fsHTMLParser Class Reference

#include <fsHTMLParser.h>

List of all members.

Public Member Functions

void ReplaceFrameUrl (int iIndex, LPCSTR pszNewUrl)
LPCSTR GetFrameUrl (int iIndex)
int GetFrameUrlCount ()
void RemoveBaseTag ()
LPCSTR Get_BaseURL ()
void ParseHTML (LPSTR pszHTML)
void SetKillDupes (BOOL bKill)
void ReplaceLinkUrl (int iIndex, LPCSTR pszNewUrl)
fsLinkRelType GetLinkUrlRelType (int iIndex)
LPCSTR GetLinkUrl (int iIndex)
int GetLinkUrlCount ()
void ReplaceImage (int iIndex, LPCSTR pszNewImg)
void ReplaceUrl (int iIndex, LPCSTR pszNewUrl)
int GetImageLinkTo (int iImage)
LPCSTR GetImage (int iIndex)
int GetImageCount ()
int GetUrlCount ()
LPCSTR GetUrl (int iIndex)
UINT GetHTMLLength ()
 fsHTMLParser ()
virtual ~fsHTMLParser ()
void ReplaceFrameUrl (int iIndex, LPCSTR pszNewUrl)
LPCSTR GetFrameUrl (int iIndex)
int GetFrameUrlCount ()
void RemoveBaseTag ()
LPCSTR Get_BaseURL ()
void ParseHTML (LPSTR pszHTML)
void SetKillDupes (BOOL bKill)
void ReplaceLinkUrl (int iIndex, LPCSTR pszNewUrl)
fsLinkRelType GetLinkUrlRelType (int iIndex)
LPCSTR GetLinkUrl (int iIndex)
int GetLinkUrlCount ()
void ReplaceImage (int iIndex, LPCSTR pszNewImg)
void ReplaceUrl (int iIndex, LPCSTR pszNewUrl)
int GetImageLinkTo (int iImage)
LPCSTR GetImage (int iIndex)
int GetImageCount ()
int GetUrlCount ()
LPCSTR GetUrl (int iIndex)
UINT GetHTMLLength ()
 fsHTMLParser ()
virtual ~fsHTMLParser ()

Protected Member Functions

LPCSTR ParseTag_Frame_Src (LPCSTR pszTag, LPCSTR pszAddUrlEnds=NULL)
LPCSTR ParseTag_Base_Href (LPCSTR pszTag, LPCSTR pszAddUrlEnds=NULL)
LPCSTR ParseTag (LPCSTR pszTag)
LPCSTR ParseTag_Meta_Content (LPCSTR pszTag, fsMetaHttpEquivType mhet)
LPCSTR ParseTag_Meta_HttpEquiv (LPCSTR pszTag, fsMetaHttpEquivType *mhet)
LPCSTR ParseTag_Link_Href (LPCSTR pszTag)
LPCSTR ParseTag_Link_Rel (LPCSTR pszTag, fsLinkRelType *lrt)
LPCSTR ParseTag_Img_Src (LPCSTR pszTag)
LPCSTR ParseTag_A_Href (LPCSTR pszTag, LPCSTR pszAddUrlEnds=NULL)
LPCSTR ParseTag_Unknown (LPCSTR pszTag)
void CorrectRegions (int nStart, int nHole)
int ReplaceString (LPCSTR pszNewVal, fsTextRegion &rgn)
void ParseHTML ()
LPCSTR Parse_HTMLGiving (LPCSTR pszGiving, LPSTR *ppszValue, LPCSTR pszAddEnds=NULL)
LPCSTR ParseTag_Frame_Src (LPCSTR pszTag, LPCSTR pszAddUrlEnds=NULL)
LPCSTR ParseTag_Base_Href (LPCSTR pszTag, LPCSTR pszAddUrlEnds=NULL)
LPCSTR ParseTag (LPCSTR pszTag)
LPCSTR ParseTag_Meta_Content (LPCSTR pszTag, fsMetaHttpEquivType mhet)
LPCSTR ParseTag_Meta_HttpEquiv (LPCSTR pszTag, fsMetaHttpEquivType *mhet)
LPCSTR ParseTag_Link_Href (LPCSTR pszTag)
LPCSTR ParseTag_Link_Rel (LPCSTR pszTag, fsLinkRelType *lrt)
LPCSTR ParseTag_Img_Src (LPCSTR pszTag)
LPCSTR ParseTag_A_Href (LPCSTR pszTag, LPCSTR pszAddUrlEnds=NULL)
LPCSTR ParseTag_Unknown (LPCSTR pszTag)
void CorrectRegions (int nStart, int nHole)
int ReplaceString (LPCSTR pszNewVal, fsTextRegion &rgn)
void ParseHTML ()
LPCSTR Parse_HTMLGiving (LPCSTR pszGiving, LPSTR *ppszValue, LPCSTR pszAddEnds=NULL)

