R自动数据收集第二章HTML笔记2(主要关于htmlTreeParse函数)
function (file, ignoreBlanks = TRUE, handlers = NULL, replaceEntities = FALSE,asText = FALSE, trim = TRUE, validate = FALSE, getDTD = TRUE,isURL = FALSE, asTree = FALSE, addAttributeNamespaces = FALSE,useInternalNodes = FALSE, isSchema = FALSE, fullNamespaceInfo = FALSE,encoding = character(), useDotNames = length(grep("^\\.",names(handlers)))>0, xinclude = TRUE, addFinalizer = TRUE,error = htmlErrorHandler, isHTML = TRUE, options = integer(),parentFirst = FALSE){#asText=T则file作为XML文本处理isMissingAsText = missing(asText)#地址大于一个时要中止程序并抛出异常if(length(file)>1){file = paste(file, collapse ="\n")if(!missing(asText)&&!asText)stop(structure(list(message ="multiple URLs passed to xmlTreeParse. If this is the content of the file, specify asText = TRUE"),class= c("MultipleURLError","XMLParserError","simpleError","error","condition")))asText = TRUE}#当isURL非空时且是XML的时候,才修改URL为数值型#比如这里isURL=1if(missing(isURL)&&!asText)isURL <- length(grep("^(http|ftp|file)://", file, useBytes = TRUE,perl = TRUE))#isHTML 默认为 TRUEif(isHTML){validate = FALSEgetDTD = FALSEisSchema = FALSEdocClass ="HTMLInternalDocument"}else docClass = character()#checkHandlerNames返回的是一个逻辑值,其作用是checkHandlerNames(handlers,"DOM")if(missing(fullNamespaceInfo)&& inherits(handlers,"RequiresNamespaceInfo"))fullNamespaceInfo = TRUEoldValidate = xmlValidity()xmlValidity(validate)on.exit(xmlValidity(oldValidate))if(!asText && isURL == FALSE){if(file.exists(file)== FALSE)if(!missing(asText)&& asText == FALSE){e = simpleError(paste("File", file,"does not exist"))class(e)= c("FileNotFound",class(e))stop(e)}else asText <- TRUE}if(asText && length(file)>1)file = paste(file, collapse ="\n")old = setEntitySubstitution(replaceEntities)on.exit(setEntitySubstitution(old), add = TRUE)if(asText && length(grep(sprintf("^%s?\\s*<",BOMRegExp),file, perl = TRUE, useBytes = TRUE))==0){if(!isHTML ||(isMissingAsText &&!inherits(file,"AsIs"))){e = simpleError(paste("XML content does not seem to be XML:",sQuote(file)))class(e)= c("XMLInputError",class(e))(if(isHTML)warningelse stop)(e)}}if(!is.logical(xinclude)){xinclude =as.logical(xinclude)}if(!asText &&!isURL)file = path.expand(as.character(file))if(useInternalNodes && trim){prevBlanks =.Call("RS_XML_setKeepBlanksDefault",0L,PACKAGE ="XML")on.exit(.Call("RS_XML_setKeepBlanksDefault", prevBlanks,PACKAGE ="XML"), add = TRUE)}.oldErrorHandler = setXMLErrorHandler(error)on.exit(.Call("RS_XML_setStructuredErrorHandler",.oldErrorHandler,PACKAGE ="XML"), add = TRUE)if(length(options))options = sum(options)ans <-.Call("RS_XML_ParseTree",as.character(file), handlers,as.logical(ignoreBlanks),as.logical(replaceEntities),as.logical(asText),as.logical(trim),as.logical(validate),as.logical(getDTD),as.logical(isURL),as.logical(addAttributeNamespaces),as.logical(useInternalNodes),as.logical(isHTML),as.logical(isSchema),as.logical(fullNamespaceInfo),as.character(encoding),as.logical(useDotNames), xinclude, error, addFinalizer,as.integer(options),as.logical(parentFirst), PACKAGE ="XML")if(!missing(handlers)&& length(handlers)&&!as.logical(asTree))return(handlers)if(!isSchema && length(class(ans)))class(ans)= c(docClass, oldClass(class(ans)))if(inherits(ans,"XMLInternalDocument"))addDocFinalizer(ans, addFinalizer)elseif(!getDTD &&!isSchema){class(ans)= oldClass("XMLDocumentContent")}ans}<environment: namespace:XML>
