void pr_htmldefs(FILE *fp)
{
int i;
fprintf(fp,"<title>GROMACS</title>\n");
fprintf(fp,"<h1>GROMACS Files</h1>\n");
fprintf(fp,"<b>GRO</b>ningen <b>MA</b>chine for <b>S</b>imulating <b>C</b>hemistry\n");
fprintf(fp,"<p>\n");
fprintf(fp,"The following %d filetypes are used by Gromacs:\n",efNR);
fprintf(fp,"<dl>\n");
for(i=0; (i<efNR); i++) {
fprintf(fp,"<dt><a href=\"%s.html\">%s.%s</a> (%s)<dd>%s\n",
ftp2ext(i),ftp2defnm(i),ftp2ext(i),ftp2ftype(i),
check_html(ftp2desc(i),NULL));
}
fprintf(fp,"</dl>\n");
}
// Definition of stringsearch() function
void session::stringsearch(){
// Whole body is in loop
// Loop ends if the list is empty or a certain number of urls have been parsed
do{
// File that stores source code of URLs
std::ofstream FILE("source.txt");
std::ofstream wordfile("index.txt", std::ios::app|std::ios::out);
// Object of url class created
url u(list.front());
// Object of Http class (found in SFML) created
// Http class only takes host names as input, so host name passed
sf::Http site(u.host());
//Generate the request, i.e the path within the webpage
sf::Http::Request request(u.path());
// Send the request to generate a response
sf::Http::Response response = site.sendRequest(request);
// Check the status code and display the result
sf::Http::Response::Status status = response.getStatus();
if (status == sf::Http::Response::Ok){
FILE << response.getBody() << std::endl;
}
else{
std::cout << "Error " << status << std::endl;
std::cout << "Skipping webpage. " << std::endl;
list.pop();
continue;
}
FILE.close();
std::cout << "Popping URL: " << list.front() << std::endl << std::endl;
Sleep(1000);
// Condition check to see if file is of html format
if (check_html() == false){
std::cout << "\nWebpage not in html format. Skipping... " << std::endl << std::endl;
list.pop();
continue;
}
// Condition check to ensure URL hasn't been crawled previously. First URL is skipped
if (count > 1 && check_urls(list.front()) == true){
std::cout << "\nWebpage has already been crawled. Skipping...\n\n";
list.pop();
continue;
}
// Opens file for reading
std::ifstream file("source.txt");
std::string s1; // String stores lines from html file
std::string s2 = "href=\""; // Reference string to locate hyperlinks
char s3[300]; // C string variable to store hyperlink URLs
// Condition check to ensure file is open
if (file.is_open()){
do{
// Both string storage variables initialised to null
s1 = "";
std::getline(file, s1); // Gets line by line information from the page source
std::size_t location = s1.find(s2); // Variable to point to location in string
int i = 0;
// Check to see if location is within string, i.e the desired element has been found
if (location != std::string::npos){
std::cout << "Hyperlink found: ";
// Location set to first element of hyperlink
// Adding 6 accounts for the 6 tag characters, i.e href"
std::size_t x = location + 6;
// Loop adds characters to array until quotation mark is reached
while (s1.at(x) != '\"'){
s3[i] = s1.at(x);
x++;
i++;
}
// Last character set to termination character
s3[i] = '\0';
std::string s4 = s3; // Converts C string to std::string
std::cout << s4 << std::endl;
// Creates url object that takes s4 as constructor argument
url u2(s4);
// Condition check to see if hyperlink has a host
// If it doesn't, it means it is an extension of the current webpage
// So current webpage is appended to it
if (u2.host() == ""){
s4 = u.protocol() + "://" + u.host() + s4;
}
std::cout << "Adding URL to queue..." << std::endl;
// Hyperlink is added to queue
list.push(s4);
std::cout << s4 << std::endl << std::endl;
}
if (wordfile.is_open()){
std::string word = "Boost";
std::size_t point = s1.find(word);
if (point != std::string::npos){
// while ()
wordfile << list.front() << std::endl;
wordfile << word << std::endl;
}
// else{
// std::cout << "word not found" << std::endl;
//std::cout << "\n";
// }
}
else{
std::cout << "index could not be opened" << std::endl;
}
} while (!file.eof());
// Adds current webpage to list of URLs parsed
urls_parsed(list.front());
// Removes current webpage from queue
list.pop();
file.close();
wordfile.close();
std::cout << "\n\nCount: " << count << std::endl;
count++;
Sleep(1000);
}
else{
std::cout << "Error in opening file" << std::endl;
exit(-1);
}
//Sleep(1000);
} while (count <= 10 && list.empty() == false);
remove("source.txt");
remove("urls.txt");
return;
}
