Data update
This commit is contained in:
parent
8e4e15fa56
commit
72eb4943cb
1853 changed files with 35514 additions and 9441 deletions
|
|
@ -1,66 +0,0 @@
|
|||
#include "windows.bi"
|
||||
#include "win/wininet.bi"
|
||||
|
||||
Const BUFFER_SIZE = 4096
|
||||
|
||||
Function GetWebPage(url As String) As String
|
||||
Dim As HINTERNET hInternet = InternetOpen("TimeGetter", INTERNET_OPEN_TYPE_DIRECT, NULL, NULL, 0)
|
||||
Dim As String resultado = ""
|
||||
|
||||
If hInternet Then
|
||||
Dim As HINTERNET hConnect = InternetOpenUrl(hInternet, url, NULL, 0, INTERNET_FLAG_RELOAD, 0)
|
||||
|
||||
If hConnect Then
|
||||
Dim As String buffer = Space(BUFFER_SIZE)
|
||||
Dim As DWORD bytesRead
|
||||
|
||||
Do
|
||||
If InternetReadFile(hConnect, Strptr(buffer), BUFFER_SIZE, @bytesRead) Then
|
||||
If bytesRead = 0 Then Exit Do
|
||||
resultado &= Left(buffer, bytesRead)
|
||||
End If
|
||||
Loop
|
||||
|
||||
InternetCloseHandle(hConnect)
|
||||
End If
|
||||
InternetCloseHandle(hInternet)
|
||||
End If
|
||||
|
||||
Return resultado
|
||||
End Function
|
||||
|
||||
Function ScrapeTime(pageAddress As String, timeZone As String) As String
|
||||
Dim As String page = GetWebPage(pageAddress)
|
||||
|
||||
If Len(page) = 0 Then Return "Cannot connect"
|
||||
|
||||
Dim As Integer startPos = 1
|
||||
Do
|
||||
Dim As Integer endPos = Instr(startPos, page, "<BR>")
|
||||
If endPos = 0 Then endPos = Len(page)
|
||||
|
||||
Dim As String linea = Mid(page, startPos, endPos - startPos)
|
||||
|
||||
If Instr(linea, timeZone) Then
|
||||
For i As Integer = 1 To Len(linea) - 7
|
||||
Dim As String char1 = Mid(linea, i, 1)
|
||||
Dim As String char2 = Mid(linea, i+4, 1)
|
||||
If char1 >= "0" And char1 <= "9" And Mid(linea, i+2, 1) = ":" And _
|
||||
char2 >= "0" And char2 <= "9" And Mid(linea, i+5, 1) = ":" Then
|
||||
Return Mid(linea, i, 8)
|
||||
End If
|
||||
Next
|
||||
End If
|
||||
|
||||
If endPos = Len(page) Then Exit Do
|
||||
startPos = endPos + 4
|
||||
Loop
|
||||
|
||||
Return "Time not found"
|
||||
End Function
|
||||
|
||||
' Main program
|
||||
Dim As String url = "https://rosettacode.org/wiki/Talk:Web_scraping"
|
||||
Print ScrapeTime(url, "UTC")
|
||||
|
||||
Sleep
|
||||
|
|
@ -1,48 +0,0 @@
|
|||
/* Web_scraping.wren */
|
||||
|
||||
import "./pattern" for Pattern
|
||||
|
||||
var CURLOPT_URL = 10002
|
||||
var CURLOPT_FOLLOWLOCATION = 52
|
||||
var CURLOPT_WRITEFUNCTION = 20011
|
||||
var CURLOPT_WRITEDATA = 10001
|
||||
|
||||
var BUFSIZE = 16384 * 4
|
||||
|
||||
foreign class Buffer {
|
||||
construct new(size) {}
|
||||
|
||||
// returns buffer contents as a string
|
||||
foreign value
|
||||
}
|
||||
|
||||
foreign class Curl {
|
||||
construct easyInit() {}
|
||||
|
||||
foreign easySetOpt(opt, param)
|
||||
|
||||
foreign easyPerform()
|
||||
|
||||
foreign easyCleanup()
|
||||
}
|
||||
|
||||
var buffer = Buffer.new(BUFSIZE)
|
||||
var curl = Curl.easyInit()
|
||||
curl.easySetOpt(CURLOPT_URL, "https://rosettacode.org/wiki/Talk:Web_scraping")
|
||||
curl.easySetOpt(CURLOPT_FOLLOWLOCATION, 1)
|
||||
curl.easySetOpt(CURLOPT_WRITEFUNCTION, 0) // write function to be supplied by C
|
||||
curl.easySetOpt(CURLOPT_WRITEDATA, buffer)
|
||||
|
||||
curl.easyPerform()
|
||||
curl.easyCleanup()
|
||||
|
||||
var html = buffer.value
|
||||
var ix = html.indexOf("(UTC)")
|
||||
ix = html.indexOf("(UTC)", ix + 1) // skip the site notice
|
||||
if (ix == -1) {
|
||||
System.print("UTC time not found.")
