ARTstor
Biodiversity Heritage Library
Chronicling America Library of Congress National Digital Newspaper Program
Connecting Repositories (CORE)
Data Archiving and Networked Services (DANS)
Data-PASS
Digital Library for Earth System Education (DLESE)
Early Canadiana Online
English Broadside Ballad Archive (EBBA)
Europeana
FLOSSmole
Great War Primary Documents Archive
HathiTrust
History Data Service (HDS)
Infochimps.org
Inter-university Consortium for Political and Social Research
Internet Archive
Jisc MediaHub
JSTOR
Koninklijke Bibliotheek
Core.ac.uk
APIs
Chronicling America (Library Of Congress) - A digitized collection of American newspaper articles from the 18th to the 20th century.
Connecting Repositories (CORE) - A collection of open access articles from various sources hosted by the Open University.
English Broadside Ballad Archive (EBBA)
History Data Service (HDS) - A collection of data from a wide variety of historical sources.
Digging into Data API List
Tuesday, February 25, 2020
Sunday, February 16, 2020
Autohotkey for Google Translate
^!r::Reload ; Assign Alt-Ctr-R as a hotkey to restart the script.
#x:: ; Windows+X - Translate segment MemoQ, Across, Trados Studio with Google Translate
FileEncoding, utf-8
WinGetActiveTitle, Title
IfInString, Title, memoQ
{
Send ^+s
Sleep, 200
SendInput ^{F8}
Sleep, 300
SendInput ^a
Sleep, 300
SendInput ^c
Clipwait
Send ^c
Sleep, 300
Clipwait
Sleep, 200
}
IfInString, Title, Across
{
Send !{PgDn}
Sleep, 200
SendInput ^a
Sleep, 300
}
IfInString, Title, Trados Studio
{
Sleep, 300
Send ^{Ins}
Sleep, 200
SendInput ^a
Sleep, 300
}
SendInput ^c
Clipwait
Send ^c
Sleep, 300
Clipwait
Sleep, 300
Clipwait
Sleep, 300
searchtext := clipboard
;StringReplace, searchtext, searchtext, .%A_SPACE%, ._, All ;StringReplace, searchtext, searchtext, %A_SPACE%., _., All
;StringReplace, searchtext, searchtext, `;%A_SPACE%, `;_, All, ; `%5F - for underscore
;StringReplace, searchtext, searchtext, `.%A_SPACE%, `._, All ;Msgbox %searchtexturlencoded%
searchtexturlencoded := UriEncode(searchtext)
;searchtexturlencoded := URLEncoding(searchtext)
; StringReplace, searchtext, searchtext, %A_SPACE%&%A_SPACE%, `%26, All
; StringReplace, searchtext, searchtext, %A_SPACE%, +, All
Sleep, 300
RunWait, wget.exe -U "Mozilla/5.0 Chrome/62.0.3202.94" "http://translate.googleapis.com/translate_a/single?client=gtx&sl=auto&tl=de&dt=t&q=%searchtexturlencoded%" -O source.out.txt,, Hide
FileRead, targettext, source.out.txt ;Msgbox %targettext%
StringTrimLeft, targettext, targettext, 4
StringTrimRight, targettext, targettext, 73
quotes := ""","""
Loop, 4 ;MsgBox, Iteration number is %A_Index%.
{
addedvalue := (A_Index - 1)
textbreak = "`,null`,null`,%addedvalue%`]`,`[" ;MsgBox Textbreak %textbreak%
IfInString, targettext, %textbreak%
{
StringReplace, targettext, targettext, %textbreak%, ‡, All ;Msgbox targettext . %targettext%
}
}
occurences =
Loop, Parse, targettext, ‡
{
loopingtext = %A_LoopField% ;Msgbox Loopfield: %loopingtext%
StringLen, targetlength, loopingtext
StringGetPos, posghilimele, loopingtext, %quotes% ;MsgBox Poziţie glilimele %posghilimele% Msgbox Target length %targetlength%
StringLen, targetlength, loopingtext
StringTrimRight, occurence, loopingtext, (targetlength - posghilimele)
occurences .= occurence ;Msgbox occurence after add %occurences% ;occurences := occurences . occurence
}
StringReplace, occurences, occurences, ș, ş, All
StringReplace, occurences, occurences, Ș, Ş, All
StringReplace, occurences, occurences, ț, ţ, All
StringReplace, occurences, occurences, Ț, Ţ, All
StringReplace, occurences, occurences, %A_SPACE%._%A_SPACE%, .%A_SPACE%, All
StringReplace, occurences, occurences, `;%A_SPACE%_, `;%A_SPACE%, All
StringReplace, occurences, occurences, `;%A_SPACE%%A_SPACE%, `;%A_SPACE%, All
StringReplace, occurences, occurences, `._, `.%A_SPACE%, All
occurences := UnSlashUnicode(occurences)
Clipboard = %occurences% ;googleout := Clipboard
Send ^v
Reload
; IfInString, Title, memoQ {Send ^{Enter} ;Send ^+{Enter}Send !{Up}}
return
uriDecode(str) {
Loop
