• 设为首页
  • 点击收藏
  • 手机版
    手机扫一扫访问
    迪恩网络手机版
  • 关注官方公众号
    微信扫一扫关注
    迪恩网络公众号

Golang page.Page类代码示例

原作者: [db:作者] 来自: [db:来源] 收藏 邀请

本文整理汇总了Golang中git/oschina/net/ciweilao/game_spider/git/page.Page的典型用法代码示例。如果您正苦于以下问题:Golang Page类的具体用法?Golang Page怎么用?Golang Page使用的例子?那么恭喜您, 这里精选的类代码示例或许可以为您提供帮助。



在下文中一共展示了Page类的7个代码示例,这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞,您的评价将有助于我们的系统推荐出更棒的Golang代码示例。

示例1: downloadHtml

func (this *HttpDownLoader) downloadHtml(p *page.Page, req *page.Request) *page.Page {
	p, destBody := this.downloadFile(p, req)
	if !p.IsSucc() {
		return p
	}
	p.SetBody(destBody)
	return p
}
开发者ID:dulumao,项目名称:game_spider,代码行数:8,代码来源:downloader_http.go


示例2: downloadFile

//下载文件,并对字符编码做相应的处理
func (this *HttpDownLoader) downloadFile(p *page.Page, req *page.Request) (*page.Page, string) {
	var err error
	var httpResp *http.Response
	var urlStr string
	var method string
	urlStr = req.GetUrl()
	if len(urlStr) == 0 {
		logs.GetFirstLogger().Error("url is empty")
		p.SetStatus(true, "url is empty")
		return p, ""
	}

	method = req.GetMethod()

	if method == "POST" {
		httpResp, err = http.Post(req.GetUrl(), "application/x-www-form-urlencoded", strings.NewReader(req.GetPostData()))
	} else {
		httpResp, err = http.Get(req.GetUrl())
	}

	if err != nil {
		logs.GetFirstLogger().Error("http visit error :" + err.Error())
		p.SetStatus(true, err.Error())
	}
	p.SetHeader(httpResp.Header)
	p.SetCookies(httpResp.Cookies())
	body, _ := ioutil.ReadAll(httpResp.Body)
	bodyStr := string(body)
	defer httpResp.Body.Close()
	return p, bodyStr
}
开发者ID:dulumao,项目名称:game_spider,代码行数:32,代码来源:downloader_http.go


示例3: parseNewsLinkListInfo

func (this *YouxiduoProcesser) parseNewsLinkListInfo(content string, p *page.Page) *page.Page {
	//println("B LINK URLS")
	if p.IsBreak() {
		return p
	}
	reg, _ := regexp.Compile(`<a href(.)*<\/a>`)
	urlStr := reg.FindAllString(content, -1)
	for _, tmp := range urlStr {
		var pos1 int = strings.Index(tmp, "href=")
		var pos2 int = strings.Index(tmp, ">")
		if (pos2 - 1) > (pos1 + 6) {
			tmp = string(tmp[pos1+6 : pos2-1])
			if strings.Index(tmp, "http://") >= 0 {
				continue
			}
			tmp = util.GetRealUrl(p.GetRequest().GetUrl(), tmp)
			p.AddNewUrl(tmp, "list")
			//	println("list url = " + tmp)
		}
	}
	//println("E LINK URLS")
	return p
}
开发者ID:dulumao,项目名称:game_spider,代码行数:23,代码来源:main.go


示例4: parseNewsBreifInfo

func (this *YouxiduoProcesser) parseNewsBreifInfo(content string, p *page.Page) *page.Page {
	logs.GetFirstLogger().Trace("B TEST LIST ITEMS")
	var pos1 int = strings.Index(content, "<li>")
	var pos2 int = strings.Index(content, "</li>")
	var count int = 1

	for pos1 >= 0 && pos2 >= 0 && (pos2 > pos1) {
		item := page.NewPageItems("")
		tmpStr := string(content[pos1 : pos2+5])
		content = string(content[pos2+5 : len(content)])

