aparler/RosettaCodeData
1
0
Fork 0
Code Issues 12 Pull requests 3 Projects Releases Packages Wiki Activity Actions

June 2018 Update

Browse source
This commit is contained in:
Ingy döt Net 2018-06-22 20:57:24 +00:00
parent ba8067c3b7
commit 22f33d4004
5278 changed files with 84726 additions and 14379 deletions
Download patch file Download diff file Expand all files Collapse all files

14
Task/Web-scraping/00DESCRIPTION
View file

@ -23,13 +23,13 @@ The relevant part of that page source looked like this:
<TITLE>What time is it?</TITLE>
<H2> US Naval Observatory Master Clock Time</H2> <H3><PRE>
<BR>Jul. 27, 22:57:22 UTC Universal Time
<BR>Jul. 27, 06:57:22 PM EDT Eastern Time
<BR>Jul. 27, 05:57:22 PM CDT Central Time
<BR>Jul. 27, 04:57:22 PM MDT Mountain Time
<BR>Jul. 27, 03:57:22 PM PDT Pacific Time
<BR>Jul. 27, 02:57:22 PM AKDT Alaska Time
<BR>Jul. 27, 12:57:22 PM HAST Hawaii-Aleutian Time
<BR>Jul. 27, 22:57:22 UTC Universal Time
<BR>Jul. 27, 06:57:22 PM EDT Eastern Time
<BR>Jul. 27, 05:57:22 PM CDT Central Time
<BR>Jul. 27, 04:57:22 PM MDT Mountain Time
<BR>Jul. 27, 03:57:22 PM PDT Pacific Time
<BR>Jul. 27, 02:57:22 PM AKDT Alaska Time
<BR>Jul. 27, 12:57:22 PM HAST Hawaii-Aleutian Time
...
</pre>

2
Task/Web-scraping/8th/web-scraping.8th
View file

@ -6,7 +6,7 @@
: get-time
read-url
/<BR>.*?(\d{2}:\d{2}:\d{2})\sUTC/
/<BR>.*?(\d{2}:\d{2}:\d{2})\sUTC/
tuck r:match if
1 r:@ . cr
then ;

12
Task/Web-scraping/App-Inventor/web-scraping.app
View file

@ -1,9 +1,9 @@
when ScrapeButton.Click do
set ScrapeWeb.Url to SourceTextBox.Text
call ScrapeWeb.Get
set ScrapeWeb.Url to SourceTextBox.Text
call ScrapeWeb.Get
when ScrapeWeb.GotText url,responseCode,responseType,responseContent do
initialize local Left to split at first text (text: get responseContent, at: PreTextBox.Text)
initialize local Right to "" in
set Right to select list item (list: get Left, index: 2)
set ResultLabel.Text to select list item (list: split at first (text:get Right, at: PostTextBox.Text), index: 1)
initialize local Left to split at first text (text: get responseContent, at: PreTextBox.Text)
initialize local Right to "" in
set Right to select list item (list: get Left, index: 2)
set ResultLabel.Text to select list item (list: split at first (text:get Right, at: PostTextBox.Text), index: 1)

