Yahoo! search interface
You are encouraged to solve this task according to the task description, using any language you may know.
Create a class for searching Yahoo! results.
It must implement a Next Page method, and read URL, Title and Content from results.
AArch64 Assembly
/* ARM assembly AARCH64 Raspberry PI 3B */
/* program yahoosearch64.s */
/* access RosettaCode.org and data extract */
/* use openssl for access to port 443 */
/* test openssl : package libssl-dev */
/*******************************************/
/* Constantes file */
/*******************************************/
/* for this file see task include a file in language AArch64 assembly*/
.include "../includeConstantesARM64.inc"
.equ TAILLEBUFFER, 500
.equ SSL_OP_NO_SSLv3, 0x02000000
.equ SSL_OP_NO_COMPRESSION, 0x00020000
.equ SSL_MODE_AUTO_RETRY, 0x00000004
.equ SSL_CTRL_MODE, 33
.equ BIO_C_SET_CONNECT, 100
.equ BIO_C_DO_STATE_MACHINE, 101
.equ BIO_C_SET_SSL, 109
.equ BIO_C_GET_SSL, 110
.equ LGBUFFERREQ, 512001
/*********************************/
/* Initialized data */
/*********************************/
.data
szMessDebutPgm: .asciz "Début du programme. \n"
szRetourLigne: .asciz "\n"
szMessFinOK: .asciz "Fin normale du programme. \n"
szMessErreur: .asciz "Erreur !!!"
szMessExtractArea: .asciz "Extraction = "
szNomSite1: .asciz "search.yahoo.com:443" // host name and port
szLibStart: .asciz ">Rosetta Code" // search string
szNomrepCertif: .asciz "/pi/certificats"
szRequete1: .asciz "GET /search?p=\"Rosettacode.org\"&b=1 HTTP/1.1 \r\nHost: search.yahoo.com\r\nConnection: keep-alive\r\nContent-Type: text/plain\r\n\r\n"
/*********************************/
/* UnInitialized data */
/*********************************/
.bss
.align 4
sBufferreq: .skip LGBUFFERREQ
szExtractArea: .skip TAILLEBUFFER
stNewSSL: .skip 200
/*********************************/
/* code section */
/*********************************/
.text
.global main
main:
ldr x0,qAdrszMessDebutPgm
bl affichageMess // start message
/* connexion host port 443 and send query */
bl envoiRequete
cmp x0,#-1
beq 99f // error ?
bl analyseReponse
ldr x0,qAdrszMessFinOK // end message
bl affichageMess
mov x0, #0 // return code ok
b 100f
99:
ldr x0,qAdrszMessErreur // error
bl affichageMess
mov x0, #1 // return code error
b 100f
100:
mov x8,EXIT // program end
svc 0 // system call
qAdrszMessDebutPgm: .quad szMessDebutPgm
qAdrszMessFinOK: .quad szMessFinOK
qAdrszMessErreur: .quad szMessErreur
/*********************************************************/
/* connexion host port 443 and send query */
/*********************************************************/
envoiRequete:
stp x1,lr,[sp,-16]! // save registers
stp x2,x3,[sp,-16]! // save registers
stp x4,x5,[sp,-16]! // save registers
//*************************************
// openSsl functions use *
//*************************************
//init ssl
bl OPENSSL_init_crypto
bl ERR_load_BIO_strings
mov x2, #0
mov x1, #0
mov x0, #2
bl OPENSSL_init_crypto
mov x2, #0
mov x1, #0
mov x0, #0
bl OPENSSL_init_ssl
cmp x0,#0
blt erreur
bl TLS_client_method
bl SSL_CTX_new
cmp x0,#0
ble erreur
mov x20,x0 // save contex
ldr x1,iFlag
bl SSL_CTX_set_options
mov x0,x20 // contex
mov x1,#0
ldr x2,qAdrszNomrepCertif
bl SSL_CTX_load_verify_locations
cmp x0,#0
ble erreur
mov x0,x20 // contex
bl BIO_new_ssl_connect
cmp x0,#0
ble erreur
mov x21,x0 // save bio
mov x1,#BIO_C_GET_SSL
mov x2,#0
ldr x3,qAdrstNewSSL
bl BIO_ctrl
ldr x0,qAdrstNewSSL
ldr x0,[x0]
mov x1,#SSL_CTRL_MODE
mov x2,#SSL_MODE_AUTO_RETRY
mov x3,#0
bl SSL_ctrl
mov x0,x21 // bio
mov x1,#BIO_C_SET_CONNECT
mov x2,#0
ldr x3,qAdrszNomSite1
bl BIO_ctrl
mov x0,x21 // bio
mov x1,#BIO_C_DO_STATE_MACHINE
mov x2,#0
mov x3,#0
bl BIO_ctrl
// compute query length
mov x2,#0
ldr x1,qAdrszRequete1 // query
1:
ldrb w0,[x1,x2]
cmp x0,#0
add x8,x2,1
csel x2,x8,x2,ne
bne 1b
// send query
mov x0,x21 // bio
// x1 = address query
// x2 = length query
mov x3,#0
bl BIO_write // send query
cmp x0,#0
blt erreur
ldr x22,qAdrsBufferreq // buffer address
2: // begin loop to read datas
mov x0,x21 // bio
mov x1,x22 // buffer address
ldr x2,qLgBuffer
mov x3,#0
bl BIO_read
cmp x0,#0
ble 4f // error ou pb server
add x22,x22,x0
sub x2,x22,#8
ldr x2,[x2]
ldr x3,qCharEnd
cmp x2,x3 // text end ?
beq 4f
mov x1,#0xFFFFFF // delay loop
3:
subs x1,x1,1
bgt 3b
b 2b // loop read other chunk
4: // read end
//ldr x0,qAdrsBufferreq // to display buffer response of the query
//bl affichageMess
mov x0, x21 // close bio
bl BIO_free_all
mov x0,#0
b 100f
erreur: // error display
ldr x1,qAdrszMessErreur
bl afficheErreur
mov x0,#-1 // error code
b 100f
100:
ldp x4,x5,[sp],16 // restaur 2 registers
ldp x2,x3,[sp],16 // restaur 2 registers
ldp x1,lr,[sp],16 // restaur 2 registers
ret // return to address lr x30
qAdrszRequete1: .quad szRequete1
qAdrsBufferreq: .quad sBufferreq
iFlag: .quad SSL_OP_NO_SSLv3 | SSL_OP_NO_COMPRESSION
qAdrstNewSSL: .quad stNewSSL
qAdrszNomSite1: .quad szNomSite1
qAdrszNomrepCertif: .quad szNomrepCertif
qCharEnd: .quad 0x0A0D0A0D300A0D0A
qLgBuffer: .quad LGBUFFERREQ - 1
/*********************************************************/
/* response analyze */
/*********************************************************/
analyseReponse:
stp x1,lr,[sp,-16]! // save registers
stp x2,x3,[sp,-16]! // save registers
ldr x0,qAdrsBufferreq // buffer address
ldr x1,qAdrszLibStart // key text address
mov x2,#2 // occurence key text
mov x3,#-11 // offset
ldr x4,qAdrszExtractArea // address result area
bl extChaine
cmp x0,#-1
beq 99f
ldr x0,qAdrszMessExtractArea
bl affichageMess
ldr x0,qAdrszExtractArea // résult display
bl affichageMess
ldr x0,qAdrszRetourLigne
bl affichageMess
b 100f
99:
ldr x0,qAdrszMessErreur // error
bl affichageMess
mov x0, #-1 // error return code
b 100f
100:
ldp x2,x3,[sp],16 // restaur 2 registers
ldp x1,lr,[sp],16 // restaur 2 registers
ret // return to address lr x30
qAdrszLibStart: .quad szLibStart
qAdrszExtractArea: .quad szExtractArea
qAdrszMessExtractArea: .quad szMessExtractArea
qAdrszRetourLigne: .quad szRetourLigne
/*********************************************************/
/* Text Extraction behind text key */
/*********************************************************/
/* x0 buffer address */
/* x1 key text to search */
/* x2 number occurences to key text */
/* x3 offset */
/* x4 result address */
extChaine:
stp x1,lr,[sp,-16]! // save registers
stp x2,x3,[sp,-16]! // save registers
stp x4,x5,[sp,-16]! // save registers
stp x6,x7,[sp,-16]! // save registers
mov x5,x0 // save buffer address
mov x6,x1 // save key text
// compute text length
mov x8,#0
1: // loop
ldrb w0,[x5,x8] // load a byte
cmp x0,#0 // end ?
add x9,x8,1
csel x8,x9,x8,ne
bne 1b // no -> loop
add x8,x8,x5 // compute text end
mov x7,#0
2: // compute length text key
ldrb w0,[x6,x7]
cmp x0,#0
add x9,x7,1
csel x7,x9,x7,ne
bne 2b
3: // loop to search niéme(x2) key text
mov x0,x5
mov x1,x6
bl rechercheSousChaine
cmp x0,#0
blt 100f
subs x2,x2,1
ble 31f
add x5,x5,x0
add x5,x5,x7
b 3b
31:
add x0,x0,x5 // add address text to index
add x3,x3,x0 // add offset
sub x3,x3,1
// and add length key text
add x3,x3,x7
cmp x3,x8 // > at text end
bge 98f
mov x0,0
4: // character loop copy
ldrb w2,[x3,x0]
strb w2,[x4,x0]
cbz x2,99f // text end ? return zero
cmp x0,48 // extraction length
beq 5f
add x0,x0,1
b 4b // and loop
5:
mov x2,0 // store final zéro
strb w2,[x4,x0]
add x0,x0,1
add x0,x0,x3 // x0 return the last position of extraction
// it is possible o search another text
b 100f
98:
mov x0,-1 // error
b 100f
99:
mov x0,0
100:
ldp x6,x7,[sp],16 // restaur 2 registers
ldp x4,x5,[sp],16 // restaur 2 registers
ldp x2,x3,[sp],16 // restaur 2 registers
ldp x1,lr,[sp],16 // restaur 2 registers
ret // return to address lr x30
/******************************************************************/
/* search substring in string */
/******************************************************************/
/* x0 contains address string */
/* x1 contains address substring */
/* x0 return start index substring or -1 if not find */
rechercheSousChaine:
stp x1,lr,[sp,-16]! // save registers
stp x2,x3,[sp,-16]! // save registers
stp x4,x5,[sp,-16]! // save registers
stp x6,x7,[sp,-16]! // save registers
mov x2,#0 // index position string
mov x3,#0 // index position substring
mov x6,#-1 // search index
ldrb w4,[x1,x3] // load first byte substring
cbz x4,99f // zero final ? error
1:
ldrb w5,[x0,x2] // load string byte
cbz x5,99f // zero final ? yes -> not found
cmp x5,x4 // compare character two strings
beq 2f
mov x6,-1 // not equal - > raz index
mov x3,0 // and raz byte counter
ldrb w4,[x1,x3] // and load byte
add x2,x2,1 // and increment byte counter
b 1b // and loop
2: // characters equal
cmp x6,-1 // first character equal ?
csel x6,x2,x6,eq // yes -> start index in x6
add x3,x3,1 // increment substring counter
ldrb w4,[x1,x3] // and load next byte
cbz x4,3f // zero final ? yes -> search end
add x2,x2,1 // else increment string index
b 1b // and loop
3:
mov x0,x6 // return start index substring in the string
b 100f
99:
mov x0,-1 // not found
100:
ldp x6,x7,[sp],16 // restaur 2 registers
ldp x4,x5,[sp],16 // restaur 2 registers
ldp x2,x3,[sp],16 // restaur 2 registers
ldp x1,lr,[sp],16 // restaur 2 registers
ret // return to address lr x30
/********************************************************/
/* File Include fonctions */
/********************************************************/
/* for this file see task include a file in language AArch64 assembly */
.include "../includeARM64.inc"
- Output:
Début du programme. Extraction = Rosetta Code is a programming chrestomathy site. Fin normale du programme.
ARM Assembly
/* ARM assembly Raspberry PI */
/* program yahoosearch.s */
/* access RosettaCode.org and data extract */
/* use openssl for access to port 443 */
/* test openssl : package libssl-dev */
/* REMARK 1 : this program use routines in a include file
see task Include a file language arm assembly
for the routine affichageMess conversion10
see at end of this program the instruction include */
/*******************************************/
/* Constantes */
/*******************************************/
.equ STDOUT, 1 @ Linux output console
.equ EXIT, 1 @ Linux syscall
.equ WRITE, 4 @ Linux syscall
.equ BRK, 0x2d @ Linux syscall
.equ CHARPOS, '@'
.equ EXIT, 1
.equ TAILLEBUFFER, 500
.equ SSL_OP_NO_SSLv3, 0x02000000
.equ SSL_OP_NO_COMPRESSION, 0x00020000
.equ SSL_MODE_AUTO_RETRY, 0x00000004
.equ SSL_CTRL_MODE, 33
.equ BIO_C_SET_CONNECT, 100
.equ BIO_C_DO_STATE_MACHINE, 101
.equ BIO_C_SET_SSL, 109
.equ BIO_C_GET_SSL, 110
.equ LGBUFFERREQ, 512001
.equ LGBUFFER2, 128001
/*********************************/
/* Initialized data */
/*********************************/
.data
szMessDebutPgm: .asciz "Début du programme. \n"
szRetourLigne: .asciz "\n"
szMessFinOK: .asciz "Fin normale du programme. \n"
szMessErreur: .asciz "Erreur !!!"
szMessExtractArea: .asciz "Extraction = "
szNomSite1: .asciz "search.yahoo.com:443" @ host name and port
szLibStart: .asciz ">Rosetta Code" @ search string
szNomrepCertif: .asciz "/pi/certificats"
szRequete1: .asciz "GET /search?p=\"Rosettacode.org\"&b=1 HTTP/1.1 \r\nHost: search.yahoo.com\r\nConnection: keep-alive\r\nContent-Type: text/plain\r\n\r\n"
/*********************************/
/* UnInitialized data */
/*********************************/
.bss
.align 4
sBufferreq: .skip LGBUFFERREQ
szExtractArea: .skip TAILLEBUFFER
stNewSSL: .skip 200
/*********************************/
/* code section */
/*********************************/
.text
.global main
main:
ldr r0,iAdrszMessDebutPgm
bl affichageMess @ start message
/* connexion host port 443 and send query */
bl envoiRequete
cmp r0,#-1
beq 99f @ error ?