Static Protected Member Functions

static LPCSTR ParseTag_Frame (LPCSTR pszTag, fsHTMLParser *pThis)
static LPCSTR ParseTag_Base (LPCSTR pszTag, fsHTMLParser *pThis)
static LPCSTR ParseTag_Meta (LPCSTR pszTag, fsHTMLParser *pThis)
static LPCSTR ParseTag_Link (LPCSTR pszTag, fsHTMLParser *parser)
static LPCSTR ParseTag_Img (LPCSTR pszTag, fsHTMLParser *pThis)
static LPCSTR ParseTag_A (LPCSTR pszTag, fsHTMLParser *pThis)
static LPCSTR ParseTag_Frame (LPCSTR pszTag, fsHTMLParser *pThis)
static LPCSTR ParseTag_Base (LPCSTR pszTag, fsHTMLParser *pThis)
static LPCSTR ParseTag_Meta (LPCSTR pszTag, fsHTMLParser *pThis)
static LPCSTR ParseTag_Link (LPCSTR pszTag, fsHTMLParser *parser)
static LPCSTR ParseTag_Img (LPCSTR pszTag, fsHTMLParser *pThis)
static LPCSTR ParseTag_A (LPCSTR pszTag, fsHTMLParser *pThis)

Protected Attributes

LPSTR m_pszHTML
fs::list< fsStringm_vUrls
fs::list< fsStringm_vImgs
fs::list< fsStringm_vLinkUrls
fs::list< fsStringm_vFrameUrls
fs::list< fsTextRegionm_vUrlsRgns
fs::list< fsTextRegionm_vImgsRgns
fs::list< fsTextRegionm_vLinkUrlsRgns
fs::list< fsTextRegionm_vFrameRgns
fs::list< fsLinkRelTypem_vLRTs
fs::list< int > m_vImgsLinksTo
int m_htmlLen
BOOL m_bKillDupes
fsString m_strBaseURL
fsTextRegion m_BaseURLPosition

Private Attributes

int m_iTagAOpened

Classes

struct  fsTextRegion


Detailed Description

Definition at line 28 of file fsHTMLParser.h.


Constructor & Destructor Documentation

fsHTMLParser::fsHTMLParser (  ) 

Definition at line 13 of file fsHTMLParser.cpp.

References m_bKillDupes, and TRUE.

fsHTMLParser::~fsHTMLParser (  )  [virtual]

Definition at line 18 of file fsHTMLParser.cpp.

fsHTMLParser::fsHTMLParser (  ) 

virtual fsHTMLParser::~fsHTMLParser (  )  [virtual]


Member Function Documentation

void fsHTMLParser::ReplaceFrameUrl ( int  iIndex,
LPCSTR  pszNewUrl 
)

LPCSTR fsHTMLParser::GetFrameUrl ( int  iIndex  ) 

Definition at line 815 of file fsHTMLParser.cpp.

References m_vFrameUrls.

Referenced by fsWebPageDownloader::ParseHTMLFrameUrls().

int fsHTMLParser::GetFrameUrlCount (  ) 

Definition at line 810 of file fsHTMLParser.cpp.

References m_vFrameUrls.

Referenced by fsWebPageDownloader::ParseHTMLFrameUrls().

void fsHTMLParser::RemoveBaseTag (  ) 

LPCSTR fsHTMLParser::Get_BaseURL (  ) 

Definition at line 741 of file fsHTMLParser.cpp.

References m_strBaseURL.

Referenced by fsHttpFiles::BuildFileList(), and fsWebPageDownloader::ParseHTML().

void fsHTMLParser::ParseHTML ( LPSTR  pszHTML  ) 

void fsHTMLParser::SetKillDupes ( BOOL  bKill  ) 

void fsHTMLParser::ReplaceLinkUrl ( int  iIndex,
LPCSTR  pszNewUrl 
)

fsLinkRelType fsHTMLParser::GetLinkUrlRelType ( int  iIndex  ) 

Definition at line 557 of file fsHTMLParser.cpp.

References m_vLRTs.

Referenced by fsWebPageDownloader::ParseHTMLLinkUrls().

LPCSTR fsHTMLParser::GetLinkUrl ( int  iIndex  ) 

Definition at line 552 of file fsHTMLParser.cpp.

References m_vLinkUrls.

