Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

No DocIDs will be created if maxPagesToFetch is reached (most times). #430

Open
wants to merge 2 commits into
base: master
Choose a base branch
from
Open

No DocIDs will be created if maxPagesToFetch is reached (most times). #430

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
d8c6690
No DocIDs will be created if maxPagesToFetch
dgoiko Jan 24, 2020
2564c09
Style fixes
dgoiko Jan 24, 2020
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
70 changes: 43 additions & 27 deletions crawler4j/src/main/java/edu/uci/ics/crawler4j/crawler/WebCrawler.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -513,40 +513,56 @@ private void processPage(WebURL curURL) throws IOException, InterruptedException
parser.parse(page, curURL.getURL());

if (shouldFollowLinksIn(page.getWebURL())) {
ParseData parseData = page.getParseData();
List<WebURL> toSchedule = new ArrayList<>();
int maxCrawlDepth = myController.getConfig().getMaxDepthOfCrawling();
for (WebURL webURL : parseData.getOutgoingUrls()) {
webURL.setParentDocid(curURL.getDocid());
webURL.setParentUrl(curURL.getURL());
int newdocid = docIdServer.getDocId(webURL.getURL());
if (newdocid > 0) {
// This is not the first time that this Url is visited. So, we set the
// depth to a negative number.
webURL.setDepth((short) -1);
webURL.setDocid(newdocid);
} else {
webURL.setDocid(-1);
webURL.setDepth((short) (curURL.getDepth() + 1));
if ((maxCrawlDepth == -1) || (curURL.getDepth() < maxCrawlDepth)) {
if (shouldVisit(page, webURL)) {
if (robotstxtServer.allows(webURL)) {
webURL.setDocid(docIdServer.getNewDocID(webURL.getURL()));
toSchedule.add(webURL);
if (frontier.canFetchPages()) {
ParseData parseData = page.getParseData();
List<WebURL> toSchedule = new ArrayList<>();
int maxCrawlDepth = myController.getConfig().getMaxDepthOfCrawling();
long remaining = frontier.numberToReachMaxPagesToFetch();
for (WebURL webURL : parseData.getOutgoingUrls()) {
// This is not threads safe. Other threads may reduce remaining elements
if (remaining == 0) {
logger.debug("Ignoring remaining links in page {}, "
+ "because maxPagesToFetch was reached",
page.getWebURL().getURL());
break;
}
webURL.setParentDocid(curURL.getDocid());
webURL.setParentUrl(curURL.getURL());
int newdocid = docIdServer.getDocId(webURL.getURL());
if (newdocid > 0) {
// This is not the first time that this Url is visited. So, we set the
// depth to a negative number.
webURL.setDepth((short) -1);
webURL.setDocid(newdocid);
} else {
webURL.setDocid(-1);
webURL.setDepth((short) (curURL.getDepth() + 1));
if ((maxCrawlDepth == -1) || (curURL.getDepth() < maxCrawlDepth)) {
if (shouldVisit(page, webURL)) {
if (robotstxtServer.allows(webURL)) {
webURL.setDocid(docIdServer.getNewDocID(webURL.getURL()));
remaining--;
toSchedule.add(webURL);
} else {
logger.debug(
"Not visiting: {} as per the server's \"robots.txt\" " +
"policy", webURL.getURL());
}
} else {
logger.debug(
"Not visiting: {} as per the server's \"robots.txt\" " +
"policy", webURL.getURL());
"Not visiting: {} as per your \"shouldVisit\" policy",
webURL.getURL());
}
} else {
logger.debug(
"Not visiting: {} as per your \"shouldVisit\" policy",
webURL.getURL());
}
}
}
frontier.scheduleAll(toSchedule);
} else {
logger.debug("Not looking for links in page {}, "
+ "because maxPagesToFetch was reached",
page.getWebURL().getURL());
}
frontier.scheduleAll(toSchedule);

} else {
logger.debug("Not looking for links in page {}, "
+ "as per your \"shouldFollowLinksInPage\" policy",
Expand Down
17 changes: 17 additions & 0 deletions crawler4j/src/main/java/edu/uci/ics/crawler4j/frontier/Frontier.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -161,6 +161,23 @@ public void getNextURLs(int max, List<WebURL> result) {
}
}

public boolean canFetchPages() {
int maxPagesToFetch = config.getMaxPagesToFetch();
return maxPagesToFetch < 0 || scheduledPages < maxPagesToFetch;
}

public long numberToReachMaxPagesToFetch() {
int maxPagesToFetch = config.getMaxPagesToFetch();
if (maxPagesToFetch < 0) {
return -1;
}
long remaining = maxPagesToFetch - scheduledPages;
if (remaining < 0) {
return 0;
}
return remaining;
}

public void setProcessed(WebURL webURL) {
counters.increment(Counters.ReservedCounterNames.PROCESSED_PAGES);
if (inProcessPages != null) {
Expand Down