声明：本文首发于soarli博客（https://blog.soarli.top/archives/383.html

）转载请注明来源。

目录：

EasyDL概述

EasyDL体验

创建、上传数据集：

图片演示：

结果反馈：

EasyDL应用案例

大作业：数据爬取、分析与内容审核

爬取数据的要点：

即：所有评论不会直接显示到默认页面元素中，每次点击更多评论按钮时就会新加载一个get_comments文件请求，我们要从此处着手分析。

请求该资源，可得下图所示资源：


老师介绍了last_id的作用是记录当前评论加载的位置，即作为下一个请求中的一个参数，是得下一个请求从当前位置继续加载。

因此，我们可尝试不断获取last_id，从而生成新的URL，再去获取新的评论。

反复如此，便可模拟用户点击“查看更多评论”的操作。

大作业参考结果

实操：

第一步：爱奇艺《青春有你2》评论数据爬取(参考链接：https://www.iqiyi.com/v_19ryfkiv8w.html#curid=15068699100_9f9bab7e0d1e30c494622af777f4ba39)

• 爬取任意一期正片视频下评论
• 评论条数不少于1000条

第二步：词频统计并可视化展示

• 数据预处理：清理清洗评论中特殊字符（如：@#￥%、emoji表情符）,清洗后结果存储为txt文档
• 中文分词：添加新增词（如：青你、奥利给、冲鸭），去除停用词（如：哦、因此、不然、也好、但是）
• 统计top10高频词
• 可视化展示高频词

第三步：绘制词云

• 根据词频生成词云
• 可选项-添加背景图片，根据背景图片轮廓生成词云

第四步：结合PaddleHub，对评论进行内容审核

需要的配置和准备

• 中文分词需要jieba
• 词云绘制需要wordcloud
• 可视化展示中需要的中文字体
• 网上公开资源中找一个中文停用词表
• 根据分词结果自己制作新增词表
• 准备一张词云背景图（附加项，不做要求，可用hub抠图实现）
• 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/
Requirement already satisfied: wordcloud in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (1.6.0)
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: 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: pytz in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from matplotlib->wordcloud) (2019.3)
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: 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: 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: cycler>=0.10 in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from matplotlib->wordcloud) (0.10.0)
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)

# Linux系统默认字体文件路径
# !ls /usr/share/fonts/
# 查看系统可用的ttf格式中文字体
!fc-list :lang=zh | grep ".ttf"
/home/aistudio/.fonts/simhei.ttf: SimHei,黑体:style=Regular,Normal,obyčejné,Standard,Κανονικά,Normaali,Normál,Normale,Standaard,Normalny,Обычный,Normálne,Navadno,Arrunta

# !wget https://mydueros.cdn.bcebos.com/font/simhei.ttf # 下载中文字体
# #创建字体目录fonts
!mkdir .fonts
# # 复制字体文件到该路径
!cp simhei.ttf .fonts/
mkdir: cannot create directory ‘.fonts’: File exists

#安装模型
!hub install porn_detection_lstm==1.1.0
!pip install --upgrade paddlehub
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/sklearn/externals/joblib/externals/cloudpickle/cloudpickle.py:47: DeprecationWarning: the imp module is deprecated in favour of importlib; see the module's documentation for alternative uses
  import imp
Module porn_detection_lstm-1.1.0 already installed in /home/aistudio/.paddlehub/modules/porn_detection_lstm
Looking in indexes: https://pypi.mirrors.ustc.edu.cn/simple/
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: 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: flake8 in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from paddlehub) (3.7.9)
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: 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: colorlog in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from paddlehub) (4.1.0)
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: Pillow in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from paddlehub) (6.2.0)
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: 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: 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: 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: requests in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from paddlehub) (2.22.0)
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: 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: nltk in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from paddlehub) (3.4.5)
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: 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: pre-commit in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from paddlehub) (1.21.0)
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: 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: 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: 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: 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: 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: 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: 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: 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: 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: Jinja2>=2.10.1 in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from flask>=1.1.0->paddlehub) (2.10.3)
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: 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: 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: 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: 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: 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: 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: 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: 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: 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: 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: 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: 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: 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: 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: 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: 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: 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: 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: 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: 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: 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: 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: 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)
Requirement already satisfied, skipping upgrade: pyasn1>=0.1.3 in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from rsa<4.1,>=3.1.4->google-auth<2,>=1.6.3->tensorboard>=1.15->paddlehub) (0.4.8)
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)

from __future__ import print_function
import requests
import json
import re #正则匹配
import time #时间处理模块
import jieba #中文分词
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  #绘制词云模块
import paddlehub as hub

#请求爱奇艺评论接口，返回response信息
def getMoveinfo(url):
    '''
    请求爱奇艺评论接口，返回response信息
    参数  url: 评论的url
    :return: response信息
    '''
    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

#解析json数据，获取评论
    '''
    解析json数据，获取评论
    参数  lastId:最后一条评论ID  arr:存放文本的list
    :return: 新的lastId
    '''
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):
    '''
    正则处理特殊字符
    参数 content:原文本
    return: 清除后的文本
    '''
    comp = re.compile('[^A-Z^a-z^0-9^\u4e00-\u9fa5]')
    return comp.sub('', content)

# text_zh = '$你好！我是个程%序^猿，标注!!#码农￥'
# print(clear_special_char(text_zh))

def fenci(text):
    '''
    利用jieba进行分词
    参数 text:需要分词的句子或文本
    return：分词结果
    '''
    # 添加自定义字典 add_words.txt
    # jieba.load_userdict('') 
    seg=jieba.lcut(text)
    return seg

def stopwordslist(file_path):
    '''
    创建停用词表
    参数 file_path:停用词文本路径
    return：停用词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/中文停用词表.txt'
# list=stopwordslist(file_path)
# print(list)

def movestopwords(sentence, stopwords, counts):
    '''
    去除停用词,统计词频
    参数 file_path:停用词文本路径 stopwords:停用词list counts: 词频统计结果
    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):
    '''
    绘制词频统计表
    参数 counts: 词频统计结果 num:绘制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('词频统计结果')
    plt.show()

def drawcloud(word_f):
    '''
    根据词频绘制词云图
    参数 word_f:统计出的词频结果
    return：none
    '''    
    cloud_mask=np.array(Image.open('cloud.jpg'))
    st=set(['东西', '这是'])
    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对评论进行内容分析
    return：分析结果

    '''
    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'])

#评论是多分页的，得多次请求爱奇艺的评论接口才能获取多页评论,有些评论含有表情、特殊字符之类的
#num 是页数，一页10条评论，假如爬取1000条评论，设置num=100
## 转换数据
if __name__ == '__main__':
    num=110
    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("共获取评论：", len(arr))
    f=open('aqy.txt', 'r', encoding='utf-8')
    counts={}
    for line in f:
        words=fenci(line)
        stopwords=stopwordslist(r'./stopwords/中文停用词表.txt')
        movestopwords(words, stopwords, counts)
    drawcounts(counts, 10)
    drawcloud(counts)
    f.close()

    file_path='aqy.txt'
    test_text=[]
    text_detection(test_text, file_path)
孔雪儿有点像张嘉倪，又有像唐嫣
虞书欣真的是太顽皮了，竟然能说出谁比她丑就坐在旁边，毫不疑问肯定是坐在赵小棠旁边了，真的给我们快乐啊。
青春有你2乃万