myhtml_collection_t * myhtml_get_nodes_by_name(myhtml_tree_t* tree, myhtml_collection_t *collection, const char* html, size_t length, mystatus_t *status) { const myhtml_tag_context_t *tag_ctx = myhtml_tag_get_by_name(tree->tags, html, length); if(tag_ctx == NULL) return NULL; return myhtml_get_nodes_by_tag_id(tree, collection, tag_ctx->id, status); }
int main(int argc, const char * argv[]) { const char* path; if (argc == 2) { path = argv[1]; } else { printf("Bad ARGV!\nUse: get_title_high_level <path_to_html_file>\n"); exit(EXIT_FAILURE); } struct res_html res = load_html_file(path); // basic init myhtml_t* myhtml = myhtml_create(); myhtml_init(myhtml, MyHTML_OPTIONS_DEFAULT, 1, 0); // init tree myhtml_tree_t* tree = myhtml_tree_create(); myhtml_tree_init(tree, myhtml); // parse html myhtml_parse(tree, MyHTML_ENCODING_UTF_8, res.html, res.size); // parse html myhtml_collection_t *collection = myhtml_get_nodes_by_tag_id(tree, NULL, MyHTML_TAG_TITLE, NULL); if(collection && collection->list && collection->length) { myhtml_tree_node_t *text_node = myhtml_node_child(collection->list[0]); if(text_node) { const char* text = myhtml_node_text(text_node, NULL); if(text) printf("Title: %s\n", text); } } // release resources myhtml_collection_destroy(collection); myhtml_tree_destroy(tree); myhtml_destroy(myhtml); free(res.html); return 0; }
int main(int argc, const char * argv[]) { const char* path; if (argc == 2) { path = argv[1]; } else { printf("Bad ARGV!\nUse: get_title_low_level <path_to_html_file>\n"); exit(EXIT_FAILURE); } struct res_html res = load_html_file(path); // basic init myhtml_t* myhtml = myhtml_create(); myhtml_init(myhtml, MyHTML_OPTIONS_DEFAULT, 1, 0); // init tree myhtml_tree_t* tree = myhtml_tree_create(); myhtml_tree_init(tree, myhtml); // parse html myhtml_parse(tree, MyENCODING_UTF_8, res.html, res.size); // get title from index myhtml_collection_t *titles_list = myhtml_get_nodes_by_tag_id(tree, NULL, MyHTML_TAG_TITLE, NULL); if(titles_list && titles_list->length != 0 && titles_list->list[0]->child) { mycore_string_raw_t str = {0}; myhtml_serialization_node(titles_list->list[0]->child, &str); printf("%s\n", str.data); mycore_string_raw_destroy(&str, false); } // release resources myhtml_collection_destroy(titles_list); myhtml_tree_destroy(tree); myhtml_destroy(myhtml); free(res.html); return 0; }
myhtml_collection_t * myhtml_get_nodes_by_name(myhtml_tree_t* tree, myhtml_collection_t *collection, const char* html, size_t length, myhtml_status_t *status) { mctree_index_t tag_ctx_idx = mctree_search_lowercase(tree->myhtml->tags->tree, html, length); return myhtml_get_nodes_by_tag_id(tree, collection, tag_ctx_idx, status); }