		pos1 = strings.Index(content, "<li>")
		pos2 = strings.Index(content, "</li>")
		logs.GetFirstLogger().Trace("B================>")
		reg, _ := regexp.Compile(`<span>(.)*[\d]{4}-[\d]{2}-[\d]{2}`)
		timeStr := reg.FindString(tmpStr)
		reg, _ = regexp.Compile(`[\d]{4}-[\d]{2}-[\d]{2}`)
		timeStr = reg.FindString(timeStr)
		if this.exitDate > timeStr {
			p.SetBreak(true)
			continue
		}
		item.AddItem("time", timeStr)

		reg, _ = regexp.Compile("title=\"(.)*\"")
		title := reg.FindString(tmpStr)
		title = string(title[strings.Index(title, "\"")+1 : len(title)])
		title = string(title[0:strings.Index(title, "\"")])
		logs.GetFirstLogger().Trace("title = " + title)
		//p.AddResultItem("title", title)
		item.AddItem("title", title)
		reg, _ = regexp.Compile("<img src=(.)*alt")
		pic := reg.FindString(tmpStr)
		pic = string(pic[strings.Index(pic, "\"")+1 : len(pic)])
		pic = string(pic[0:strings.Index(pic, "\"")])

		if util.IsRelativePath(pic) {
			pic = util.GetRealUrl(p.GetRequest().GetUrl(), pic)
		}
		logs.GetFirstLogger().Trace("pic = " + pic)
		//p.AddResultItem("pic", pic)
		item.AddItem("pic", pic)

		reg, _ = regexp.Compile("<p>(.)*</p>")
		info := reg.FindString(tmpStr)
		logs.GetFirstLogger().Trace("info = " + info)
		//p.AddResultItem("info", info)
		info = strings.Replace(info, "'", "\"", -1)
		info = strings.Replace(info, "&#39;", "\"", -1)

		item.AddItem("info", info)

		reg, _ = regexp.Compile("<span(.)*<a(.)*</span>")
		detailurl := reg.FindString(tmpStr)
		reg, _ = regexp.Compile("href(.)*\">")
		detailurl = reg.FindString(detailurl)
		detailurl = detailurl[strings.Index(detailurl, "\"")+1 : len(detailurl)]
		detailurl = detailurl[0:strings.Index(detailurl, "\"")]
		logs.GetFirstLogger().Trace("detailurl = " + detailurl)
		//p.AddResultItem("detailurl", detailurl)
		item.AddItem("detailurl", detailurl)
		//p.AddResultItem("key", detailurl)
		item.SetKey(detailurl)
		p.AddNewUrl(detailurl, "content")

		logs.GetFirstLogger().Trace("E================>")
		logs.GetFirstLogger().Tracef("count = %d", count)
		count = count + 1
		logs.GetFirstLogger().Warn(title)

		pos1 = strings.Index(content, "<li>")
		pos2 = strings.Index(content, "</li>")
		p.AddPageItems(item)
	}

	return p
}
开发者ID:dulumao,项目名称:game_spider,代码行数:77,代码来源:main.go


示例5: Process

func (this *YouxiduoProcesser) Process(p *page.Page) {
	if !p.IsSucc() {
		println(p.GetErrMsg())
		return
	}
	var body string = p.GetBody()
	var urlTag string = p.GetRequest().GetUrlTag()
	p.SetUrlTag(urlTag)
	//分析这个页面是LIST页面还是内容页面
	// <div class="infroList"><ul><li>...</div>===>LIST
	// <div class="pagebreak">...</div>===>LIST
	// CONTENT
	//<div class="article"

	if urlTag == "list" {
		//
		//1.寻找news-brief的content
		regList, err := regexp.Compile(`<div class=\"infroList\">(\s|.)*<\/ul>(\s|.)*<div class=\"pagebreak\">`)
		if err != nil {
			logs.GetFirstLogger().Error("分析页面出错,正则表达式错误了,url = " + p.GetRequest().GetUrl())
		}
		var infroList []string = regList.FindAllString(body, -1)

