avg3.2msperarticle,accuracy>=98%(对比其他开源实现,可能是目前最快的html2article实现,我们测试的数据集约3kw来自于微信公众号,各大类中文科技媒体历史文章,目前能达到98%以上准确率)
Examples参考examples from_url.go
package mainimport ("github.com/sundy-li/html2article")func main() {article, err := html2article.FromUrl("https://www.leiphone.com/news/201602/DsiQtR6c1jCu7iwA.html")if err != nil {panic(err)}println("article title is =>", article.Title)println("article publishtime is =>", article.Publishtime)println("article content is =>", article.Content)}Algorithm参考论文
Java实现
评论