bl analyseReponse
ldr r0,iAdrszMessFinOK @ end message
bl affichageMess
mov r0, #0 @ return code ok
b 100f
99:
ldr r0,iAdrszMessErreur @ error
bl affichageMess
mov r0, #1 @ return code error
b 100f
100:
mov r7,#EXIT @ program end
svc #0 @ system call
iAdrszMessDebutPgm: .int szMessDebutPgm
iAdrszMessFinOK: .int szMessFinOK
iAdrszMessErreur: .int szMessErreur
/*********************************************************/
/* connexion host port 443 and send query */
/*********************************************************/
envoiRequete:
push {r2-r8,lr} @ save registers
@*************************************
@ openSsl functions use *
@*************************************
@init ssl
bl OPENSSL_init_crypto
bl ERR_load_BIO_strings
mov r2, #0
mov r1, #0
mov r0, #2
bl OPENSSL_init_crypto
mov r2, #0
mov r1, #0
mov r0, #0
bl OPENSSL_init_ssl
cmp r0,#0
blt erreur
bl TLS_client_method
bl SSL_CTX_new
cmp r0,#0
ble erreur
mov r6,r0 @ save ctx
ldr r1,iFlag
bl SSL_CTX_set_options
mov r0,r6
mov r1,#0
ldr r2,iAdrszNomrepCertif
bl SSL_CTX_load_verify_locations
cmp r0,#0
ble erreur
mov r0,r6
bl BIO_new_ssl_connect
cmp r0,#0
ble erreur
mov r5,r0 @ save bio
mov r1,#BIO_C_GET_SSL
mov r2,#0
ldr r3,iAdrstNewSSL
bl BIO_ctrl
ldr r0,iAdrstNewSSL
ldr r0,[r0]
mov r1,#SSL_CTRL_MODE
mov r2,#SSL_MODE_AUTO_RETRY
mov r3,#0
bl SSL_ctrl
mov r0,r5 @ bio
mov r1,#BIO_C_SET_CONNECT
mov r2,#0
ldr r3,iAdrszNomSite1
bl BIO_ctrl
mov r0,r5 @ bio
mov r1,#BIO_C_DO_STATE_MACHINE
mov r2,#0
mov r3,#0
bl BIO_ctrl
@ compute query length
mov r2,#0
ldr r1,iAdrszRequete1 @ query
1:
ldrb r0,[r1,r2]
cmp r0,#0
addne r2,#1
bne 1b
@ send query
mov r0,r5 @ bio
@ r1 = address query
@ r2 = length query
mov r3,#0
bl BIO_write @ send query
cmp r0,#0
blt erreur
ldr r7,iAdrsBufferreq @ buffer address
2: @ begin loop to read datas
mov r0,r5 @ bio
mov r1,r7 @ buffer address
mov r2,#LGBUFFERREQ - 1
mov r3,#0
bl BIO_read
cmp r0,#0
ble 4f @ error ou pb server
add r7,r0
sub r2,r7,#6
ldr r2,[r2]
ldr r3,iCharEnd
cmp r2,r3 @ text end ?
beq 4f
mov r1,#0xFFFFFF @ delay loop
3:
subs r1,#1
bgt 3b
b 2b @ loop read other chunk
4: @ read end
//ldr r0,iAdrsBufferreq @ to display buffer response of the query
//bl affichageMess
mov r0, r5 @ close bio
bl BIO_free_all
mov r0,#0
b 100f
erreur: @ error display
ldr r1,iAdrszMessErreur
bl afficheerreur
mov r0,#-1 @ error code
b 100f
100:
pop {r2-r8,lr} @ restaur registers
bx lr
iAdrszRequete1: .int szRequete1
iAdrsBufferreq: .int sBufferreq
iFlag: .int SSL_OP_NO_SSLv3 | SSL_OP_NO_COMPRESSION
iAdrstNewSSL: .int stNewSSL
iAdrszNomSite1: .int szNomSite1
iAdrszNomrepCertif: .int szNomrepCertif
iCharEnd: .int 0x0A0D300A
/*********************************************************/
/* response analyze */
/*********************************************************/
analyseReponse:
push {r1-r4,lr} @ save registers
ldr r0,iAdrsBufferreq @ buffer address
ldr r1,iAdrszLibStart @ key text address
mov r2,#2 @ occurence key text
mov r3,#-11 @ offset
ldr r4,iAdrszExtractArea @ address result area
bl extChaine
cmp r0,#-1
beq 99f
ldr r0,iAdrszMessExtractArea
bl affichageMess
ldr r0,iAdrszExtractArea @ résult display
bl affichageMess
ldr r0,iAdrszRetourLigne
bl affichageMess
b 100f
99:
ldr r0,iAdrszMessErreur @ error
bl affichageMess
mov r0, #-1 @ error return code
b 100f
100:
pop {r1-r4,lr} @ restaur registers
bx lr
iAdrszLibStart: .int szLibStart
iAdrszExtractArea: .int szExtractArea
iAdrszMessExtractArea: .int szMessExtractArea
iAdrszRetourLigne: .int szRetourLigne
/*********************************************************/
/* Text Extraction behind text key */
/*********************************************************/
/* r0 buffer address */
/* r1 key text to search */
/* r2 number occurences to key text */
/* r3 offset */
/* r4 result address */
extChaine:
push {r2-r8,lr} @ save registers
mov r5,r0 @ save buffer address
mov r6,r1 @ save key text
@ compute text length
mov r7,#0
1: @ loop
ldrb r0,[r5,r7] @ load a byte
cmp r0,#0 @ end ?
addne r7,#1 @ no -> loop
bne 1b
add r7,r5 @ compute text end
mov r8,#0
2: @ compute length text key
ldrb r0,[r6,r8]
cmp r0,#0
addne r8,#1
bne 2b
3: @ loop to search nième(r2) key text
mov r0,r5
mov r1,r6
bl rechercheSousChaine
cmp r0,#0
blt 100f
subs r2,#1
addgt r5,r0
addgt r5,r8
bgt 3b
add r0,r5 @ add address text to index
add r3,r0 @ add offset
sub r3,#1
@ and add length key text
add r3,r8
cmp r3,r7 @ > at text end
movge r0,#-1 @ yes -> error
bge 100f
mov r0,#0
4: @ character loop copy
ldrb r2,[r3,r0]
strb r2,[r4,r0]
cmp r2,#0 @ text end ?
moveq r0,#0 @ return zero
beq 100f
cmp r0,#48 @ extraction length
beq 5f
add r0,#1
b 4b @ and loop
5:
mov r2,#0 @ store final zéro
strb r2,[r4,r0]
add r0,#1
add r0,r3 @ r0 return the last position of extraction
@ it is possible o search another text
100:
pop {r2-r8,lr} @ restaur registers
bx lr
/******************************************************************/
/* search substring in string */
/******************************************************************/
/* r0 contains address string */
/* r1 contains address substring */
/* r0 return start index substring or -1 if not find */
rechercheSousChaine:
push {r1-r6,lr} @ save registers
mov r2,#0 @ index position string
mov r3,#0 @ index position substring
mov r6,#-1 @ search index
ldrb r4,[r1,r3] @ load first byte substring
cmp r4,#0 @ zero final ?
moveq r0,#-1 @ error
beq 100f
1:
ldrb r5,[r0,r2] @ load string byte
cmp r5,#0 @ zero final ?
moveq r0,#-1 @ yes -> not find
beq 100f
cmp r5,r4 @ compare character two strings
beq 2f
mov r6,#-1 @ not equal - > raz index
mov r3,#0 @ and raz byte counter
ldrb r4,[r1,r3] @ and load byte
add r2,#1 @ and increment byte counter
b 1b @ and loop
2: @ characters equal
cmp r6,#-1 @ first character equal ?
moveq r6,r2 @ yes -> start index in r6
add r3,#1 @ increment substring counter
ldrb r4,[r1,r3] @ and load next byte
cmp r4,#0 @ zero final ?
beq 3f @ yes -> search end
add r2,#1 @ else increment string index
b 1b @ and loop
3:
mov r0,r6 @ return start index substring in the string
100:
pop {r1-r6,lr} @ restaur registres
bx lr
/***************************************************/
/* ROUTINES INCLUDE */
/***************************************************/
.include "../affichage.inc"
- Output:
Début du programme. Extraction = Rosetta Code is a programming chrestomathy site. Fin normale du programme.
AutoHotkey
translated from python example
test:
yahooSearch("test", 1)
yahooSearch("test", 2)
return
yahooSearch(query, page)
{
global
start := ((page - 1) * 10) + 1
filedelete, search.txt
urldownloadtofile, % "http://search.yahoo.com/search?p=" . query
. "&b=" . start, search.txt
fileread, content, search.txt
reg = <a class="yschttl spt" href=".+?" >(.+?)</a></h3></div><div class="abstr">(.+?)</div><span class=url>(.+?)</span>
index := found := 1
while (found := regexmatch(content, reg, self, found + 1))
{
msgbox % title%A_Index% := fix(self1)
content%A_Index% := fix(self2)
url%A_Index% := fix(self3)
}
}
fix(url)
{
if pos := instr(url, "</a></h3></div>")
StringLeft, url, url, pos - 1
url := regexreplace(url, "<.*?>")
return url
}
C#
Generally it is not a good idea to scrape web pages. E. g. all implementations for this task which regex for "<a class=" fail by now, after Yahoo has changed its output format.
using System;
using System.Net;
using System.Text.RegularExpressions;
using System.Collections.Generic;
class YahooSearch {
private string query;
private string content;
private int page;
const string yahoo = "http://search.yahoo.com/search?";
public YahooSearch(string query) : this(query, 0) { }
public YahooSearch(string query, int page) {
this.query = query;
this.page = page;
this.content = new WebClient()
.DownloadString(
string.Format(yahoo + "p={0}&b={1}", query, this.page * 10 + 1)
);
}
public YahooResult[] Results {
get {
List<YahooResult> results = new List<YahooResult>();
Func<string, string, string> substringBefore = (str, before) =>
{
int iHref = str.IndexOf(before);
return iHref < 0 ? "" : str.Substring(0, iHref);
};
Func<string, string, string> substringAfter = (str, after) =>
{
int iHref = str.IndexOf(after);
return iHref < 0 ? "" : str.Substring(iHref + after.Length);
};
Converter<string, string> getText = p =>
Regex.Replace(p, "<[^>]*>", x => "");
Regex rx = new Regex(@"
<li>
<div \s class=""res"">
<div>
<h3>
<a \s (?'LinkAttributes'[^>]+)>
(?'LinkText' .*?)
(?></a>)
</h3>
</div>
<div \s class=""abstr"">
(?'Abstract' .*?)
(?></div>)
.*?
(?></div>)
</li>",
RegexOptions.IgnorePatternWhitespace
| RegexOptions.ExplicitCapture
);
foreach (Match e in rx.Matches(this.content)) {
string rurl = getText(substringBefore(substringAfter(
e.Groups["LinkAttributes"].Value, @"href="""), @""""));
string rtitle = getText(e.Groups["LinkText"].Value);
string rcontent = getText(e.Groups["Abstract"].Value);
results.Add(new YahooResult(rurl, rtitle, rcontent));
}
return results.ToArray();
}
}
public YahooSearch NextPage() {
return new YahooSearch(this.query, this.page + 1);
}
public YahooSearch GetPage(int page) {
return new YahooSearch(this.query, page);
}
}
class YahooResult {
public string URL { get; set; }
public string Title { get; set; }
public string Content { get; set; }
public YahooResult(string url, string title, string content) {
this.URL = url;
this.Title = title;
this.Content = content;
}
public override string ToString()
{
return string.Format("\nTitle: {0}\nLink: {1}\nText: {2}",
Title, URL, Content);
}
}
// Usage:
class Prog {
static void Main() {
foreach (int page in new[] { 0, 1 })
{
YahooSearch x = new YahooSearch("test", page);
foreach (YahooResult result in x.Results)
{
Console.WriteLine(result);
}
}
}
}
D
import std.stdio, std.exception, std.regex, std.algorithm, std.string,
std.net.curl;
struct YahooResult {
string url, title, content;
string toString() const {
return "\nTitle: %s\nLink: %s\nText: %s"
.format(title, url, content);
}
}
struct YahooSearch {
private string query, content;
private uint page;
this(in string query_, in uint page_ = 0) {
this.query = query_;
this.page = page_;
this.content = "http://search.yahoo.com/search?p=%s&b=%d"
.format(query, page * 10 + 1).get.assumeUnique;
}
@property results() const {
immutable re = `<li>
<div \s class="res">
<div>
<h3>
<a \s (?P<linkAttributes> [^>]+)>
(?P<linkText> .*?)
</a>
</h3>
</div>
<div \s class="abstr">
(?P<abstract> .*?)
</div>
.*?
</div>
</li>`;
const clean = (string s) => s.replace("<[^>]*>".regex("g"),"");
return content.match(re.regex("gx")).map!(m => YahooResult(
clean(m.captures["linkAttributes"]
.findSplitAfter(`href="`)[1]
.findSplitBefore(`"`)[0]),
clean(m.captures["linkText"]),
clean(m.captures["abstract"])
));
}
YahooSearch nextPage() const {
return YahooSearch(query, page + 1);
}
}
void main() {
writefln("%(%s\n%)", "test".YahooSearch.results);
}
- Output (shortened):
Title: Test.com Link: http://www.test.com/ Text: Test.com provides a complete software solution for creating online tests and managing enterprise and specialist certification programs, in up to 22 languages. Title: Speakeasy Speed Test Link: http://www.speakeasy.net/speedtest/ Text: Test your Internet Connection with Speakeasy's reliable and accurate broadband speed test. What's your speed? Title: Test | Define Test at Dictionary.com Link: http://dictionary.reference.com/browse/test Text: noun 1. the means by which the presence, quality, or genuineness of anything is determined; a means of trial. 2. the trial of the quality of something: to put to the ...
Gambas
Public Sub Form_Open()
Dim hWebView As WebView
Me.Arrangement = Arrange.Fill
Me.Maximized = True
Me.Title = "Yahoo! search interface"
hWebView = New WebView(Me)
hWebView.Expand = True
hWebView.URL = "https://www.yahoo.com"
End
Click here to see output (I have typed 'rosettacode' in the search box)
Go
Yahoo! has evidently changed its search output format over the years and, if it is currently documented anywhere, then I couldn't find it.
The regular expression used below was figured out by studying the raw HTML and works fine as at 18th November, 2019.
package main
import (
"fmt"
"golang.org/x/net/html"
"io/ioutil"
"net/http"
"regexp"
"strings"
)
var (
expr = `<h3 class="title"><a class=.*?href="(.*?)".*?>(.*?)</a></h3>` +
`.*?<div class="compText aAbs" ><p class=.*?>(.*?)</p></div>`
rx = regexp.MustCompile(expr)
)
type YahooResult struct {
title, url, content string
}
func (yr YahooResult) String() string {
return fmt.Sprintf("Title : %s\nUrl : %s\nContent: %s\n", yr.title, yr.url, yr.content)
}
type YahooSearch struct {
query string
page int
}
func (ys YahooSearch) results() []YahooResult {
search := fmt.Sprintf("http://search.yahoo.com/search?p=%s&b=%d", ys.query, ys.page*10+1)
resp, _ := http.Get(search)
body, _ := ioutil.ReadAll(resp.Body)
s := string(body)
defer resp.Body.Close()
var results []YahooResult
for _, f := range rx.FindAllStringSubmatch(s, -1) {
yr := YahooResult{}
yr.title = html.UnescapeString(strings.ReplaceAll(strings.ReplaceAll(f[2], "<b>", ""), "</b>", ""))
yr.url = f[1]
yr.content = html.UnescapeString(strings.ReplaceAll(strings.ReplaceAll(f[3], "<b>", ""), "</b>", ""))
results = append(results, yr)
}
return results
}
func (ys YahooSearch) nextPage() YahooSearch {
return YahooSearch{ys.query, ys.page + 1}
}
func main() {
ys := YahooSearch{"rosettacode", 0}
// Limit output to first 5 entries, say, from pages 1 and 2.
fmt.Println("PAGE 1 =>\n")
for _, res := range ys.results()[0:5] {
fmt.Println(res)
}
fmt.Println("PAGE 2 =>\n")
for _, res := range ys.nextPage().results()[0:5] {
fmt.Println(res)
}
}
- Output:
Note there is some repetition between the pages.