|
||||
return
|
||||
}
|
||||
var p = Pattern.new("/d/d:/d/d, #12/d +1/a =4/d")
|
||||
var m = p.find(html[(ix - 30).max(0)...ix])
|
||||
System.print(m.text)
|
||||
|
|
@ -1,173 +0,0 @@
|
|||
/* gcc Web_scraping.c -o Web_scraping -lcurl -lwren -lm */
|
||||
|
||||
#include <stdio.h>
|
||||
#include <stdlib.h>
|
||||
#include <string.h>
|
||||
#include <curl/curl.h>
|
||||
#include "wren.h"
|
||||
|
||||
/* C <=> Wren interface functions */
|
||||
|
||||
char *url, *read_file, *write_file;
|
||||
|
||||
size_t bufsize;
|
||||
size_t lr = 0;
|
||||
|
||||
size_t filterit(void *ptr, size_t size, size_t nmemb, void *stream) {
|
||||
if ((lr + size*nmemb) > bufsize) return bufsize;
|
||||
memcpy(stream+lr, ptr, size * nmemb);
|
||||
lr += size * nmemb;
|
||||
return size * nmemb;
|
||||
}
|
||||
|
||||
void C_bufferAllocate(WrenVM* vm) {
|
||||
bufsize = (int)wrenGetSlotDouble(vm, 1);
|
||||
wrenSetSlotNewForeign(vm, 0, 0, bufsize);
|
||||
}
|
||||
|
||||
void C_curlAllocate(WrenVM* vm) {
|
||||
CURL** pcurl = (CURL**)wrenSetSlotNewForeign(vm, 0, 0, sizeof(CURL*));
|
||||
*pcurl = curl_easy_init();
|
||||
}
|
||||
|
||||
void C_value(WrenVM* vm) {
|
||||
const char *s = (const char *)wrenGetSlotForeign(vm, 0);
|
||||
wrenSetSlotString(vm, 0, s);
|
||||
}
|
||||
|
||||
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) {
|
||||
char *buffer = (char *)wrenGetSlotForeign(vm, 2);
|
||||
curl_easy_setopt(curl, opt, buffer);
|
||||
} 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, &filterit);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
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;
|
||||
} 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 = "Web_scraping.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;
|
||||
}
|
||||
13
Task/Web-scraping/Wren/web-scraping.wren
Normal file
13
Task/Web-scraping/Wren/web-scraping.wren
Normal file
|
|
@ -0,0 +1,13 @@
|
|||
import "os" for Process
|
||||
import "./pattern" for Pattern
|
||||
|
||||
var page = "https://rosettacode.org/wiki/Talk:Web_scraping"
|
||||
var html = Process.read("curl -s %(page)")
|
||||
var ix = html.indexOf("(UTC)")
|
||||
if (ix == -1) {
|
||||
System.print("UTC time not found.")
|
||||
return
|
||||
}
|
||||
var p = Pattern.new("/d/d:/d/d, #12/d +1/a =4/d")
|
||||
var m = p.find(html[(ix - 30).max(0)...ix])
|
||||
System.print(m.text)
|
||||
Loading…
Add table
Add a link
Reference in a new issue