## ----eval=FALSE--------------------------------------------------------------- # install.packages("wikiTools") ## ----echo=TRUE---------------------------------------------------------------- library(wikiTools) ## ----eval=FALSE--------------------------------------------------------------- # df <- w_SearchByLabel(string='Iranzo', langsorder='es|en') # df <- w_SearchByLabel(string='Iranzo', langsorder='es|en', instanceof = 'Q5') # df <- w_SearchByLabel(string='Iranzo', langsorder='es|en', instanceof = 'Q5|Q101352') # df <- w_SearchByLabel(string='Iranzo', langsorder='es|en', instanceof = 'Q5', # Pproperty = 'P21|P569|P570') ## ----eval=FALSE--------------------------------------------------------------- # df <- w_SearchByLabel(string='Iranzo', lang='en', langsorder='es|en', mode='startswith') # df <- w_SearchByLabel(string='Iranzo', lang='en', langsorder='es|en', instanceof = 'Q5', # mode='startswith') # df <- w_SearchByLabel(string='Iranzo', lang='en', langsorder='es|en', # instanceof = 'Q5|Q101352', mode='startswith') # df <- w_SearchByLabel(string='Iranzo', lang='en', langsorder='en', instanceof = 'Q5', # Pproperty = 'P21|P569|P570', mode='startswith') ## ----eval = FALSE------------------------------------------------------------- # df <- w_SearchByLabel(string='Iranzo', langsorder='es|en', mode='inlabel') ## ----eval=FALSE--------------------------------------------------------------- # df <- w_SearchByLabel(string='Iranzo', langsorder='zh|es', lang='zh', mode='inlabel') ## ----eval = FALSE------------------------------------------------------------- # df <- w_SearchByLabel(string='Iranzo', langsorder='es|en', instanceof = 'Q5', # mode='inlabel') # df <- w_SearchByLabel(string='Iranzo', langsorder='es|en', instanceof = 'Q5|Q101352', # mode='inlabel') # df <- w_SearchByLabel(string='Iranzo', langsorder='es|en', instanceof = 'Q5', # Pproperty = 'P21|P569|P570', mode='inlabel') ## ----w_SearchByLabel, echo=TRUE----------------------------------------------- df <- w_SearchByLabel(string='Iranzo', langsorder='es|en', mode='inlabel') if(length(df)){ l <- df$entity } ## ----w_isIntanceOf, echo=TRUE------------------------------------------------- df <- w_isInstanceOf(entity_list=l, instanceof='Q5') # Not TRUE if(length(df)){ df[!df$instanceof_Q5,] } ## ----eval = FALSE------------------------------------------------------------- # df <- w_Wikipedias(entity_list=l) # df <- w_Wikipedias(entity_list=l, wikilangs='es|en|fr') # df <- w_Wikipedias(entity_list=l, wikilangs='es|en|fr', instanceof="Q5") ## ----w_SearchByOccupation, eval = FALSE--------------------------------------- # w_SearchByOccupation(Qoc="Q2306091", mode='count') # "Q2306091" Qoc for Sociologist # q <- w_SearchByOccupation(Qoc="Q2306091") ## ----echo=TRUE, eval=FALSE---------------------------------------------------- # lw <- w_SearchByOccupation(Qoc='Q2306091', mode='wikipedias') # lw=dataframe # # We can obtain the same information using previous function w_Wikipedias: # lw2 <- w_Wikipedias(entity_list=l) # # Verifying: # all(lw['Q10320558','pages'] == lw2['Q10320558','pages']) # # Verifying: # all(sort(strsplit(lw['Q9061', 'pages'], '|', fixed = T)[[1]]) == # sort(strsplit(lw2['Q9061', 'pages'], '|', fixed = T)[[1]])) ## ----w_isValid, echo=TRUE----------------------------------------------------- l2 <- append(l, c("Q115637688", "Q105660123")) # Note: adding two new entities v <- w_isValid(l2) if(length(v)){ # Not valid v[!v$valid,] } ## ----eval = FALSE------------------------------------------------------------- # p <- w_Property(l, Pproperty = 'P21|P569|P214', langsorder = 'es|en') ## ----eval = FALSE------------------------------------------------------------- # mncars <- w_SearchByAuthority(Pauthority="P4439", langsorder = 'es|en') # # 1286 [human, groups, etc.] # mncarsQ5 <- w_SearchByAuthority(Pauthority="P4439", langsorder = 'es|en', # instanceof = 'Q5') # 1280 # # Entities are not 'human' (Q5) [see entityDescription column): # mncars <- w_SearchByAuthority(Pauthority="P4439", langsorder = 'es|en') # if(length(mncars) && length(mncarsQ5)){ # mncars[!