PAGE 1 => Title : Rosetta Code Url : https://rosettacode.org/wiki/Rosetta_Code Content: Rosetta Code Rosetta Code is a programming chrestomathy site. Rosetta Code currently has 976 tasks, 231 draft tasks, and is aware of 756 languages, though we do not (and cannot) have solutions to every task in every language. 1 Places to start Title : Rosetta Code - Wikipedia Url : https://en.wikipedia.org/wiki/Rosetta_Code Content: Rosetta Code is a wiki -based programming chrestomathy website with implementations of common algorithms and solutions to various programming problems in many different programming languages. 1 Website 1.1 Data and structure 1.2 Languages Title : Rosetta Code (@rosettacode) | Twitter Url : https://twitter.com/rosettacode Content: The latest Tweets from Rosetta Code (@rosettacode). Twitter account for http://t.co/DuRZFWDfRn. The general idea here is for short announcements and the like. The ... Title : Best of Rosettacode Url : https://examples.p6c.dev/categories/best-of-rosettacode.html Content: 99 Problems Rosettacode Cookbook Euler Games Interpreters Modules Other Grammars Perlmonks Rosalind Shootout ... Title : Rosetta Code Blog Url : https://blog.rosettacode.org/ Content: (If you point 'rosettacode.com' to RosettaCode.org's IP address, you should still be able to see it) Second, I don't care if you want to use the name 'rosettacode' or 'rosetta code' in similar pursuits. I love that people have been calling task pages that have cropped up on various forums around the web as "rosetta code problems." That speaks ... PAGE 2 => Title : Rosetta Code | R-bloggers Url : https://www.r-bloggers.com/rosetta-code/ Content: Rosetta Code is a programming chrestomathy site. The idea is to present solutions to the same task in as many different languages as possible, to demonstrate how languages are similar and different, and to aid a person with a grounding in one approach to a problem in learning another. Title : Best of Rosettacode Url : https://examples.p6c.dev/categories/best-of-rosettacode.html Content: 99 Problems Rosettacode Cookbook Euler Games Interpreters Modules Other Grammars Perlmonks Rosalind Shootout ... Title : Rosetta Code Blog Url : https://blog.rosettacode.org/ Content: (If you point 'rosettacode.com' to RosettaCode.org's IP address, you should still be able to see it) Second, I don't care if you want to use the name 'rosettacode' or 'rosetta code' in similar pursuits. I love that people have been calling task pages that have cropped up on various forums around the web as "rosetta code problems." That speaks ... Title : What exactly is the purpose of Rosetta Code? - Quora Url : https://www.quora.com/What-exactly-is-the-purpose-of-Rosetta-Code Content: The name is a play on the Rosetta Stone. The Rosetta Stone featured a decree by King Ptolomy written in three scripts - Egyption hieroglyphs, Demotic, and Ancient Greek. Title : One R Tip A Day: Rosetta Code Url : https://onertipaday.blogspot.com/2009/07/rosetta-code.html Content: Today I'd like to suggest the interesting Rosetta Code site: Rosetta Code is a programming chrestomathy site. The idea is to present solutions to the same task in as many different languages as possible, to demonstrate how languages are similar and different, and to aid a person with a grounding in one approach to a problem in learning another.
GUISS
Start,Programs,Applications,Mozilla Firefox,Inputbox:address bar>www.yahoo.co.uk,
Button:Go,Area:browser window,Inputbox:searchbox>elephants,Button:Search
Haskell
Haskell is not an object oriented language, so this example does not implement an object class. However, it can be interesting as an example of how HTML source code can be parsed using the Parsec library.
import Network.HTTP
import Text.Parsec
data YahooSearchItem = YahooSearchItem {
itemUrl, itemTitle, itemContent :: String }
data YahooSearch = YahooSearch {
searchQuery :: String,
searchPage :: Int,
searchItems :: [YahooSearchItem] }
-- URL for Yahoo! searches, without giving a page number
yahooUrl = "http://search.yahoo.com/search?p="
-- make an HTTP request and return a YahooSearch
yahoo :: String -> IO YahooSearch
yahoo q = simpleHTTP (getRequest $ yahooUrl ++ q) >>=
getResponseBody >>= return . YahooSearch q 1 . items
-- get some results and return the next page of results
next :: YahooSearch -> IO YahooSearch
next (YahooSearch q p _) =
simpleHTTP (getRequest $
-- add the page number to the search
yahooUrl ++ q ++ "&b=" ++ show (p + 1)) >>=
getResponseBody >>= return . YahooSearch q (p + 1) . items
printResults :: YahooSearch -> IO ()
printResults (YahooSearch q p items) = do
putStrLn $ "Showing Yahoo! search results for query: " ++ q
putStrLn $ "Page: " ++ show p
putChar '\n'
mapM_ printOne items
where
printOne (YahooSearchItem itemUrl itemTitle itemContent) = do
putStrLn $ "URL : " ++ itemUrl
putStrLn $ "Title : " ++ itemTitle
putStrLn $ "Abstr : " ++ itemContent
putChar '\n'
urlTag, titleTag, contentTag1, contentTag2, ignoreTag,
ignoreText :: Parsec String () String
-- parse a tag containing the URL of a search result
urlTag = do { string "<a id=\"link-";
many digit; string "\" class=\"yschttl spt\" href=\"";
url <- manyTill anyChar (char '"'); manyTill anyChar (char '>');
return url }
-- the title comes after the URL tag, so parse it first, discard it
-- and get the title text
titleTag = do { urlTag; manyTill anyChar (try (string "</a>")) }
-- parse a tag containing the description of the search result
-- the tag can be named "sm-abs" or "abstr"
contentTag1 = do { string "<div class=\"sm-abs\">";
manyTill anyChar (try (string "</div>")) }
contentTag2 = do { string "<div class=\"abstr\">";
manyTill anyChar (try (string "</div>")) }
-- parse a tag and discard it
ignoreTag = do { char ('<'); manyTill anyChar (char '>');
return "" }
-- parse some text and discard it
ignoreText = do { many1 (noneOf "<"); return "" }
-- return only non-empty strings
nonempty :: [String] -> Parsec String () [String]
nonempty xs = return [ x | x <- xs, not (null x) ]
-- a template to parse a whole source file looking for items of the
-- same class
parseCategory x = do
res <- many x
eof
nonempty res
urls, titles, contents :: Parsec String () [String]
-- parse HTML source looking for URL tags of the search results
urls = parseCategory url where
url = (try urlTag) <|> ignoreTag <|> ignoreText
-- parse HTML source looking for titles of the search results
titles = parseCategory title where
title = (try titleTag) <|> ignoreTag <|> ignoreText
-- parse HTML source looking for descriptions of the search results
contents = parseCategory content where
content = (try contentTag1) <|> (try contentTag2) <|>
ignoreTag <|> ignoreText
-- parse the HTML source three times looking for URL, title and
-- description of all search results and return them as a list of
-- YahooSearchItem
items :: String -> [YahooSearchItem]
items q =
let ignoreOrKeep = either (const []) id
us = ignoreOrKeep $ parse urls "" q
ts = ignoreOrKeep $ parse titles "" q
cs = ignoreOrKeep $ parse contents "" q
in [ YahooSearchItem { itemUrl = u, itemTitle = t, itemContent = c } |
(u, t, c) <- zip3 us ts cs ]
Simple invocation from GHCi:
yahoo "Rosetta%20code" >>= printResults
. Notice that spaces must be expressed as "%20", because spaces are not allowed in URLs.
Icon and Unicon
The following uses the Unicon pre-processor and messaging extensions and won't run under Icon without significant modification. The code provides a suitable demonstration; however, could be made more robust by things such as URL escaping the search string
printf.icn provides formatting strings.icn provides deletec
Sample Output (truncated):
Title : "<b>Rosetta Code</b> - <b>Rosetta Code</b>" URL : "http://rosettacode.org/" Abstr : "<b>Rosetta Code</b> is a programming chrestomathy site. The idea is to present solutions to the same task in as many different languages as possible, t o demonstrate how ..." Title : "<b>Rosetta Code</b> - Wikipedia, the free <wbr />encyclopedia" URL : "http://en.wikipedia.org/wiki/Rosetta_Code" Abstr : " <b>Rosetta Code</b> is a wiki -based programming chrestomathy website with solutions to various programming problems in many different programming lan guages. It was created ..." Title : "Category:AutoHotkey - <b>Rosetta Code</b>" URL : "http://rosettacode.org/wiki/Category:AutoHotkey" Abstr : "Listed below are all of the tasks on <b>Rosetta Code</b> which have bee n solved using AutoHotkey." ... Title : "RosettaCON2011 Tutorials Collection | <wbr />RosettaCommons" URL : "http://www.rosettacommons.org/" Abstr : "Foldit in the news. Cooper et al. 2010 Predicting protein structures wi th a multiplayer online game, Nature 466 , 756 see also video. Rosetta-3.3 is no w available!" Title : "CALL: call a SUBROUTINE - HicEst: <wbr />Windows IDE programming ..." URL : "http://www.hicest.com/CALL.htm" Abstr : "\xe2\x87\x92 Example of a CALL call in "Roman_numerals" (<b>R osettaCode</b>) CALL transfers control to the first statement of a SUBROUTINE. C ALL subroutine_name[argument1, ..."
Java
import java.io.BufferedReader;
import java.io.IOException;
import java.io.InputStreamReader;
import java.net.MalformedURLException;
import java.net.URISyntaxException;
import java.net.URL;
import java.net.URLDecoder;
import java.net.URLEncoder;
import java.util.ArrayList;
import java.util.List;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
class YahooSearch {
private String query;
// Page number
private int page = 1;
// Regexp to look for the individual results in the returned page
private static final Pattern pattern = Pattern.compile(
"<a class=\"yschttl spt\" href=\"[^*]+?\\*\\*([^\"]+?)\">(.+?)</a></h3>.*?<div class=\"(?:sm-abs|abstr)\">(.+?)</div>");
public YahooSearch(String query) {
this.query = query;
}
public List<YahooResult> search() throws MalformedURLException, URISyntaxException, IOException {
// Build the search string, starting with the Yahoo search URL,
// then appending the query and optionally the page number (if > 1)
StringBuilder searchUrl = new StringBuilder("http://search.yahoo.com/search?");
searchUrl.append("p=").append(URLEncoder.encode(query, "UTF-8"));
if (page > 1) {searchUrl.append("&b=").append((page - 1) * 10 + 1);}
// Query the Yahoo search engine
URL url = new URL(searchUrl.toString());
List<YahooResult> result = new ArrayList<YahooResult>();
StringBuilder sb = new StringBuilder();
// Get the search results using a buffered reader
BufferedReader in = null;
try {
in = new BufferedReader(new InputStreamReader(url.openStream()));
// Read the results line by line
String line = in.readLine();
while (line != null) {
sb.append(line);
line = in.readLine();
}
}
catch (IOException ioe) {
ioe.printStackTrace();
}
finally {
try {in.close();} catch (Exception ignoreMe) {}
}
String searchResult = sb.toString();
// Look for the individual results by matching the regexp pattern
Matcher matcher = pattern.matcher(searchResult);
while (matcher.find()) {
// Extract the result URL, title and excerpt
String resultUrl = URLDecoder.decode(matcher.group(1), "UTF-8");
String resultTitle = matcher.group(2).replaceAll("</?b>", "").replaceAll("<wbr ?/?>", "");
String resultContent = matcher.group(3).replaceAll("</?b>", "").replaceAll("<wbr ?/?>", "");
// Create a new YahooResult and add to the list
result.add(new YahooResult(resultUrl, resultTitle, resultContent));
}
return result;
}
public List<YahooResult> search(int page) throws MalformedURLException, URISyntaxException, IOException {
// Set the page number and search
this.page = page;
return search();
}
public List<YahooResult> nextPage() throws MalformedURLException, URISyntaxException, IOException {
// Increment the page number and search
page++;
return search();
}
public List<YahooResult> previousPage() throws MalformedURLException, URISyntaxException, IOException {
// Decrement the page number and search; if the page number is 1 return an empty list
if (page > 1) {
page--;
return search();
} else return new ArrayList<YahooResult>();
}
}
class YahooResult {
private URL url;
private String title;
private String content;
public URL getUrl() {
return url;
}
public void setUrl(URL url) {
this.url = url;
}
public void setUrl(String url) throws MalformedURLException {
this.url = new URL(url);
}
public String getTitle() {
return title;
}
public void setTitle(String title) {
this.title = title;
}
public String getContent() {
return content;
}
public void setContent(String content) {
this.content = content;
}
public YahooResult(URL url, String title, String content) {
setUrl(url);
setTitle(title);
setContent(content);
}
public YahooResult(String url, String title, String content) throws MalformedURLException {
setUrl(url);
setTitle(title);
setContent(content);
}
@Override
public String toString() {
StringBuilder sb = new StringBuilder();
if (title != null) {
sb.append(",title=").append(title);
}
if (url != null) {
sb.append(",url=").append(url);
}
return sb.charAt(0) == ',' ? sb.substring(1) : sb.toString();
}
}
public class TestYahooSearch {
public static void main(String[] args) throws MalformedURLException, URISyntaxException, IOException {
// Create a new search
YahooSearch search = new YahooSearch("Rosetta code");
// Get the search results
List<YahooResult> results = search.search();
// Show the search results
for (YahooResult result : results) {
System.out.println(result.toString());
}
}
}
Julia
""" Rosetta Code Yahoo search task. https://rosettacode.org/wiki/Yahoo!_search_interface """
using EzXML
using HTTP
using Logging
const pagesize = 7
const URI = "https://search.yahoo.com/search?fr=opensearch&pz=$pagesize&"
struct SearchResults
title::String
content::String
url::String
end
mutable struct YahooSearch
search::String
yahoourl::String
currentpage::Int
usedpages::Vector{Int}
results::Vector{SearchResults}
end
YahooSearch(s, url = URI) = YahooSearch(s, url, 1, Int[], SearchResults[])
function NextPage(yah::YahooSearch, link, pagenum)
oldpage = yah.currentpage
yah.currentpage = pagenum
search(yah)
yah.currentpage = oldpage
end
function search(yah::YahooSearch)
push!(yah.usedpages, yah.currentpage)
queryurl = yah.yahoourl * "b=$(yah.currentpage)&p=" * HTTP.escapeuri(yah.search)
req = HTTP.request("GET", queryurl)
# Yahoo's HTML is nonstandard, so send excess warnings from the parser to NullLogger
html = with_logger(NullLogger()) do
parsehtml(String(req.body))
end
for div in findall("//li/div", html)
if haskey(div, "class")
if startswith(div["class"], "dd algo") &&
(a = findfirst("div/h3/a", div)) != nothing &&
haskey(a, "href")
url, title, content = a["href"], nodecontent(a), "None"
for span in findall("div/p/span", div)
if haskey(span, "class") && occursin("fc-falcon", span["class"])
content = nodecontent(span)
end
end
push!(yah.results, SearchResults(title, content, url))
elseif startswith(div["class"], "dd pagination")
for a in findall("div/div/a", div)
if haskey(a, "href")
lnk, n = a["href"], tryparse(Int, nodecontent(a))
