基于flask 搭建新词发现提取网站

这个项目是结合了 凝聚度、信息熵 、n_gram 、 aotuphrasex算法和flask后端算法的集成。​

首先看一下这个文件的分布：

注意 html 页面一定要在 ：templates文件夹下

2w 1234.txt都是进行关键词提取的测试文件

 首先是主函数：

import os
from string import Template
from flask import Flask, request, send_file
from werkzeug.utils import secure_filename
from flask import Flask, render_template, redirect, url_for,make_response
import urllib.request
app = Flask(__name__)
pwd = os.path.dirname(__file__)
print(pwd)
import urllib
import requests
import os
import time
import threading
import lxml
import datetime
import requests
import json
import pandas as pd
import math
from autophrasex import *
import numpy as np
import re
from numpy import log, min
from collections import defaultdict
from tqdm import tqdm
from collections import Counter

# 基于autophrase方法
autophrase = AutoPhrase(
    reader=DefaultCorpusReader(tokenizer=JiebaTokenizer()),
    selector=DefaultPhraseSelector(),
    extractors=[NgramsExtractor(N=4),IDFExtractor(),EntropyExtractor()])

# 基于信息熵的挖掘方法
def xin_xi_shang(file):
    f = open(file, 'r')  # 读取文章
    s = f.read()  # 读取为一个字符串
    # 定义要去掉的标点字
    drop_dict = [u'，', u'\n', u'。', u'、', u'：', u'(', u')', u'[', u']', u'.', u',', u' ', u'\u3000', u'”', u'“', u'？', u'?',
                 u'！', u'‘', u'’', u'…']
    for i in drop_dict:  # 去掉标点字
        s = s.replace(i, '')
    # 为了方便调用，自定义了一个正则表达式的词典
    myre = {2: '(..)', 3: '(...)', 4: '(....)', 5: '(.....)', 6: '(......)', 7: '(.......)'}
    min_count = 10  # 录取词语最小出现次数
    min_support = 30  # 录取词语最低支持度，1代表着随机组合
    min_s = 3  # 录取词语最低信息熵，越大说明越有可能独立成词
    max_sep = 4 # 候选词语的最大字数
    t = []  # 保存结果用。
    t.append(pd.Series(list(s)).value_counts())  # 逐字统计
    tsum = t[0].sum()  # 统计总字数
    rt = []  # 保存结果用
    for m in range(2, max_sep + 1):
        print(u'正在生成%s字词...' % m)
        t.append([])
        for i in range(m):  # 生成所有可能的m字词
            t[m - 1] = t[m - 1] + re.findall(myre[m], s[i:])
        t[m - 1] = pd.Series(t[m - 1]).value_counts()  # 逐词统计
        t[m - 1] = t[m - 1][t[m - 1] > min_count]  # 最小次数筛选
        tt = t[m - 1][:]
        for k in range(m - 1):
            qq = np.array(list(map(lambda ms: tsum * t[m - 1][ms] / t[m - 2 - k][ms[:m - 1 - k]] / t[k][ms[m - 1 - k:]],
                                   tt.index))) > min_support  # 最小支持度筛选。
            tt = tt[qq]
        rt.append(tt.index)
    def cal_S(sl):  # 信息熵计算函数
        return -((sl / sl.sum()).apply(log) * sl / sl.sum()).sum()
    for i in range(2, max_sep + 1):
        print(u'正在进行%s字词的最大熵筛选(%s)...' % (i, len(rt[i - 2])))
        pp = []  # 保存所有的左右邻结果
        for j in range(i + 2):
            pp = pp + re.findall('(.)%s(.)' % myre[i], s[j:])
        pp = pd.DataFrame(pp).set_index(1).sort_index()  # 先排序，这个很重要，可以加快检索速度
        index = np.sort(np.intersect1d(rt[i - 2], pp.index))  # 作交集
        # 下面两句分别是左邻和右邻信息熵筛选
        index = index[np.array(list(map(lambda s: cal_S(pd.Series(pp[0][s]).value_counts()), index))) > min_s]
        rt[i - 2] = index[np.array(list(map(lambda s: cal_S(pd.Series(pp[2][s]).value_counts()), index))) > min_s]
    for i in range(len(rt)):
        t[i + 1] = t[i + 1][rt[i]]
        t[i + 1].sort_index(ascending=True)
    words_sum={}
    for i in t[1:]:
        for idx in range(len(i)):
            words_sum[i.index[idx]]=i[idx]
    words_sum=sorted(words_sum.items(),key=lambda x:x[1],reverse=True)
    key_sorce={}
    words=[]
    for word,score in words_sum:
        key_sorce[word]=score
        words.append(word)
    return key_sorce,words