		if len(infroList) > 0 {
			this.parseNewsBreifInfo(infroList[0], p)
		} else {
			logs.GetFirstLogger().Info("No more list items")
		}
		//先寻找额外的LIST页面
		if !p.IsBreak() {
			regPageBreak, err := regexp.Compile(`<div class=\"pagebreak\">(\s|.)+<li class=\"lastPage\">`)
			if err != nil {
				logs.GetFirstLogger().Error("分析页面出错,翻页正则表达式错误,url = " + p.GetRequest().GetUrl())
			}
			var pageBreakList []string = regPageBreak.FindAllString(body, -1)
			if len(pageBreakList) > 0 {
				this.parseNewsLinkListInfo(pageBreakList[0], p)
			} else {
				logs.GetFirstLogger().Info("No more links")
			}

		}

	} else {
		//CONTENT
		this.parseNewsDetail(body, p)
	}

}
开发者ID:dulumao,项目名称:game_spider,代码行数:49,代码来源:main.go


示例6: parseNewsDetail

func (this *YouxiduoProcesser) parseNewsDetail(content string, p *page.Page) *page.Page {
	logs.GetFirstLogger().Trace("B TEST ARTICLE")
	//println(content)
	//tile , 不用考虑,在前面已经获取过了
	item := page.NewPageItems(p.GetRequest().GetUrl())
	reg, _ := regexp.Compile(`<div><span><em(.)*<\/span></div>`)
	newssrc := reg.FindString(content)

	//news_src,新闻来源
	reg, _ = regexp.Compile(`<a(.)*<\/a>`)
	newssrc = reg.FindString(newssrc)
	newssrc = newssrc[strings.Index(newssrc, ">")+1 : len(newssrc)]
	if strings.Index(newssrc, "<") >= 0 {
		newssrc = newssrc[0:strings.Index(newssrc, "<")]
	}

	logs.GetFirstLogger().Trace("newssrc = " + newssrc)
	//p.AddResultItem("news_src", newssrc)
	item.AddItem("news_src", newssrc)
	//news_content,新闻内容
	reg, _ = regexp.Compile(`<div class=\"artCon\">(.|\s)*<\/div>(\s)*<div class=\"pagebreak\"`)
	news := reg.FindString(content)
	if len(news) > 0 {
		pbIndex := strings.Index(news, "<div class=\"pagebreak\"")
		if pbIndex > 0 {
			news = news[0:pbIndex]
		}

	}
	newsIndex1 := strings.Index(news, ">")
	newsIndex2 := strings.Index(news, "</div>")
	if newsIndex1 >= 0 && newsIndex2 >= 0 {
		news = news[newsIndex1+1 : newsIndex2]
	}

	//p.AddResultItem("news_content", news)
	news = strings.Replace(news, "'", "\"", -1)
	news = strings.Replace(news, "&#39;", "\"", -1)
	//	imgSrcIndex := strings.Index(news, "<img src=\"/")
	//	if imgSrcIndex >= 0 {
	//		news = strings.Replace(news, "<img src=\"/", "<img src=\""+util.GetUrlDomain(p.GetRequest().GetUrl())+"/", -1)
	//	}
	////////////////////
	imgSrcIndex := strings.Index(news, "<img ")
	if imgSrcIndex >= 0 {
		news = strings.Replace(news, "<img src=\"/", "<img src=\""+util.GetUrlDomain(p.GetRequest().GetUrl())+"/", -1)
		news = strings.Replace(news, "<img alt=\"[^\"]\" src=\"/", "<img src=\""+util.GetUrlDomain(p.GetRequest().GetUrl())+"/", -1)
		//println(news_content)

		//	println("===============")
		reg, _ = regexp.Compile(`<img[^>]*>`)
		imgList := reg.FindAllString(news, -1)
		for _, img := range imgList {
			//strings.Replace(news_content, img)
			//println("old img ==>" + img)
			newImg := img
			styleIndex := strings.Index(newImg, "style=\"")
			if styleIndex >= 0 {
				styleStr := newImg[styleIndex+len("style=\""):]
				endIndex := strings.Index(styleStr, "\"")
				if endIndex > 0 {
					styleStr = styleStr[0:endIndex]
				}
				newstyleStr := changeImgSize(styleStr)
				newImg = strings.Replace(img, styleStr, newstyleStr, -1)