!isnothing(n) && !(n in yah.usedpages) && NextPage(yah, lnk, n)
end
end
end
end
end
end
ysearch = YahooSearch("RosettaCode")
search(ysearch)
println("Searching Yahoo for `RosettaCode`:")
println(
"Found ",
length(ysearch.results),
" entries on ",
length(ysearch.usedpages),
" pages.\n",
)
for res in ysearch.results
println("Title: ", res.title)
println("Content: ", res.content)
println("URL: ", res.url, "\n")
end
- Output:
Searching Yahoo for `RosettaCode`: Found 34 entries on 5 pages. Title: rosettacode.orgRosetta Code Content: Rosetta Code is a programming chrestomathy site. The idea is to present solutions to the same task in as many different languages as possible, to demonstrate how languages are similar and different, and to aid a person with a grounding in one approach to a problem in learning another. URL: https://rosettacode.org/wiki/Rosetta_Code Title: en.wikipedia.org › wiki › Rosetta_CodeRosetta Code - Wikipedia Content: Rosetta Code is a wiki-based programming website with implementations of common algorithms and solutions to various programming problems in many different programming languages. It is named for the Rosetta Stone , which has the same text inscribed on it in three languages, and thus allowed Egyptian hieroglyphs to be deciphered for the first time. URL: https://en.wikipedia.org/wiki/Rosetta_Code Title: raku.org › community › rosettacodeRaku on Rosetta Code Content: Raku on Rosetta Code. Rosetta Code is a community site that presents solutions to programming tasks in many different languages. It is an excellent place to see how various languages approach the same task, as well as to get a feel for the style and fluent use of each language across a variety of domains. URL: https://raku.org/community/rosettacode/ Title: github.com › gerph › rosettacodeGitHub - gerph/rosettacode: Library for accessing Rosetta Code Content: None URL: https://github.com/gerph/rosettacode Title: simple.wikipedia.org › wiki › Rosetta_CodeRosetta Code - Simple English Wikipedia, the free encyclopedia Content: Website. Rosetta Code was created in 2007 by Michael Mol. The site's content is licensed under the GNU Free Documentation License 1.2, though some components may have two licenses under less strict terms. URL: https://simple.wikipedia.org/wiki/Rosetta_Code Title: blog.rosettacode.org › 2011Rosetta Code Blog: 2011 Content: (If you point 'rosettacode.com' to RosettaCode.org's IP address, you should still be able to see it) Second, I don't care if you want to use the name 'rosettacode' or 'rosetta code' in similar pursuits. I love that people have been calling task pages that have cropped up on various forums around the web as "rosetta code problems." That speaks ... URL: https://blog.rosettacode.org/2011/ Title: rosettacode.org › wiki › Category:Programming_LanguagesCategory:Programming Languages - Rosetta Code Content: A programming language is a symbolic representation of a specification for computer behavior. A side-by-side comparison of many of the languages on Rosetta Code can be seen here . These are the programming languages that are mentioned throughout Rosetta Code. If you know a language not listed here then suggest or add it. URL: https://rosettacode.org/wiki/Category:Programming_Languages Title: en.wikipedia.org › wiki › Rosetta_CodeRosetta Code - Wikipedia Content: Rosetta Code is a wiki-based programming website with implementations of common algorithms and solutions to various programming problems in many different programming languages. It is named for the Rosetta Stone , which has the same text inscribed on it in three languages, and thus allowed Egyptian hieroglyphs to be deciphered for the first time. URL: https://en.wikipedia.org/wiki/Rosetta_Code Title: github.com › gerph › rosettacodeGitHub - gerph/rosettacode: Library for accessing Rosetta Code Content: Rosetta Code reading Introduction. The rosettacode.org site provides example code for a variety for different tasks in many different languages. Because the code is generally pretty self contained and simple - as the point is to show the differences in the way languages do things - it makes a good source of code to try things out with. URL: https://github.com/gerph/rosettacode Title: raku.org › community › rosettacodeRaku on Rosetta Code Content: Raku on Rosetta Code. Rosetta Code is a community site that presents solutions to programming tasks in many different languages. It is an excellent place to see how various languages approach the same task, as well as to get a feel for the style and fluent use of each language across a variety of domains. URL: https://raku.org/community/rosettacode/ Title: www.retailmenot.com › view › rosettastone10% Off Rosetta Stone Coupons, Promo Codes + 1% Cash Back 2021 Content: Rosetta Stone offers computer assisted language learning programs for 31 different languages. It has kiosk outlets located in almost all major airports of the world and it offers trials and demos in addition to its 6 month money back guarantee. URL: https://www.retailmenot.com/view/rosettastone.com Title: simple.wikipedia.org › wiki › Rosetta_CodeRosetta Code - Simple English Wikipedia, the free encyclopedia Content: Website. Rosetta Code was created in 2007 by Michael Mol. The site's content is licensed under the GNU Free Documentation License 1.2, though some components may have two licenses under less strict terms. URL: https://simple.wikipedia.org/wiki/Rosetta_Code Title: twitter.com › rosettacodeRosetta Code (@RosettaCode) | Twitter Content: We would like to show you a description here but the site won’t allow us. URL: https://twitter.com/rosettacode Title: rosettacode.org › wiki › Category:Programming_TasksCategory:Programming Tasks - Rosetta Code Content: Category:Programming Tasks. Programming tasks are problems that may be solved through programming. When such a task is defined, Rosetta Code users are encouraged to solve them using as many different languages as they know. The end goal is to demonstrate how the same task is accomplished in different languages. URL: https://rosettacode.org/wiki/Category:Programming_Tasks Title: en.wikipedia.org › wiki › Rosetta_CodeRosetta Code - Wikipedia Content: Rosetta Code is a wiki-based programming website with implementations of common algorithms and solutions to various programming problems in many different programming languages. It is named for the Rosetta Stone , which has the same text inscribed on it in three languages, and thus allowed Egyptian hieroglyphs to be deciphered for the first time. URL: https://en.wikipedia.org/wiki/Rosetta_Code Title: improbotics.org › rosetta-codeRosetta Code – Improbotics Content: Rosetta Code was scheduled to perform at Brighton Fringe 2020 at The Warren: Theatre Box and at Camden Fringe 2020 at The Cockpit Theatre and will return live in 2021. Our show was the subject of a scientific research paper “Rosetta Code: Improv in Any Language“, published at the International Conference on Computational Creativity 2020. URL: https://improbotics.org/rosetta-code/ Title: raku.org › community › rosettacodeRaku on Rosetta Code Content: Raku on Rosetta Code. Rosetta Code is a community site that presents solutions to programming tasks in many different languages. It is an excellent place to see how various languages approach the same task, as well as to get a feel for the style and fluent use of each language across a variety of domains. URL: https://raku.org/community/rosettacode/ Title: www.retailmenot.com › view › rosettastone10% Off Rosetta Stone Coupons, Promo Codes + 1% Cash Back 2021 Content: Rosetta Stone offers computer assisted language learning programs for 31 different languages. It has kiosk outlets located in almost all major airports of the world and it offers trials and demos in addition to its 6 month money back guarantee. URL: https://www.retailmenot.com/view/rosettastone.com Title: github.com › gerph › rosettacodeGitHub - gerph/rosettacode: Library for accessing Rosetta Code Content: Rosetta Code reading Introduction. The rosettacode.org site provides example code for a variety for different tasks in many different languages. Because the code is generally pretty self contained and simple - as the point is to show the differences in the way languages do things - it makes a good source of code to try things out with. URL: https://github.com/gerph/rosettacode Title: twitter.com › rosettacodeRosetta Code (@RosettaCode) | Twitter Content: We would like to show you a description here but the site won’t allow us. URL: https://twitter.com/rosettacode Title: en.wikipedia.org › wiki › Rosetta_CodeRosetta Code - Wikipedia Content: Rosetta Code is a wiki-based programming website with implementations of common algorithms and solutions to various programming problems in many different programming languages. It is named for the Rosetta Stone , which has the same text inscribed on it in three languages, and thus allowed Egyptian hieroglyphs to be deciphered for the first time. URL: https://en.wikipedia.org/wiki/Rosetta_Code Title: en.wikipedia.org › wiki › RosettacodeRosetta Code - Wikipedia Content: Rosetta Code is a wiki-based programming website with implementations of common algorithms and solutions to various programming problems in many different programming languages. It is named for the Rosetta Stone , which has the same text inscribed on it in three languages, and thus allowed Egyptian hieroglyphs to be deciphered for the first time. URL: https://en.wikipedia.org/wiki/Rosettacode Title: improbotics.org › rosetta-codeRosetta Code – Improbotics Content: Rosetta Code was scheduled to perform at Brighton Fringe 2020 at The Warren: Theatre Box and at Camden Fringe 2020 at The Cockpit Theatre and will return live in 2021. Our show was the subject of a scientific research paper “Rosetta Code: Improv in Any Language“, published at the International Conference on Computational Creativity 2020. URL: https://improbotics.org/rosetta-code/ Title: rosettacode.org › wiki › OpenGLOpenGL/Phix - Rosetta Code Content: OpenGL/Phix. From Rosetta Code. < OpenGL. Jump to: navigation. , search. Older win32-only and OpenGL 1.0 (ie not p2js compatible) versions of the OpenGL task. Adapted from the included demo\Arwen32dibdemo\shadepol.exw, draws the same thing as the image at the top of this page, but (as per the talk page) does not use openGL, just windows api ... URL: https://rosettacode.org/wiki/OpenGL/Phix Title: rosettacode.org › wiki › Matrix_multiplicationMatrix multiplication - Rosetta Code Content: 360 Assembly [] * Matrix multiplication 06/08/2015 MATRIXRC CSECT Matrix multiplication USING MATRIXRC,R13 SAVEARA B STM-SAVEARA(R15) URL: https://rosettacode.org/wiki/Matrix_multiplication Title: github.com › gerph › rosettacodeGitHub - gerph/rosettacode: Library for accessing Rosetta Code Content: Rosetta Code reading Introduction. The rosettacode.org site provides example code for a variety for different tasks in many different languages. Because the code is generally pretty self contained and simple - as the point is to show the differences in the way languages do things - it makes a good source of code to try things out with. URL: https://github.com/gerph/rosettacode Title: raku.org › community › rosettacodeRaku on Rosetta Code Content: Raku on Rosetta Code. Rosetta Code is a community site that presents solutions to programming tasks in many different languages. It is an excellent place to see how various languages approach the same task, as well as to get a feel for the style and fluent use of each language across a variety of domains. URL: https://raku.org/community/rosettacode/ Title: en.wikipedia.org › wiki › Rosetta_CodeRosetta Code - Wikipedia Content: Rosetta Code is a wiki-based programming website with implementations of common algorithms and solutions to various programming problems in many different programming languages. It is named for the Rosetta Stone , which has the same text inscribed on it in three languages, and thus allowed Egyptian hieroglyphs to be deciphered for the first time. URL: https://en.wikipedia.org/wiki/Rosetta_Code Title: en.wikipedia.org › wiki › RosettacodeRosetta Code - Wikipedia Content: Rosetta Code is a wiki-based programming website with implementations of common algorithms and solutions to various programming problems in many different programming languages. It is named for the Rosetta Stone , which has the same text inscribed on it in three languages, and thus allowed Egyptian hieroglyphs to be deciphered for the first time. URL: https://en.wikipedia.org/wiki/Rosettacode Title: improbotics.org › rosetta-codeRosetta Code – Improbotics Content: Rosetta Code was scheduled to perform at Brighton Fringe 2020 at The Warren: Theatre Box and at Camden Fringe 2020 at The Cockpit Theatre and will return live in 2021. Our show was the subject of a scientific research paper “Rosetta Code: Improv in Any Language“, published at the International Conference on Computational Creativity 2020. URL: https://improbotics.org/rosetta-code/ Title: rosettacode.org › wiki › OpenGLOpenGL/Phix - Rosetta Code Content: OpenGL/Phix. From Rosetta Code. < OpenGL. Jump to: navigation. , search. Older win32-only and OpenGL 1.0 (ie not p2js compatible) versions of the OpenGL task. Adapted from the included demo\Arwen32dibdemo\shadepol.exw, draws the same thing as the image at the top of this page, but (as per the talk page) does not use openGL, just windows api ... URL: https://rosettacode.org/wiki/OpenGL/Phix Title: raku.org › community › rosettacodeRaku on Rosetta Code Content: Raku on Rosetta Code. Rosetta Code is a community site that presents solutions to programming tasks in many different languages. It is an excellent place to see how various languages approach the same task, as well as to get a feel for the style and fluent use of each language across a variety of domains. URL: https://raku.org/community/rosettacode/ Title: rosettacode.org › wiki › Fast_Fourier_transformFast Fourier transform - Rosetta Code Content: Task. Calculate the FFT ( F ast F ourier T ransform) of an input sequence. The most general case allows for complex numbers at the input and results in a sequence of equal length, again of complex numbers. If you need to restrict yourself to real numbers, the output should be the magnitude (i.e.: sqrt (re 2 + im 2 )) of the complex result. URL: https://rosettacode.org/wiki/Fast_Fourier_transform Title: simple.wikipedia.org › wiki › Rosetta_CodeRosetta Code - Simple English Wikipedia, the free encyclopedia Content: Website. Rosetta Code was created in 2007 by Michael Mol. The site's content is licensed under the GNU Free Documentation License 1.2, though some components may have two licenses under less strict terms. URL: https://simple.wikipedia.org/wiki/Rosetta_Code
Kotlin
This is based on the C# entry but uses a regular expression based on what appears to be the Yahoo! format as at the date of this entry (4 December 2017).
