mdl_extract.h

Go to the documentation of this file.

#pragma once
 
#include <stddef.h>
#include <stdint.h>
 
#include "ra8_err.h"

typedef enum : uint16_t {
  k_mdl_max_urls = 2048, 
  k_mdl_url_max  = 512,  
} mdl_extract_limits_t;

typedef struct {
  char   urls[k_mdl_max_urls][k_mdl_url_max]; 
  size_t count;                               
} mdl_url_list_t;

typedef enum : uint16_t {
  k_mdl_max_hits      = 128, 
  k_mdl_hit_title_max = 256, 
} mdl_hit_limits_t;

typedef struct {
  char title[k_mdl_hit_title_max]; 
  char url[k_mdl_url_max];         
} mdl_hit_t;

typedef struct {
  mdl_hit_t hits[k_mdl_max_hits]; 
  size_t    count;                
  size_t    anchors_seen;         
} mdl_hit_list_t;

bool mdl_extract_resolve_url(const char* base, const char* raw, char* out, size_t out_cap);

ra8_err_t mdl_extract_selector(const char* html,
                               size_t      html_len,
                               const char* selector,
                               char*       out,
                               size_t      out_cap);

ra8_err_t mdl_extract_images(const char*     html,
                             size_t          html_len,
                             const char*     base_url,
                             const char*     prefer_attr,
                             const char*     url_contains,
                             mdl_url_list_t* out);

ra8_err_t mdl_extract_anchors(const char*     html,
                              size_t          html_len,
                              const char*     base_url,
                              const char*     href_contains,
                              mdl_url_list_t* out);

ra8_err_t mdl_extract_hits(const char*     html,
                           size_t          html_len,
                           const char*     base_url,
                           const char*     url_contains,
                           mdl_hit_list_t* out);