spider

package
v0.3.0 Latest Latest
Warning

This package is not in the latest version of its module.

Go to latest
Published: Apr 29, 2020 License: AFL-3.0, CC-BY-3.0 Imports: 16 Imported by: 0

Documentation

Index

Constants

This section is empty.

Variables

View Source
var AacrJournalLinks = []string{"aacrjournals.org", "cancerdiscovery.aacrjournals.org",
	"clincancerres.aacrjournals.org", "cancerimmunolres.aacrjournals.org"}
View Source
var AosisCoZaJournalLinks = []string{"actacommercii.co.za", "aejonline.org", "ajcd.africa", "ajod.org", "ajlmonline.org", "phcfm.org", "ajopa.org", "avehjournal.org", "apsdpr.org", "curationis.org.za", "hsag.co.za", "hts.org.za", "indieskriflig.org.za", "jamba.org.za", "jafonline.org", "jefjournal.org.za", "insulinresistance.org", "jolgri.org", "jomped.org", "jsava.co.za", "jtscm.co.za", "koedoe.co.za", "literator.org.za", "ojvr.org", "pythagoras.org.za", "rw.org.za", "sajhrm.co.za", "sajip.co.za", "sajo.org.za", "sajr.org.za", "safpj.co.za", "sajbm.org", "sajce.co.za", "sajcd.org.za", "sajems.org", "sajim.co.za", "sajip.co.za", "sajip.org.za", "sajhivmed.org.za", "sajid.co.za", "td-sa.net", "sajesbm.co.za", "theologiaviatorum.org", "thejournal.org.za", "verbumetecclesia.org.za", "www.actacommercii.co.za", "www.aejonline.org", "www.ajcd.africa", "www.ajod.org", "www.ajlmonline.org", "www.phcfm.org", "www.ajopa.org", "www.avehjournal.org", "www.apsdpr.org", "www.curationis.org.za", "www.hsag.co.za", "www.hts.org.za", "www.indieskriflig.org.za", "www.jamba.org.za", "www.jafonline.org", "www.jefjournal.org.za", "www.insulinresistance.org", "www.jolgri.org", "www.jomped.org", "www.jsava.co.za", "www.jtscm.co.za", "www.koedoe.co.za", "www.literator.org.za", "www.ojvr.org", "www.pythagoras.org.za", "www.rw.org.za", "www.sajhrm.co.za", "www.sajip.co.za", "www.sajo.org.za", "www.sajr.org.za", "www.safpj.co.za", "www.sajbm.org", "www.sajce.co.za", "www.sajcd.org.za", "www.sajems.org", "www.sajim.co.za", "www.sajip.co.za", "www.sajip.org.za", "www.sajhivmed.org.za", "www.sajid.co.za", "www.td-sa.net", "www.sajesbm.co.za", "www.theologiaviatorum.org", "www.thejournal.org.za", "www.verbumetecclesia.org.za"}
View Source
var BiomedcentralJournalLinks = []string{} /* 336 elements not displayed */
View Source
var BmjComJournalLinks = []string{"ard.bmj.com", "adc.bmj.com", "casereports.bmj.com", "ebm.bmj.com", "gh.bmj.com", "informatics.bmj.com", "innovations.bmj.com", "bmjleader.bmj.com", "militaryhealth.bmj.com", "neurologyopen.bmj.com", "nutrition.bmj.com", "bmjopen.bmj.com", "drc.bmj.com", "bmjopengastro.bmj.com", "bmjophth.bmj.com", "qir.bmj.com", "bmjopenrespres.bmj.com", "openscience.bmj.com", "bmjopensem.bmj.com", "qualitysafety.bmj.com", "bmjpaedsopen.bmj.com", "srh.bmj.com", "stel.bmj.com", "spcare.bmj.com", "sit.bmj.com", "bjo.bmj.com", "bjsm.bmj.com", "considerations.bmj.com", "dtb.bmj.com", "ep.bmj.com", "emj.bmj.com", "esmoopen.bmj.com", "ejhp.bmj.com", "ebmh.bmj.com", "ebn.bmj.com", "fmch.bmj.com", "fn.bmj.com", "fg.bmj.com", "gpsych.bmj.com", "gut.bmj.com", "heart.bmj.com", "heartasia.bmj.com", "injuryprevention.bmj.com", "inpractice.bmj.com", "ihj.bmj.com", "ijgc.bmj.com", "jitc.bmj.com", "jcp.bmj.com", "jech.bmj.com", "jim.bmj.com", "jisakos.bmj.com", "jme.bmj.com", "jmg.bmj.com", "jnnp.bmj.com", "jnis.bmj.com", "lupus.bmj.com", "mh.bmj.com", "oem.bmj.com", "openheart.bmj.com", "pmj.bmj.com", "pn.bmj.com", "rapm.bmj.com", "rmdopen.bmj.com", "sti.bmj.com", "svn.bmj.com", "www.bmj.com", "thorax.bmj.com", "tobaccocontrol.bmj.com", "tsaco.bmj.com", "veterinaryrecord.bmj.com", "vetrecordcasereports.bmj.com", "vetrecordopen.bmj.com", "wjps.bmj.com"}
View Source
var CellComJournalLinks = []string{"www.cell.com", "cell.com",
	"linkinghub.elsevier.com", "secure.jbs.elsevierhealth.com",
	"id.elsevier.com", "www.cancercell.org", "www.sciencedirect.com",
	"pdf.sciencedirectassets.com", "www.thelancet.com", "www.gastrojournal.org",
	"www.clinicalkey.com"}
View Source
var CitationMetaKeys = []string{"citation_title", "citation_doi", "citation_pmid",
	"citation_journal_title", "citation_journal_abbrev", "citation_issn",
	"citation_publication_date", "citation_publisher", "citation_pdf_url",
	"citation_volume", "citation_issue", "citation_num_pages",
	"citation_lastpage", "citation_firstpage",
	"citation_publication_number", "citation_section", "citation_article_type",
	"citation_version_number", "citation_keywords", "citation_description",
	"citation_abstract"}
View Source
var DirectJournalLinks = []string{"10.4274/tjh.galenos", "10.4415/ANN", "10.5231/psy."}
View Source
var DoiSpidersPool = map[string]func(opt *DoiSpiderOpt) []string{}/* 137 elements not displayed */