#test#导包library(XML)#链接url <-"http://www.r-datacollection.com/materials/html/fortunes.html"#handers函数h2 <- list(startElement = function(node,...){name <- xmlName(node)if(name %in% c("div","title")){NULL}else{node}},comment = function(node){NULL})#正式开始,函数参数file=urlignoreBlanks = TRUEhandlers = h2replaceEntities = FALSEasText = FALSEtrim = TRUEvalidate = FALSEgetDTD = TRUEisURL = FALSEasTree = TRUEaddAttributeNamespaces = FALSEuseInternalNodes = FALSEisSchema = FALSEfullNamespaceInfo = FALSEencoding = character()useDotNames = length(grep("^\\.", names(handlers)))>0xinclude = TRUEaddFinalizer = TRUEerror = XML:::htmlErrorHandlerisHTML = TRUEoptions = integer()parentFirst = FALSE#函数体部分#asText参数没有传入#我们将其从missing(asText)改为TRUEisMissingAsText = TRUE#file的长度是否大于1,大于1如果asText未传入则要报错:传入了多个URL#不大于1,则跳过if(length(file)>1){file = paste(file, collapse ="\n")if(!missing(asText)&&!asText)stop(structure(list(message ="multiple URLs passed to xmlTreeParse. If this is the content of the file, specify asText = TRUE"),class= c("MultipleURLError","XMLParserError","simpleError","error","condition")))asText = TRUE}# 本来是if (missing(isURL) && !asText)# 我们修改为if (TURE && !asText)#isURL参数没有传递且asText参数为假才执行if(TRUE &&!asText)isURL <- length(grep("^(http|ftp|file)://", file, useBytes = TRUE,perl = TRUE))#只要有http|ftp|file中的一个协议开头,比如http://,就是URL了。# 此时isURL=1#是否为HTML,是的if(isHTML){validate = FALSEgetDTD = FALSE #从默认值T改为了FisSchema = FALSEdocClass ="HTMLInternalDocument"}else{docClass = character()}#否则创建空的# class(docClass)#返回TRUE通过检验了,否则函数会中止并抛出异常XML:::checkHandlerNames(handlers,"DOM")#fullNamespaceInfo参数whether to provide the namespace URI and prefix on each node#其实就是是否在节点面前带上URI信息#fullNamespaceInfo为空且handlers含有该属性,才执行这一步#missing(fullNamespaceInfo)被替换为TRUE#handlers并没有RequiresNamespaceInfo属性,所以不执行if( TRUE && inherits(handlers,"RequiresNamespaceInfo"))fullNamespaceInfo = TRUE#以下两行的结果都是integer(0)#奇妙~,先保存原有的配置oldValidate = XML:::xmlValidity()#当前的配置XML:::xmlValidity(validate)#还原原来的配置on.exit(XML:::xmlValidity(oldValidate))#asText为假,且isURL是假的#结果为TFALSE,我们不必管他if(!asText && isURL == FALSE){if(file.exists(file)== FALSE)#如果本地文件不存在if(!missing(asText)&& asText == FALSE){#抛出异常,文件不存在e = simpleError(paste("File", file,"does not exist"))class(e)= c("FileNotFound",class(e))stop(e)}else asText <- TRUE}#此时asText是FALSE,这个跟我们无关if(asText && length(file)>1)file = paste(file, collapse ="\n")#replaceEntities的默认值是FALSEold = XML:::setEntitySubstitution(replaceEntities)#old的值是FALSEon.exit(XML:::setEntitySubstitution(old), add = TRUE)#BOMRegExp是一个内置的常量吧#看名字应该是基于BOM的正则表达式#因为是FALSE,所以我们也先不去管它if(asText && length(grep(sprintf("^%s?\\s*<", XML:::BOMRegExp),file, perl = TRUE, useBytes = TRUE))==0){if(!isHTML ||(isMissingAsText &&!inherits(file,"AsIs"))){e = simpleError(paste("XML content does not seem to be XML:",sQuote(file)))class(e)= c("XMLInputError",class(e))(if(isHTML)warningelse stop)(e)}}#xinclude默认值是TRUE#以下三个if都是F,所以不管了if(!is.logical(xinclude)){xinclude =as.logical(xinclude)}if(!asText &&!isURL)file = path.expand(as.character(file))if(useInternalNodes && trim){prevBlanks =.Call("RS_XML_setKeepBlanksDefault",0L,PACKAGE ="XML")on.exit(.Call("RS_XML_setKeepBlanksDefault", prevBlanks,PACKAGE ="XML"), add = TRUE)}.oldErrorHandler = XML:::setXMLErrorHandler(error)#所以,这种点开头的命名是什么鬼?