Browse Source

Merge pull request '延长抓取时间' (#68) from xmz_weibo_demo into master

Reviewed-on: #68
pull/77/head
longchao 3 days ago
parent
commit
85f2718fb3
  1. 2
      model/mSpider.php
  2. 9
      queue/deal/spider_weibo_comment.php

2
model/mSpider.php

@ -365,7 +365,7 @@ class mSpider extends mBase {
} }
public function requestComment($uid, $url, $headers) { public function requestComment($uid, $url, $headers) {
$res = $this->getRequest($url, $headers, 10, true); $res = $this->getRequest($url, $headers, 40, true);
if (strpos($res, '登录 - 微博')) { if (strpos($res, '登录 - 微博')) {
$this->setError('cookie失效'); $this->setError('cookie失效');
return false; return false;

9
queue/deal/spider_weibo_comment.php

@ -68,18 +68,19 @@ class spiderWeiboComment extends dealBase {
$obj->writeLog(ZHISHIKU_SPIDER_LOG, ZHISHIKU_SPIDER_COMMENT, '队列评论抓取失败,重试中:'.$error.'|'.$baselog); $obj->writeLog(ZHISHIKU_SPIDER_LOG, ZHISHIKU_SPIDER_COMMENT, '队列评论抓取失败,重试中:'.$error.'|'.$baselog);
if($error == 'cookie失效') { if($error == 'cookie失效') {
$rdobj->rpush($this->task_key, json_encode($rq_data)); $rdobj->lpush($this->task_key, json_encode($rq_data));
unset($cookie_data[PROC_CODE]); unset($cookie_data[PROC_CODE]);
$rdobj->set(_RC_WEIBO_LOGIN_COOKIE2, json_encode($cookie_data)); $rdobj->set(_RC_WEIBO_LOGIN_COOKIE2, json_encode($cookie_data));
if ($obj->is_change_ip && PROC_CODE == 0) $rdobj->del(_RC_SPIDER_WEIBO_COMMENT_USE_IP); if ($obj->is_change_ip && PROC_CODE == 0) $rdobj->del(_RC_SPIDER_WEIBO_COMMENT_USE_IP);
$obj->sendMail(array('1432334894@qq.com'), date('Y年m月d日', time()) . '-微博评论数据抓取', $error); $obj->sendMail(array('1432334894@qq.com'), date('Y年m月d日', time()) . '-微博评论数据抓取', $error);
sleep(10);
// $rdobj->del($this->task_key); // $rdobj->del($this->task_key);
// $rdobj->del(_RS_SPIDER_WEIBO_COMMENT); // $rdobj->del(_RS_SPIDER_WEIBO_COMMENT);
exit; exit;
} }
$rdobj->rpush($this->task_key, json_encode($rq_data)); $rdobj->lpush($this->task_key, json_encode($rq_data));
if ($obj->is_change_ip && PROC_CODE == 0) $rdobj->del(_RC_SPIDER_WEIBO_COMMENT_USE_IP); if ($obj->is_change_ip && PROC_CODE == 0) $rdobj->del(_RC_SPIDER_WEIBO_COMMENT_USE_IP);
sleep(30); sleep(30);
@ -98,7 +99,7 @@ class spiderWeiboComment extends dealBase {
} }
if(!$res['is_load_all']) { if(!$res['is_load_all']) {
$rdobj->rpush($this->task_key, json_encode($res)); $rdobj->lpush($this->task_key, json_encode($res));
return true; return true;
} }
@ -112,7 +113,7 @@ class spiderWeiboComment extends dealBase {
$obj->writeLog(ZHISHIKU_SPIDER_LOG, ZHISHIKU_SPIDER_COMMENT, '抓取成功:'.$baselog); $obj->writeLog(ZHISHIKU_SPIDER_LOG, ZHISHIKU_SPIDER_COMMENT, '抓取成功:'.$baselog);
$rdobj->sRem(_RS_SPIDER_WEIBO_COMMENT, $weibo_id); $rdobj->sRem(_RS_SPIDER_WEIBO_COMMENT, $weibo_id);
sleep(2); sleep(4);
return true; return true;
} }

Loading…
Cancel
Save