|
|
@@ -670,6 +670,7 @@ func BodyAnalysis2(body string) (expertNumStr, expertContentStr, interviewDateSt
|
|
|
if len(expertContentArr) > 0 {
|
|
|
expertContentStr = expertContentArr[0]
|
|
|
}
|
|
|
+ //当处理过之后的专家背景长度大于600的时候，说明他的格式跟之前的不一样，还要做二次处理 600 是一个约值，先运行看看
|
|
|
if len(expertContentStr) > 600 {
|
|
|
strnum := strings.Index(expertContentStr, "#专家评价：")
|
|
|
content := expertContentStr[strnum:len(expertContentStr)]
|
|
|
@@ -686,12 +687,12 @@ func BodyAnalysis2(body string) (expertNumStr, expertContentStr, interviewDateSt
|
|
|
var hrefRegexp = regexp.MustCompile("(?m)<a.*?[^<]>.*?</a>")
|
|
|
match := hrefRegexp.FindAllString(body, -1)
|
|
|
if match != nil {
|
|
|
- for k, v := range match {
|
|
|
- if k == 0 && strings.Index(v, ".pdf") > 0 {
|
|
|
- numStar := strings.Index(v, "http")
|
|
|
- numEnd := strings.Index(v, ".pdf")
|
|
|
- fileLink = v[numStar : numEnd+4]
|
|
|
- }
|
|
|
+ for _, v := range match {
|
|
|
+ //if k == 0 && strings.Index(v, ".pdf") > 0 {
|
|
|
+ // numStar := strings.Index(v, "http")
|
|
|
+ // numEnd := strings.Index(v, ".pdf")
|
|
|
+ // fileLink = v[numStar : numEnd+4]
|
|
|
+ //}
|
|
|
//处理a标签中的PDF
|
|
|
numStarAcount := strings.Index(v, "<a")
|
|
|
numEndAcount := strings.Index(v, "<img")
|
xingzai