示例#1
0
文件: github.go 项目: aosen/spiders
// Parse html dom here and record the parse result that we want to Page.
// Package goquery (http://godoc.org/github.com/PuerkitoBio/goquery) is used to parse html.
func (this *MyPageProcesser) Process(p *robot.Page) {
	if !p.IsSucc() {
		println(p.Errormsg())
		return
	}

	query := p.GetHtmlParser()
	var urls []string
	query.Find("h3[class='repo-list-name'] a").Each(func(i int, s *goquery.Selection) {
		href, _ := s.Attr("href")
		urls = append(urls, "http://github.com/"+href)
	})
	// these urls will be saved and crawed by other coroutines.
	p.AddTargetRequests(urls, "html")

	name := query.Find(".entry-title .author").Text()
	name = strings.Trim(name, " \t\n")
	repository := query.Find(".entry-title .js-current-repository").Text()
	repository = strings.Trim(repository, " \t\n")
	//readme, _ := query.Find("#readme").Html()
	if name == "" {
		p.SetSkip(true)
	}
	// the entity we want to save by Pipeline
	p.AddField("author", name)
	p.AddField("project", repository)
	//p.AddField("readme", readme)
}
示例#2
0
文件: weixin.go 项目: aosen/spiders
// Parse html dom here and record the parse result that we want to Page.
// Package goquery (http://godoc.org/github.com/PuerkitoBio/goquery) is used to parse html.
func (this *MyPageProcesser) Process(p *robot.Page) {
	if !p.IsSucc() {
		println(p.Errormsg())
		return
	}

	query := p.GetHtmlParser()

	query.Find(`div[class="wx-rb bg-blue wx-rb_v1 _item"]`).Each(func(i int, s *goquery.Selection) {
		name := s.Find("div.txt-box > h3").Text()
		href, _ := s.Attr("href")

		fmt.Printf("WeName:%v link:http://http://weixin.sogou.com%v \r\n", name, href)
		// the entity we want to save by Pipeline
		p.AddField("name", name)
		p.AddField("href", href)
	})

	next_page_href, _ := query.Find("#sogou_next").Attr("href")
	if next_page_href == "" {
		p.SetSkip(true)
	} else {
		p.AddTargetRequestWithHeaderFile("http://weixin.sogou.com/weixin"+next_page_href, "html", "weixin.sogou.com.json")
	}

}
示例#3
0
文件: process.go 项目: aosen/robot
//小说内容解析
func (self *Www79xsComProcessor) contentParse(p *robot.Page) {
	meta := p.GetRequest().GetMeta().(map[string]interface{})
	//开始解析页面
	query := p.GetHtmlParser()
	html, _ := query.Find(".contentbox").Html()
	meta["content"] = strings.Replace(strings.Replace(html, "<br/><br/>", "\n", -1), "<br/>", "\n", -1)
	p.AddField("code", "0")
	for k, v := range meta {
		p.AddField(k, v.(string))
	}
}
示例#4
0
文件: process.go 项目: kjfcpua/robot
//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))
		}
	})
}
示例#5
0
文件: process.go 项目: kjfcpua/robot
//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))
}
示例#6
0
文件: mgo.go 项目: aosen/robot
func (self *MyProcessor) Process(p *robot.Page) {
	if !p.IsSucc() {
		mlog.LogInst().LogError(p.Errormsg())
		return
	}

	u, err := url.Parse(p.GetRequest().GetUrl())
	if err != nil {
		mlog.LogInst().LogError(err.Error())
		return
	}
	if !strings.HasSuffix(u.Host, "jiexieyin.org") {
		return
	}

	var urls []string
	query := p.GetHtmlParser()

	query.Find("a").Each(func(i int, s *goquery.Selection) {
		href, _ := s.Attr("href")
		reJavascript := regexp.MustCompile("^javascript\\:")
		reLocal := regexp.MustCompile("^\\#")
		reMailto := regexp.MustCompile("^mailto\\:")
		if reJavascript.MatchString(href) || reLocal.MatchString(href) || reMailto.MatchString(href) {
			return
		}

		//处理相对路径
		var absHref string
		urlHref, err := url.Parse(href)
		if err != nil {
			mlog.LogInst().LogError(err.Error())
			return
		}
		if !urlHref.IsAbs() {
			urlPrefix := p.GetRequest().GetUrl()
			absHref = urlPrefix + href
			urls = append(urls, absHref)
		} else {
			urls = append(urls, href)
		}

	})

	p.AddTargetRequests(initrequests(urls))
	p.AddField("test1", p.GetRequest().GetUrl())
	p.AddField("test2", p.GetRequest().GetUrl())
}
示例#7
0
文件: process.go 项目: kjfcpua/robot
//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))
		}
	})
}
示例#8
0
文件: process.go 项目: kjfcpua/robot
//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))
	})
}
示例#9
0
文件: process.go 项目: kjfcpua/robot
//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))
	}
}
示例#10
0
文件: sohujson.go 项目: aosen/spiders
func (this MyPageProcesser) Process(p *robot.Page) {
	query := p.GetHtmlParser()

	if p.GetUrlTag() == "index" {
		query.Find(`div[class="main area"] div[class="lc"] ul li a`).Each(func(i int, s *goquery.Selection) {
			url, isExsit := s.Attr("href")
			if isExsit {
				reg := regexp.MustCompile(`^do not know what is this`)
				var fmtStr string
				if rxYule.MatchString(url) {
					reg = rxYule
					fmtStr = wkSohuYule
				}

				if rxPic.MatchString(url) {
					reg = rxPic
					fmtStr = wkSohuPic
				}

				regxpArrag := reg.FindStringSubmatch(url)
				if len(regxpArrag) == 2 {
					addRequest(p, "changyan", fmt.Sprintf(fmtStr, regxpArrag[1]), "", s.Text())
				}
			}
		})
	}

	if p.GetUrlTag() == "changyan" {
		jsonMap := ChangyanJson{}
		err := json.NewDecoder(strings.NewReader(p.GetBodyStr())).Decode(&jsonMap)
		if err == nil {
			content, ok := p.GetRequest().GetMeta().(string)
			if ok {
				fmt.Println("Title:", content, " CommentCount:", jsonMap.ListData.OuterCmtSum, " ParticipationCount:", jsonMap.ListData.ParticipationSum)
			}
		}
	}
}