// version 1.2.0
import java.net.URL
val rx = Regex("""<div class=\"yst result\">.+?<a href=\"(.*?)\" class=\"\">(.*?)</a>.+?class="abstract ellipsis">(.*?)</p>""")
class YahooResult(var title: String, var link: String, var text: String) {
override fun toString() = "\nTitle: $title\nLink : $link\nText : $text"
}
class YahooSearch(val query: String, val page: Int = 0) {
private val content: String
init {
val yahoo = "http://search.yahoo.com/search?"
val url = URL("${yahoo}p=$query&b=${page * 10 + 1}")
content = url.readText()
}
val results: MutableList<YahooResult>
get() {
val list = mutableListOf<YahooResult>()
for (mr in rx.findAll(content)) {
val title = mr.groups[2]!!.value.replace("<b>", "").replace("</b>", "")
val link = mr.groups[1]!!.value
val text = mr.groups[3]!!.value.replace("<b>", "").replace("</b>", "")
list.add (YahooResult(title, link, text))
}
return list
}
fun nextPage() = YahooSearch(query, page + 1)
fun getPage(newPage: Int) = YahooSearch(query, newPage)
}
fun main(args: Array<String>) {
for (page in 0..1) {
val x = YahooSearch("rosettacode", page)
println("\nPAGE ${page + 1} =>")
for (result in x.results.take(3)) println(result)
}
}
Output (restricted to first three results on first two pages):
PAGE 1 => Title: Rosetta Code - Official Site Link : http://rosettacode.org/wiki/Rosetta_Code Text : Rosetta Code is a programming chrestomathy site. The idea is to present solutions to the same task in as ... Title: Rosetta Code - Wikipedia Link : https://en.wikipedia.org/wiki/Rosetta_Code Text : Rosetta Code is a wiki-based programming chrestomathy website with implementations of common algorithms ... Title: Rosetta Code (@rosettacode) | Twitter Link : https://twitter.com/rosettacode Text : The latest Tweets from Rosetta Code (@rosettacode). Twitter account for http://t.co/DuRZFWDfRn. The ... PAGE 2 => Title: Rosetta Code Blog Link : http://blog.rosettacode.org/ Text : As I noted, there was an expectation of downtime as the VPS hostRosetta Code sits on moved from one data ... Title: Rosetta Code - Wikipedia Link : https://en.wikipedia.org/wiki/User:Paddy3118/Rosetta_Code Text : Rosetta Code is a wiki-based programming chrestomathy website with implementations of common algorithms ... Title: Rosetta Code and ABAP | SAP Blogs Link : https://blogs.sap.com/2015/03/27/rosetta-code-and-abap/ Text : Last week Christian Drumm (@ceedee666) and Fred Verheul (@fredverheul) had a short conversation on ...
Mathematica /Wolfram Language
We cannot define a class in Mathematica, so I generate a "Manipulate" object instead.
Manipulate[
Column[Flatten[
StringCases[
StringCases[
URLFetch[
"http://search.yahoo.com/search?p=" <> query <> "&b=" <>
ToString@page], "<ol" ~~ ___ ~~ "</ol>"],
"<a" ~~ Shortest[__] ~~ "class=\"yschttl spt\" href=\"" ~~
Shortest[url__] ~~ "\"" ~~ Shortest[__] ~~ ">" ~~
Shortest[title__] ~~
"<div class=\"abstr\">" | "<div class=\"sm-abs\">" ~~
Shortest[abstr__] ~~ "</div>" :>
Column[{Hyperlink[Style[#[[1]], Larger], #[[2]]], #[[3]],
Style[#[[2]], Smaller]} &@
StringReplace[{title, url,
abstr}, {"<" ~~ Shortest[__] ~~ ">" -> "",
"&#" ~~ n : DigitCharacter ... ~~ ";" :>
FromCharacterCode[FromDigits@n], "&" -> "&",
""" -> "\"", "<" -> "<", ">" -> ">"}]]], 1],
Spacings -> 2], {{input, "", "Yahoo!"},
InputField[Dynamic@input, String] &}, {{query, ""},
ControlType -> None}, {{page, 1}, ControlType -> None},
Row[{Button["Search", page = 1; query = input],
Button["Prev", page -= 10, Enabled -> Dynamic[page >= 10]],
Button["Next", page += 10]}]]
Nim
import httpclient, strutils, htmlparser, xmltree, strtabs
const
PageSize = 7
YahooURLPattern = "https://search.yahoo.com/search?fr=opensearch&b=$$#&pz=$#&p=".format(PageSize)
type
SearchResult = ref object
url, title, content: string
SearchInterface = ref object
client: HttpClient
urlPattern: string
page: int
results: array[PageSize+2, SearchResult]
proc newSearchInterface(question: string): SearchInterface =
new result
result.client = newHttpClient()
# result.client = newHttpClient(proxy = newProxy(
# "http://localhost:40001")) # only http_proxy supported
result.urlPattern = YahooURLPattern&question
proc search(si: SearchInterface) =
let html = parseHtml(si.client.getContent(si.urlPattern.format(
si.page*PageSize+1)))
var
i: int
attrs: XmlAttributes
for d in html.findAll("div"):
attrs = d.attrs
if attrs != nil and attrs.getOrDefault("class").startsWith("dd algo algo-sr relsrch"):
let d_inner = d.child("div")
for a in d_inner.findAll("a"):
attrs = a.attrs
if attrs != nil and attrs.getOrDefault("class") == " ac-algo fz-l ac-21th lh-24":
si.results[i] = SearchResult(url: attrs["href"], title: a.innerText,
content: d.findAll("p")[0].innerText)
i+=1
break
while i < len(si.results) and si.results[i] != nil:
si.results[i] = nil
i+=1
proc nextPage(si: SearchInterface) =
si.page+=1
si.search()
proc echoResult(si: SearchInterface) =
for res in si.results:
if res == nil:
break
echo(res[])
var searchInf = newSearchInterface("weather")
searchInf.search()
searchInf.echoResult()
echo("searching for next page...")
searchInf.nextPage()
searchInf.echoResult()
- Output:
(url: "https://weather.com/", title: "National and Local Weather Radar, Daily Forecast, Hurricane ...", content: "The Weather Channel and weather.com provide a national and local weather forecast for cities, as well as weather radar, report and hurricane coverage ") (url: "https://weather.com/weather/tenday/l/California+MO?canonicalCityId=d58964aa4d5c9ba2a8e76fe9175052ef5d1ed9ee98eb5514e2b58d67722f7e0e", title: "California, MO 10-Day Weather Forecast - The Weather Channel ...", content: "Be prepared with the most accurate 10-day forecast for California, MO with highs, lows, chance of precipitation from The Weather Channel and Weather.com ") (url: "https://www.accuweather.com/", title: "Local, National, & Global Daily Weather Forecast | AccuWeather", content: "AccuWeather has local and international weather forecasts from the most accurate weather forecasting technology featuring up to the minute weather reports ") (url: "https://www.weather.gov/", title: "National Weather Service", content: "Surface Weather Upper Air Marine and Buoy Reports Snow Cover Satellite Space Weather International Observations. FORECAST Local Forecast International Forecasts Severe Weather Current Outlook Maps Drought Fire Weather Fronts/Precipitation Maps Current Graphical Forecast Maps Rivers Marine Offshore and High Seas Hurricanes Aviation Weather ") (url: "https://www.wunderground.com/", title: "Local Weather Forecast, News and Conditions | Weather Underground", content: "Weather Underground provides local & long-range weather forecasts, weather reports, maps & tropical weather conditions for locations worldwide ") (url: "https://graphical.weather.gov/sectors/missouri.php", title: "NOAA Graphical Forecast for Missouri - National Weather Service", content: "National Weather Service 1325 East West Highway Silver Spring, MD 20910 Page Author: NWS Internet Services Team: Disclaimer Information Quality Credits ... ") (url: "https://www.weatherbug.com/weather-forecast/now/macon-mo-63552", title: "Macon, Missouri | Current Weather Forecasts, Live Radar Maps ...", content: "For more than 20 years Earth Networks has operated the world’s largest and most comprehensive weather observation, lightning detection, and climate networks. We are now leveraging our big data smarts to deliver on the promise of IoT. ") (url: "https://www.accuweather.com/en/us/lakeview-heights-mo/65338/weather-forecast/2107359", title: "Lakeview Heights, MO Today, Tonight & Tomorrow\'s Weather ...", content: "Get the forecast for today, tonight & tomorrow\'s weather for Lakeview Heights, MO. Hi/Low, RealFeel®, precip, radar, & everything you need to be ready for the day, commute, and weekend! ") (url: "https://www.wunderground.com/forecast/us/az/tucson", title: "Tucson, AZ 10-Day Weather Forecast | Weather Underground", content: "Tucson Weather Forecasts. Weather Underground provides local & long-range weather forecasts, weatherreports, maps & tropical weather conditions for the Tucson area. ") searching for next page... (url: "https://forecast.weather.gov/", title: "National Weather Service", content: "NOAA National Weather Service National Weather Service. Widespread Heat This Week; Monsoon Rain Lingers. Widespread heat concerns are expected through at least midweek as high pressure covers a large portion of the U.S., especially the Central half. ") (url: "https://weather.com/weather/tenday/l/Port+Huron+MI?canonicalCityId=772884de37d69a70824031f9ab1202b956e665bdf14a6ffd3257184d64d33351", title: "Port Huron, MI 10-Day Weather Forecast - The Weather Channel ...", content: "Be prepared with the most accurate 10-day forecast for Port Huron, MI with highs, lows, chance of precipitation from The Weather Channel and Weather.com ") (url: "https://www.weather.gov/sgx/", title: "San Diego, CA - National Weather Service", content: "Jul 17, 2021 · NOAA National Weather Service San Diego, CA. Seasonable temperatures will be felt tonight with low cloudiness along the coast and into the valleys with a mostly clear sky inland. ") (url: "https://www.weatherbug.com/weather-forecast/now/houston-tx-77007", title: "Houston, Texas | Current Weather Forecasts, Live Radar Maps ...", content: "For more than 20 years Earth Networks has operated the world’s largest and most comprehensive weather observation, lightning detection, and climate networks. We are now leveraging our big data smarts to deliver on the promise of IoT. ") (url: "https://www.msn.com/en-us/weather", title: "MSN", content: "Sunny. There will be mostly sunny skies. The high will be 103°. Feels Like. 65°. Air Quality. Moderate air ( 51 - 100) Primary pollutant PM2.5 11 μg/m³. 52. ") (url: "https://www.noaa.gov/weather", title: "Weather | National Oceanic and Atmospheric Administration", content: "Jun 04, 2021 · Weather, water and climate events, cause an average of approximately 650 deaths and $15 billion in damage per year and are responsible for some 90 percent of all presidentially-declared disasters. About one-third of the U.S. economy – some $3 trillion – is sensitive to weather and climate. ") (url: "https://www.nbcphiladelphia.com/weather/", title: "NBC10 Philadelphia – Philadelphia News, Local News, Weather ...", content: "Weather stories. severe weather 3 mins ago ‘Destructive Damage\' to Be Added to National Weather Service Cell Phone Alerts weather 5 hours ago Today\'s NBC10 First Alert Forecast ... ")
Oz
Instead of a class the implementation defines a function which returns a lazy list of result pages. This also makes it possible to request e.g. the first and the third page without any resources wasted on an unneeded second page.
We implement some simple parsing with logic programming. Regular expressions in Oz don't seem to support lazy quantification which makes parsing the result pages with them difficult.
declare
[HTTPClient] = {Module.link ['x-ozlib://mesaros/net/HTTPClient.ozf']}
[StringX] = {Module.link ['x-oz://system/String.ozf']}
[Regex] = {Module.link ['x-oz://contrib/regex']}
%% Displays page 1 and 3 of the search results.
%% The user can request and display more with context menu->Actions->Make Needed.
proc {ExampleUsage}
Pages = {YahooSearch "Rosetta code"}
in
{Inspector.configure widgetShowStrings true}
{ForAll {Nth Pages 1} Value.makeNeeded}
{ForAll {Nth Pages 3} Value.makeNeeded}
%% Display the infinite list of search result pages.
{Inspect Pages}
end
%% Returns a lazy list of pages.
%% A page is a lazy list of entries like this: result(url:U title:T content:C).
fun {YahooSearch Query}
FetchURL = {CreateURLFetcher}
fun {Page Nr}
StartResult = (Nr-1)*10+1
%% only retrieve it when really needed
Doc = {Value.byNeed fun {$}
{FetchURL "http://search.yahoo.com/search"
["p"#Query "b"#{Int.toString StartResult}]}
end}
RE = "<a class=\"yschttl spt\" href="
in
%% Lazily returns results.
%% In this way it is possible to build the pages list structure
%% without creating the single elements
%% (e.g. retrieve page 1 and 3 but not 2).
for Match in {Regex.allMatches RE Doc} yield:Yield do
Xs = {List.drop Doc Match.0.2}
in
{Yield {ParseEntry Xs}}
end
end
in
for PageNr in 1;PageNr+1 yield:Yield do
{Yield {Page PageNr}}
end
end
fun {CreateURLFetcher}
Client = {New HTTPClient.cgiGET
init(inPrms(toFile:false toStrm:true)
httpReqPrms
)}
%% close when no longer used
{Finalize.register Client proc {$ C} {C closeAll(true)} end}
fun {FetchURL Url Params}
OutParams
in
{Client getService(Url Params ?OutParams ?_)}
OutParams.sOut
end
in
FetchURL
end
%% Xs: String containing HtmL
%% Result: "result(url:U title:T content:C)" or "parseError"
fun {ParseEntry Xs}
proc {Parse Root}
R1 R2 R3 R4 R4 R5 R6 R7
Url = {Fix {QuotedString Xs R1}}
{Const ">" R1 R2}
Title = {Fix {Until "</a>" R2 R3}}
{Const "</h3></div>" R3 R4}
choice
%% "enchanted" result?
{Const "<div class=\"sm-bd sm-nophoto\" id=\"sm-bd-4-1\">" R4 R5}
{Until "</div>" R5 R6 _}
[] %% result with links into document
{Const "<div class=\"sm-bd sm-r\" id=\"sm-bd-8-1\">" R4 R5}
{Until "</ul></div>" R5 R6 _}
[] %% PDF file
{Const "<div class=\"format\">" R4 R5}
{Until "</a></div>" R5 R6 _}
[] %% With Review
{Const "<div class=\"sm-bd sm-r\" id=\"sm-bd-9-1\">" R4 R5}
R6 = nil %% no nice abstract when a review is there
[] %% normal result
R6 = R4
end
Abstract =
choice
{Const "<div class=\"abstr\">" R6 R7}
{Fix {Until "</div>" R7 _}}
[] {Const "<div class=\"sm-abs\">" R6 R7}
{Fix {Until "</div>" R7 _}}
[] ""
end
in
Root = result(url:Url title:Title content:Abstract)
end
in
{CondSelect {SearchOne Parse} 1 parseError}
end
%% Result: contents of Xs until M is found.
%% Xs = {Append M Yr}
fun {Until M Xs ?Yr}
L R
in
{List.takeDrop Xs {Length M} L R}
if L == M then Yr = R nil
elsecase Xs of X|Xr then X|{Until M Xr Yr}
[] nil then Yr = nil nil
end
end
%% Asserts that Xs starts with C. Returns the remainder in Ys.
proc {Const C Xs ?Ys}
{List.takeDrop Xs {Length C} C Ys}
end
%% Assert that a quoted string follows.
%% Returns the unquoted string and binds Ys to the remainder of Xs.
fun {QuotedString &"|Xs ?Ys}
fun {Loop Xs Ys}
case Xs of &\\|&"|Xr then &\\|&"|{Loop Xr Ys}
[] &"|Xr then Ys = Xr nil
[] X|Xr then X|{Loop Xr Ys}
end
end
in
{Loop Xs Ys}
end
%% Remove formatting tags.
fun {Fix Xs}
{Until "</a></h3>"
{FoldL ["<b>" "</b>" "<wbr />" "<wbr>" "<b>...</b>"]
fun {$ Ys Z}
{StringX.replace Ys Z ""}
end
Xs}
_}
end
in
{ExampleUsage}
Perl
package YahooSearch;
use Encode;
use HTTP::Cookies;
use WWW::Mechanize;
# --- Internals -------------------------------------------------
sub apply (&$)
{my $f = shift; local $_ = shift; $f->(); return $_;}
# We construct a cookie to get 100 results per page and prevent
# "enhanced results".
my $search_prefs = 'v=1&n=100&sm=' .
apply {s/([^a-zA-Z0-9])/sprintf '%%%02X', ord $1/ge}
join '|',
map {'!' . $_}
qw(hsb Zq0 XbM sss dDO VFM RQh uZ0 Fxe yCl GP4 FZK yNC mEG niH);
my $cookies = HTTP::Cookies->new;
$cookies->set_cookie(0, 'sB', $search_prefs, '/', 'search.yahoo.com');
my $mech = new WWW::Mechanize
(cookie_jar => $cookies,
stack_depth => 0);
sub read_page
{my ($next, $page, @results) =
($mech->find_link(text => 'Next >')->url,
decode 'iso-8859-1', $mech->content);
while ($page =~ m
{<h3> <a \s class="yschttl \s spt" \s
href=" ([^"]+) " \s* > #"
(.+?) </a>
.+?
