{"id":349,"date":"2022-03-19T21:42:26","date_gmt":"2022-03-19T13:42:26","guid":{"rendered":"https:\/\/linguopeng.top\/?p=349"},"modified":"2022-03-19T21:42:28","modified_gmt":"2022-03-19T13:42:28","slug":"compoundname%e8%bd%ac%e6%8d%a2inchikeys_smiles%e4%b8%8epubchem_id","status":"publish","type":"post","link":"https:\/\/linguopeng.top\/?p=349","title":{"rendered":"CompoundName\u8f6c\u6362InChiKeys_SMILES\u4e0ePubchem_ID"},"content":{"rendered":"\n<pre class=\"wp-block-code\"><code># # install.packages(\"devtools\")\r\n# library(devtools)\r\n# install_github('yikeshu0611\/rs.driver')\r\n# \u5b89\u88c5R\u5305\r\n#install.packages('RSelenium')\r\n#java -Dwebdriver.chrome.driver=\"chromedriver.exe\" -jar selenium-server-standalone-4.0.0-alpha-2.jar -port 4444\r\n# \u52a0\u8f7dR\u5305\r\n#library(devtools)\r\nlibrary(readxl)\r\nlibrary(RSelenium)\r\nlibrary(rvest)\r\nlibrary(xml2)\r\nlibrary(RS.Driver)\r\nlibrary(tidyverse)\r\nname &lt;- read_xlsx(\"example_tempelate.xlsx\",sheet = 1)\r\nRS.OpenChrome()\r\nurl &lt;- c()\r\nid&lt;-name$`Compound Name`\r\nfor (i in id) {\r\n  url &lt;- c(url,paste('https:\/\/www.mzcloud.org\/compound\/Search?Query=',\r\n                     i,sep = ''))\r\n}\r\ntitle &lt;- c()\r\nID &lt;- c()\r\nfor(i in 1:length(url)){\r\n  RS.open_Url(url&#91;i])\r\n  Sys.sleep(2)\r\n  title &lt;- c(title,RS.get_Text('\/html\/body\/div\/div&#91;2]\/div\/div\/\/div&#91;2]\/div\/div&#91;2]\/div\/div&#91;1]\/a'))\r\n  ID &lt;- c(ID,RS.get_Text('\/html\/body\/div\/div&#91;2]\/div\/div\/div&#91;*]\/div&#91;2]\/div\/div&#91;2]\/div\/div&#91;2]\/p\/span'))\r\n}\r\ndf &lt;- data.frame(title = title,ID=ID)\r\ndf&lt;- filter(df,!duplicated(df$ID))\r\ndf1&lt;-c()\r\nfor(i in 1:length(id)){\r\n  df1 &lt;- c(df1,df1&lt;-df&#91;id&#91;i]==df$title,])\r\n}\r\nlibrary(plyr)\r\ndf2 &lt;-ldply(df1, data.frame)\r\ncolnames(df2)&lt;-c('id','name')\r\ndf3&lt;-data.frame(df2&#91;df2$id=='title',])\r\ndf3.1&lt;-data.frame(df2&#91;df2$id=='ID',])\r\ndf4&lt;-cbind(df3,df3.1)\r\ndf4&lt;-df4&#91;,c(2,4)]\r\ncolnames(df4)&lt;-c('name','id')\r\ndf4_1&lt;-gsub(\"ID: Reference\",\"\",df4$id)\r\ndf4_2&lt;-cbind(df4,df4_1)\r\ncolnames(df4_2)&lt;-c('name','id_1','id')\r\ndf4&lt;-df4_2&#91;,c(1,3)]\r\nid2&lt;-df4$id\r\nurl2&lt;-c()\r\nfor (i in id2) {\r\n  url2 &lt;- c(url2,paste('https:\/\/www.mzcloud.org\/compound\/Reference\/',\r\n                     i,sep = ''))\r\n}\r\nRS.OpenChrome()\r\nKey&lt;-c()\r\nSMILES&lt;-c()\r\ntitle&lt;-c()\r\nfor(i in 1:length(url2)){\r\n  RS.open_Url(url2&#91;i])\r\n  Sys.sleep(2.5)\r\n  Key &lt;- c(Key,RS.get_Text('\/html\/body\/div\/div&#91;7]\/div\/div\/table\/tbody\/tr&#91;2]\/td&#91;2]'))\r\n  SMILES&lt;-c(SMILES,RS.get_Text('\/html\/body\/div\/div&#91;7]\/div\/div\/table\/tbody\/tr&#91;3]\/td&#91;2]'))\r\n  title &lt;- c(title,RS.get_Text('\/html\/body\/div\/div&#91;1]\/div\/h3'))\r\n}\r\ntitle_Key_SMILES &lt;- data.frame(Compound_Name=title,\r\n                               InChiKeys = Key,\r\n                               SMILES=SMILES)\r\nRS.OpenChrome()\r\nPubchem_ID&lt;-c()\r\nurl3&lt;-c()\r\nfor (i in length(Key)) {\r\n  url3 &lt;- c(url3,paste('https:\/\/pubchem.ncbi.nlm.nih.gov\/#query=',\r\n                       Key,sep = ''))\r\n}\r\nfor(i in 1:length(Key)){\r\n  RS.open_Url(url3&#91;i])\r\n  Sys.sleep(2.5)\r\n  