func (s *Searcher) GetDataFromPage(urlName string, spider *configure.Spider) (KeyData, error) {
if urlName == "" {
return nil, fmt.Errorf("URL's name can't empty!")
}
// contentName is a slice
contentNames := spider.GetContentNames(urlName)
// 初始化用于保存结果的map
data := make(KeyData, len(contentNames))
for _, name := range contentNames {
// 获取每一个名字对应的正则表达式
re := spider.GetContentValue(urlName, name)
// 将匹配到的内容匹配到对应的名称下
data[name] = re.FindAllStringSubmatch(s.Html, -1)
}
return data, nil
}
// 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
}
