// Parse html dom here and record the parse result that we want to crawl.
// Package simplejson (https://github.com/bitly/go-simplejson) is used to parse data of json.
func (this *MyPageProcesser) Process(p *robot.Page) {
if !p.IsSucc() {
println(p.Errormsg())
return
}
query := p.GetJson()
status, err := query.GetPath("result", "status", "code").Int()
if status != 0 || err != nil {
log.Panicf("page is crawled error : errorinfo=%s : status=%d : startNewsId=%d", err.Error(), status, this.startNewsId)
}
num, err := query.GetPath("result", "pageStr", "pageSize").Int()
if num == 0 || err != nil {
// Add url of next crawl
startIdstr := strconv.Itoa(this.startNewsId)
p.AddTargetRequest("http://live.sina.com.cn/zt/api/l/get/finance/globalnews1/index.htm?format=json&id="+startIdstr+"&pagesize=10&dire=f", "json")
return
}
var idint, nextid int
var nextidstr string
query = query.Get("result").Get("data")
for i := 0; i < num; i++ {
id, err := query.GetIndex(i).Get("id").String()
if id == "" || err != nil {
continue
}
idint, err = strconv.Atoi(id)
if err != nil {
continue
}
if idint <= this.startNewsId {
break
}
if i == 0 {
nextid = idint
nextidstr = id
}
content, err := query.GetIndex(i).Get("content").String()
if content == "" || err != nil {
continue
}
time, err := query.GetIndex(i).Get("created_at").String()
if err != nil {
continue
}
p.AddField(id+"_id", id)
p.AddField(id+"_content", content)
p.AddField(id+"_time", time)
}
// Add url of next crawl
this.startNewsId = nextid
p.AddTargetRequest("http://live.sina.com.cn/zt/api/l/get/finance/globalnews1/index.htm?format=json&id="+nextidstr+"&pagesize=10&dire=f", "json")
//println(p.GetTargetRequests())
}
//主页解析
func (self *Www79xsComProcessor) mainParse(p *robot.Page) {
//开始解析页面
query := p.GetHtmlParser()
query.Find(".subnav ul li a").Each(func(i int, s *goquery.Selection) {
addr, _ := s.Attr("href")
if addr == utils.GirlUrl {
p.AddTargetRequest(utils.InitRequest(utils.BaseUrl+addr, map[string]string{"first": utils.GIRL}, self.urlListParse))
} else {
p.AddTargetRequest(utils.InitRequest(utils.BaseUrl+addr, map[string]string{"first": utils.BOY}, self.urlListParse))
}
})
}
//解析小说详情页
func (self *Www79xsComProcessor) introParse(p *robot.Page) {
meta := p.GetRequest().GetMeta().(map[string]string)
//开始解析页面
query := p.GetHtmlParser()
intro := query.Find("#info h3 p").Eq(1).Text()
img, _ := query.Find(".img img").Attr("src")
// 小说章节列表地址
chaptersource, _ := query.Find(".b1 a").Attr("href")
tmp := utils.MapCopy(meta)
tmp["introduction"] = intro
tmp["img"] = utils.BaseUrl + img
tmp["chaptersource"] = utils.BaseUrl + chaptersource
p.AddTargetRequest(utils.InitRequest(utils.BaseUrl+chaptersource, tmp, self.chaperParse))
}
//小说章节解析
func (self *Www79xsComProcessor) chaperParse(p *robot.Page) {
meta := p.GetRequest().GetMeta().(map[string]string)
//开始解析页面
query := p.GetHtmlParser()
query.Find(".insert_list li").Each(func(i int, s *goquery.Selection) {
tmp := utils.MapCopy(meta)
tmp["chapter"] = strconv.Itoa(i)
tmp["subtitle"] = s.Find("strong a").Text()
addr, _ := s.Find("strong a").Attr("href")
tmp["contenturl"] = p.GetRequest().GetBaseUrl() + addr
//检测contenturl, 如果数据库中存在，则跳过本次抓取，如果不存在则将url加入调度队列
//这个需求有时间再做
if len(tmp["subtitle"]) != 0 {
p.AddTargetRequest(utils.InitRequest(tmp["contenturl"], tmp, self.contentParse))
}
})
}
//分类列表解析
func (self *Www79xsComProcessor) classParse(p *robot.Page) {
meta := p.GetRequest().GetMeta().(map[string]string)
//开始解析页面
query := p.GetHtmlParser()
query.Find("div .yl_nr_lt2 ul").Each(func(i int, s *goquery.Selection) {
//获取二级分类, 小说标题，作者
second := s.Find(".ynl2 a").Text()
title := s.Find(".ynl3 a").Eq(1).Text()
author := s.Find(".ynl6 a").Text()
novelsource := utils.BaseUrl + func() string {
addr, _ := s.Find(".ynl3 a").Eq(1).Attr("href")
return addr
}()
tmp := make(map[string]string)
tmp["first"] = meta["first"]
tmp["second"] = second
tmp["title"] = title
tmp["author"] = author
tmp["novelsource"] = novelsource
p.AddTargetRequest(utils.InitRequest(novelsource, tmp, self.introParse))
})
}
//获取分类页面的url list，并解析
func (self *Www79xsComProcessor) urlListParse(p *robot.Page) {
meta := p.GetRequest().GetMeta()
//开始解析页面
query := p.GetHtmlParser()
//获取尾页addr
lastaddr, ok := query.Find("tbody a").Last().Attr("href")
if ok {
//解析addr
kv := goutils.GetKVInRelaPath(lastaddr)
//url拼接
maxpage, _ := strconv.Atoi(kv["page"])
for i := 1; i <= maxpage; i++ {
page := strconv.Itoa(i)
p.AddTargetRequest(utils.InitRequest(
"http://www.79xs.com/Book/ShowBookList.aspx?tclassid="+kv["tclassid"]+"&page="+page,
meta.(map[string]string),
self.classParse))
}
} else {
p.AddTargetRequest(utils.InitRequest(p.GetRequest().GetUrl(), meta.(map[string]string), self.classParse))
}
}