(mncars$entity %in% mncarsQ5$entity),] # not instance of Q5. # } ## ----eval = FALSE------------------------------------------------------------- # df <- w_EntityInfo(entity_list='Q134644', langsorder='es|en') # df <- w_EntityInfo(entity_list='Q134644', langsorder='es|en', wikilangs='es|en|fr') # df <- w_EntityInfo(c('Q270510', 'Q1675466', 'Q24871'), mode='film', langsorder='es|en', wikilangs='es|en|fr') # # Search string 'van Beethoven' inlabel # w <- w_SearchByLabel('van Beethoven', mode='inlabel', langsorder = '', instanceof = 'Q5') # if(length(w)){ # df <- w_EntityInfo(w$entity, langsorder='en', wikilangs='en|es|fr', debug='info') # } # # Search 3D films # w <- w_SearchByInstanceof(instanceof='Q229390', langsorder = 'en|es', debug = 'info') # if(length(w)){ # df <- w_EntityInfo(w$entity, mode="film", langsorder='en', wikilangs='en', debug='info') # } ## ----eval = FALSE------------------------------------------------------------- # df <- m_Opensearch(string='Duque de Alba', project='es.wikipedia.org', # profile="engine_autoselect", redirects="resolve") # df <- m_Opensearch(string='Duque de Alba', project='es.wikipedia.org', profile="strict") # df <- m_Opensearch(string='Duque de Alba', project='es.wikipedia.org', profile="fuzzy") ## ----eval = FALSE------------------------------------------------------------- # df <- m_reqMediaWiki(c('Max Planck', URLdecode("a%CC%8C"), 'Max', 'Cervante', 'humanist'), # mode='wikidataEntity', project='en.wikipedia.org') ## ----mreqMediaWiki, echo=TRUE------------------------------------------------- a <- m_reqMediaWiki(c('Cervantes', 'Planck', 'Noexiste'), mode='redirects', project='es.wikipedia.org') a ## ----eval = FALSE------------------------------------------------------------- # i <- m_reqMediaWiki(c('Max Planck', URLdecode("a%CC%8C"), 'Max', 'Cervante', 'humanist'), # mode='pagePrimaryImage') # # f <- m_reqMediaWiki(c('Max Planck', URLdecode("a%CC%8C"), 'Max', 'Cervante', 'humanist'), # mode='pageFiles', exclude_ext = "svg|webp|xcf") ## ----eval = FALSE------------------------------------------------------------- # v <- m_Pageviews(article="Miguel de Cervantes", start="20230101", end="2026028", # project="es.wikipedia.org", granularity="monthly") ## ----eval = FALSE------------------------------------------------------------- # x <- m_XtoolsInfo(article="Cervantes", infotype="articleinfo", project="es.wikipedia.org") # xx <- m_XtoolsInfo(article="Cervantes", infotype="articleinfo", project="es.wikipedia.org", # redirects=TRUE) # # y <- m_XtoolsInfo(article="Miguel de Cervantes", infotype="links", project="es.wikipedia.org") # yy <- m_XtoolsInfo(article="Cervantes", infotype="links", project="es.wikipedia.org", # redirects=TRUE) ## ----eval = FALSE------------------------------------------------------------- # z <- m_XtoolsInfo(article="Miguel de Cervantes", infotype="all", project="es.wikipedia.org") # zz <- m_XtoolsInfo(article="Cervantes", infotype="all", project="es.wikipedia.org", # redirects=TRUE) ## ----eval = FALSE------------------------------------------------------------- # v_AutoSuggest('Iranzo') # v_AutoSuggest('Esparza, María') # v_AutoSuggest('Escobar, Modesto') # # Note that four rows are returned, but only two different viafids. ## ----v_Search, echo=TRUE------------------------------------------------------ CQL_Query <- 'cql.any = "García Iranzo, Juan"' r <- v_Search(CQL_Query) # r contains complete VIAF records (sometimes seen as a "cluster record", # which is unified by combining records from many libraries around the world) v_Extract(r) ## ----echo=TRUE---------------------------------------------------------------- r <- v_Search("García Iranzo, Juan", mode="anyField") v_Extract(r) ## ----eval = FALSE------------------------------------------------------------- # CQL_Query <- 'local.names all "Figuerola"' # r <- v_Search(CQL_Query) ## ----eval = FALSE------------------------------------------------------------- # r2 <- v_Search("Figuerola", mode="allNames") # cat(length(r), length(r2)) ## ----eval = FALSE------------------------------------------------------------- # CQL_Query <- 'local.names all "Bolero"' # r3 <- v_Search(CQL_Query) ## ----echo=TRUE---------------------------------------------------------------- CQL_Query <- 'local.personalNames all "Modesto Escobar"' r <- v_Search(CQL_Query) v_Extract(r) ## ----eval = FALSE------------------------------------------------------------- # r <- v_Search("Escobar Mercado, Modesto", mode='allmainHeadingEl') ## ----echo=TRUE---------------------------------------------------------------- CQL_Query <- 'local.title all "Los pronósticos electorales con encuestas"' r <- v_Search(CQL_Query) v_Extract(r)