<div \s class="abstr">
(.+?) </div>}xg)
{push @results, {url => $1, title => $2, content => $3};
foreach ( @{$results[-1]}{qw(title content)} )
{s/<.+?>//g;
$_ = encode 'utf8', $_;}}
return $next, \@results;}
# --- Methods ---------------------------------------------------
sub new
{my $invocant = shift;
my $class = ref($invocant) || $invocant;
$mech->get('http://search.yahoo.com/search?p=' . apply
{s/([^a-zA-Z0-9 ])/sprintf '%%%02X', ord $1/ge;
s/ /+/g;}
shift);
my ($next, $results) = read_page();
return bless {link_to_next => $next, results => $results}, $class;}
sub results
{@{shift()->{results}};}
sub next_page
{my $invocant = shift;
my $next = $invocant->{link_to_next};
unless ($next)
{$invocant->{results} = [];
return undef;}
$mech->get($next);
($next, my $results) = read_page();
$invocant->{link_to_next} = $next;
$invocant->{results} = $results;
return 1;}
Phix
As noted elsewhere, Yahoo and other search sites will regularly change the output format, so don't be too shocked if this is once again broken. Last fixed 22/4/2022 (with previous left in as comments). The glyphs constants do not show up properly on rosettacode, so here they are in plain text, and I even had to edit that by hand:
constant glyphs = {{"\xC2\xB7 ","*"}, -- bullet point {"'",`'`}, -- single quote {""",`"`}, -- double quote {"&","&"}, -- ampersand {"\xE2\x94\xAC\xC2\xAB","[R]"}, -- registered {"\xC2\xAE","[R]"}}, -- registered
-- -- demo\rosetta\Yahoo_search_interface.exw -- ======================================= -- without js -- (libcurl) include builtins\libcurl.e constant glyphs = {{"\xC2\xB7 ","*"}, -- bullet point {"'",`'`}, -- single quote {""",`"`}, -- double quote {"&","&"}, -- ampersand {"\xE2\x94\xAC\xC2\xAB","[R]"}, -- registered {"\xC2\xAE","[R]"}}, -- registered {gutf8,gascii} = columnize(glyphs), tags = {{`<a `,`</a>`}, {`<b>`,`</b>`}, {`<span class=" fc-2nd">`,`</span>`}} function grab(string txt, opener, closer, integer tdx, bool crop) integer openidx = match(opener,txt,tdx) if openidx=0 then return {0,""} end if integer closeidx = match(closer,txt,openidx) txt = txt[openidx+length(opener)..closeidx-1] tdx = 1 while tdx<=length(tags) do {opener,closer} = tags[tdx] integer i = match(opener,txt) if i=0 then tdx += 1 else if opener[$]='>' then txt[i..i+length(opener)-1] = "" else txt[i..find('>',txt,i)] = "" end if i = match(closer,txt,i) txt[i..i+length(closer)-1] = "" end if end while txt = substitute_all(txt,gutf8,gascii) if crop and length(txt)>80 then txt[78..$] = ".." end if return {closeidx+length(closer),txt} end function procedure YahooSearch(string query, integer page=1) printf(1,"Page %d:\n=======\n",page) string url = sprintf("https://search.yahoo.com/search?p=%s&b=%d", {query, (page-1)*10+1}) --?url object res = curl_easy_perform_ex(url) --?res if not string(res) then ?{"some error",res,curl_easy_strerror(res)} return end if integer rdx = 1 string title, link, desc while true do -- {rdx,title} = grab(res,`<h3 class="title ov-h">`,`</h3>`,rdx) -- {rdx,title} = grab(res,`<span class=" d-ib p-abs t-0 l-0 fz-14 lh-20 fc-obsidian wr-bw ls-n pb-4">`,`</span>`,rdx) {rdx,title} = grab(res,`<h3 style="display:block;margin-top:24px;margin-bottom:2px;" class="title">`,`</h3>`,rdx,false) if rdx=0 then exit end if -- {rdx,title} = grab(res,`</span>`,`</a>`,rdx) -- title = title[rmatch(`</span>`,title)+7..rmatch(`<\a>`,title)] title = title[rmatch(`</span>`,title)+7..$] -- {rdx,link} = grab(res,`<span class=" fz-ms fw-m fc-12th wr-bw lh-17">`,`</span>`,rdx) {rdx,link} = grab(res,`<span>`,`</span>`,rdx,true) -- {rdx,desc} = grab(res,`<p class="fz-ms lh-1_43x">`,`</p>`,rdx) {rdx,desc} = grab(res,`<span class=" fc-falcon">`,`</span>`,rdx,true) printf(1,"title:%s\nlink:%s\ndesc:%s\n\n",{title,link,desc}) end while end procedure YahooSearch("rosettacode") YahooSearch("rosettacode",2) ?"done" {} = wait_key()
- Output:
Page 1: ======= title:Rosetta Code link:rosettacode.org desc:Jan 29, 2016 * Rosetta Code is a programming chrestomathy site. The idea is t.. title:Rosetta Code - Wikipedia link:en.wikipedia.org/wiki/Rosetta_Code desc:Rosetta Code is a wiki -based programming website with implementations of com.. title:@rosettacode | Twitter link:twitter.com/rosettacode desc:The latest tweets from @rosettacode title:Rosetta Code - Simple English Wikipedia, the free encyclopedia link:simple.wikipedia.org/wiki/Rosetta_Code desc:Rosetta Code is a wiki-based website that features ways to solve various prog.. <snip> Page 2: ======= title:Category:Guile - Rosetta Code link:rosettacode.org/wiki/Category:Guile desc:May 30, 2020 * Listed below are all of the tasks on Rosetta Code which have b.. title:Rosetta Code - c2.com link:wiki.c2.com/?RosettaCode desc:Rosetta Code is a repository for code examples that go beyond the traditional.. <snip> title:Rosetta Stone | Discovery, History, & Facts | Britannica link:www.britannica.com/topic/Rosetta-Stone desc:Rosetta Stone, ancient Egyptian stone bearing inscriptions in several languag..
PicoLisp
(load "@lib/http.l")
(de yahoo (Query Page)
(default Page 1)
(client "search.yahoo.com" 80
(pack
"search?p=" (ht:Fmt Query)
"&b=" (inc (* 10 (dec Page))) )
(make
(while (from "<a class=\"yschttl spt\" href=\"")
(link
(make
(link (till "\"" T)) # Url
(from "<b>")
(link (till "<" T)) # Title
(from "class=\"abstr\"")
(from ">")
(link # Content
(pack
(make
(loop
(link (till "<" T))
(T (eof))
(T (= "</div" (till ">" T)))
(char) ) ) ) ) ) ) ) ) ) )
Output:
: (more (yahoo "test")) ("http://www.test.com/" "Test" "Offers practice online tests for many ... ("http://www.test.com/aboutus.htm" "Test" "Test.com has a successful ... ("http://en.wikipedia.org/wiki/Test" "Test" "YUI Test is a testing ... ("http://en.wikipedia.org/wiki/F-test" "test " "test n. A procedure for ... ...
Python
import urllib
import re
def fix(x):
p = re.compile(r'<[^<]*?>')
return p.sub('', x).replace('&', '&')
class YahooSearch:
def __init__(self, query, page=1):
self.query = query
self.page = page
self.url = "http://search.yahoo.com/search?p=%s&b=%s" %(self.query, ((self.page - 1) * 10 + 1))
self.content = urllib.urlopen(self.url).read()
def getresults(self):
self.results = []
for i in re.findall('<a class="yschttl spt" href=".+?">(.+?)</a></h3></div>(.+?)</div>.*?<span class=url>(.+?)</span>', self.content):
title = fix(i[0])
content = fix(i[1])
url = fix(i[2])
self.results.append(YahooResult(title, content, url))
return self.results
def getnextpage(self):
return YahooSearch(self.query, self.page+1)
search_results = property(fget=getresults)
nextpage = property(fget=getnextpage)
class YahooResult:
def __init__(self,title,content,url):
self.title = title
self.content = content
self.url = url
# Usage:
x = YahooSearch("test")
for result in x.search_results:
print result.title
R
Rather than using regexes to find the content (like some of the other solutions here) this method parses the HTML and finds the appropriate sections.
YahooSearch <- function(query, page=1, .opts=list(), ignoreMarkUpErrors=TRUE)
{
if(!require(RCurl) || !require(XML))
{
stop("Could not load required packages")
}
# Replace " " with "%20", etc
query <- curlEscape(query)
# Retrieve page
b <- 10*(page-1)+1
theurl <- paste("http://uk.search.yahoo.com/search?p=",
query, "&b=", b, sep="")
webpage <- getURL(theurl, .opts=.opts)
# Save search for nextpage function
.Search <- list(query=query, page=page, .opts=.opts,
ignoreMarkUpErrors=ignoreMarkUpErrors)
assign(".Search", .Search, envir=globalenv())
# Parse HTML; retrieve results block
webpage <- readLines(tc <- textConnection(webpage)); close(tc)
if(ignoreMarkUpErrors)
{
pagetree <- htmlTreeParse(webpage, error=function(...){})
} else
{
pagetree <- htmlTreeParse(webpage)
}
findbyattr <- function(x, id, type="id")
{
ids <- sapply(x, function(x) x$attributes[type])
x[ids==id]
}
body <- pagetree$children$html$children$body
bd <- findbyattr(body$children$div$children, "bd")
left <- findbyattr(bd$div$children$div$children, "left")
web <- findbyattr(left$div$children$div$children, "web")
resol <- web$div$children$ol
#Get url, title, content from results
gettextfromnode <- function(x)
{
un <- unlist(x$children)
paste(un[grep("value", names(un))], collapse=" ")
}
n <- length(resol)
results <- list()
length(results) <- n
for(i in 1:n)
{
mainlink <- resol[[i]]$children$div$children[1]$div$children$h3$children$a
url <- mainlink$attributes["href"]
title <- gettextfromnode(mainlink)
contenttext <- findbyattr(resol[[i]]$children$div$children[2], "abstr", type="class")
if(length(contenttext)==0)
{
contenttext <- findbyattr(resol[[i]]$children$div$children[2]$div$children$div$children,
"sm-abs", type="class")
}
content <- gettextfromnode(contenttext$div)
results[[i]] <- list(url=url, title=title, content=content)
}
names(results) <- as.character(seq(b, b+n-1))
results
}
nextpage <- function()
{
if(exists(".Search", envir=globalenv()))
{
.Search <- get(".Search", envir=globalenv())
.Search$page <- .Search$page + 1L
do.call(YahooSearch, .Search)
} else
{
message("No search has been performed yet")
}
}
#Usage
YahooSearch("rosetta code")
nextpage()
Racket
#lang racket
(require net/url)
(define *yaho-url* "http://search.yahoo.com/search?p=~a&b=~a")
(define *current-page* 0)
(define *current-query* "")
(define request (compose port->string get-pure-port string->url))
;;strip html tags
(define (remove-tags text)
(regexp-replace* #px"<[^<]+?>" text ""))
;;search, parse and print
(define (search-yahoo query)
(unless (string=? *current-query* query) ;different query, go back to page 1
(set! *current-query* query)
(set! *current-page* 0))
(let* ([current-page (number->string (add1 (* 10 *current-page*)))]
[html (request (format *yaho-url* query current-page))]
[results (regexp-match* #px"lass=\"yschttl spt\" href=\".+?\">(.+?)<span class=url>(.+?)</span>.+?<div class=\"abstr\">(.+?)</div>" html #:match-select cdr)])
(for ([result (in-list results)])
(printf "Title: ~a \n Link: ~a \n Text: ~a \n\n"
(remove-tags (first result))
(remove-tags (second result) )
(remove-tags (third result))))))
;;search nexxt page
(define (next-page)
(set! *current-page* (add1 *current-page*))
(search-yahoo *current-query*))
- REPL:
(search-yahoo "Rosetta") Title: Partner With Our Interactive Marketing Agency Today | Rosetta Link: www.rosetta.com Text: Learn about the fastest growing interactive marketing agency in the country - Rosetta. Our strategic marketing planning is custom built and connects you with your ... Title: Official Rosetta Stone® - Language Learning - Learn a Language Link: www.rosettastone.com Text: Learn a new language with Rosetta Stone®. SUMMER SALE! $349 Levels 1-5 Set + Free Shipping. Ending Soon! Title: Rosetta (spacecraft) - Wikipedia, the free encyclopedia Link: en.wikipedia.org/wiki/Rosetta_probe Text: noun 1. a town in N Egypt, at a mouth of the Nile. 2. a female given name . Relevant Questions Why Was The Rosetta Ston... Who Is Rosetta Stone? Why Is The Rosetta ... Title: Rosetta stone: Definition from Answers.com Link: www.answers.com/topic/rosetta-stone Text: Rosetta stone n. A basalt tablet bearing inscriptions in Greek and in Egyptian hieroglyphic and demotic scripts that w Title: Rosetta (1999) - IMDb Link: www.imdb.com/title/tt0200071 Text: The first scene, like almost all others, is a fighting scene. A girl, about 18, is sacked from her factory work because her trial period is over. The girl, Rosetta ... Title: Welcome to Rosetta Stone® Classroom Link: salem-keizersd.rosettastoneclassroom.com Text: Welcome to Rosetta Stone® Classroom. First Time Users; © 2013 Rosetta Stone Ltd. All rights reserved. Title: Rosetta Hardscapes Link: www.discoverrosetta.com/index.html Text: Rosetta Hardscapes sells and licenses concrete pavers, fire pits, retaining walls and landscaping features with the colors and textures of natural stone. (next-page) Title: Rosetta Stone Link: www.rosettastone.com/?prid=rosettaclassroom_com Text: Find great prices & selection on Rosetta Stone language software for Windows & Mac; shop & buy titles to learn Spanish, French, & more. Title: rosetta stone spanish | eBay - Electronics, Cars, Fashion ... Link: www.ebay.com/sch/i.html?_nkw=rosetta+stone+spanish Text: Find great deals on eBay for rosetta stone spanish and rosetta stone spanish latin america. Shop with confidence. Title: Apple - Rosetta Link: www.apple.com/asia/rosetta Text: Applications bearing the Universal symbol will run natively on both Intel- and PowerPC-based Mac computers. What about the applications you already own? Enter Rosetta. Title: Rosetta | Free Music, Tour Dates, Photos, Videos Link: www.myspace.com/rosetta Text: The International Rosetta Mission was approved in ... Lutetia is revealed by a comprehensive analysis of the data gathered by ESA's Rosetta spacecraft when it ... Title: Amazon.com: rosetta stone Link: www.amazon.com/s?ie=UTF8&page=1&rh=i%3Aaps%2Ck%3Arosetta... Text: Rosetta Stone Spanish (Latin America) Level 1 by Rosetta Stone (CD-ROM - Sept. 14, 2010) - Mac OS X 10.6 Snow Leopard, Windows 7 / 8 / XP. Buy new: $179.00 . Title: Rosetta - Disney Wiki Link: disney.wikia.com/wiki/Rosetta Text: Rosetta: Yea, no, I don't really do mud.Vidia: But, you're a garden fairy!Rosetta: Ironic, isn't... Title: Rosetta - Hamilton, NJ - Company | Facebook Link: www.facebook.com/rosetta Text: Rosetta, Hamilton, NJ. 2,060 likes · 36 talking about this · 135 were here. We are currently ranked by Ad Age among the top US digital agencies and recently named ... Title: Rosetta Stone (Game) - CNET Download.com Link: download.cnet.com/Rosetta-Stone/3000-2111_4-10835868.html Text: Whether your are playing Greek number mode or Egyptian letter mode, the number one rule to keep in mind is keeping the scales balanced but its not that ...
