Skip to content

[Fix] #698 修复使用Redis,Request丢失附加信息问题 #702

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

Merged
merged 1 commit into from
Nov 30, 2017
Merged

[Fix] #698 修复使用Redis,Request丢失附加信息问题 #702

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
35 changes: 31 additions & 4 deletions webmagic-extension/src/main/java/us/codecraft/webmagic/scheduler/RedisScheduler.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,6 +2,7 @@

import com.alibaba.fastjson.JSON;
import org.apache.commons.codec.digest.DigestUtils;
import org.apache.commons.lang3.StringUtils;
import redis.clients.jedis.Jedis;
import redis.clients.jedis.JedisPool;
import redis.clients.jedis.JedisPoolConfig;
Expand Down Expand Up @@ -60,7 +61,7 @@ protected void pushWhenNoDuplicate(Request request, Task task) {
Jedis jedis = pool.getResource();
try {
jedis.rpush(getQueueKey(task), request.getUrl());
if (request.getExtras() != null) {
if (CheckForAdditionalInfo(request)) {
String field = DigestUtils.shaHex(request.getUrl());
String value = JSON.toJSONString(request);
jedis.hset((ITEM_PREFIX + task.getUUID()), field, value);
Expand All @@ -70,6 +71,33 @@ protected void pushWhenNoDuplicate(Request request, Task task) {
}
}

private boolean CheckForAdditionalInfo(Request request) {
if (request == null) {
return false;
}

if (!request.getHeaders().isEmpty() || !request.getCookies().isEmpty()) {
return true;
}

if (StringUtils.isNotBlank(request.getCharset()) || StringUtils.isNotBlank(request.getMethod())) {
return true;
}

if (request.isBinaryContent() || request.getRequestBody() != null) {
return true;
}

if (request.getExtras() != null && !request.getExtras().isEmpty()) {
return true;
}
if (request.getPriority() != 0L) {
return true;
}

return false;
}

@Override
public synchronized Request poll(Task task) {
Jedis jedis = pool.getResource();
Expand All @@ -85,7 +113,7 @@ public synchronized Request poll(Task task) {
Request o = JSON.parseObject(new String(bytes), Request.class);
return o;
}
Request request = new Request(url);
Request request = new Request(url);
return request;
} finally {
pool.returnResource(jedis);
Expand All @@ -100,8 +128,7 @@ protected String getQueueKey(Task task) {
return QUEUE_PREFIX + task.getUUID();
}

protected String getItemKey(Task task)
{
protected String getItemKey(Task task) {
return ITEM_PREFIX + task.getUUID();
}

Expand Down