由于初次尝试用c++写个简单的爬虫系统,不免用到正则,正则有多行匹配等特性,以前一直用php开发pcre_match加上正则修正符m多行,i忽略大小写 s.代表任意字符,不要太方便,所以在使用cpp的时候遇到了困惑。
实际上pcre匹配数据是多次去匹配的,
我匹配到一个数据,然后对源数据进行偏移,然后匹配下一个,这样子,知道最后一个
#include "pcre.h"
#include <stdio.h>
#include <string.h>
#include <regex.h>
#include <iostream>
#include <fstream>
#define OVECCOUNT 256
using namespace std;
int tpcre();
int tmysql();
int main(int argc, char ** argv)
{
tpcre();
return 0;
}
int tmysql(){
return 0;
}
int tpcre(){
char pText[1024] = "\"21,537511285427,50005701,,shopsearch,1,shopcon,2950270077,,\" href=\"//detail.tmall.com/item.htm?id=537511285427&rn=54eb0efc1a7a49f5b93ed2051aa4fe9c&abbucket=0\" target=\"_blank\" data-gold-url=\"/inshopse\" href=\"//detail.tmall.com/item.htm?id=537511285421&rn=54eb0efc1a7a49f5b93ed2051aa4fe9c&abbucket=0\"href=\"//detail.tmall.com/item.htm?id=537511285422&rn=54eb0efc1a7a49f5b93ed2051aa4fe9c&abbucket=0\"href=\"//detail.tmall.com/item.htm?id=537511285423&rn=54eb0efc1a7a49f5b93ed2051aa4fe9c&abbucket=0\"href=\"//detail.tmall.com/item.htm?id=537511285424&rn=54eb0efc1a7a49f5b93ed2051aa4fe9c&abbucket=0\" ";
/*
string filename = "/Users/kang/Library/Developer/Xcode/DerivedData/TmailSpider-batmyukengwdwjcsejwqossttbhu/Build/Products/Debug/2.txt";
fstream fp;
fp.open(filename);
char buf[256];
string html;
while (!fp.eof()) {
fp.read(buf, 200);
html.append(buf);
}
fp.close();
char *pText = (char*)html.c_str();
*/
std::cout << pText;
//const char * pPattern = "(\\d+)\\w+";
//const char *pPattern="href=\\\"(//detail.tmall.com/item.htm[^\\]+)\\";
//const char * pPattern = "(//detail.tmall.com/item.htm[^\\\\]+)";
const char * pPattern = "(//detail.tmall.com/item.htm\\?id=\\d+)";
const char * pErrMsg = NULL;
pcre * pPcre = NULL;
int nOffset = -1;
//PCRE_MULTILINE|PCRE_UTF8|PCRE_NO_AUTO_CAPTURE
//pPcre = pcre_compile(pPattern, PCRE_DOTALL|PCRE_CASELESS|PCRE_MULTILINE, &pErrMsg, &nOffset, NULL);
pPcre = pcre_compile(pPattern, PCRE_DOTALL|PCRE_CASELESS|PCRE_MULTILINE, &pErrMsg, &nOffset, NULL);
if(pPcre == NULL){
printf("pcre match error\n");
return 1;
}
int ovector[OVECCOUNT];
int matchFlag;
int exec_offset = 0;
int count = 0;
do{
matchFlag = (int)pcre_exec(pPcre, NULL, pText, (int)strlen(pText),exec_offset,0, ovector, OVECCOUNT);
if(matchFlag > 0){
++count;
printf("\nOK, has matched ...\n\n");
for(int i=0;i<matchFlag;i++){
char *strStart = pText+ovector[2*i];
int substrLen = ovector[2*i+1] - ovector[2*i];
char matched[1024];
memset(matched, 0, 1024);
strncpy(matched, strStart, substrLen);
printf( "match:$%d=%s\n",i,matched );
}
exec_offset = ovector[1];
}
}while (matchFlag > 0);
cout << "count="<<count<<endl;
pcre_free(pPcre);
return 0;
}