import requests
from urllib.request import urlopen
from bs4 import BeautifulSoup
txt = open(r‘C:\Users\Administrator\Desktop\result.txt‘,‘w‘,encoding=‘utf-8‘) 
#打开文件
i = 0
def getPaper(newsUrl):   #获取相关信息的函数
  res = requests.get(newsUrl)  #打开链接
  res.encoding = ‘utf-8‘
  soup = BeautifulSoup(res.text,‘html.parser‘)   #把网页内容存进容器
  Title = soup.select(‘#papertitle‘)[0].text.strip()  #找到标题元素爬取
  print("Title:",Title,file=txt)
  Abstract = soup.select(‘#abstract‘)[0].text.strip() #找到摘要元素爬取
  print("Abstract:",Abstract,"\n\n",file=txt)
  return 

sUrl = ‘http://openaccess.thecvf.com/CVPR2018.py‘
res1 = requests.get(sUrl)
res1.encoding = ‘utf-8‘
soup1 = BeautifulSoup(res1.text,‘html.parser‘)
for titles in soup1.select(‘.ptitle‘):    #返回每个超链接
    t = ‘http://openaccess.thecvf.com/‘+ titles.select(‘a‘)[0][‘href‘]  
    print(i,file=txt)
    getPaper(t)     #循环打开每个子页面并进行爬取
    i=i+1

while (1) //循环判断命令行参数
    {
        i++;
        if (i == argc)    
            break;
        if (argv[i][0] == ‘-‘)   //判断当前参数首字符是否为‘-‘
        {
            switch (argv[i][1])    //判断当前参数第二个字符
            {
            case ‘i‘:
            {
                i++;
                input = argv[i];//第二个字符为i时输入下一个参数赋值给input
                break;
            }
            case ‘o‘:
            {
                i++;
                output = argv[i];//第二个字符为o时输入下一个参数赋值给output
                break;
            }
            case ‘w‘:
            {
                i++;
                judgeW = atoi(argv[i]);//第二个字符为w时judgeW为下一个参数的整数值留作输出判断
                break;
            }
            case ‘m‘:
            {
                i++;
                judgeM = atoi(argv[i]);//第二个字符为m时judgeM为下一个参数的整数值留作输出判断
                break;
            }
            case ‘n‘:
            {
                i++;
                judgeN = atoi(argv[i]);//第二个字符为n时judgeN为下一个参数的整数值留作输出判断
                break;
            }
            default:
                cout << "输入参数有误" << endl;
                break;
            }
        }
    }

if (judgeW == 0)
    {
        if (judgeM == 0)    //非权重词频统计
        {
            f1 = f1.countline(input, f1);
            f1.Abstract = changeDx(f1.Abstract);
            f1.Title = changeDx(f1.Title);//大小写转换
            f1 = f1.countword(f1, f1.Title, 1);
            f1 = f1.countword(f1, f1.Abstract, 1);
        }
        else  //非权重词组词频统计
        {
            f1 = f1.outputByLine(input, f1, 1, judgeM);
        }
    }
    else
    {
        if (judgeM == 0)  //权重词频统计
        {
            f1 = f1.countline(input, f1);
            f1.Abstract = changeDx(f1.Abstract);
            f1.Title = changeDx(f1.Title);//大小写转换
            f1 = f1.countword(f1, f1.Title, 10);
            f1 = f1.countword(f1, f1.Abstract, 1);
        }
        else   //权重词组词频统计
        {
            f1 = f1.outputByLine(input, f1, 10, judgeM);
        }
    }

if (judgeN == 0)//如果没有定义n那么按默认输出
        outCome1(ww, num, output, f1);
    else
    {
        if (judgeN > f1.getwords())
        {
            cout << "输入的n值超过了文本的所有单词数，将为您按序输出文本的所有单词" << endl;//对于参数过大的错误判断
            outCome2(ww, f1.getwords(), output, f1);
        }
        else
        {
            outCome2(ww, judgeN, output, f1);//如果定义了n那么输出前n个
        }
    }