DoiSpidersPool map doi to golang function

View Source
var KoreaMedJournalDois = []string{"10.4110", "10.3346", "10.3348", "10.4168", "10.35371"}
View Source
var KoreaMedJournalLinks = []string{"immunenetwork.org", "jkms.org", "kjronline.org", "e-aair.org", "aoemj.org"}
View Source
var MedknowJournalLinks = []string{} /* 193 elements not displayed */
View Source
var ScienseComJournalLinks = []string{"advances.sciencemag.org", "immunology.sciencemag.org",
	"robotics.sciencemag.org", "stke.sciencemag.org", "stm.sciencemag.org", "secure.jbs.elsevierhealth.com",
	"id.elsevier.com", "science.sciencemag.org", "www.sciencemag.org"}
View Source
var UniversalJournalLinks = []string{"doi.org", "dx.doi.org", "www.iss.it", "ajas.info", "www.scielo.br", "californiaagriculture.ucanr.org", "www.journalssystem.com", "online.reed.es", "www.bioone.org",
	"www.ingentaconnect.com", "www.karger.com", "digital-library.theiet.org", "www.nature.com", "medrxiv.org",
	"psycnet.apa.org", "doi.apa.org", "www.aging-us.com"}

Functions

func AacrJournalsSpider

func AacrJournalsSpider(opt *DoiSpiderOpt) (urls []string)

AacrJournalsSpider access aacrjournals.org files via spider

func AappublicationsOrgSpider

func AappublicationsOrgSpider(opt *DoiSpiderOpt) (urls []string)

func AddDownloadSpider

func AddDownloadSpider(opt *DoiSpiderOpt) (urls []string)

func AddLastPdfSpider

func AddLastPdfSpider(opt *DoiSpiderOpt) (urls []string)

func AddPdfSpider

func AddPdfSpider(opt *DoiSpiderOpt) (urls []string)

func AddPdfSuffixSpider

func AddPdfSuffixSpider(opt *DoiSpiderOpt) (urls []string)

func AddPdfWithSupplSpider

func AddPdfWithSupplSpider(opt *DoiSpiderOpt) (urls []string)