# 基于 滴滴侧接口提取的方法
class OracleClient(object):
    def __init__(self, url, apikey):
        """
        We provide two functions as examples, for other functions
        please implement them by yourself
        :param url:
        :param caller:
        """
        self.url = url
        self.headers = {
            'content-type': 'application/json',
            'apikey': apikey
        }
        self.keyword_url = url + '/api/v2/keyword'

    def keyword(self, text):
        data = {
            'text': text
        }
        resp = requests.post(self.keyword_url, data=json.dumps(data), headers=self.headers)
        return resp.json()
headers = ''
client = OracleClient('', headers)
def key_word(text_list):
    """
    关键字请求接口
    存放句子的list :text_list
    使用全局变量 ：keyword_sum = {}
    """
    for line in text_list :
            try:
                res = client.keyword(line)
                print(res)
                if len(res) > 0 and len(res['data']['keyword']) > 0:  # 防止这个是空出现错误
                    key_sum = len(res['data']['keyword'])  # 统计所有的关键字
                    key_dist = res['data']['keyword']
                    for i in key_dist:
                        if i['word'] not in list(keyword_sum.keys()):
                            keyword_sum[i['word']]=1 # 第一次 的时候是赋值1
                        else:
                            keyword_sum[i['word']] =keyword_sum[i['word']]+1 # 第二次的时候是 赋值 +1
            except:
                pass

def list_of_groups(list_info, per_list_len):
    " 把一个列表分成多个长度相等的列表 "
    list_of_group = zip(*(iter(list_info),) *per_list_len)
    end_list = [list(i) for i in list_of_group] # i is a tuple
    count = len(list_info) % per_list_len
    end_list.append(list_info[-count:]) if count !=0 else end_list
    return end_list


def Multi_threading(file,threading_sum):
    """
        texts_list： 存放句子的列表
       hreading_sum "开线程的个数
    """
    global keyword_sum
    keyword_sum = {}# 设置一个全局变量解决多线程的数据存储问题
    with open(file,"r") as f:
        lines=f.readlines()
    if len(lines)<500:
        threading_sum=1
    end_lists=list_of_groups(lines,int(len(lines)/threading_sum))
    # print(len(end_lists))
    ts = [threading.Thread(target=key_word, args=(i,)) for i in end_lists]
    [t.start() for t in ts]
    [t.join() for t in ts]
    print("keyword_sum",keyword_sum)
    return keyword_sum



# 基于凝固度的方法
class ning_gu_du(object):
    def __init__(self, txt_path, min_count=25, token_length=4, min_proba={2: 5, 3: 25, 4: 125}):
        self.txt_path = txt_path
        self.min_count = min_count
        self.token_length = token_length
        self.min_proba = min_proba
        self.read_text()
        self.statistic_ngrams()
        self.filter_ngrams()
        self.sentences_cut()
        self.judge_exist()
        self.calculate_prob_score()

    def read_text(self):
        print("reading text！")
        with open(self.txt_path, encoding='utf-8') as f:
            texts = f.readlines()
        texts = list(map(lambda x: x.strip(), texts))
        self.texts = list(
            map(lambda x: re.sub('[\s+\.\!\/_,$%^*(+\"\')]+|[+——()?【】“”！，。？、~@#￥%……&*（）0-9a-zA-Z]+', "", x), texts))
        # print(self.texts[0:2])

    def statistic_ngrams(self):  # 粗略统计1，2..ngrams
        print('Starting statistic ngrams!')
        ngrams = defaultdict(int)
        for txt in self.texts:
            for char_id in range(len(txt)):
                for step in range(1, self.token_length + 1):
                    if char_id + step <= len(txt):
                        ngrams[txt[char_id:char_id + step]] += 1
        self.ngrams = {k: v for k, v in ngrams.items() if v >= self.min_count}

