#include <webcrawler.h>
|
void | visitUrls () |
| Spider main functionality Takes urls from frontier queue and downloads their HTML source code. More...
|
|
◆ WebCrawler_Spider()
WebCrawler_Spider::WebCrawler_Spider |
( |
| ) |
|
spider's constructor - does nothing
◆ ~WebCrawler_Spider()
WebCrawler_Spider::~WebCrawler_Spider |
( |
| ) |
|
◆ finished
void WebCrawler_Spider::finished |
( |
QString |
| ) |
|
|
signal |
◆ getUrl
void WebCrawler_Spider::getUrl |
( |
const QNetworkRequest & |
request | ) |
|
|
signal |
◆ load()
void WebCrawler_Spider::load |
( |
WebCrawler_Parser * |
wc_parser, |
|
|
const QString & |
url, |
|
|
const int & |
maxN, |
|
|
const bool & |
delayedRequests |
|
) |
| |
Called from Graph to init variables.
- Parameters
-
url | |
maxN | |
maxLinksPerPage | |
extLinks | |
intLinks | |
◆ parse
void WebCrawler_Spider::parse |
( |
QNetworkReply * |
reply | ) |
|
|
signal |
◆ visitUrls
void WebCrawler_Spider::visitUrls |
( |
| ) |
|
|
slot |
Spider main functionality Takes urls from frontier queue and downloads their HTML source code.
◆ currentUrl
QUrl WebCrawler_Spider::currentUrl |
|
private |
◆ m_delayedRequests
bool WebCrawler_Spider::m_delayedRequests |
|
private |
◆ m_maxNodes
int WebCrawler_Spider::m_maxNodes |
|
private |
◆ m_seed
QString WebCrawler_Spider::m_seed |
|
private |
◆ m_visitedNodes
int WebCrawler_Spider::m_visitedNodes |
|
private |
◆ m_wait_msecs
int WebCrawler_Spider::m_wait_msecs |
|
private |
◆ reply
QNetworkReply* WebCrawler_Spider::reply |
|
private |
The documentation for this class was generated from the following files: