用库算法提取URL

gistfile1.cpp

#include <string>
#include <vector>
#include <algorithm>
#include <functional>
#include <fstream>
#include <iterator>
#include <iostream>

using namespace std;

typedef string::const_iterator iter;

bool isurlch(char ch)
{
    static const string urlcs = "~;/?:@=&$-_.+!*'{},";
    return isalnum(ch) || find(urlcs.begin(), urlcs.end(), ch) != urlcs.end();
}

iter url_end(iter begin, iter end)
{
    return find_if(begin, end, [](char ch){ return !isurlch(ch); });
}

iter url_begin(iter begin, iter end)
{
    static const string sep = "://";
    iter i = begin;
    while (true)
    {
        i = search(i, end, sep.begin(), sep.end());
        if (i == end) break;
        if (i != begin && i + sep.size() != end && isurlch(i[sep.size()]))
        {
            iter result = i;
            //while (result != begin && isalpha(result[-1])) --result;
            result = find_if_not(string::const_reverse_iterator(i), string::const_reverse_iterator(begin), isalpha).base();
            if (result != i) return result;
        }
        if (i != end) i += sep.size();
    }
    return end;
}

vector<string> extract_url(const string &text)
{
    vector<string> urls;
    iter begin = text.begin();
    while (begin != text.end())
    {
        begin = url_begin(begin, text.end());
        if (begin != text.end())
        {
            iter end = url_end(begin, text.end());
            urls.push_back(string(begin, end));
            begin = end;
        }
    }
    return urls;
}

int main()
{
    ifstream ifs("in.txt");
    string line;
    string text;
    while (getline(ifs, line))
    {
        text += line + "\n";
    }
    auto urls = extract_url(text);
    copy(urls.begin(), urls.end(), ostream_iterator<string>(cout, "\n"));
    return 0;
}