# class(.oldErrorHandler)# [1] "list"on.exit(.Call("RS_XML_setStructuredErrorHandler",.oldErrorHandler,PACKAGE ="XML"), add = TRUE)# length(options)是0,所以不执行if(length(options))options = sum(options)#调用一个叫做RS_XML_ParseTree的函数getAnywhere("RS_XML_ParseTree")ans <-.Call("RS_XML_ParseTree",as.character(file), handlers,as.logical(ignoreBlanks),as.logical(replaceEntities),as.logical(asText),as.logical(trim),as.logical(validate),as.logical(getDTD),as.logical(isURL),as.logical(addAttributeNamespaces),as.logical(useInternalNodes),as.logical(isHTML),as.logical(isSchema),as.logical(fullNamespaceInfo),as.character(encoding),as.logical(useDotNames), xinclude, error, addFinalizer,as.integer(options),as.logical(parentFirst), PACKAGE ="XML")print(ans)print("-------我是可爱的分割线------------------")#这里的missing(handlers)我们就不改了哈#毕竟只要有默认值,他都觉得是TRUE#和我们的确传递了处理函数的效果TRUE是一样的if(!missing(handlers)&& length(handlers)&&!as.logical(asTree))return("呵呵")if(!isSchema && length(class(ans)))class(ans)= c(docClass, oldClass(class(ans)))if(inherits(ans,"XMLInternalDocument")){addDocFinalizer(ans, addFinalizer)}elseif(!getDTD &&!isSchema){print("看我的类型")print(class(ans))class(ans)= oldClass("XMLDocumentContent")print(class(ans))}print("看条件判断的逻辑值")print("1")print(!missing(handlers)&& length(handlers)&&!as.logical(asTree))print("2")print(!isSchema && length(class(ans)))print("3")print(inherits(ans,"XMLInternalDocument"))print("4")print(!getDTD &&!isSchema)print(class(ans))ans

#例子1testMissing<-function(a=TRUE,b=FALSE){if(missing(b))return("b is missing")else"b is here "+b}testMissing(F)# [1] "b is missing"#例子2if(missing(b))return("b is missing")# Error in missing(b) : 'missing' can only be used for arguments#例子3b=NULLif(missing(b))return("b is missing")#没有输出
if(isHTML){validate = FALSEgetDTD = FALSE #从默认值T改为了FisSchema = FALSEdocClass ="HTMLInternalDocument"}else{docClass = character()}#否则创建空的
}else docClass = character()
function(){if(isHTML){validate = FALSEgetDTD = FALSE #从默认值T改为了FisSchema = FALSEdocClass ="HTMLInternalDocument"}else docClass = character()#否则创建空的}
否则,会报错:
function (handlers, id ="SAX"){if(is.null(handlers)) #为空,则返回TRUEreturn(TRUE)ids = names(handlers) #取出handlers中的函数名i = match(ids,GeneralHandlerNames) #匹配,返回逻辑值向量prob = any(!is.na(i))#任一个回空才是TRUEif(prob){warning("future versions of the XML package will require names of general handler functionsto be prefixed by a . to distinguish them from handlers for nodes with those names. This _may_ affect the ",paste(names(handlers)[!is.na(i)], collapse =", "))}#任意一个handler中的函数不是函数类型,则抛出异常if(any(w <-!sapply(handlers,is.function)))warning("some handlers are not functions: ", paste(names(handlers[w]),collapse =", "))#返回TRUE,后续代码继续运行!prob}<environment: namespace:XML>
注释3.2关于GeneralHandlerNames属性
> XML:::GeneralHandlerNames$SAX[1]"text" "startElement"[3]"endElement" "comment"[5]"startDocument" "endDocument"[7]"processingInstruction""entityDeclaration"[9]"externalEntity"$DOM[1]"text" "startElement"[3]"comment" "entity"[5]"cdata" "processingInstruction"
分别有SAX和DOM两种方式,想起学Java时的DOM和SAX解析没?
