Go-pholcus Crawl Ijguc All periodicals

This is a creation in Article, where the information may have evolved or changed.

 PackageSpider_lib//Basic PackageImport(//"Log"    "Github.com/puerkitobio/goquery"                        //dom parsing    "Github.com/henrylee2cn/pholcus/app/downloader/request" //Required."Github.com/henrylee2cn/pholcus/app/spider"           //Required    //"github.com/henrylee2cn/pholcus/logs"//Information output    // . "Github.com/henrylee2cn/pholcus/app/spider/common"//Selection    //NET package    //"net/http"//Set HTTP. Header    //"Net/url"    //Code pack    //"Encoding/xml"    //"Encoding/json"    //String processing package    "RegExp"    "StrConv"    //"strings"    //Other packages    //"FMT"    //"math"    //"Time")funcInit () {Ijguc. Register ()}varIJGUC = &spider{Name:"IJGUC Journal", Description:"IJGUC Journal",//pausetime:300,    //Keyin:keyin,    //Limit:limit,Enablecookie:false, Ruletree: &ruletree{Root:func(CTX *context) {ctx. Addqueue (&request. request{URL:"Http://www.inderscience.com/info/inarticletoc.php?jcode=ijguc&year=2016&vol=7&issue=1", Rule:"Journal list",})}, Trunk:Map[string]*rule{"Journal list": {parsefunc:func(CTX *context) {query: = CTX. GetDOM () forI: =1; I <=7; i++ {id: ="#eventbody"+ StrConv. Itoa (i) +"a"Query. Find (ID). each (func(jint, S *goquery. Selection) {ifURL, OK: = S.attr ("href"); OK {//log. Print (URL)CTx. Addqueue (&request. Request{url:url, Rule:"article List"})                            }                        })                    }                },            },"article List": {parsefunc:func(CTX *context) {query: = CTX. GetDOM ()//#journalcol1 Article Table tbody tr td:eq (1) table:eq (1) aQuery. Find ("#journalcol1 article table tbody tr TD"). each (func(Iint, TD *goquery. Selection) {ifi = =1{TD. Find ("Table"). each (func(jint, table *goquery. Selection) {ifj = =1{table. Find ("a"). each (func(kint, a *goquery. Selection) {ifK%2==0{ifURL, OK: = A.attr ("href"); OK {//log. Print (URL)CTx. Addqueue (&request. Request{url:url, Rule:"article page"})                                            }                                        }                })                                }                            })                        }                    }) },            },"article page": {//Note: There is no word Qi and whether the output data must be consistentItemfields: []string{"Title","Author","Addresses","Journal","Abstract","Keywords","DOI",}, Parsefunc:func(CTX *context) {query: = CTX. GetDOM ()//Get contentContent: = Query. Find ("#col1"). Text ()//Filter LabelRe, _: = Regexp.compile ("\\<[\\s\\s]+?\\>") content = Re. Replaceallstring (Content,"")//TitleRe, _ = Regexp.compile ("Title: (. *?) Author: ") Title: = Re. Findstringsubmatch (content)[1]//AuthorRe, _ = Regexp.compile ("Author: (. *?) Addresses: ") au: = re. Findstringsubmatch (content)varAuthorstring                    if Len(AU) >0{Author = au[1]                    }Else{Re, _ = Regexp.compile ("Author: (. *?) Address: ") Author = re. Findstringsubmatch (content)[1]                    }//Addresses & AddressRe, _ = Regexp.compile ("Addresses: (. *?) Journal: "Address: = Re. Findstringsubmatch (content)varAddressesstring                    if Len(address) >0{addresses = Address[1]                    }Else{Re, _ = Regexp.compile ("Address: (. *?) Journal: ") addresses = Re. Findstringsubmatch (content)[1]                    }//JournalRe, _ = Regexp.compile ("Journal: (. *?) Abstract: ") Journal: = Re. Findstringsubmatch (content)[1]//AbstractRe, _ = Regexp.compile ("Abstract: (. *?) Keywords: ") Abstract: = Re. Findstringsubmatch (content)[1]//KeywordsRe, _ = Regexp.compile ("Keywords: (. *?) DOI: ") Keywords: = Re. Findstringsubmatch (content)[1]//DOIRe, _ = Regexp.compile ("DOI:") Doiindex: = Re. Findstringsubmatchindex (content) rs: = []Rune(content) Left: = Doiindex[1] -8Right: = left + +DOI: =string(Rs[left:right])//Results deposited response relayCTx. Output (Map[int]Interface{}{0: Title,1: Author,2: Addresses,3: Journal,4: abstract,5: keywords,6: DOI,})},},},},}