func AddPdfplusSpider

func AddPdfplusSpider(opt *DoiSpiderOpt) (urls []string)

func AddPdfplusWithSupplSpider

func AddPdfplusWithSupplSpider(opt *DoiSpiderOpt) (urls []string)

func AddTextPdfSuffixSpider

func AddTextPdfSuffixSpider(opt *DoiSpiderOpt) (urls []string)

func AdiccionesEsSpider

func AdiccionesEsSpider(opt *DoiSpiderOpt) (urls []string)

func AeawebOrgSpider

func AeawebOrgSpider(opt *DoiSpiderOpt) (urls []string)

func AerzteblattDeSpider

func AerzteblattDeSpider(opt *DoiSpiderOpt) (urls []string)

func AhajournalsSpider

func AhajournalsSpider(opt *DoiSpiderOpt) (urls []string)

AhajournalsSpider access https://www.ahajournals.org files via spider

func AltexOrgSpider

func AltexOrgSpider(opt *DoiSpiderOpt) (urls []string)

func AmegroupsSpider

func AmegroupsSpider(opt *DoiSpiderOpt) (urls []string)

func AmetsocOrgSpider

func AmetsocOrgSpider(opt *DoiSpiderOpt) (urls []string)

func AnnalsOrgSpider

func AnnalsOrgSpider(opt *DoiSpiderOpt) (urls []string)

func AnnualReviewsSpider

func AnnualReviewsSpider(opt *DoiSpiderOpt) (urls []string)

PubsRscSpider access https://www.annualreviews.org/ files via spider

func AomOrgSpider

func AomOrgSpider(opt *DoiSpiderOpt) (urls []string)

func AosisCoZaSpider

func AosisCoZaSpider(opt *DoiSpiderOpt) (urls []string)

func AscopubsSpider

func AscopubsSpider(opt *DoiSpiderOpt) (urls []string)

AscopubsSpider access https://ascopubs.org/ files via spider

func AsnjournalsOrgSpider

func AsnjournalsOrgSpider(opt *DoiSpiderOpt) (urls []string)

func AutopsyandcasereportsSpider

func AutopsyandcasereportsSpider(opt *DoiSpiderOpt) (urls []string)

AutopsyandcasereportsSpider access https://autopsyandcasereports.org files via spider

func Bbk19Spider

func Bbk19Spider(opt *DoiSpiderOpt) (urls []string)

func BiomedcentralSpider

func BiomedcentralSpider(opt *DoiSpiderOpt) (urls []string)

BiomedcentralSpider access GenomeBiology files via spider

func BloodJournalSpider

func BloodJournalSpider(opt *DoiSpiderOpt) (urls []string)

BloodJournalSpider access http://www.bloodjournal.org files via spider

func BmjComSpider

func BmjComSpider(opt *DoiSpiderOpt) (urls []string)

BmjComSpider access www.bmj.com files via spider

func CellComSpider

func CellComSpider(opt *DoiSpiderOpt) (urls []string)

CellComSpider access cell.com journal files via spider

func CellimageLibrarySpider

func CellimageLibrarySpider(opt *DoiSpiderOpt) (urls []string)

func CogitatiopressComSpider

func CogitatiopressComSpider(opt *DoiSpiderOpt) (urls []string)

func CshlpSpider

func CshlpSpider(opt *DoiSpiderOpt) (urls []string)

CshlpSpider access CshlpSpider files via spider

func DirectSpider

func DirectSpider(opt *DoiSpiderOpt) (urls []string)

func DovepressSpider

func DovepressSpider(opt *DoiSpiderOpt) (urls []string)

DovepressSpider access http://www.dovepress.com files via spider

func EajmOrgSpider

func EajmOrgSpider(opt *DoiSpiderOpt) (urls []string)

func EjcrimSpider

func EjcrimSpider(opt *DoiSpiderOpt) (urls []string)

JciSpider access www.ejcrim.com files via spider

func ElifeSpider

func ElifeSpider(opt *DoiSpiderOpt) (urls []string)

ElifeSpider access https://elifesciences.org files via spider

func EmbopressSpider

func EmbopressSpider(opt *DoiSpiderOpt) (urls []string)