Pubchem_ID&lt;-c(Pubchem_ID,RS.get_Text('\/html\/body\/div&#91;1]\/div\/div\/main\/div&#91;2]\/div&#91;2]\/div&#91;3]\/div\/div\/div\/div&#91;2]\/ul\/li\/div\/div\/div&#91;1]\/div&#91;2]\/div&#91;2]\/div\/span\/a\/span\/span'))\r\n}\r\nPubchem_ID &lt;- data.frame(Pubchem_ID=Pubchem_ID)\r\ntotal&lt;-cbind(title_Key_SMILES,Pubchem_ID)\r<\/code><\/pre>\n\n\n\n<figure class=\"wp-block-image size-full\"><div class='fancybox-wrapper lazyload-container-unload' data-fancybox='post-images' href='https:\/\/linguopeng.top\/wp-content\/uploads\/2022\/03\/1.png'><img class=\"lazyload lazyload-style-1\" src=\"data:image\/svg+xml;base64,PCEtLUFyZ29uTG9hZGluZy0tPgo8c3ZnIHdpZHRoPSIxIiBoZWlnaHQ9IjEiIHhtbG5zPSJodHRwOi8vd3d3LnczLm9yZy8yMDAwL3N2ZyIgc3Ryb2tlPSIjZmZmZmZmMDAiPjxnPjwvZz4KPC9zdmc+\"  loading=\"lazy\" decoding=\"async\" width=\"356\" height=\"183\" data-original=\"https:\/\/linguopeng.top\/wp-content\/uploads\/2022\/03\/1.png\" src=\"data:image\/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAAAXNSR0IArs4c6QAAAARnQU1BAACxjwv8YQUAAAAJcEhZcwAADsQAAA7EAZUrDhsAAAANSURBVBhXYzh8+PB\/AAffA0nNPuCLAAAAAElFTkSuQmCC\" alt=\"\" class=\"wp-image-350\"\/><\/div><\/figure>\n\n\n\n<figure class=\"wp-block-image size-full\"><div class='fancybox-wrapper lazyload-container-unload' data-fancybox='post-images' href='https:\/\/linguopeng.top\/wp-content\/uploads\/2022\/03\/2.png'><img class=\"lazyload lazyload-style-1\" src=\"data:image\/svg+xml;base64,PCEtLUFyZ29uTG9hZGluZy0tPgo8c3ZnIHdpZHRoPSIxIiBoZWlnaHQ9IjEiIHhtbG5zPSJodHRwOi8vd3d3LnczLm9yZy8yMDAwL3N2ZyIgc3Ryb2tlPSIjZmZmZmZmMDAiPjxnPjwvZz4KPC9zdmc+\"  loading=\"lazy\" decoding=\"async\" width=\"916\" height=\"246\" data-original=\"https:\/\/linguopeng.top\/wp-content\/uploads\/2022\/03\/2.png\" src=\"data:image\/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAAAXNSR0IArs4c6QAAAARnQU1BAACxjwv8YQUAAAAJcEhZcwAADsQAAA7EAZUrDhsAAAANSURBVBhXYzh8+PB\/AAffA0nNPuCLAAAAAElFTkSuQmCC\" alt=\"\" class=\"wp-image-351\"\/><\/div><\/figure>\n","protected":false},"excerpt":{"rendered":"","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1],"tags":[],"class_list":["post-349","post","type-post","status-publish","format-standard","hentry","category-uncategorized"],"_links":{"self":[{"href":"https:\/\/linguopeng.top\/index.php?rest_route=\/wp\/v2\/posts\/349","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/linguopeng.top\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/linguopeng.top\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/linguopeng.top\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/linguopeng.top\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=349"}],"version-history":[{"count":1,"href":"https:\/\/linguopeng.top\/index.php?rest_route=\/wp\/v2\/posts\/349\/revisions"}],"predecessor-version":[{"id":352,"href":"https:\/\/linguopeng.top\/index.php?rest_route=\/wp\/v2\/posts\/349\/revisions\/352"}],"wp:attachment":[{"href":"https:\/\/linguopeng.top\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=349"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/linguopeng.top\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=349"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/linguopeng.top\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=349"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}