void linksWrite(struct pagewordsFormat *pagewords,struct addNewUrlhaFormat addNewUrlha[]) { int i, len; struct updateFormat updatePost; for(i=0;i<(*pagewords).nrOfOutLinks;i++) { if ((IndexerMaxLinks)> i) { if ((*pagewords).outlinks[i].good) { len = (*pagewords).outlinks[i].linktextlen; //fjerner space på slutten if (len > 0) { (*pagewords).outlinks[i].linktext[len -1] = '\0'; } //tømmer minne for å gjøre filene mer komprimeringsvendlige memset(updatePost.url,'\0',sizeof(updatePost.url)); memset(updatePost.linktext,'\0',sizeof(updatePost.linktext)); strscpy((char *)updatePost.url,(*pagewords).outlinks[i].url,sizeof((*pagewords).outlinks[i].url)); strscpy((char *)updatePost.linktext,(*pagewords).outlinks[i].linktext,sizeof( (*pagewords).outlinks[i].linktext )); updatePost.DocID_from = (*pagewords).curentDocID; //bruker sidens DocID til å velge hvilken fil. Usikker på om det er lurt, men det er lett og implementere for nå addNewUrl(&addNewUrlha[(*pagewords).curentDocID % NEWURLFILES_NR],&updatePost); } } } }
Spider::Spider(){ page = new WebPage(); page->flag = true; isRegionNode = false; connect(page, SIGNAL(addNewUrl(QUrl)), this, SLOT(addUrlToQueue(QUrl))); server = new QLocalServer(); shared = new QSharedMemory(global::KEY_SHARED_MEMORY,0); instance = new NetWorker(); }
bool WebPage::acceptNavigationRequest(QWebFrame * frame, const QNetworkRequest & request, NavigationType type) { //qDebug()<<"NavigationType :"<<type; //qDebug()<<"[acceptNavigationRequest] url : "<<request.url(); if(!flag){ emit addNewUrl(request.url()); qDebug()<< "emit singal:"<<request.url(); } return flag; }
void linkadd(char word[]) { struct updateFormat updatePost; if ((strchr(word,'?') != NULL) && (global_curentUrlIsDynamic)) { //printf("NO add %s\n",word); } else if (strlen(word) > sizeof(updatePost.url)) { //printf("url to long at %i char\n",strlen(word)); } else { //printf("link: %s\n",word); strncpy(updatePost.url,word,sizeof(updatePost.url)); strncpy(updatePost.linktext,"",sizeof(updatePost.linktext)); updatePost.DocID_from = global_curentDocID; addNewUrl(&updatePost,""); } }