    def calculate_prob(self, token):  # 计算2grams及以上的凝固度
        self.total = sum([v for k, v in self.ngrams.items() if len(k) == 1])
        sorce_list = []
        if len(token) >= 2:
            score = min(
                [self.total * self.ngrams[token] / (self.ngrams[token[:i + 1]] * self.ngrams[token[i + 1:]]) for i in
                 range(len(token) - 1)])
            # print(score)
            if score > self.min_proba[len(token)]:
                return True
        else:
            return False

    def calculate_prob_score(self):  # 计算2grams及以上的凝固度 返回一个列表分数
        sorce_list = []
        for token in self.ngrams:
            self.total = sum([v for k, v in self.ngrams.items() if len(k) == 1])
            if len(token) >= 2:
                score = min(
                    [self.total * self.ngrams[token] / (self.ngrams[token[:i + 1]] * self.ngrams[token[i + 1:]]) for i
                     in range(len(token) - 1)])
                # print(score)
                if score > self.min_proba[len(token)]:
                    sorce_list.append(score)
            else:
                pass
        return sorce_list

    def filter_ngrams(self):  # 过滤凝固度小于设定阈值的词
        key_sorce = []
        self.ngrams_ = set(token for token in self.ngrams if self.calculate_prob(token))
        self.sorce_list = self.calculate_prob_score()
        return self.ngrams_, self.sorce_list

    def cut_sentence(self, txt):
        mask = np.zeros(len(txt) - 1)  # 从第二个字开始标注
        for char_id in range(len(txt) - 1):
            for step in range(2, self.token_length + 1):
                if txt[char_id:char_id + step] in self.ngrams_:
                    mask[char_id:char_id + step - 1] += 1
        sent_token = [txt[0]]
        for index in range(1, len(txt)):
            if mask[index - 1] > 0:
                sent_token[-1] += txt[index]
            else:
                sent_token.append(txt[index])
        return (txt, sent_token)

    def sentences_cut(self):
        self.sentences_tokens = []
        all_tokens = defaultdict(int)
        for txt in self.texts:
            if len(txt) > 2:
                for token in self.cut_sentence(txt)[1]:
                    all_tokens[token] += 1
                self.sentences_tokens.append(self.cut_sentence(txt))
        self.all_tokens = {k: v for k, v in all_tokens.items() if v >= self.min_count}

    def is_real(self, token):
        if len(token) >= 3:
            for i in range(3, self.token_length + 1):
                for j in range(len(token) - i + 1):
                    if token[j:j + i] not in self.ngrams_:
                        return False
            return True
        else:
            return True

    def judge_exist(self):
        self.pairs = []  ##按照句子-token  进行显示
        for sent, token in self.sentences_tokens:
            real_token = []
            for tok in token:
                if self.is_real(tok) and len(tok) != 1:
                    real_token.append(tok)
            self.pairs.append((sent, real_token))

        self.new_word = {k: v for k, v in self.all_tokens.items() if self.is_real(k)}
        key_sorce = {}
        for word, sorce in self.new_word.items():
            if len(word) > 1:
                key_sorce[word] = sorce
        key_sorce = sorted(key_sorce.items(), key=lambda x: x[1], reverse=True)
        words = []
        for word, sorce in key_sorce:
            words.append(word)
        return key_sorce, words

    def statistic_token(self):  # 统计发现的新词的个数
        count = defaultdict(int)
        length = list(map(lambda x: len(x), self.new_word.keys()))
        for i in length:
            count[i] += 1
        # print("每个词的字符串长度的个数统计：", count)




def action_keyword(path,data_name):
    txt_path=path+data_name
    findtoken = ning_gu_du(txt_path)
    words_sum_nigudu, words_nigudu = findtoken.judge_exist()