			} else {
				//找width,找height
				reg2, _ := regexp.Compile(`width=\"[0-9]+\"`)
				tmpWidthStr := reg2.FindString(img)

				reg2, _ = regexp.Compile(`height=\"[0-9]+\"`)
				tmpHeightStr := reg2.FindString(img)
				//println("tmp height str = " + tmpHeightStr)
				var f float32 = 1.0
				if len(tmpWidthStr) > 0 {
					tmpStr1 := tmpWidthStr[strings.Index(tmpWidthStr, "\"")+1:]
					tmpStr1 = tmpStr1[0:strings.Index(tmpStr1, "\"")]

					tmpWidth, _ := strconv.Atoi(tmpStr1)
					if tmpWidth > 360 {
						f = float32(tmpWidth) / 360.0
						if len(tmpHeightStr) > 0 {
							tmpStr2 := tmpHeightStr[strings.Index(tmpHeightStr, "\"")+1:]
							tmpStr2 = tmpStr2[0:strings.Index(tmpStr2, "\"")]
							tmpHeight, _ := strconv.Atoi(tmpStr2)

							newImg = strings.Replace(img, tmpWidthStr, "width=\"360\"", -1)
							tmpHeight = int(float32(tmpHeight) / f)
							newImg = strings.Replace(newImg, tmpHeightStr, "height=\""+strconv.Itoa(tmpHeight)+"\"", -1)

						} else {
							newImg = strings.Replace(img, tmpWidthStr, "width=\"360\"", -1)
						}

					}
				}

			}

//.........这里部分代码省略.........
开发者ID:dulumao,项目名称:game_spider,代码行数:101,代码来源:main.go


示例7: pageProcess

func (this *Spider) pageProcess(req *page.Request) {
	var p *page.Page
	//下载页面
	for i := 0; i < 3; i++ {
		p = this.m_downLoader.DownLoad(req)
		if p.IsSucc() {
			break
		}
		time.Sleep(time.Microsecond * 1000)
	}

	if !p.IsSucc() {
		this.finishForReqProcesser(req.GetUrl())
		return
	}

	//分析页面内容
	this.m_pageProcesser.Process(p)

	//获取新的链接
	if p.CountNewUrls() > 0 {
		newUrls := p.GetNewUrls()
		for tmpUrl, tmpUrlTag := range newUrls {
			this.AddUrl(tmpUrl, "html", tmpUrlTag)
		}
	}

	this.finishForReqProcesser(req.GetUrl())

	//输出
	for _, tmpOut := range this.m_outputs {
		tmpOut.Process(p.GetPageItemsList(), p.GetRequest().GetUrl())
	}

}
开发者ID:dulumao,项目名称:game_spider,代码行数:35,代码来源:spider.go



注:本文中的git/oschina/net/ciweilao/game_spider/git/page.Page类示例整理自Github/MSDocs等源码及文档管理平台,相关代码片段筛选自各路编程大神贡献的开源项目,源码版权归原作者所有,传播和使用请参考对应项目的License;未经允许,请勿转载。


鲜花

握手

雷人

路过

鸡蛋
该文章已有0人参与评论

请发表评论

全部评论

专题导读
上一篇:
Golang log.Infof函数代码示例发布时间:2022-05-24
下一篇:
Golang testUtil.IsNil函数代码示例发布时间:2022-05-24
热门推荐
热门话题
阅读排行榜

扫描微信二维码

查看手机版网站

随时了解更新最新资讯

139-2527-9053

在线客服(服务时间 9:00~18:00)

在线QQ客服
地址:深圳市南山区西丽大学城创智工业园
电邮:jeky_zhao#qq.com
移动电话:139-2527-9053

Powered by 互联科技 X3.4© 2001-2213 极客世界.|Sitemap