EmbopressSpider access https://www.embopress.org files via spider

func EurosurveillanceOrgSpider

func EurosurveillanceOrgSpider(opt *DoiSpiderOpt) (urls []string)

func FigshareSpider

func FigshareSpider(opt *DoiSpiderOpt) (urls []string)

FigshareSpider access https://figshare.com/ files via spider

func FrontiersinSpider

func FrontiersinSpider(opt *DoiSpiderOpt) (urls []string)

FrontiersinSpider access Frontiers files via spider

func GeoSpider

func GeoSpider(opt *QuerySpiderOpt, gpl bool) (gseURLs []string, gplURLs []string, sraLink string)

GeoSpider access https://www.ncbi.nlm.nih.gov/geo files via spider

func GeochemicalperspectivesOrgSpider

func GeochemicalperspectivesOrgSpider(opt *DoiSpiderOpt) (urls []string)

func Geofetch

func Geofetch(geo string, outDir string, gpl bool,
	uncompress bool, opt *cnet.Params) (err error)

Geofetch get GEO files

func GeoscienceworldOrg

func GeoscienceworldOrg(opt *DoiSpiderOpt) (urls []string)

func GeoscienceworldOrgSpider

func GeoscienceworldOrgSpider(opt *DoiSpiderOpt) (urls []string)

func HaematologicaSpider

func HaematologicaSpider(opt *DoiSpiderOpt) (urls []string)

HaematologicaSpider access https://ascopubs.org/ files via spider

func IeeexploreSpider

func IeeexploreSpider(opt *DoiSpiderOpt) (urls []string)

func InformsOrgSPider

func InformsOrgSPider(opt *DoiSpiderOpt) (urls []string)

func IopOrgSpider

func IopOrgSpider(opt *DoiSpiderOpt) (urls []string)

func IospressComSpider

func IospressComSpider(opt *DoiSpiderOpt) (urls []string)

func IucrOrgSpider

func IucrOrgSpider(opt *DoiSpiderOpt) (urls []string)

func JamaNetworkSpider

func JamaNetworkSpider(opt *DoiSpiderOpt) (urls []string)

JamaNetworkSpider access https://jamanetwork.com files via spider

func JciSpider

func JciSpider(opt *DoiSpiderOpt) (urls []string)

JciSpider access https://www.jci.org files via spider

func JmirOrgSpider

func JmirOrgSpider(opt *DoiSpiderOpt) (urls []string)

func JournalsApsSpider

func JournalsApsSpider(opt *DoiSpiderOpt) (urls []string)

JournalsApsSpider access https://journals.aps.org/ files via spider

func JstatsoftSpider

func JstatsoftSpider(opt *DoiSpiderOpt) (urls []string)

JstatsoftSpider access https://www.jstatsoft.org files via spider

func JstrokeOrgSpider

func JstrokeOrgSpider(opt *DoiSpiderOpt) (urls []string)

func KargerComSpider

func KargerComSpider(opt *DoiSpiderOpt) (urls []string)

func KoreaMedSpider

func KoreaMedSpider(opt *DoiSpiderOpt) (urls []string)

func KosuyoluheartjournalSpider

func KosuyoluheartjournalSpider(opt *DoiSpiderOpt) (urls []string)

KosuyoluheartjournalSpider access http://www.kosuyoluheartjournal.com/ files

func LiebertpubSpider

func LiebertpubSpider(opt *DoiSpiderOpt) (urls []string)

func LwwComSpider

func LwwComSpider(opt *DoiSpiderOpt) (urls []string)

func MedknowSpider

func MedknowSpider(opt *DoiSpiderOpt) (urls []string)

func NatureComSpider

func NatureComSpider(opt *DoiSpiderOpt) (urls []string)

NatureComSpider access Nature.com files via spider

func NejmSpider

func NejmSpider(opt *DoiSpiderOpt) (urls []string)

NejmSpider access http://www.nejm.org files via spider

func OupComSpider

func OupComSpider(opt *DoiSpiderOpt) (urls []string)

OupComSpider access academic.oup.com files via spider

func PeerjSpider

func PeerjSpider(opt *DoiSpiderOpt) (urls []string)