    corpus_files = txt_path
    quality_phrase_files = '/Users/didi/Documents/AutoPhraseX-main/data/wiki_quality.txt'
    # 开始挖掘
    predictions = autophrase.mine(corpus_files=[corpus_files],quality_phrase_files=quality_phrase_files,
        callbacks=[LoggingCallback(),ConstantThresholdScheduler(),EarlyStopping(patience=2, min_delta=3)])
    words_autophrase=[]
    word_sum_autophrase={}
    for word,score in predictions:
        word = word.replace(' ', '')
        words_autophrase.append(word)
        word_sum_autophrase[word]=score


    keyword_sum=Multi_threading(txt_path,100,)# 多线程
    keyword_sum = sorted(keyword_sum.items(), key=lambda x: x[1], reverse=True)
    words_key = []
    for word, sorce in keyword_sum:
        words_key.append(word)

    file=txt_path
    words_sum_xin_xi_shang,words_xin_xi_shang=xin_xi_shang(file)


    # 四种方法 每种方法去分数排名的前1000个单词
    # 处理速度 一秒处理100个句子
    def Summary_4000(words_nigudu,words_xin_xi_shang,words_key,words_autophrase):
        if len(words_nigudu)>1000:
            words_nigudu=words_nigudu[0:1000]
        if len(words_xin_xi_shang) > 1000:
            words_xin_xi = words_xin_xi_shang[0:1000]
        if len(words_key) > 1000:
            words_key = words_key[0:1000]
        if len(words_autophrase) > 1000:
            words_autophrase = words_autophrase[0:1000]
        return words_nigudu+words_xin_xi_shang+words_key+words_autophrase
    result=Summary_4000(words_nigudu,words_xin_xi_shang,words_key,words_autophrase)
    print("完成了",len(result))
    #path = '/Users/didi/Documents/三种方法词表挖掘线上项目/flask 文件下载上传/save_file/'
    key_filename=path+"关键词_"+str(data_name)
    print("key_filename",key_filename)
    with open(key_filename, "a+") as f:
        for i in result:
            f.write(i)
            f.write("\n")

    return len(result)



# 定义文件的保存路径和文件名尾缀
UPLOAD_FOLDER = os.path.join(pwd, 'save_file')
ALLOWED_EXTENSIONS = {'txt'}
app.config['UPLOAD_FOLDER'] = UPLOAD_FOLDER

HOST = "172.25.109.2"
PORT = 5000


@app.route('/index',methods=['GET', 'POST'])
def index():# 第一个页面是进行上传的页面
    """
    返回一个网页端提交的页面
    :return:
    """
    html = Template("""
    <!DOCTYPE html>
    <html>
    <head>
        <meta charset="UTF-8">
        <title>关键词提取接口（智能客服）</title>
        <style>
          body{width:1450px; height:500px; text-align:center; line-height:50px; border:blue solid 1px;}
        </style>
    </head>
       <body>
       <div><strong>key_word(1.0)</strong></div>
          <form action = "http://$HOST:$PORT/upload" method = "POST"
             enctype = "multipart/form-data">
             <input type = "file" name = "file" />
             <input type = "submit"/>
          </form>
          <p>温馨提示：文件名最好用当日时间命名比如：20211207.txt，避免文件命名重复，且不可出现中文命名！</p>
          <p>温馨提示：该接口每小时可以处理35万条文本数据，请自行估计时间</p>
          <p>温馨提示：生成关键词文件：关键词_20211207.txt</p>
          <p><a href="http://172.25.109.2:5000/index4_5">文件查看+文件进行关键词提取</a></p>
          <p><a href="http://172.25.109.2:5000/index1">文件查看+文件下载</a></p>
          <p><a href="http://172.25.109.2:5000/index3">文件查看+文件删除</a></p>
       </body>
    </html>
    """)
    html = html.substitute({"HOST": HOST, "PORT": PORT})
    return html

