您的位置:首页 > 编程语言 > Go语言

Go语言小爬虫--第一步

2017-01-23 15:58 459 查看
解析新浪手机新闻网页,获取5条新的新闻的url存入到数据库
package linksql

import (
"database/sql"
"log"
_"github.com/go-sql-driver/mysql"

)

func Open_url_table() *sql.DB{
db,err:=sql.Open("mysql","root:root@/mysql")
Checkerror(err)
return db
}
func Insertlink(id int,src string,url string){
db:=Open_url_table()
stmt,err1:=db.Prepare("insert into url_table(id,src,url) values(?,?,?)")
if err1!=nil{
log.Fatalln("prepare error",err1)
}
_,err2:=stmt.Exec(id,src,url)
if err2!=nil{
log.Fatalln("Exec error")
}
}

func Checkerror(err error){ //差错
if err!=nil{
log.Fatal(err)
}
}

package search_sina

import (
"net/http"
"log"
"gopkg.in/xmlpath.v2"

"test/linksql"
)

func Get_url(url string){ //找新URL
resp,err:=http.Get(url)
Checkerror(err)
root,err1:=xmlpath.ParseHTML(resp.Body)
Checkerror(err1)
path:=xmlpath.MustCompile(`//dl[@class="f_card"]/../@href`)
iter:=path.Iter(root)
i:=1
for iter.Next() && i<6{
//fmt.Println(iter.Node())
linksql.Insertlink(i,"sina",iter.Node().String())
i++
}

}
func Checkerror(err error){
if err!=nil{
log.Fatalln(err)
}
}

+----+------+-------------------------------------------------------------------------------+
| id | src  | url                                                                           |
+----+------+-------------------------------------------------------------------------------+
|  1 | sina | http://tech.sina.cn/tech_zt/meitu_ipo?vt=4&pos=18                             |
|  2 | sina | http://tech.sina.cn/i/gj/2016-12-15/detail-ifxytqav9330894.d.html?vt=4&pos=18 |
|  3 | sina | http://zhuanlan.sina.cn/article?vt=4&pos=18&id=57660&ch=tech                  |
|  4 | sina | http://tech.sina.cn/i/gj/2016-12-15/detail-ifxytqax6095612.d.html?vt=4&pos=18 |
|  5 | sina | http://tech.sina.cn/i/gj/2016-12-15/detail-ifxytqav9326149.d.html?vt=4&pos=18 |
+----+------+-------------------------------------------------------------------------------+
内容来自用户分享和网络整理,不保证内容的准确性,如有侵权内容,可联系管理员处理 点击这里给我发消息
标签:  Go