Referenced by fsWebPageDownloader::ParseHTMLLinkUrls().

int fsHTMLParser::GetLinkUrlCount (  ) 

Definition at line 547 of file fsHTMLParser.cpp.

References m_vLinkUrls.

Referenced by fsWebPageDownloader::ParseHTMLLinkUrls().

void fsHTMLParser::ReplaceImage ( int  iIndex,
LPCSTR  pszNewImg 
)

void fsHTMLParser::ReplaceUrl ( int  iIndex,
LPCSTR  pszNewUrl 
)

int fsHTMLParser::GetImageLinkTo ( int  iImage  ) 

Definition at line 320 of file fsHTMLParser.cpp.

References m_vImgsLinksTo.

Referenced by fsWebPageDownloader::ParseHTMLImages().

LPCSTR fsHTMLParser::GetImage ( int  iIndex  ) 

Definition at line 315 of file fsHTMLParser.cpp.

References m_vImgs.

Referenced by fsWebPageDownloader::ParseHTMLImages().

int fsHTMLParser::GetImageCount (  ) 

Definition at line 310 of file fsHTMLParser.cpp.

References m_vImgs.

Referenced by fsWebPageDownloader::ParseHTMLImages().

int fsHTMLParser::GetUrlCount (  ) 

LPCSTR fsHTMLParser::GetUrl ( int  iIndex  ) 

UINT fsHTMLParser::GetHTMLLength (  ) 

Definition at line 388 of file fsHTMLParser.cpp.

References m_htmlLen.

Referenced by fsWebPageDownloader::CorrectUnpUrls(), and fsWebPageDownloader::ParseHTML().

LPCSTR fsHTMLParser::ParseTag_Frame_Src ( LPCSTR  pszTag,
LPCSTR  pszAddUrlEnds = NULL 
) [protected]

LPCSTR fsHTMLParser::ParseTag_Frame ( LPCSTR  pszTag,
fsHTMLParser pThis 
) [static, protected]

Definition at line 755 of file fsHTMLParser.cpp.

References fsStrIsDivider(), NULL, and ParseTag_Frame_Src().

Referenced by ParseTag().

LPCSTR fsHTMLParser::ParseTag_Base_Href ( LPCSTR  pszTag,
LPCSTR  pszAddUrlEnds = NULL 
) [protected]

Definition at line 724 of file fsHTMLParser.cpp.

References LPSTR, m_strBaseURL, and Parse_HTMLGiving().

Referenced by ParseTag_Base().

LPCSTR fsHTMLParser::ParseTag_Base ( LPCSTR  pszTag,
fsHTMLParser pThis 
) [static, protected]

LPCSTR fsHTMLParser::ParseTag ( LPCSTR  pszTag  )  [protected]

LPCSTR fsHTMLParser::ParseTag_Meta_Content ( LPCSTR  pszTag,
fsMetaHttpEquivType  mhet 
) [protected]

LPCSTR fsHTMLParser::ParseTag_Meta_HttpEquiv ( LPCSTR  pszTag,
fsMetaHttpEquivType mhet 
) [protected]

Definition at line 612 of file fsHTMLParser.cpp.

References LPSTR, MHET_REFRESH, MHET_UNKNOWN, and Parse_HTMLGiving().

Referenced by ParseTag_Meta().

LPCSTR fsHTMLParser::ParseTag_Meta ( LPCSTR  pszTag,
fsHTMLParser pThis 
) [static, protected]

LPCSTR fsHTMLParser::ParseTag_Link_Href ( LPCSTR  pszTag  )  [protected]

LPCSTR fsHTMLParser::ParseTag_Link_Rel ( LPCSTR  pszTag,
fsLinkRelType lrt 
) [protected]

Definition at line 483 of file fsHTMLParser.cpp.

References LPSTR, LRT_STYLESHEET, LRT_UNKNOWN, and Parse_HTMLGiving().

Referenced by ParseTag_Link().

LPCSTR fsHTMLParser::ParseTag_Link ( LPCSTR  pszTag,
fsHTMLParser parser 
) [static, protected]

Definition at line 440 of file fsHTMLParser.cpp.

References BOOL, FALSE, fsStrIsDivider(), LRT_UNKNOWN, m_vLRTs, NULL, ParseTag_Link_Href(), ParseTag_Link_Rel(), and TRUE.

Referenced by ParseTag().

LPCSTR fsHTMLParser::ParseTag_Img_Src ( LPCSTR  pszTag  )  [protected]

LPCSTR fsHTMLParser::ParseTag_A_Href ( LPCSTR  pszTag,
LPCSTR  pszAddUrlEnds = NULL 
) [protected]

LPCSTR fsHTMLParser::ParseTag_Unknown ( LPCSTR  pszTag  )  [protected]

Definition at line 170 of file fsHTMLParser.cpp.

