// 从页面中获取指定的URL
func (s *Searcher) GetURLsFromPage(spider *configure.Spider) error {
if s.Html == "" {
return fmt.Errorf("Please get Html source first!")
}
urlnames := spider.GetURLName()
if len(urlnames) == 0 {
return fmt.Errorf("URL is empty!")
}
s.Urls = make(map[string][]string, len(urlnames))
for _, name := range urlnames {
// 忽略slice中可能产生的气泡
if name == "" {
continue
}
re := spider.GetURLByName(name)
if re == nil {
return fmt.Errorf("There is nothing in ", name)
}
s.Urls[name] = re.FindAllString(s.Html, -1)
}
return nil
}
