真心。變得越來越好了。
覺得許馨文已經是一個成熟歌手的水平 ，好多風格的曲目都能hold住 加油衝鴨 從現在開始發光 ！期待着你！
哈哈哈
在這一期節目當中，真的是看青春有你這一節目都會笑的，感覺已經養成了習慣了。
我的曾可妮和喻言太粉了，感覺就像班裏的女班長和男班長，一路走來，進步太大了。
大虞海棠真的是看別人都這麼開心的，那看自己不更加開心了嘛，而且還說有意思的話呢，她們兩個簡直是我的開心果呢。
謝可寅！！
安崎，喻言，孔雪兒，金子涵必須出道啊啊啊啊啊啊啊啊啊啊啊啊
我這麼多年一直堅持喜歡許佳琪，她是我們的星星，我們在她的眼裏也都閃閃發光。陪她一起成長。
謝可寅，安琪，孔雪兒，王承渲，還挺喜歡她們的
孔雪兒有點像張嘉倪，又有像唐嫣
虞書欣真的是太頑皮了，竟然能說出誰比她醜就坐在旁邊，毫不疑問肯定是坐在趙小棠旁邊了，真的給我們快樂啊。
青春有你2乃萬💚🍼 實力rapper乃萬💚🍼 原創歌手乃萬💚 🍼 可鹽可甜乃萬💚🍼 可奶可酷乃萬💚🍼 美貌殺人乃萬💚🍼 絕美嗓音乃萬💚 🍼心動狙擊乃萬💚 🍼 魅力爆表乃萬💚 🍼 舞臺王者乃萬💚
你看到這一期之後，就知道虞書欣的造型是多麼的好笑呢，這會讓人家的心情會變得好起來喲。
那個說只有你一個人不喜歡陳珏的，告訴你只有你一個人。
劉雨昕小姐姐
你是最棒的呦!!!
哈哈
演員
如果排名全部都只算製作人的助力值，那分班的作用氣勢不大
上官呢
大虞海棠真的是給我們帶來了很多的快樂呢。比如人家哭的時候，她就說別哭了喲，而且還擺了造型，討人家可愛呢。
戴燕妮，金子涵，戴燕妮，金子涵，戴燕妮。金子涵
戴燕妮戴燕妮，金子涵金子涵，戴燕妮戴燕妮，金子涵金子涵，戴燕妮金子涵戴燕妮金子涵，戴燕妮金子涵，戴燕妮金子涵
戴燕妮姐姐戴燕妮姐姐我愛你我愛你
戴燕妮姐姐
喻言衝鴨!
別在這裏說青你學員差好嗎，去看看創造營的那幫孩子吧，要多沒實力多沒實力👀
[呲牙][呲牙][呲牙][呲牙]
那個爆炸頭好醜。[得意][得意][得意][得意][得意]
你的包紮頭好醜哦
永遠支持大魚海棠
虞書欣
真的，喻言真的好像一個男班，穩住方向、活躍氛圍。經常說點逗比話讓大家情緒積極一點，看着她們真好！
看起來很高冷的可妮，私底下其實是關心隊友，願意把外套分給別人穿的女孩，一路走來，看着她們成長。
虞書欣的眨眨眼果然是很撩人啊，竟然把趙小棠都撩了，然後就幫她擰蓋了，她們兩個說話還有意思啊。
虞書欣說話還真的太有魔性了，竟然寧瓶蓋都這麼可愛，真的是把我給笑哭了呢。
乃萬加油
來看一下這一期吧，真的是給人家的快樂的，如果你不開心的話，那就快帶你來看喲。
趙小棠還蠻有意思的啊，看到虞書欣就說了一個張三丰，蠻搞笑的，都不知道張三丰這個稱號是怎麼得來的呢？
欣欣你最棒
要笑死誰虞書欣
許馨文真的是我看着變好的！唱歌實力真的強，她看上去憨憨的，希望她越走越好吧！
虞書欣❤️
劉雨昕
嗯？
劉雨昕劉雨昕劉雨昕[抓狂][抓狂][抓狂]
今天的怎麼沒看見
她們的努力與懈怠、前進與落後、優點與缺陷，都理應被共同正視。加油吧！
劉雨昕給我衝！！！！！！！
9.23分了
蔡PD我來了
蔡徐坤
我想看虞書欣，關鍵時刻咋還沒更新呢[流淚]......慢慢等待
虞書欣你很好，你真實，做好你自己加油
今天爲什麼沒有更新
今天怎麼回事，不是8點正播放嗎？現在都8點18了怎麼回事？
我的寶藏女孩啊！！許馨文終於要被發現了嘛！看着她從八十幾到五十幾到現在的29，我真的太驕傲了。
劉雨昕劉雨昕劉雨昕劉雨昕
13期怎麼還沒放 ，遲到了？
喜歡她的樂觀勇敢 可愛 不喜歡的人會覺得作 別的節目也有不喜歡她的時候 至少這裏可以
虞書欣這期第一嗎
你們要加油，還是那句話，這你弟的那個人都會有糖吃。[微笑]
劉雨昕，加油
.
這個排名是來搞笑的吧！
你一票我一票，書欣明天就出道
都喜歡，反而不知道該投誰了～有人要給點建議嗎？～[微笑]
坤坤好暖
謝可寅加油喔！希望你下次可以進前三！
好喜歡謝可迎
大家喜歡SNH48嗎？（我個人很喜歡！）
歡迎評論！！！
虞書欣加油不要在意別人的評論
虞書欣！！！欣欣子衝啊！！！
蔡徐坤好帥
虞書欣加油
Building prefix dict from the default dictionary ...
2020-04-27 22:52:09,383-DEBUG: Building prefix dict from the default dictionary ...
共獲取評論： 199
Dumping model to file cache /tmp/jieba.cache
2020-04-27 22:52:10,142-DEBUG: Dumping model to file cache /tmp/jieba.cache
Loading model cost 0.830 seconds.
2020-04-27 22:52:10,214-DEBUG: Loading model cost 0.830 seconds.
Prefix dict has been built successfully.
2020-04-27 22:52:10,216-DEBUG: Prefix dict has been built successfully.
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/matplotlib/font_manager.py:1331: UserWarning: findfont: Font family ['sans-serif'] not found. Falling back to DejaVu Sans
(prop.get_family(), self.defaultFamily[fontext]))
[外鏈圖片轉存失敗,源站可能有防盜鏈機制,建議將圖片保存下來直接上傳(img-FmdijHQJ-1587999458794)(output_16_4.png)]
[32m[2020-04-27 22:52:10,744] [ INFO] - Installing porn_detection_lstm module[0m
[32m[2020-04-27 22:52:10,809] [ INFO] - Module porn_detection_lstm already installed in /home/aistudio/.paddlehub/modules/porn_detection_lstm[0m
讓我康下我昕姐的粉在哪裏吖劉總真的太了好愛好愛色
: 0.7552
劉雨欣劉雨欣劉雨欣劉雨欣劉雨欣劉雨欣劉雨欣劉雨欣劉雨欣劉雨欣劉雨欣劉雨欣劉雨欣劉雨欣劉雨欣劉雨欣劉雨欣劉雨欣劉雨欣啊啊啊啊媽媽愛你嗷嗷嗷嗷嗷麼麼噠親親親親親親親親加油喔
: 0.8556
喻言劉雨欣曾可妮謝可寅劉令姿許佳琪這幾個比較適合色色
: 0.9986
display(Image.open('pic.png')) #顯示生成的詞雲圖像