testfile testfile::phrasecounts(string temp, int t, int quan, testfile f1)
{
    int word = 0;
    int i = 0;
    int j = 0;
    long int n = 0;
    int m = 0;
    string sumwr = "";//初始化一个存放词组的字符串 
    n = temp.length();
    char x[10];
    for (j = 0; j < n; j++)
    {
        if (temp[j] >= ‘A‘&&temp[j] <= ‘Z‘)
        {
            temp[j] += 32;
        }
    }
    string phrase;
    int  flag = 0, k = 0;
    int mark = 0, al = 0;//mark用来记录存储的单词数，al用来记录成词组的第二个单词的首字母序号 
    for (i = 0; i < n; i++)
    {

        if (!((temp[i] >= 48 && temp[i] <= 57) || (temp[i] >= 97 && temp[i] <= 122)))
        {
            if (mark > 0)
            {
                sumwr = sumwr + temp[i];//如果此时已记录一个及以上的单词，将此分隔符也录入词组字符串 
            }
            continue;
        }
        else
        {
            for (j = 0; j < 4 && i < n; j++)
            {

                if (!((temp[i] >= 48 && temp[i] <= 57) || (temp[i] >= 97 && temp[i] <= 122)))
                {
                    mark = 0;
                    sumwr = "";//检测到非法单词，重新初始化mark和词组字符串 
                    break;
                }
                else
                {
                    if (j == 0 && mark == 1)
                    {
                        al = i;
                    }
                    x[j] = temp[i++];//temp中存入四个非空格字符
                }
            }
            if (j == 4)
            {
                for (m = 0; m < 4; m++)
                {
                    if (x[m] < 97 || x[m]>122)
                    {
                        flag = 1;
                        mark = 0;
                        sumwr = "";
                        break;//判断这四个字符是否都是字母，检测到非法单词，重新初始化mark和词组字符串
                    }
                }
                if (flag == 0)//判断为一个单词
                {
                    char *w = new char[100];//存放单词 
                    for (m = 0; m < 4; m++)
                    {
                        w[k++] = x[m];//temp中字符存入w
                    }
                    while (((temp[i] >= 48 && temp[i] <= 57) || (temp[i] >= 97 && temp[i] <= 122)) && i < n)//继续存入单词剩余字符
                    {
                        w[k++] = temp[i++];
                    }
                    w[k] = ‘\0‘;
                    sumwr = sumwr + w;//将单词存入词组字符串数组 
                    mark++;
                    delete[]w;
                    k = 0;
                    if (mark == t)
                    {
                        loadword(sumwr, quan);//如果此时单词存入达到所需数量，将此词组字符串存入map函数，并初始化mark和字符串 
                        word++;
                        mark = 0;
                        i = al;//让i等于存入字符串的第二个单词的第一个字母序号，重新开始查询词组 
                        sumwr = "";
                    }
                    i--;
                }
                else
                {
                    flag = 0;
                    j = 0;
                    mark = 0;
                    sumwr = "";
                }
            }
        }

    }
    i = 0;
    f1.words += word;
    return f1;
}

#include "stdafx.h"
#include "CppUnitTest.h"
#include "C:\Users\Administrator\Desktop\软工实践\结对作业2\单元测试\WordCount2\WordCount2\WordCount2\WordCount2.h"
#include <iostream>
using namespace Microsoft::VisualStudio::CppUnitTestFramework;

namespace WordCountTest1
{        
    TEST_CLASS(UnitTest1)
    {
    public:
        
        TEST_METHOD(phraseCount)
        {
            testfile f1;
            f1=f1.outputByLine("C:\\Users\\Administrator\\Desktop\\result.txt", f1, 1, 3);//按行输出后进行词组词频统计
        }
        TEST_METHOD(wordCount)
        {
            testfile f1;
            f1 = f1.countline("C:\\Users\\Administrator\\Desktop\\result.txt", f1);
            f1 = f1.countword(f1, f1.Abstract, 1);
            f1 = f1.countword(f1, f1.Title, 1);
        }
        TEST_METHOD(countCharacters)
        {
            testfile f1;
            string a;
            f1 = f1.countcha("C:\\Users\\Administrator\\Desktop\\result.txt", f1);
            Assert::AreEqual(f1.getcharacters(), (int)1220332);
        }
        TEST_METHOD(countLine)
        {
            testfile f1;
            f1 = f1.countline("C:\\Users\\Administrator\\Desktop\\result.txt", f1);
            Assert::AreEqual(f1.getlines(), (int)2937);
        }
    };
}