Thanks to visit codestin.com
Credit goes to github.com

Skip to content

Commit 6d7d3c2

Browse files
committed
可以配置最多包含多少链接
1 parent f2cc713 commit 6d7d3c2

File tree

2 files changed

+3
-1
lines changed

2 files changed

+3
-1
lines changed

config/env.sample.ini

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -86,6 +86,7 @@ project_url = xxx
8686
article_title_pattern = xxx
8787
preset_users = xx
8888
preset_uids = x
89+
contain_link = x
8990

9091
[search]
9192
engine_url = http://127.0.0.1:7070/solr/studygolang

src/logic/article.go

Lines changed: 2 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -17,6 +17,7 @@ import (
1717
"time"
1818

1919
"github.com/PuerkitoBio/goquery"
20+
"github.com/polaris1119/config"
2021
"github.com/polaris1119/goutils"
2122
"github.com/polaris1119/logger"
2223
"github.com/polaris1119/set"
@@ -161,7 +162,7 @@ func (self ArticleLogic) ParseArticle(ctx context.Context, articleUrl string, au
161162
return nil, errors.New("content is short")
162163
}
163164

164-
if auto && strings.Count(content, "<a") > 10 {
165+
if auto && strings.Count(content, "<a") > config.ConfigFile.MustInt("crawl", "contain_link", 10) {
165166
logger.Errorln(articleUrl, "content contains too many link!")
166167
return nil, errors.New("content contains too many link")
167168
}

0 commit comments

Comments
 (0)