Referenced by ParseTag().

LPCSTR fsHTMLParser::ParseTag_Img ( LPCSTR  pszTag,
fsHTMLParser pThis 
) [static, protected]

Definition at line 98 of file fsHTMLParser.cpp.

References fsStrIsDivider(), NULL, and ParseTag_Img_Src().

Referenced by ParseTag().

LPCSTR fsHTMLParser::ParseTag_A ( LPCSTR  pszTag,
fsHTMLParser pThis 
) [static, protected]

Definition at line 65 of file fsHTMLParser.cpp.

References fsStrIsDivider(), NULL, and ParseTag_A_Href().

Referenced by ParseTag().

void fsHTMLParser::CorrectRegions ( int  nStart,
int  nHole 
) [protected]

int fsHTMLParser::ReplaceString ( LPCSTR  pszNewVal,
fsTextRegion rgn 
) [protected]

void fsHTMLParser::ParseHTML (  )  [protected]

LPCSTR fsHTMLParser::Parse_HTMLGiving ( LPCSTR  pszGiving,
LPSTR ppszValue,
LPCSTR  pszAddEnds = NULL 
) [protected]

void fsHTMLParser::ReplaceFrameUrl ( int  iIndex,
LPCSTR  pszNewUrl 
)

LPCSTR fsHTMLParser::GetFrameUrl ( int  iIndex  ) 

int fsHTMLParser::GetFrameUrlCount (  ) 

void fsHTMLParser::RemoveBaseTag (  ) 

LPCSTR fsHTMLParser::Get_BaseURL (  ) 

void fsHTMLParser::ParseHTML ( LPSTR  pszHTML  ) 

void fsHTMLParser::SetKillDupes ( BOOL  bKill  ) 

void fsHTMLParser::ReplaceLinkUrl ( int  iIndex,
LPCSTR  pszNewUrl 
)

fsLinkRelType fsHTMLParser::GetLinkUrlRelType ( int  iIndex  ) 

LPCSTR fsHTMLParser::GetLinkUrl ( int  iIndex  ) 

int fsHTMLParser::GetLinkUrlCount (  ) 

void fsHTMLParser::ReplaceImage ( int  iIndex,
LPCSTR  pszNewImg 
)

void fsHTMLParser::ReplaceUrl ( int  iIndex,
LPCSTR  pszNewUrl 
)

int fsHTMLParser::GetImageLinkTo ( int  iImage  ) 

LPCSTR fsHTMLParser::GetImage ( int  iIndex  ) 

int fsHTMLParser::GetImageCount (  ) 

int fsHTMLParser::GetUrlCount (  ) 

LPCSTR fsHTMLParser::GetUrl ( int  iIndex  ) 

UINT fsHTMLParser::GetHTMLLength (  ) 

LPCSTR fsHTMLParser::ParseTag_Frame_Src ( LPCSTR  pszTag,
LPCSTR  pszAddUrlEnds = NULL 
) [protected]

static LPCSTR fsHTMLParser::ParseTag_Frame ( LPCSTR  pszTag,
fsHTMLParser pThis 
) [static, protected]

LPCSTR fsHTMLParser::ParseTag_Base_Href ( LPCSTR  pszTag,
LPCSTR  pszAddUrlEnds = NULL 
) [protected]

static LPCSTR fsHTMLParser::ParseTag_Base ( LPCSTR  pszTag,
fsHTMLParser pThis 
) [static, protected]

LPCSTR fsHTMLParser::ParseTag ( LPCSTR  pszTag  )  [protected]

LPCSTR fsHTMLParser::ParseTag_Meta_Content ( LPCSTR  pszTag,
fsMetaHttpEquivType  mhet 
) [protected]

LPCSTR fsHTMLParser::ParseTag_Meta_HttpEquiv ( LPCSTR  pszTag,
fsMetaHttpEquivType mhet 
) [protected]

static LPCSTR fsHTMLParser::ParseTag_Meta ( LPCSTR  pszTag,
fsHTMLParser pThis 
) [static, protected]

LPCSTR fsHTMLParser::ParseTag_Link_Href ( LPCSTR  pszTag  )  [protected]

LPCSTR fsHTMLParser::ParseTag_Link_Rel ( LPCSTR  pszTag,
fsLinkRelType lrt 
) [protected]

static LPCSTR fsHTMLParser::ParseTag_Link ( LPCSTR  pszTag,
fsHTMLParser parser 
) [static, protected]