Raku
(formerly Perl 6)
YahooSearch.rakumod:
use Gumbo;
use LWP::Simple;
use XML::Text;
class YahooSearch {
has $!dom;
submethod BUILD (:$!dom) { }
method new($term) {
self.bless(
dom => parse-html(
LWP::Simple.get("http://search.yahoo.com/search?p={ $term }")
)
);
}
method next {
$!dom = parse-html(
LWP::Simple.get(
$!dom.lookfor( TAG => 'a', class => 'next' ).head.attribs<href>
)
);
self;
}
method text ($node) {
return '' unless $node;
return $node.text if $node ~~ XML::Text;
$node.nodes.map({ self.text($_).trim }).join(' ');
}
method results {
state $n = 0;
for $!dom.lookfor( TAG => 'h3', class => 'title') {
given .lookfor( TAG => 'a' )[0] {
next unless $_; # No Link
next if .attribs<href> ~~ / ^ 'https://r.search.yahoo.com' /; # Ad
say "=== #{ ++$n } ===";
say "Title: { .contents[0] ?? self.text( .contents[0] ) !! '' }";
say " URL: { .attribs<href> }";
my $pt = .parent.parent.parent.elements( TAG => 'div' ).tail;
say " Text: { self.text($pt) }";
}
}
self;
}
}
sub MAIN (Str $search-term) is export {
YahooSearch.new($search-term).results.next.results;
}
And the invocation script is simply:
yahoo-search.raku
use YahooSearch;
So:
raku yahoo-search.raku test
Should give out something like the following:
=== #1 ===
Title:
URL: https://www.speedtest.net/
Text: At Ookla, we are committed to ensuring that individuals with disabilities can access all of the content at www.speedtest.net. We also strive to make all content in Speedtest apps accessible. If you are having trouble accessing www.speedtest.net or Speedtest apps, please email legal@ziffdavis.com for assistance. Please put "ADA Inquiry" in the ...
=== #2 ===
Title: Test | Definition of Test by Merriam-Webster
URL: https://www.merriam-webster.com/dictionary/test
Text: Test definition is - a means of testing: such as. How to use test in a sentence.
=== #3 ===
Title: - Video Results
URL: https://video.search.yahoo.com/search/video?p=test
Text: More Test videos
...and should go up to result #21!
Ruby
Uses
to parse the HTML. Someone more skillful than I at XPath or CSS could tighten up the parse_html
method.
require 'open-uri'
require 'hpricot'
SearchResult = Struct.new(:url, :title, :content)
class SearchYahoo
@@urlinfo = [nil, 'ca.search.yahoo.com', 80, '/search', nil, nil]
def initialize(term)
@term = term
@page = 1
@results = nil
@url = URI::HTTP.build(@@urlinfo)
end
def next_result
if not @results
@results = []
fetch_results
elsif @results.empty?
next_page
end
@results.shift
end
def fetch_results
@url.query = URI.escape("p=%s&b=%d" % [@term, @page])
doc = open(@url) { |f| Hpricot(f) }
parse_html(doc)
end
def next_page
@page += 10
fetch_results
end
def parse_html(doc)
doc.search("div#main").search("div").each do |div|
next unless div.has_attribute?("class") and div.get_attribute("class").index("res") == 0
result = SearchResult.new
div.search("a").each do |link|
next unless link.has_attribute?("class") and link.get_attribute("class") == "yschttl spt"
result.url = link.get_attribute("href")
result.title = link.inner_text
end
div.search("div").each do |abstract|
next unless abstract.has_attribute?("class") and abstract.get_attribute("class").index("abstr")
result.content = abstract.inner_text
end
@results << result
end
end
end
s = SearchYahoo.new("test")
15.times do |i|
result = s.next_result
puts i+1
puts result.title
puts result.url
puts result.content
puts
end
Run BASIC
'--------------------------------------------------------------------------
' send this from the server to the clients browser
'--------------------------------------------------------------------------
html "<table border=1 cellpadding=0 cellspacing=0 bgcolor=wheat>"
html "<tr><td align=center colspan=2>Yahoo Search</td></tr>"
html "<tr><td align=right>Find</td><td>"
textbox #find,findThis$,30
html "</td></tr><tr><td align=right>Page</td><td>"
textbox #page,findPage$,2
html "</td></tr><tr><td align=center colspan=2>"
button #s, "Search", [search]
html " "
button #ex, "Exit", [exit]
html "</td><td></td></tr></table>"
wait
'--------------------------------------------------------------------------
' get search stuff from the clients browser
'--------------------------------------------------------------------------
[search]
findThis$ = trim$(#find contents$())
findPage$ = trim$(#page contents$())
findPage = max(val(findPage$),1) ' must be at least 1
'--------------------------------------------------------------------------
' sho page but keep user interface at the top by not clearing the page (cls)
' so they can change the search or page
' -------------------------------------------------------------------------
url$ = "http://search.yahoo.com/search?p=";findThis$;"&b=";((findPage - 1) * 10) + 1
html httpget$(url$)
wait
[exit]
cls ' clear browser screen and get outta here
wait
This user input sits at the top of the yahoo page so they can select a new search or page
Tcl
package require http
proc fix s {
string map {<b>...</b> "" <b> "" </b> "" <wbr> "" "<wbr />" ""} \
[regsub "</a></h3></div>.*" $s ""]
}
proc YahooSearch {term {page 1}} {
# Build the (ugly) scraper URL
append re {<a class="yschttl spt" href=".+?" >(.+?)</a></h3>}
append re {</div><div class="abstr">(.+?)}
append re {</div><span class=url>(.+?)</span>}
# Perform the query; note that this handles special characters
# in the query term correctly
set q [http::formatQuery p $term b [expr {$page*10-9}]]
set token [http::geturl http://search.yahoo.com/search?$q]
set data [http::data $token]
http::cleanup $token
# Assemble the results into a nice list
set results {}
foreach {- title content url} [regexp -all -inline $re $data] {
lappend results [fix $title] [fix $content] [fix $url]
}
# set up the call for the next page
interp alias {} Nextpage {} YahooSearch $term [incr page]
return $results
}
# Usage: get the first two pages of results
foreach {title content url} [YahooSearch "test"] {
puts $title
}
foreach {title content url} [Nextpage] {
puts $title
}
With Tcl 8.6, more options are available for managing the global state, through objects and coroutines. First, an object-based solution that takes the basic YahooSearch functionality and dresses it up to be more Tcl-like:
package require Tcl 8.6
oo::class create WebSearcher {
variable page term results
constructor searchTerm {
set page 0
set term $searchTerm
my nextPage
}
# This next method *is* a very Tcl-ish way of doing iteration.
method for {titleVar contentsVar urlVar body} {
upvar 1 $titleVar t $contentsVar c $urlVar v
foreach {t c v} $results {
uplevel 1 $body
}
}
# Reuse the previous code for simplicity rather than writing it anew
# Of course, if we were serious about this, we'd put the code here properly
method nextPage {} {
set results [YahooSearch $term [incr page]]
return
}
}
# How to use. Note the 'foreach' method use below; new "keywords" as methods!
set ytest [WebSearcher new "test"]
$ytest for title - url {
puts "\"$title\" : $url"
}
$ytest nextPage
$ytest for title - url {
puts "\"$title\" : $url"
}
$ytest delete ;# standard method that deletes the object
However, the paradigm of an iterator is also interesting and is more appropriately supported through a coroutine. This version conceals the fact that the service produces output in pages; care should be taken with it because it can produce rather a lot of network traffic...
package require Tcl 8.6
proc yahoo! term {
coroutine yahoo![incr ::yahoo] apply {term {
yield [info coroutine]
while 1 {
set results [YahooSearch $term [incr step]]
if {[llength $results] == 0} {
return -code break
}
foreach {t c u} $results {
yield [dict create title $t content $c url $u]
}
}
}} $term
}
# test by getting first fifty titles...
set it [yahoo! "test"]
for {set i 50} {$i>0} {incr i -1} {
puts [dict get [$it] title]
after 300 ;# Slow the code down... :-)
}
Another approach: uses a class as specified in the task. Also, uses an html parser from tcllib (parsing html with regular expressions is a particular annoyance of mine).
package require Tcl 8.6
package require http
package require htmlparse
package require textutil::adjust
oo::class create yahoosearch {
method search {s} {
my variable searchterm page baseurl
set searchterm $s
set page 1
set baseurl {http://ca.search.yahoo.com/search}
}
method getresults {} {
my variable state results current_data
set results [list]
set current_data [dict create]
set state looking_for_results
htmlparse::parse -cmd [list [self] html_parser_callback] [my gethtml]
}
method nextpage {} {
my variable page
incr page 10
my getresults
}
method nextresult {} {
my variable results page
if { ! [info exists results]} {
my getresults
} elseif {[llength $results] == 0} {
my nextpage
}
set results [lassign $results result]
return $result
}
method gethtml {} {
my variable searchterm page baseurl
set url [format {%s?%s} $baseurl [::http::formatQuery p $searchterm b $page]]
set response [http::geturl $url]
set html [http::data $response]
http::cleanup $response
return $html
}
method html_parser_callback {tag slash param textBehindTheTag} {
my variable state results current_data
switch -exact -- $state {
looking_for_results {
if {$tag eq "div" && [string first {id="main"} $param] != -1} {
set state ready
}
}
ready {
if {($tag eq "div" && [string first {class="res} $param] != -1) ||
($tag eq "html" && $slash eq "/")
} { #" -- unbalanced quote disturbs syntax highlighting
if {[dict size $current_data] > 0} {lappend results $current_data}
set current_data [dict create]
set state getting_url
}
}
getting_url {
if {$tag eq "a" && [string match "*yschttl spt*" $param]} {
if {[regexp {href="(.+?)"} $param - url]} {
dict set current_data url $url
} else {
dict set current_data url "no href in tag params: '$param'"
}
dict set current_data title $textBehindTheTag
set state getting_title
}
}
getting_title {
if {$tag eq "a" && $slash eq "/"} {
set state looking_for_abstract
} else {
dict append current_data title $textBehindTheTag
}
}
looking_for_abstract {
if {$tag eq "span" && [string first {class="url} $param] != -1} {
set state ready
} elseif {$tag eq "div" && [string first {class="abstr} $param] != -1} {
dict set current_data abstract $textBehindTheTag
set state getting_abstract
}
}
getting_abstract {
if {$tag eq "div" && $slash eq "/"} {
set state ready
} else {
dict append current_data abstract $textBehindTheTag
}
}
}
}
}
yahoosearch create searcher
searcher search "search text here"
for {set x 1} {$x <= 15} {incr x} {
set result [searcher nextresult]
dict with result {
puts $title
puts $url
puts [textutil::adjust::indent [textutil::adjust::adjust $abstract] " "]
puts ""
}
}
TXR
The following gives us a shell utility which we can invoke with arguments like "rosetta 0" to get the first page of search results for "rosetta".
The two arguments are handled as if they were two lines of text from a data source using @(next :args). We throw an exception if there is no match (insufficient arguments are supplied). The @(cases) directive has strictly ordered evaluation, so the throw in the second branch does not happen if the first branch has a successful pattern match. If the similar @(maybe) or @(some) directives were used, this wouldn't work.
A little sprinkling of regex is used.
#!/usr/bin/txr -f
@(next :args)
@(cases)
@ QUERY
@ PAGE
@(or)
@ (throw error "specify query and page# (from zero)")
@(end)
@(next (open-command "!wget -O - http://search.yahoo.com/search?p=@QUERY\&b=@{PAGE}1 2> /dev/null"))
@(all)
@ (coll)<a class="yschttl spt" href="@URL" @/[^>]+/>@TITLE</a>@(end)
@(and)
@ (coll)<div class="@/abstr|sm-abs/">@ABSTR</div>@(end)
@(end)
@(output)
@ (repeat)
TITLE: @TITLE
URL: @URL
TEXT: @ABSTR
---
@ (end)
@(end)
Sample run:
$ ./yahoosearch.txr rosetta 0 TITLE: <b>Rosetta</b> | Partner With Our Interactive <wbr />Marketing Agency Today URL: http://www.rosetta.com/Pages/default.aspx TEXT: Learn about the fastest growing interactive marketing agency in the country - <b>Rosetta</b>. Our strategic marketing planning is custom built and connects you with your ... --- TITLE: Official <b>Rosetta</b> Stone® - Learn a <wbr />Language Online - Language ... URL: http://www.rosettastone.com/ TEXT: <b>Rosetta</b> Stone is the world's #1 language-learning software. Our comprehensive foreign language program provides language learning for individuals and language learning ... --- TITLE: <b>Rosetta</b> (software) - Wikipedia, the <wbr />free encyclopedia URL: http://en.wikipedia.org/wiki/Rosetta_(software) TEXT: Rosettais a lightweight dynamic translatorfor Mac OS Xdistributed by Apple. It enabled applications compiled for the PowerPCfamily of processors to run on Apple systems that use... --- TITLE: <b>Rosetta</b> (spacecraft) - Wikipedia, the <wbr />free encyclopedia URL: http://en.wikipedia.org/wiki/Rosetta_space_probe TEXT: Rosettais a robotic spacecraftof the European Space Agencyon a mission to study the comet 67P/ChuryumovâGerasimenko. <b>Rosetta </b>consists of two main elements: the <b>Rosetta </b>space probeand... --- TITLE: Apple - Mac URL: http://www.apple.com/mac/ TEXT: Discover the world of Mac. Check out MacBook, iMac, iLife, and more. Download QuickTime, Safari, and widgets for free. --- TITLE: <b>Rosetta</b> | Free Music, Tour Dates, <wbr />Photos, Videos URL: http://www.myspace.com/rosetta TEXT: <b>Rosetta</b>'s official profile including the latest music, albums, songs, music videos and more updates. --- TITLE: <b>Rosetta</b> URL: http://rosettaband.com/ TEXT: Metal for astronauts. Philadelphia, since 2003. Contact us at rosettaband@gmail.com Twitter | Facebook --- TITLE: <b>Rosetta</b> URL: http://rosetta.jpl.nasa.gov/ TEXT: The <b>Rosetta</b> spacecraft is on its way to catch and land a robot on a comet! <b>Rosetta</b> will reach comet '67P/Churyumov-Gerasimenko' ('C-G') in 2014. The European Space Agency ... --- TITLE: <b>Rosetta</b> : Multi-script Typography URL: http://rosettatype.com/ TEXT: <b>Rosetta</b> is a new independent foundry with a strong focus on multi-script typography. We are committed to promote research and knowledge in that area and to support ... --- TITLE: <b>Rosetta</b> (1999) - IMDb URL: http://www.imdb.com/title/tt0200071/ TEXT: With Ãmilie Dequenne, Fabrizio Rongione, Anne Yernaux, Olivier Gourmet. Young and impulsive <b>Rosetta</b> lives with her alcoholic mother and, moved by despair, she will ... ---
Wren
An embedded program so we can use libcurl.