If RegExMatch(str, "i)(?<=%)[\da-f]{1,2}", hex)
StringReplace, str, str, `%%hex%, % Chr("0x" . hex), All
Else Break
return
, str
}
UriEncode(Uri, RE="[0-9A-Za-z]"){
VarSetCapacity(Var,StrPut(Uri,"UTF-8"),0),StrPut(Uri,&Var,"UTF-8")
While Code:=NumGet(Var,A_Index-1,"UChar")
Res.=(Chr:=Chr(Code))~=RE?Chr:Format("%{:02X}",Code)
return, Res
}
UnSlashUnicode(s) ; unslash unicode sequences like \u0026
{
rx = \\u([0-9a-fA-F]{4})
pos = 0
loop
{
pos := RegExMatch(s,rx,m,pos+1)
if (pos = 0)
break
StringReplace, s, s, %m%, % Chr("0x" . SubStr(m,3,4))
}
return, s
}
#x:: ; Windows+X - Translate segment MemoQ, Across, Trados Studio with Google Translate
FileEncoding, utf-8
WinGetActiveTitle, Title
IfInString, Title, memoQ
{
Send ^+s
Sleep, 200
SendInput ^{F8}
Sleep, 300
SendInput ^a
Sleep, 300
SendInput ^c
Clipwait
Send ^c
Sleep, 300
Clipwait
Sleep, 200
}
IfInString, Title, Across
{
Send !{PgDn}
Sleep, 200
SendInput ^a
Sleep, 300
}
IfInString, Title, Trados Studio
{
Sleep, 300
Send ^{Ins}
Sleep, 200
SendInput ^a
Sleep, 300
}
SendInput ^c
Clipwait
Send ^c
Sleep, 300
Clipwait
Sleep, 300
Clipwait
Sleep, 300
searchtext := clipboard
;StringReplace, searchtext, searchtext, .%A_SPACE%, ._, All ;StringReplace, searchtext, searchtext, %A_SPACE%., _., All
;StringReplace, searchtext, searchtext, `;%A_SPACE%, `;_, All, ; `%5F - for underscore
;StringReplace, searchtext, searchtext, `.%A_SPACE%, `._, All ;Msgbox %searchtexturlencoded%
searchtexturlencoded := UriEncode(searchtext)
;searchtexturlencoded := URLEncoding(searchtext)
; StringReplace, searchtext, searchtext, %A_SPACE%&%A_SPACE%, `%26, All
; StringReplace, searchtext, searchtext, %A_SPACE%, +, All
Sleep, 300
RunWait, wget.exe -U "Mozilla/5.0 Chrome/62.0.3202.94" "http://translate.googleapis.com/translate_a/single?client=gtx&sl=auto&tl=de&dt=t&q=%searchtexturlencoded%" -O source.out.txt,, Hide
FileRead, targettext, source.out.txt ;Msgbox %targettext%
StringTrimLeft, targettext, targettext, 4
StringTrimRight, targettext, targettext, 73
quotes := ""","""
Loop, 4 ;MsgBox, Iteration number is %A_Index%.
{
addedvalue := (A_Index - 1)
textbreak = "`,null`,null`,%addedvalue%`]`,`[" ;MsgBox Textbreak %textbreak%
IfInString, targettext, %textbreak%
{
StringReplace, targettext, targettext, %textbreak%, ‡, All ;Msgbox targettext . %targettext%
}
}
occurences =
Loop, Parse, targettext, ‡
{
loopingtext = %A_LoopField% ;Msgbox Loopfield: %loopingtext%
StringLen, targetlength, loopingtext
StringGetPos, posghilimele, loopingtext, %quotes% ;MsgBox Poziţie glilimele %posghilimele% Msgbox Target length %targetlength%
StringLen, targetlength, loopingtext
StringTrimRight, occurence, loopingtext, (targetlength - posghilimele)
occurences .= occurence ;Msgbox occurence after add %occurences% ;occurences := occurences . occurence
}
StringReplace, occurences, occurences, ș, ş, All
StringReplace, occurences, occurences, Ș, Ş, All
StringReplace, occurences, occurences, ț, ţ, All
StringReplace, occurences, occurences, Ț, Ţ, All
StringReplace, occurences, occurences, %A_SPACE%._%A_SPACE%, .%A_SPACE%, All
StringReplace, occurences, occurences, `;%A_SPACE%_, `;%A_SPACE%, All
StringReplace, occurences, occurences, `;%A_SPACE%%A_SPACE%, `;%A_SPACE%, All
StringReplace, occurences, occurences, `._, `.%A_SPACE%, All
occurences := UnSlashUnicode(occurences)
Clipboard = %occurences% ;googleout := Clipboard
Send ^v
Reload
; IfInString, Title, memoQ {Send ^{Enter} ;Send ^+{Enter}Send !{Up}}
return
uriDecode(str) {
Loop
If RegExMatch(str, "i)(?<=%)[\da-f]{1,2}", hex)
StringReplace, str, str, `%%hex%, % Chr("0x" . hex), All
Else Break
return
, str
}
UriEncode(Uri, RE="[0-9A-Za-z]"){
VarSetCapacity(Var,StrPut(Uri,"UTF-8"),0),StrPut(Uri,&Var,"UTF-8")
While Code:=NumGet(Var,A_Index-1,"UChar")
Res.=(Chr:=Chr(Code))~=RE?Chr:Format("%{:02X}",Code)
return, Res
}
UnSlashUnicode(s) ; unslash unicode sequences like \u0026
{
rx = \\u([0-9a-fA-F]{4})
pos = 0
loop
{
pos := RegExMatch(s,rx,m,pos+1)
if (pos = 0)
break
StringReplace, s, s, %m%, % Chr("0x" . SubStr(m,3,4))
}
return, s
}
Subscribe to:
Posts (Atom)