102
Task/Web-scraping/Cache-ObjectScript/web-scraping.cos
View file

@ -3,58 +3,58 @@ Class Utils.Net [ Abstract ]
ClassMethod ExtractHTMLData(pHost As %String = "", pPath As %String = "", pRegEx As %String = "", Output list As %List) As %Status
{
// implement error handling
Try {
// implement error handling
Try {
// some initialisation
Set list="", sc=$$$OK
// check input parameters
If $Match(pHost, "^([a-zA-Z0-9]([a-zA-Z0-9\-]{0,61}[a-zA-Z0-9])?\.)+[a-zA-Z]{2,6}$")=0 {
Set sc=$$$ERROR($$$GeneralError, "Invalid host name.")
Quit
}
// create http request and get page
Set req=##class(%Net.HttpRequest).%New()
Set req.Server=pHost
Do req.Get(pPath)
// check for success
If $Extract(req.HttpResponse.StatusCode)'=2 {
Set sc=$$$ERROR($$$GeneralError, "Page not loaded.")
Quit
}
// read http response stream
Set html=req.HttpResponse.Data
Set html.LineTerminator=$Char(10)
Set sc=html.Rewind()
// read http response stream
While 'html.AtEnd {
Set line=html.ReadLine(, .sc, .eol)
Set pos=$Locate(line, pRegEx)
If pos {
Set parse=$Piece($Extract(line, pos, *), $Char(9))
Set slot=$ListLength(list)+1
Set $List(list, slot)=parse
}
}
} Catch err {
// an error has occurred
If err.Name="<REGULAR EXPRESSION>" {
Set sc=$$$ERROR($$$GeneralError, "Invalid regular expression.")
} Else {
Set sc=$$$ERROR($$$CacheError, $ZError)
}
}
// return status
Quit sc
// some initialisation
Set list="", sc=$$$OK
// check input parameters
If $Match(pHost, "^([a-zA-Z0-9]([a-zA-Z0-9\-]{0,61}[a-zA-Z0-9])?\.)+[a-zA-Z]{2,6}$")=0 {
Set sc=$$$ERROR($$$GeneralError, "Invalid host name.")
Quit
}
// create http request and get page
Set req=##class(%Net.HttpRequest).%New()
Set req.Server=pHost
Do req.Get(pPath)
// check for success
If $Extract(req.HttpResponse.StatusCode)'=2 {
Set sc=$$$ERROR($$$GeneralError, "Page not loaded.")
Quit
}
// read http response stream
Set html=req.HttpResponse.Data
Set html.LineTerminator=$Char(10)
Set sc=html.Rewind()
// read http response stream
While 'html.AtEnd {
Set line=html.ReadLine(, .sc, .eol)
Set pos=$Locate(line, pRegEx)
If pos {
Set parse=$Piece($Extract(line, pos, *), $Char(9))
Set slot=$ListLength(list)+1
Set $List(list, slot)=parse
}
}
} Catch err {
// an error has occurred
If err.Name="<REGULAR EXPRESSION>" {
Set sc=$$$ERROR($$$GeneralError, "Invalid regular expression.")
} Else {
Set sc=$$$ERROR($$$CacheError, $ZError)
}
}
// return status
Quit sc
}
}

31
Task/Web-scraping/Ceylon/web-scraping.ceylon Normal file
View file

@ -0,0 +1,31 @@
import ceylon.uri {
parse
}
import ceylon.http.client {
get
}
shared void run() {
// apparently the cgi link is deprecated?
value oldUri = "http://tycho.usno.navy.mil/cgi-bin/timer.pl";
value newUri = "http://tycho.usno.navy.mil/timer.pl";
value contents = downloadContents(newUri);
value time = extractTime(contents);
print(time else "nothing found");
}
String downloadContents(String uriString) {
value uri = parse(uriString);
value request = get(uri);
value response = request.execute();
return response.contents;
}
String? extractTime(String contents) =>
contents
.lines
.filter((String element) => element.contains("UTC"))
.first
?.substring(4, 21);

2
Task/Web-scraping/Delphi/web-scraping-1.delphi
View file

@ -146,7 +146,7 @@ begin
for i := 0 to Pred(HTTPResponse.Count) do
begin
{ The line we're looking for is something like this:
<BR>May. 04. 21:55:19 UTC Universal Time }
<BR>May. 04. 21:55:19 UTC Universal Time }
// Check each line
if Pos('UTC',HTTPResponse[i]) > 0 then

8
Task/Web-scraping/Erlang/web-scraping.erl
View file

@ -4,7 +4,7 @@
-define(Match, "<BR>(.+ UTC)").
main() ->
inets:start(),
{ok, {_Status, _Header, HTML}} = httpc:request(?Url),
{match, [Time]} = re:run(HTML, ?Match, [{capture, all_but_first, binary}]),
io:format("~s~n",[Time]).
inets:start(),
{ok, {_Status, _Header, HTML}} = httpc:request(?Url),
{match, [Time]} = re:run(HTML, ?Match, [{capture, all_but_first, binary}]),
io:format("~s~n",[Time]).