A somewhat ad hoc solution as the output format for Yahoo! search seems to change quite frequently. All I can say is that this worked on 5th January, 2022.
/* Yahoo_search_interface.wren */
import "./pattern" for Pattern
class YahooSearch {
construct new(url, title, desc) {
_url = url
_title = title
_desc = desc
}
toString { "URL: %(_url)\nTitle: %(_title)\nDescription: %(_desc)\n" }
}
var CURLOPT_URL = 10002
var CURLOPT_FOLLOWLOCATION = 52
var CURLOPT_WRITEFUNCTION = 20011
var CURLOPT_WRITEDATA = 10001
foreign class Buffer {
construct new() {} // C will allocate buffer of a suitable size
foreign value // returns buffer contents as a string
}
foreign class Curl {
construct easyInit() {}
foreign easySetOpt(opt, param)
foreign easyPerform()
foreign easyCleanup()
}
var curl = Curl.easyInit()
var getContent = Fn.new { |url|
var buffer = Buffer.new()
curl.easySetOpt(CURLOPT_URL, url)
curl.easySetOpt(CURLOPT_FOLLOWLOCATION, 1)
curl.easySetOpt(CURLOPT_WRITEFUNCTION, 0) // write function to be supplied by C
curl.easySetOpt(CURLOPT_WRITEDATA, buffer)
curl.easyPerform()
return buffer.value
}
var p1 = Pattern.new("class/=\" d-ib ls-05 fz-20 lh-26 td-hu tc va-bot mxw-100p\" href/=\"[+1^\"]\"")
var p2 = Pattern.new("class/=\" d-ib p-abs t-0 l-0 fz-14 lh-20 fc-obsidian wr-bw ls-n pb-4\">[+1^<]<")
var p3 = Pattern.new("<span class/=\" fc-falcon\">[+1^<]<")
var pageSize = 7
var totalCount = 0
var yahooSearch = Fn.new { |query, page|
System.print("Page %(page):\n=======\n")
var next = (page - 1) * pageSize + 1
var url = "https://search.yahoo.com/search?fr=opensearch&pz=%(pageSize)&p=%(query)&b=%(next)"
var content = getContent.call(url).replace("<b>", "").replace("</b>", "")
var matches1 = p1.findAll(content)
var count = matches1.count
if (count == 0) return false
var matches2 = p2.findAll(content)
var matches3 = p3.findAll(content)
totalCount = totalCount + count
var ys = List.filled(count, null)
for (i in 0...count) {
var url = matches1[i].capsText[0]
var title = matches2[i].capsText[0]
var desc = matches3[i].capsText[0].replace("'", "'")
ys[i] = YahooSearch.new(url, title, desc)
}
System.print(ys.join("\n"))
return true
}
var page = 1
var limit = 2
var query = "rosettacode"
System.print("Searching for '%(query)' on Yahoo!\n")
while (page <= limit && yahooSearch.call(query, page)) {
page = page + 1
System.print()
}
System.print("Displayed %(limit) pages with a total of %(totalCount) entries.")
curl.easyCleanup()
We now embed this script in the following C program, build and run.
/* gcc Yahoo_search_interface.c -o Yahoo_search_interface -lcurl -lwren -lm */
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <curl/curl.h>
#include "wren.h"
struct MemoryStruct {
char *memory;
size_t size;
};
/* C <=> Wren interface functions */
static size_t WriteMemoryCallback(void *contents, size_t size, size_t nmemb, void *userp) {
size_t realsize = size * nmemb;
struct MemoryStruct *mem = (struct MemoryStruct *)userp;
char *ptr = realloc(mem->memory, mem->size + realsize + 1);
if(!ptr) {
/* out of memory! */
printf("not enough memory (realloc returned NULL)\n");
return 0;
}
mem->memory = ptr;
memcpy(&(mem->memory[mem->size]), contents, realsize);
mem->size += realsize;
mem->memory[mem->size] = 0;
return realsize;
}
void C_bufferAllocate(WrenVM* vm) {
struct MemoryStruct *ms = (struct MemoryStruct *)wrenSetSlotNewForeign(vm, 0, 0, sizeof(struct MemoryStruct));
ms->memory = malloc(1);
ms->size = 0;
}
void C_bufferFinalize(void* data) {
struct MemoryStruct *ms = (struct MemoryStruct *)data;
free(ms->memory);
}
void C_curlAllocate(WrenVM* vm) {
CURL** pcurl = (CURL**)wrenSetSlotNewForeign(vm, 0, 0, sizeof(CURL*));
*pcurl = curl_easy_init();
}
void C_value(WrenVM* vm) {
struct MemoryStruct *ms = (struct MemoryStruct *)wrenGetSlotForeign(vm, 0);
wrenSetSlotString(vm, 0, ms->memory);
}
void C_easyPerform(WrenVM* vm) {
CURL* curl = *(CURL**)wrenGetSlotForeign(vm, 0);
curl_easy_perform(curl);
}
void C_easyCleanup(WrenVM* vm) {
CURL* curl = *(CURL**)wrenGetSlotForeign(vm, 0);
curl_easy_cleanup(curl);
}
void C_easySetOpt(WrenVM* vm) {
CURL* curl = *(CURL**)wrenGetSlotForeign(vm, 0);
CURLoption opt = (CURLoption)wrenGetSlotDouble(vm, 1);
if (opt < 10000) {
long lparam = (long)wrenGetSlotDouble(vm, 2);
curl_easy_setopt(curl, opt, lparam);
} else if (opt < 20000) {
if (opt == CURLOPT_WRITEDATA) {
struct MemoryStruct *ms = (struct MemoryStruct *)wrenGetSlotForeign(vm, 2);
curl_easy_setopt(curl, opt, (void *)ms);
} else if (opt == CURLOPT_URL) {
const char *url = wrenGetSlotString(vm, 2);
curl_easy_setopt(curl, opt, url);
}
} else if (opt < 30000) {
if (opt == CURLOPT_WRITEFUNCTION) {
curl_easy_setopt(curl, opt, &WriteMemoryCallback);
}
}
}
WrenForeignClassMethods bindForeignClass(WrenVM* vm, const char* module, const char* className) {
WrenForeignClassMethods methods;
methods.allocate = NULL;
methods.finalize = NULL;
if (strcmp(module, "main") == 0) {
if (strcmp(className, "Buffer") == 0) {
methods.allocate = C_bufferAllocate;
methods.finalize = C_bufferFinalize;
} else if (strcmp(className, "Curl") == 0) {
methods.allocate = C_curlAllocate;
}
}
return methods;
}
WrenForeignMethodFn bindForeignMethod(
WrenVM* vm,
const char* module,
const char* className,
bool isStatic,
const char* signature) {
if (strcmp(module, "main") == 0) {
if (strcmp(className, "Buffer") == 0) {
if (!isStatic && strcmp(signature, "value") == 0) return C_value;
} else if (strcmp(className, "Curl") == 0) {
if (!isStatic && strcmp(signature, "easySetOpt(_,_)") == 0) return C_easySetOpt;
if (!isStatic && strcmp(signature, "easyPerform()") == 0) return C_easyPerform;
if (!isStatic && strcmp(signature, "easyCleanup()") == 0) return C_easyCleanup;
}
}
return NULL;
}
static void writeFn(WrenVM* vm, const char* text) {
printf("%s", text);
}
void errorFn(WrenVM* vm, WrenErrorType errorType, const char* module, const int line, const char* msg) {
switch (errorType) {
case WREN_ERROR_COMPILE:
printf("[%s line %d] [Error] %s\n", module, line, msg);
break;
case WREN_ERROR_STACK_TRACE:
printf("[%s line %d] in %s\n", module, line, msg);
break;
case WREN_ERROR_RUNTIME:
printf("[Runtime Error] %s\n", msg);
break;
}
}
char *readFile(const char *fileName) {
FILE *f = fopen(fileName, "r");
fseek(f, 0, SEEK_END);
long fsize = ftell(f);
rewind(f);
char *script = malloc(fsize + 1);
fread(script, 1, fsize, f);
fclose(f);
script[fsize] = 0;
return script;
}
static void loadModuleComplete(WrenVM* vm, const char* module, WrenLoadModuleResult result) {
if( result.source) free((void*)result.source);
}
WrenLoadModuleResult loadModule(WrenVM* vm, const char* name) {
WrenLoadModuleResult result = {0};
if (strcmp(name, "random") != 0 && strcmp(name, "meta") != 0) {
result.onComplete = loadModuleComplete;
char fullName[strlen(name) + 6];
strcpy(fullName, name);
strcat(fullName, ".wren");
result.source = readFile(fullName);
}
return result;
}
int main(int argc, char **argv) {
WrenConfiguration config;
wrenInitConfiguration(&config);
config.writeFn = &writeFn;
config.errorFn = &errorFn;
config.bindForeignClassFn = &bindForeignClass;
config.bindForeignMethodFn = &bindForeignMethod;
config.loadModuleFn = &loadModule;
WrenVM* vm = wrenNewVM(&config);
const char* module = "main";
const char* fileName = "Yahoo_search_interface.wren";
char *script = readFile(fileName);
WrenInterpretResult result = wrenInterpret(vm, module, script);
switch (result) {
case WREN_RESULT_COMPILE_ERROR:
printf("Compile Error!\n");
break;
case WREN_RESULT_RUNTIME_ERROR:
printf("Runtime Error!\n");
break;
case WREN_RESULT_SUCCESS:
break;
}
wrenFreeVM(vm);
free(script);
return 0;
}
- Output:
Limited to first two pages.
Searching for 'rosettacode' on Yahoo! Page 1: ======= URL: https://rosettacode.org/wiki/Rosetta_Code Title: rosettacode.org Description: Enjoy amazing savings with our 50% off URL: https://en.wikipedia.org/wiki/Rosetta_Code Title: en.wikipedia.org Description: Rosetta Code is a programming chrestomathy site. The idea is to present solutions to the same task in as many different languages as possible, to demonstrate how languages are similar and different, and to aid a person with a grounding in one approach to a problem in learning another. URL: https://raku.org/community/rosettacode/ Title: raku.org Description: Rosetta Code is a wiki-based programming website with implementations of common algorithms and solutions to various programming problems in many different programming languages. It is named for the Rosetta Stone , which has the same text inscribed on it in three languages, and thus allowed Egyptian hieroglyphs to be deciphered for the first time. URL: https://metacpan.org/dist/RosettaCode/view/bin/rosettacode Title: metacpan.org Description: Raku on Rosetta Code. Rosetta Code is a community site that presents solutions to programming tasks in many different languages. It is an excellent place to see how various languages approach the same task, as well as to get a feel for the style and fluent use of each language across a variety of domains. URL: https://simple.wikipedia.org/wiki/Rosetta_Code Title: simple.wikipedia.org Description: To install RosettaCode, copy and paste the appropriate command in to your terminal. cpanm. cpanm RosettaCode. CPAN shell. perl -MCPAN -e shell install RosettaCode Page 2: ======= URL: https://improbotics.org/rosetta-code/ Title: improbotics.org Description: Enjoy amazing savings with our 50% off URL: https://en.wikipedia.org/wiki/Rosetta_Code Title: en.wikipedia.org Description: Rosetta Code was scheduled to perform at Brighton Fringe 2020 at The Warren: Theatre Box and at Camden Fringe 2020 at The Cockpit Theatre and will return live in 2021. Our show was the subject of a scientific research paper “Rosetta Code: Improv in Any Language“, published at the International Conference on Computational Creativity 2020. URL: https://www.freecodecamp.org/news/rosetta-code-unlocking-the-mysteries-of-the-programming-languages-that-power-our-world-300b787d8401/ Title: www.freecodecamp.org Description: Rosetta Code is a wiki-based programming website with implementations of common algorithms and solutions to various programming problems in many different programming languages. It is named for the Rosetta Stone , which has the same text inscribed on it in three languages, and thus allowed Egyptian hieroglyphs to be deciphered for the first time. URL: https://raku.org/community/rosettacode/ Title: raku.org Description: Rosetta Code — unlocking the mysteries of the programming languages that power our world. Peter Gleeson. The original Rosetta Stone, via History.com. It’s no secret that the tech world is dominated by a relatively small pool of programming languages. While exact figures are difficult to obtain (and no doubt vary over time), you could ... URL: https://rosettacode.org/wiki/SHA-256 Title: rosettacode.org Description: Raku on Rosetta Code. Rosetta Code is a community site that presents solutions to programming tasks in many different languages. It is an excellent place to see how various languages approach the same task, as well as to get a feel for the style and fluent use of each language across a variety of domains. URL: https://twitter.com/rosettacode Title: twitter.com Description: SHA-256 is the recommended stronger alternative to SHA-1.See FIPS PUB 180-4 for implementation details.. Either by using a dedicated library or implementing the ... URL: https://deals.usnews.com/coupons/rosetta-stone Title: deals.usnews.com Description: We would like to show you a description here but the site won’t allow us. Displayed 2 pages with a total of 12 entries.
- Programming Tasks
- Programming environment operations
- Networking and Web Interaction
- AArch64 Assembly
- ARM Assembly
- AutoHotkey
- C sharp
- D
- Gambas
- Go
- GUISS
- Haskell
- Unicon
- Icon Programming Library
- Java
- Java examples needing attention
- Examples needing attention
- Julia
- Kotlin
- Kotlin examples needing attention
- Mathematica
- Wolfram Language
- Nim
- Oz
- OzHttpClient
- Perl
- Phix
- Phix/libcurl
- PicoLisp
- Python
- R
- RCurl
- XML
- Racket
- Raku
- Gumbo
- LWP-Simple
- Exemel
- Ruby
- Ruby examples needing attention
- RubyGems
- Hpricot
- Run BASIC
- Tcl
- Tcllib
- TXR
- Wren
- Libcurl
- Wren-pattern
- Batch File/Omit
- Brlcad/Omit
- EasyLang/Omit
- Lilypond/Omit
- Locomotive Basic/Omit
- Lotus 123 Macro Scripting/Omit
- M4/Omit
- Maxima/Omit
- ML/I/Omit
- Openscad/Omit
- PARI/GP/Omit
- PostScript/Omit
- Retro/Omit
- TI-83 BASIC/Omit
- TI-89 BASIC/Omit
- TPP/Omit
- ZX Spectrum Basic/Omit