# 开始页面
@app.route('/index1')#, methods=['GET', 'POST']
def index1():
    resp=os.walk("/Users/didi/Documents/三种方法词表挖掘线上项目/flask 文件下载上传/save_file")
    data_list = []
    for root, dirs, files in resp:
        data_list.append(files)
    if len(data_list) > 0:
         data_list=data_list[0]
    print(data_list)
    return render_template("index1.html", data=data_list,herf=" ")
# 下载页面显示➕下载之后继续跳转
@app.route('/index2',methods=['POST'])#, methods=['GET', 'POST']
def index2():
    resp=os.walk("/Users/didi/Documents/三种方法词表挖掘线上项目/flask 文件下载上传/save_file")
    data_list = []
    for root, dirs, files in resp:
        data_list.append(files)
    if len(data_list) > 0:
         data_list=data_list[0]

    data = request.form['Name']
    print(data)
    if data not in data_list:
        resp = os.walk("/Users/didi/Documents/三种方法词表挖掘线上项目/flask 文件下载上传/save_file")
        data_list1 = []
        for root, dirs, files in resp:
            data_list1.append(files)
        if len(data_list1) > 0:
            data1= data_list1[0]
        else:
            data1=[]
        attachment_url=""
        tishi="您输入的文件名有误！"
        return render_template("index2.html", data=data1, tishi=tishi, herf=attachment_url)
    elif data in data_list:
        attachment_url = 'http://172.25.109.2:5000/download?fileId='+str(data)
        data1 = ""
        tishi = "请用浏览器访问这个链接下载！"
        return render_template("index2.html",data=data1 ,tishi =tishi ,herf=attachment_url )

# 删除页面显示
@app.route('/index3',)#, methods=['GET', 'POST']
def index3():
    resp=os.walk("/Users/didi/Documents/三种方法词表挖掘线上项目/flask 文件下载上传/save_file")
    data_list = []
    for root, dirs, files in resp:
        data_list.append(files)
    if len(data_list) > 0:
        data_list=data_list[0]
    return render_template("index3.html",data=data_list,herf=" " )
# 删除返回页面
@app.route('/index4',methods=['GET', 'POST'])#, methods=['GET', 'POST']
def index4():
    resp=os.walk("/Users/didi/Documents/三种方法词表挖掘线上项目/flask 文件下载上传/save_file")
    data_list = []
    for root, dirs, files in resp:
        data_list.append(files)
    if len(data_list)>0:
        data_list=data_list[0]
    data_name = request.form['Name']
    print(data_name)
    if data_name not in data_list:
        resp1 = os.walk("/Users/didi/Documents/三种方法词表挖掘线上项目/flask 文件下载上传/save_file")
        data_list1 = []
        for root, dirs, files in resp1:
            data_list1.append(files)
        if len(data_list1) > 0:
             data1 = data_list1[0]
        else:
            data1=[]
        tishi="您输入的文件名有误！"
        attachment_url=""
        return render_template("index3.html", data=data1, tishi=tishi, herf=attachment_url)
    elif data_name in data_list:
        attachment_url =""
        tishi = " "
        os.remove("/Users/didi/Documents/三种方法词表挖掘线上项目/flask 文件下载上传/save_file/" + str(data_name))
        resp1 = os.walk("/Users/didi/Documents/三种方法词表挖掘线上项目/flask 文件下载上传/save_file")
        data_list2 = []
        for root, dirs, files in resp1:
            data_list2.append(files)
        if len(data_list2) > 0:
            data1 = data_list2[0]
        return render_template("index3.html",data=data1,tishi=tishi,herf=attachment_url )
# 提取文件显示
@app.route('/index4_5')#, methods=['GET', 'POST']
def index4_5():
    resp=os.walk("/Users/didi/Documents/三种方法词表挖掘线上项目/flask 文件下载上传/save_file")
    data_list = []
    for root, dirs, files in resp:
        data_list.append(files)
    if len(data_list)>0:
       data_list=data_list[0]
    return render_template("index4_5.html",data=data_list,herf=" " )