> h2 <- list(+ startElement = function(node,...){+ name <- xmlName(node)+ if(name %in% c("div","title")){NULL}else{node}+ },+ comment = function(node){NULL}+)> handlers<-h2> ids = names(handlers)> ids[1]"startElement""comment"> i = match(ids, XML:::GeneralHandlerNames)> i[1] NA NA>?matchstarting httpd help server ... done>!is.na(i)#如果i中有NA,则返回F,没有NA则返回T[1] FALSE FALSE> prob = any(!is.na(i))#当i中的任意一个元素都不是NA的时候,prob才返回T> prob[1] FALSE
match returns a vector of the positions of (first) matches of its first argument in its second.
> testMatch<-c("a","c")> testSet <- c('a','b','c')> match(testMatch,testSet)[1]13
x <-10class(x)# "numeric"oldClass(x)# NULL#看了下文档,我个人觉得oldClass是S语言的余毒啊!!!inherits(x,"a")#FALSEclass(x)<- c("a","b")# x# [1] 10# attr(,"class")# [1] "a" "b"#即,x为10这个变量被赋予了两个class,分别名为"a"和 "b"inherits(x,"a")#TRUEinherits(x,"a", TRUE)# 1inherits(x, c("a","b","c"), TRUE)# 1 2 0
#以下两行的结果都是integer(0)#奇妙~,先保存原有的配置oldValidate = XML:::xmlValidity()#使用当前的配置XML:::xmlValidity(validate)#还原on.exit(XML:::xmlValidity(oldValidate))
> XML:::xmlValidity()integer(0)> getAnywhere(xmlValidity)A single object matching ‘xmlValidity’ was foundIt was found in the following placesnamespace:XMLwith valuefunction (val = integer(0)){.Call("RS_XML_getDefaultValiditySetting",as.integer(val),PACKAGE ="XML")}<environment: namespace:XML>
on.exit records the expression given as its argument as needing to be executed when the current function exits (either naturally or as the result of an error). This is useful for resetting graphical parameters or performing other cleanup actions.
> opar <- par(bg='lightblue')> on.exit(par(opar))> plot(c(1,2,3),c(4,5,6))#蓝色背景> plot(c(1,2,3,4,5),runif(5))#蓝色背景#此时关闭绘图窗口> plot(c(1,2,3,4,5),rnorm(5))#白色背景
plot_with_big_margins <- function(...){old_pars <- par(mar = c(10,9,9,7))on.exit(par(old_pars))plot(...)}plot_with_big_margins(with(cars, speed, dist))
#不关闭图像窗口,此时再运行如下语句plot(c(1,2,3),c(4,5,6))
对比plot_with_big_margins <- function(...){par(mar = c(10,9,9,7))plot(...)}plot_with_big_margins(with(cars, speed, dist))
#不关闭图像窗口,此时再运行:plot(c(1,2,3),c(4,5,6))
old_pars <- par(mar = c(10,9,9,7))on.exit(par(old_pars))
不是要还原吗?为什么是把old_pars传递给par()?