30
Task/Web-scraping/Java/web-scraping.java
View file

@ -6,19 +6,19 @@ import java.net.URLConnection;
public class WebTime{
public static void main(String[] args){
try{
URL address = new URL(
"http://tycho.usno.navy.mil/cgi-bin/timer.pl");
URLConnection conn = address.openConnection();
BufferedReader in = new BufferedReader(
new InputStreamReader(conn.getInputStream()));
String line;
while(!(line = in.readLine()).contains("UTC"));
System.out.println(line.substring(4));
}catch(IOException e){
System.err.println("error connecting to server.");
e.printStackTrace();
}
}
public static void main(String[] args){
try{
URL address = new URL(
"http://tycho.usno.navy.mil/cgi-bin/timer.pl");
URLConnection conn = address.openConnection();
BufferedReader in = new BufferedReader(
new InputStreamReader(conn.getInputStream()));
String line;
while(!(line = in.readLine()).contains("UTC"));
System.out.println(line.substring(4));
}catch(IOException e){
System.err.println("error connecting to server.");
e.printStackTrace();
}
}
}

4
Task/Web-scraping/Julia/web-scraping-1.julia
View file

@ -8,8 +8,8 @@ function getusnotime()
@sprintf "get(%s)\n => %s" url err
end
isa(s, Requests.Response) || return (s, false)
t = match(r"(?<=<BR>)(.*?UTC)", readall(s))
isa(t, RegexMatch) || return (@sprintf("raw html:\n %s", readall(s)), false)
t = match(r"(?<=<BR>)(.*?UTC)", readstring(s))
isa(t, RegexMatch) || return (@sprintf("raw html:\n %s", readstring(s)), false)
return (t.match, true)
end

18
Task/Web-scraping/Lasso/web-scraping.lasso
View file

@ -1,13 +1,13 @@
/* have to be used
local(raw_htmlstring = '<TITLE>What time is it?</TITLE>
<H2> US Naval Observatory Master Clock Time</H2> <H3><PRE>
<BR>Jul. 27, 22:57:22 UTC Universal Time
<BR>Jul. 27, 06:57:22 PM EDT Eastern Time
<BR>Jul. 27, 05:57:22 PM CDT Central Time
<BR>Jul. 27, 04:57:22 PM MDT Mountain Time
<BR>Jul. 27, 03:57:22 PM PDT Pacific Time
<BR>Jul. 27, 02:57:22 PM AKDT Alaska Time
<BR>Jul. 27, 12:57:22 PM HAST Hawaii-Aleutian Time
<BR>Jul. 27, 22:57:22 UTC Universal Time
<BR>Jul. 27, 06:57:22 PM EDT Eastern Time
<BR>Jul. 27, 05:57:22 PM CDT Central Time
<BR>Jul. 27, 04:57:22 PM MDT Mountain Time
<BR>Jul. 27, 03:57:22 PM PDT Pacific Time
<BR>Jul. 27, 02:57:22 PM AKDT Alaska Time
<BR>Jul. 27, 12:57:22 PM HAST Hawaii-Aleutian Time
</PRE></H3>
')
*/
@ -16,8 +16,8 @@ local(raw_htmlstring = '<TITLE>What time is it?</TITLE>
local(raw_htmlstring = string(include_url('http://tycho.usno.navy.mil/cgi-bin/timer.pl')))
local(
reg_exp = regexp(-find = `<br>(.*?) UTC`, -input = #raw_htmlstring, -ignorecase),
datepart_txt = #reg_exp -> find ? #reg_exp -> matchstring(1) | string
reg_exp = regexp(-find = `<br>(.*?) UTC`, -input = #raw_htmlstring, -ignorecase),
datepart_txt = #reg_exp -> find ? #reg_exp -> matchstring(1) | string
)
#datepart_txt

2
Task/Web-scraping/MATLAB/web-scraping.m
View file

@ -3,6 +3,6 @@ ix = [findstr(s,'<BR>'), length(s)+1];
for k = 2:length(ix)
tok = s(ix(k-1)+4:ix(k)-1);
if findstr(tok,'UTC')
disp(tok);
disp(tok);
end;
end;