# 文件进行提取操作
@app.route('/index5',methods=['GET', 'POST'])#, methods=['GET', 'POST']
def index5():
    resp=os.walk("/Users/didi/Documents/三种方法词表挖掘线上项目/flask 文件下载上传/save_file")
    data_list = []
    for root, dirs, files in resp:
        data_list.append(files)
    print(data_list)
    if len(data_list)>0:
        data_list=data_list[0]
    else:
        data_list=[]
    data_name = request.form['Name']
    print(data_name)
    if data_name not in data_list:
        resp1 = os.walk("/Users/didi/Documents/三种方法词表挖掘线上项目/flask 文件下载上传/save_file")
        data_list1 = []
        for root, dirs, files in resp1:
            data_list1.append(files)
        if len(data_list1)>0:
            data1= data_list1[0]
        else:
            data1=[]
        tishi="您输入的文件名有误！ "
        attachment_url=""
        return render_template("index5.html", data=data1, tishi=tishi, herf=attachment_url)
    elif  data_name in data_list:
        txt_path = '/Users/didi/Documents/三种方法词表挖掘线上项目/flask 文件下载上传/save_file/'

        # while 1:
        #     a=0
        #     if a==0:
        #         key_word_sum = action_keyword(txt_path)
        #     a=a+1
        #
        #     time.sleep(2)
        #     attachment_url = ""
        #     tishi = "文件正在提取中...，请勿重复提交！"
        #     data1="每次只对一个文件进行提取"
        #     rep = os.walk("/Users/didi/Documents/三种方法词表挖掘线上项目/flask 文件下载上传/save_file")
        #     name_file= []
        #     for root, dirs, files in rep:
        #         name_file.append(files)
        #     name_files = name_file[0]
        #     if "关键词_"+str(data_name) in name_files:
        #         break
        #     return render_template("index5.html",data=data1,tishi=tishi,herf=attachment_url )

        key_word_sum = action_keyword(txt_path,data_name)
        return '<a href="http://172.25.109.2:5000/index">程序执行结束，点击返回首页</a>'
        # attachment_url = ""
        # tishi = "文件提取完成"
        # data1 = "提取到关键词"+str(key_word_sum)+"个"
        # return render_template("index5.html", data=data1, tishi=tishi, herf=attachment_url)

def allowed_file(filename):
    """
    检验文件名尾缀是否满足格式要求
    :param filename:
    :return:
    """
    return '.' in filename and \
           filename.rsplit('.', 1)[1].lower() in ALLOWED_EXTENSIONS


@app.route('/upload', methods=['GET', 'POST'])
def upload_file():
    """
    上传文件到save_file文件夹
    以requests上传举例
    wiht open('路径','rb') as file_obj:
        rsp = requests.post('http://localhost:5000/upload,files={'file':file_obj})
        print(rsp.text) --> file uploaded successfully
    """
    if 'file' not in request.files:
        return "No file part"
    file = request.files['file']
    if file.filename == '':
        return 'No selected file'
    if file and allowed_file(file.filename):
        filename = secure_filename(file.filename)
        print(app.config['UPLOAD_FOLDER'])
        print(filename)
        file.save(os.path.join(app.config['UPLOAD_FOLDER'], filename))
        return '<a href="http://172.25.109.2:5000/index">返回提交首页</a>'
    return "file uploaded Fail"


@app.route("/download")
def download_file():
    """
    下载save_file目录下面的文件
    eg：下载当前目录下面的123.tar 文件，eg:http://localhost:5000/download?fileId=123.tar
    :return:
    """
    file_name = request.args.get('fileId')
    file_path = os.path.join(pwd, 'save_file', file_name)
    if os.path.isfile(file_path):
        return send_file(file_path, as_attachment=True)
    else:
        return "The downloaded file does not exist"

#
# if __name__ == '__main__':
#     app.run(host=HOST, port=PORT)
from gevent import pywsgi
if __name__ == '__main__':
    server = pywsgi.WSGIServer(('0.0.0.0', 5000), app)
    server.serve_forever()
# http://172.25.109.2:5000/index
# http://172.25.109.2:5000/index1
# url:http://172.25.109.2:5000/download?fileId=test.txt

# 下面这种方式也是可以的
# if __name__ == "__main__":
#     print("端口号={}".format(FLAGS.port))
#     app.run(host="10.178.27.59", port=FLAGS.port, debug=True)

index1.html:

<!DOCTYPE html>
<html lang="en">
<head>
    <meta charset="UTF-8">
    <title>文件显示</title>
    <style>
      body{width:1450px; height:500px; text-align:center; line-height:50px; border:blue solid 1px;}
    </style>
</head>
<body>
<div>文件显示</div>
<p>{{data}}</p>
<p>{{herf}}</p>
<form action = "http://172.25.109.2:5000/index2" method = "POST">
 <p>请输入您要下载的文件名<input type = "text" name = "Name" /></p>
 <p><input type = "submit" value = "提交" /></p>
</form>
<a href="http://172.25.109.2:5000/index">返回提交首页</a>
</body>
</html>

index2.html

<!DOCTYPE html>
<html lang="en">
<head>
    <meta charset="UTF-8">
    <title>文件显示</title>
    <style>
      body{width:1450px; height:500px; text-align:center; line-height:50px; border:blue solid 1px;}
    </style>
</head>
<body>
<div>文件显示</div>
<p>{{data}}</p>
<p>{{tishi}}</p>
<p>{{herf}}</p>
<form action = "http://172.25.109.2:5000/index2" method = "POST">
 <p>请输入您要下载的文件名<input type = "text" name = "Name" /></p>
 <p><input type = "submit" value = "提交" /></p>
</form>
<a href="http://172.25.109.2:5000/index">返回提交首页</a>
</body>
</html>

index3.html 

<!DOCTYPE html>
<html lang="en">
<head>
    <meta charset="UTF-8">
    <title>文件显示</title>
    <style>
      body{width:1450px; height:500px; text-align:center; line-height:50px; border:blue solid 1px;}
    </style>
</head>
<body>
<div>文件显示</div>

<p>{{data}}</p>
<p>{{tishi}}</p>
<p>{{herf}}</p>

<form action = "http://172.25.109.2:5000/index4" method = "POST">
 <p>请输入您要删除的文件名<input type = "text" name = "Name" /></p>
 <p><input type = "submit" value = "提交" /></p>
</form>
<a href="http://172.25.109.2:5000/index">返回提交首页</a>
</body>
</html>

index4.html 

<!DOCTYPE html>
<html lang="en">
<head>
    <meta charset="UTF-8">
    <title>文件显示</title>
    <style>
      body{width:1450px; height:500px; text-align:center; line-height:50px; border:blue solid 1px;}
    </style>
</head>
<body>
<div>文件显示</div>
<p>{{data}}</p>
<p>{{herf}}</p>

<form action = "http://172.25.109.2:5000/index2" method = "POST">
 <p>请输入您要删除的文件名<input type = "text" name = "Name" /></p>
 <p><input type = "submit" value = "提交" /></p>
</form>
<a href="http://172.25.109.2:5000/index">返回提交首页</a>
</body>
</html>

index4_5.html

<!DOCTYPE html>
<html lang="en">
<head>
    <meta charset="UTF-8">
    <title>文件显示</title>
    <style>
      body{width:1450px; height:500px; text-align:center; line-height:50px; border:blue solid 1px;}
    </style>
</head>
<body>
<div>文件显示</div>
<p>{{data}}</p>
<p>{{tishi}}</p>
<p>{{herf}}</p>
<form action = "http://172.25.109.2:5000/index5" method = "POST">
 <p>请输入您要提取的文件名<input type = "text" name = "Name" /></p>
 <p><input type = "submit" value = "提交" /></p>
</form>
<p>每次只能提交一个文件，提交之后请在页面静候等待</p>
<a href="http://172.25.109.2:5000/index">返回提交首页</a>
</body>
</html>

index5.html 

<!DOCTYPE html>
<html lang="en">
<head>
    <meta charset="UTF-8">
    <title>文件显示</title>
    <style>
      body{width:1450px; height:500px; text-align:center; line-height:50px; border:blue solid 1px;}
    </style>
</head>
<body>
<div>文件显示</div>
<p>{{data}}</p>
<p>{{tishi}}</p>
<p>{{herf}}</p>
<form action = "http://172.25.109.2:5000/index5" method = "POST">
 <p>请输入您要提取的文件名<input type = "text" name = "Name" /></p>
 <p><input type = "submit" value = "提交" /></p>
</form>
<p>每次只能提交一个文件，提交之后请在页面静候等待</p>
<a href="http://172.25.109.2:5000/index">返回提交首页</a>
</body>
</html>

最后看一下效果图：