> old_pars <- par(mar = c(10,9,9,7))> old_pars$mar[1]5.14.14.12.1> op <- options(stringsAsFactors = FALSE)> op$stringsAsFactors[1] TRUE
par() #得到的mar是5.14.14.12.1plot_with_big_margins <- function(...){old_pars <- par(mar = c(10,9,9,7)) #原参数被保存,新参数设置生效print(par()),9,9,7on.exit(par(old_pars)) #参数被还原为原来的参数plot(...)}plot_with_big_margins(with(cars, speed, dist))par()#得到的mar是5.14.14.12.1
my_plot <- function(){with(cars, plot(speed, dist))}save_base_plot <- function(plot_fn, file){png(file)on.exit(dev.off())plot_fn()}save_base_plot(my_plot,"testcars.png")
#replaceEntities的默认值是FALSEold = XML:::setEntitySubstitution(replaceEntities)#old的值是FALSEon.exit(XML:::setEntitySubstitution(old), add = TRUE)
这几行代码的功能是类似的
> XML:::setEntitySubstitutionfunction (val).Call("RS_XML_SubstituteEntitiesDefault",as.logical(val), PACKAGE ="XML")<environment: namespace:XML>
.oldErrorHandler = XML:::setXMLErrorHandler(error)#所以,这种点开头的命名是什么鬼?# class(.oldErrorHandler)# [1] "list"on.exit(.Call("RS_XML_setStructuredErrorHandler",.oldErrorHandler,PACKAGE ="XML"), add = TRUE)> XML:::htmlErrorHandlerfunction (msg, code, domain, line, col, level, filename,class="XMLError"){e = makeXMLError(msg, code, domain, line, col, level, filename,class)dom = names(e$domain)class(e)= c(names(e$code), sprintf("%s_Error", gsub("_FROM_","_", dom)),class(e))if(e$code == xmlParserErrors["XML_IO_LOAD_ERROR"])stop(e)}<environment: namespace:XML>> XML:::setXMLErrorHandlerfunction (fun){prev =.Call("RS_XML_getStructuredErrorHandler", PACKAGE ="XML")sym = getNativeSymbolInfo("R_xmlStructuredErrorHandler","XML")$address.Call("RS_XML_setStructuredErrorHandler", list(fun, sym),PACKAGE ="XML")prev}<environment: namespace:XML>
> getAnywhere(BOMRegExp)A single object matching ‘BOMRegExp’ was foundIt was found in the following placesnamespace:XMLwith value[1]"(\\xEF\\xBB\\xBF|\\xFE\\xFF|\\xFF\\xFE)"

untar(download.packages(pkgs ="XML",destdir =".",type ="source")[,2])
附件列表
R自动数据收集第二章HTML笔记2(主要关于htmlTreeParse函数)的更多相关文章
- R自动数据收集第二章HTML笔记1(主要关于handler处理器函数和帮助文档所有示例)
本文知识点: 1潜在畸形页面使用htmlTreeParse函数 2startElement的用法 3闭包 4handler函数的命令和函数体主要写法 5节点的丢弃,取出,取出标签名称.属性.属 ...
- R自动数据收集第一章概述——《List of World Heritage in Danger》
导包 library(stringr) library(XML) library(maps) heritage_parsed <- htmlParse("http://en ...
- AS开发实战第二章学习笔记——其他
第二章学习笔记(1.19-1.22)像素Android支持的像素单位主要有px(像素).in(英寸).mm(毫米).pt(磅,1/72英寸).dp(与设备无关的显示单位).dip(就是dp).sp(用 ...
- #Spring实战第二章学习笔记————装配Bean
Spring实战第二章学习笔记----装配Bean 创建应用对象之间协作关系的行为通常称为装配(wiring).这也是依赖注入(DI)的本质. Spring配置的可选方案 当描述bean如何被装配时, ...