PeerjSpider access Peerj files via spider supp not support now, need chromedp

func PhysiologyOrgSpider

func PhysiologyOrgSpider(opt *DoiSpiderOpt) (urls []string)

func PlosSpider

func PlosSpider(opt *DoiSpiderOpt) (urls []string)

PlosSpider access PlosSpider files via spider

func PmcSpider

func PmcSpider(opt *DoiSpiderOpt) (urls []string)

func PnasSpider

func PnasSpider(opt *DoiSpiderOpt) (urls []string)

PnasSpider access PnasSpider files via spider

func PortlandpressComSpider

func PortlandpressComSpider(opt *DoiSpiderOpt) (urls []string)

func PubsRscSpider

func PubsRscSpider(opt *DoiSpiderOpt) (urls []string)

PubsRscSpider access https://pubs.rsc.org/ files via spider

func PubsacsSpider

func PubsacsSpider(opt *DoiSpiderOpt) (urls []string)

PubsacsSpider access https://pubs.acs.org/ files via spider

func ReplaceHtmlSpider

func ReplaceHtmlSpider(opt *DoiSpiderOpt) (urls []string)
func RetriveRedirectLink(url string, timeout int, proxy string) (string, error)

func RoyalsocietypublishingOrgSpider

func RoyalsocietypublishingOrgSpider(opt *DoiSpiderOpt) (urls []string)

func SagepubComSpider

func SagepubComSpider(opt *DoiSpiderOpt) (urls []string)

func ScienseComSpider

func ScienseComSpider(opt *DoiSpiderOpt) (urls []string)

ScienseComSpider access sciencemag.org journal files via spider

func ScihupSpider

func ScihupSpider(opt *DoiSpiderOpt) (urls []string)

ScihupSpider access http://sci-hub.tw/ files via spider

func SpringerComSpider

func SpringerComSpider(opt *DoiSpiderOpt) (urls []string)

func TandfonlineSpider

func TandfonlineSpider(opt *DoiSpiderOpt) (urls []string)

TandfonlineSpider access https://www.tandfonline.com files via spider not support now, need chromedp

func TheietOrgSpider

func TheietOrgSpider(opt *DoiSpiderOpt) (urls []string)

func ThiemeConnectDeSpider

func ThiemeConnectDeSpider(opt *DoiSpiderOpt) (urls []string)

func ThnoOrgSpider

func ThnoOrgSpider(opt *DoiSpiderOpt) (urls []string)

func TosOrgSpider

func TosOrgSpider(opt *DoiSpiderOpt) (urls []string)

func UniVersalDoiSpider

func UniVersalDoiSpider(opt *DoiSpiderOpt) (urls []string)

func UniVersalDoiSpiderListenPart1

func UniVersalDoiSpiderListenPart1(c *colly.Collector, opt *DoiSpiderOpt, urls *[]string)

func UniVersalDoiSpiderListenPart2

func UniVersalDoiSpiderListenPart2(c *colly.Collector, opt *DoiSpiderOpt, urls *[]string)

func UniVersalDoiSpiderListenPart3

func UniVersalDoiSpiderListenPart3(c *colly.Collector, opt *DoiSpiderOpt, urls *[]string)

func UniVersalDoiSpiderListenPart4

func UniVersalDoiSpiderListenPart4(c *colly.Collector, opt *DoiSpiderOpt, urls *[]string)

func Visit

func Visit(c *colly.Collector, url string) error

func WileyComSpider

func WileyComSpider(opt *DoiSpiderOpt) (urls []string)

WileyComSpider access https://onlinelibrary.wiley.com files via spider

func ZenodoSpider

func ZenodoSpider(opt *DoiSpiderOpt) (urls []string)

ZenodoSpider access Zendo files via spider

Types

type DoiSpiderOpt

type DoiSpiderOpt struct {
	Doi               string
	Proxy             string
	Timeout           int
	FullText          bool
	Supplementary     bool
	Citations         bool
	PrintSiteMeta     bool
	PrintCrossRefMeta bool
	CitationMeta      *map[string]string
	URL               *neturl.URL
}

type QuerySpiderOpt

type QuerySpiderOpt struct {
	Query   string
	Proxy   string
	Timeout int
}

Jump to

Keyboard shortcuts

? : This menu
/ : Search site
f or F : Jump to
y or Y : Canonical URL