问通过wget下载服务器上的最新文件

EN

filename=`wget -q -O - http://thredds.ucar.edu/thredds/catalog/grib/nexrad/composite/unidata/NEXRAD_Unidata_Reflectivity-20140501/files/catalog.html | grep '<a href=' | head -1 | sed -e 's/.*\(Level3_Composite_N0R_[0-9]*_[0-9]*.grib2\).*/\1/'`

#include <iostream>
#include <string>
#include <stdio.h>
#include <time.h>
#include <iostream>
#include <fstream>
#include <sstream>
using namespace std;


int main() 

{

// First, I open the catalog.html which was downloaded using wget, and put the entire file into a string.

ifstream inFile; // create instance
inFile.open("catalog.html"); // opens the file
stringstream strStream; // create stringstream
strStream << inFile.rdbuf();  //read the file
string str = strStream.str();  //str holds the content of the file

cout << str << endl;  // The string contains the entire catalog ... you can do anything with the string

// Now I will create the entire URL we need automatically by getting the base URL which is known (step 1 is : string "first")

string first= "http://thredds-test.unidata.ucar.edu/thredds/fileServer/satellite/goes16/GRB16/ABI/CONUS/Channel02/current/";

// The string "second" is the actual filename, since (to my knowledge) the filename in the HTML file never changes, but this must be watched in case it DOES change     in the future. I use the c++ substring function to extract it.

string second = str.substr(252784,76); 


// I then create a batch file and write "wget (base url + filename)" which can now automatically launch/download the latest GRIB2 file.

ofstream myfile2;
myfile2.open ("downloadGOESLatest.bat");
myfile2 << "wget ";
myfile2 << first;
myfile2 << second;
myfile2.close();


return 0;

}