2
Task/Web-scraping/Maple/web-scraping.maple Normal file
View file

@ -0,0 +1,2 @@
text := URL:-Get("http://tycho.usno.navy.mil/cgi-bin/timer.pl"):
printf(StringTools:-StringSplit(text,"<BR>")[2]);

6
Task/Web-scraping/PHP/web-scraping-2.php
View file

@ -1,7 +1,7 @@
<?
echo preg_replace(
"/^.*<BR>(.*) UTC.*$/su",
"\\1",
file_get_contents('http://tycho.usno.navy.mil/cgi-bin/timer.pl')
"/^.*<BR>(.*) UTC.*$/su",
"\\1",
file_get_contents('http://tycho.usno.navy.mil/cgi-bin/timer.pl')
);

8
Task/Web-scraping/REBOL/web-scraping.rebol
View file

@ -1,8 +1,8 @@
REBOL [
Title: "Web Scraping"
Author: oofoe
Date: 2009-12-07
URL: http://rosettacode.org/wiki/Web_Scraping
Title: "Web Scraping"
Author: oofoe
Date: 2009-12-07
URL: http://rosettacode.org/wiki/Web_Scraping
]
; Notice that REBOL understands unquoted URL's:

12
Task/Web-scraping/Scala/web-scraping.scala
View file

@ -1,10 +1,10 @@
import scala.io.Source
object WebTime extends Application {
val text = Source.fromURL("http://tycho.usno.navy.mil/cgi-bin/timer.pl")
val utc = text.getLines.find(_.contains("UTC"))
utc match {
case Some(s) => println(s.substring(4))
case _ => println("error")
}
val text = Source.fromURL("http://tycho.usno.navy.mil/cgi-bin/timer.pl")
val utc = text.getLines.find(_.contains("UTC"))
utc match {
case Some(s) => println(s.substring(4))
case _ => println("error")
}
}

38
Task/Web-scraping/VBA/web-scraping.vba Normal file
View file

@ -0,0 +1,38 @@
Rem add Microsoft VBScript Regular Expression X.X to your Tools References
Function GetUTC() As String
Url = "http://tycho.usno.navy.mil/cgi-bin/timer.pl"
With CreateObject("MSXML2.XMLHTTP.6.0")
.Open "GET", Url, False
.send
arrt = Split(.responseText, vbLf)
End With
For Each t In arrt
If InStr(t, "UTC") Then
GetUTC = StripHttpTags(t)
Exit For
End If
Next
End Function
Function StripHttpTags(s)
With New RegExp
.Global = True
.Pattern = "\<.+?\>"
If .Test(s) Then
StripHttpTags = .Replace(s, "")
Else
StripHttpTags = s
End If
End With
End Function
Sub getTime()
Rem starting point
Dim ReturnValue As String
ReturnValue = GetUTC
Rem debug.print can be removed
Debug.Print ReturnValue
MsgBox (ReturnValue)
End Sub

45
Task/Web-scraping/VBScript/web-scraping.vb
View file

@ -1,28 +1,29 @@
Function GetUTC()
url = "http://tycho.usno.navy.mil/cgi-bin/timer.pl"
With CreateObject("MSXML2.XMLHTTP.6.0")
.open "GET", url, False
.send
arrt = Split(.responseText,vbLf)
End With
For Each t In arrt
If InStr(t,"UTC") Then
GetUTC = StripHttpTags(t)
Exit For
End If
Next
Function GetUTC() As String
Url = "http://tycho.usno.navy.mil/cgi-bin/timer.pl"
With CreateObject("MSXML2.XMLHTTP.6.0")
.Open "GET", Url, False
.send
arrt = Split(.responseText, vbLf)
End With
For Each t In arrt
If InStr(t, "UTC") Then
GetUTC = StripHttpTags(t)
Exit For
End If
Next
End Function
Function StripHttpTags(s)
With New RegExp
.Global = True
.Pattern = "\<.+?\>"
If .Test(s) Then
StripHttpTags = .Replace(s,"")
Else
StripHttpTags = s
End If
End With
With New RegExp
.Global = True
.Pattern = "\<.+?\>"
If .Test(s) Then
StripHttpTags = .Replace(s, "")
Else
StripHttpTags = s
End If
End With
End Function
WScript.StdOut.Write GetUTC