- CentOS6安装各种大数据软件 第二章:Linux各个软件启动命令
相关文章链接 CentOS6安装各种大数据软件 第一章:各个软件版本介绍 CentOS6安装各种大数据软件 第二章:Linux各个软件启动命令 CentOS6安装各种大数据软件 第三章:Linux基础 ...
- Machine Learning In Action 第二章学习笔记: kNN算法
本文主要记录<Machine Learning In Action>中第二章的内容.书中以两个具体实例来介绍kNN(k nearest neighbors),分别是: 约会对象预测 手写数 ...
- Day2 《机器学习》第二章学习笔记
这一章应该算是比价了理论的一章,我有些概率论基础,不过起初有些地方还是没看多大懂.其中有些公式的定义和模型误差的推导应该还是很眼熟的,就是之前在概率论课上提过的,不过有些模糊了,当时课上学得比较浅. ...
- Python核心编程第三版第二章学习笔记
第二章 网络编程 1.学习笔记 2.课后习题 答案是按照自己理解和查阅资料来的,不保证正确性.如由错误欢迎指出,谢谢 1. 套接字:A network socket is an endpoint of ...
- Linux第一章第二章学习笔记
第一章 Linux内核简介 1.1 Unix的历史 它是现存操作系统中最强大最优秀的系统. 设计简洁,在发布时提供原代码. 所有东西都被当做文件对待. Unix的内核和其他相关软件是用C语言编写而成的 ...
随机推荐
- pptpvpn 连接后 无法上外网
VPN拨号后只能连内网,不能上外网的原因和解决方法 因为众所周知的原因,很多个人或者单位需要架设自己的VPN.会遇到一些奇怪的情况,比如说:为什么连上单位的VPN后就只好上公司的内网(局域网),外网( ...
- String构造器中originalValue.length>size 发生的情况
最近在看Jdk6中String的源码的时候发现String的有个这样的构造方法,源代码内容如下: public String(String original) { int size = origina ...
- Linux下的ctrl常用组合键
在linux的命令模式下使用ctrl组合键能让操作更便捷. ctrl + k -- 剪切光标及其后边的内容: ctrl + u -- 剪切光标之前的内容: ctrl + y -- 在光标处粘贴上两个命 ...
- C#体检套餐项目
使用泛型集合写的一个小项目 1.要实现新建体检套餐,并且如果已经有了该体检套餐就不能再次新建, 2.要实现套餐列表动态更新,没添加一个体检套餐,在套餐列表里就自动添加一项; 3.向当前套餐类表里添加检 ...
- [LeetCode] Find the Celebrity 寻找名人
Suppose you are at a party with n people (labeled from 0 to n - 1) and among them, there may exist o ...
- C#进阶系列——一步一步封装自己的HtmlHelper组件:BootstrapHelper
前言:之前学习过很多的Bootstrap组件,博主就在脑海里构思:是否可以封装一套自己Bootstrap组件库呢.再加上看到MVC的Razor语法里面直接通过后台方法输出前端控件的方式,于是打算仿照H ...
- Ubuntu apache2.4 设置虚拟主机
每次重装系统如何配置都上网找,搞半天,都是不对的,还不如自己记下来,以作参考呢.我的项目目录是 /home/feiffy/demo/test,映射的域名是 test.com,这样在浏览器输入 test ...
- 初探Socket
使用Socket Socket是两台主机之间的一个连接,它可以完成7个操作. 连接远程机器 发送数据 接收数据 关闭连接 绑定端口 监听入站数据 在绑定端口上接受来自远程机器的连接 Java中的Soc ...
- 使用css3做钟表
<!DOCTYPE html> <html> <head> <meta charset="UTF-8"> <title> ...
- ThreadPoolTimer -延迟执行, 周期执行
介绍重新想象 Windows 8 Store Apps 之 线程池 通过 ThreadPoolTimer 实现延迟执行 通过 ThreadPoolTimer 实现周期执行 通过 ThreadPool ...