LPCSTR fsHTMLParser::ParseTag_Img_Src ( LPCSTR  pszTag  )  [protected]

LPCSTR fsHTMLParser::ParseTag_A_Href ( LPCSTR  pszTag,
LPCSTR  pszAddUrlEnds = NULL 
) [protected]

LPCSTR fsHTMLParser::ParseTag_Unknown ( LPCSTR  pszTag  )  [protected]

static LPCSTR fsHTMLParser::ParseTag_Img ( LPCSTR  pszTag,
fsHTMLParser pThis 
) [static, protected]

static LPCSTR fsHTMLParser::ParseTag_A ( LPCSTR  pszTag,
fsHTMLParser pThis 
) [static, protected]

void fsHTMLParser::CorrectRegions ( int  nStart,
int  nHole 
) [protected]

int fsHTMLParser::ReplaceString ( LPCSTR  pszNewVal,
fsTextRegion rgn 
) [protected]

void fsHTMLParser::ParseHTML (  )  [protected]

LPCSTR fsHTMLParser::Parse_HTMLGiving ( LPCSTR  pszGiving,
LPSTR ppszValue,
LPCSTR  pszAddEnds = NULL 
) [protected]


Member Data Documentation

fs::list< fsString > fsHTMLParser::m_vUrls [protected]

Definition at line 115 of file fsHTMLParser.h.

Referenced by GetUrl(), GetUrlCount(), ParseHTML(), and ParseTag_A_Href().

fs::list< fsString > fsHTMLParser::m_vImgs [protected]

Definition at line 115 of file fsHTMLParser.h.

Referenced by GetImage(), GetImageCount(), ParseHTML(), and ParseTag_Img_Src().

fs::list< fsString > fsHTMLParser::m_vLinkUrls [protected]

Definition at line 115 of file fsHTMLParser.h.

Referenced by GetLinkUrl(), GetLinkUrlCount(), ParseHTML(), and ParseTag_Link_Href().

fs::list< fsString > fsHTMLParser::m_vFrameUrls [protected]

Definition at line 115 of file fsHTMLParser.h.

Referenced by GetFrameUrl(), GetFrameUrlCount(), and ParseTag_Frame_Src().

fs::list< fsTextRegion > fsHTMLParser::m_vUrlsRgns [protected]

Definition at line 116 of file fsHTMLParser.h.

Referenced by CorrectRegions(), ParseHTML(), ParseTag_A_Href(), and ReplaceUrl().

fs::list< fsTextRegion > fsHTMLParser::m_vImgsRgns [protected]

Definition at line 116 of file fsHTMLParser.h.

Referenced by CorrectRegions(), ParseHTML(), ParseTag_Img_Src(), and ReplaceImage().

Definition at line 116 of file fsHTMLParser.h.

Referenced by CorrectRegions(), ParseHTML(), ParseTag_Link_Href(), and ReplaceLinkUrl().

fs::list< fsTextRegion > fsHTMLParser::m_vFrameRgns [protected]

Definition at line 116 of file fsHTMLParser.h.

Referenced by CorrectRegions(), ParseTag_Frame_Src(), and ReplaceFrameUrl().

fs::list< fsLinkRelType > fsHTMLParser::m_vLRTs [protected]

Definition at line 117 of file fsHTMLParser.h.

Referenced by GetLinkUrlRelType(), ParseHTML(), and ParseTag_Link().

fs::list< int > fsHTMLParser::m_vImgsLinksTo [protected]

Definition at line 118 of file fsHTMLParser.h.

Referenced by GetImageLinkTo(), ParseHTML(), and ParseTag_Img_Src().

int fsHTMLParser::m_htmlLen [protected]

Definition at line 119 of file fsHTMLParser.h.

Referenced by GetHTMLLength(), ParseHTML(), and ReplaceString().

BOOL fsHTMLParser::m_bKillDupes [protected]

Definition at line 120 of file fsHTMLParser.h.

Referenced by fsHTMLParser(), ParseTag_A_Href(), ParseTag_Link_Href(), and SetKillDupes().

Definition at line 121 of file fsHTMLParser.h.

Referenced by Get_BaseURL(), ParseHTML(), and ParseTag_Base_Href().

Definition at line 122 of file fsHTMLParser.h.

Referenced by ParseTag_Base(), and RemoveBaseTag().

Definition at line 124 of file fsHTMLParser.h.

Referenced by ParseHTML(), ParseTag(), ParseTag_A_Href(), and ParseTag_Img_Src().


The documentation for this class was generated from the following files:

Generated on Sun May 25 00:21:04 2008 by  doxygen 1.5.6