From 595eda2215d61dae5965a858fa92d36aa26bc02c Mon Sep 17 00:00:00 2001
From: sergiotarxz <sergiotarxz@posteo.net>
Date: Sun, 17 Oct 2021 19:41:52 +0200
Subject: [PATCH] Making some fixes and searching for divs.

Next step is pcre2 integration.
---
 mangafox.c | 94 ++++++++++++++++++++++++++++++------------------------
 1 file changed, 53 insertions(+), 41 deletions(-)

diff --git a/mangafox.c b/mangafox.c
index 91d42d8..3747c24 100644
--- a/mangafox.c
+++ b/mangafox.c
@@ -15,40 +15,16 @@ xmlXPathObjectPtr
 get_nodes_xpath_expression (
 		const xmlDocPtr document,
 		char *xpath);
+char *
+get_request (const char *url, gsize *size_response_text);
 void
-retrieve_mangafox_title() {
-	SoupSession
-		*soup_session;
-	SoupMessage *msg;
-	GValue response = G_VALUE_INIT;
-	guint status;
-	gsize size_response_text;
+retrieve_mangafox_title () {
 	xmlDocPtr html_response;
-	
-	g_value_init (&response, G_TYPE_BYTES);
-
-	soup_session = 
-		soup_session_new();
-	msg = 
-		soup_message_new(
-			"GET",
-			mangafox_url
-			);
-	status = 
-		soup_session_send_message (soup_session, msg);
-	g_object_get_property(
-			G_OBJECT (msg),
-			"response-body-data",
-			&response);
-	const char *response_text = 
-		g_bytes_get_data (
-				(GBytes *)
-				g_value_peek_pointer 
-				(&response),
-				&size_response_text
-				);
+	gsize *size_response_text = malloc (sizeof (gsize));
+	char *response_text = get_request (mangafox_url,
+			size_response_text);
 	html_response = htmlReadMemory (response_text,
-			size_response_text,
+			*size_response_text,
 			NULL,
 			NULL,
 			HTML_PARSE_RECOVER | HTML_PARSE_NODEFDTD 
@@ -56,39 +32,75 @@ retrieve_mangafox_title() {
 			);
 	size_t manga_size;
 	parse_main_mangafox_page (html_response, &manga_size);
+	free (response_text);
+}
+
+char *
+get_request (const char *url, gsize *size_response_text) {
+	SoupSession *soup_session;
+	SoupMessage *msg;
+	GValue response = G_VALUE_INIT;
+	guint status;
+
+	*size_response_text = 0;
+	
+	g_value_init (&response, G_TYPE_BYTES);
+
+	soup_session = soup_session_new ();
+	msg = soup_message_new ("GET", url);
+	status = soup_session_send_message (soup_session, msg);
+	g_object_get_property(
+			G_OBJECT (msg),
+			"response-body-data",
+			&response);
+
 	printf("%u\n", status);
+	const char *html_response = g_bytes_get_data ((GBytes *)
+			g_value_peek_pointer (&response),
+			size_response_text);
+
+	char *return_value = g_strndup (html_response, *size_response_text);
+
+	g_value_unset (&response);
+	g_object_unref (soup_session);
+	g_object_unref (msg);
+
+	return return_value;
 }
 
 
 struct Manga *
-parse_main_mangafox_page (
-		const xmlDocPtr html_document,
+parse_main_mangafox_page (const xmlDocPtr html_document,
 		const size_t *size) {
 	xmlIndentTreeOutput = 1;
-//	xmlDocDump (stderr, html_document);
 	xmlXPathObjectPtr xpath_result = get_nodes_xpath_expression (html_document,
-			"//a");
+			"//div[@class]");
 	if (!xpath_result) {
 		fprintf(stderr, "Empty xpath result\n");
 		return NULL;
 	}
 	xmlNodeSetPtr node_set = xpath_result->nodesetval;
-	printf("%d\n", node_set->nodeNr);
+	if (!node_set) {
+		fprintf(stderr, "No match\n");
+		return NULL;
+	}
 	for (int i = 0; i < node_set->nodeNr; i++) {
 		xmlNodePtr node = node_set->nodeTab[i];
-			for (xmlAttr *attrs = node->properties; attrs->next; attrs=attrs->next) {
-				if (!xmlStrcmp(attrs->name, (const xmlChar *)"href")) {
+		for (xmlAttr *attrs = node->properties; attrs; attrs=attrs->next) {
+			if (!xmlStrcmp(attrs->name, (const xmlChar *)"class")) {
+				if (attrs->children
+						&& attrs->children->content) {
 					printf("%s\n", (const char *)attrs->children->content);
+					break;
 				}
 			}
+		}
 		
 	}
 }
 
 xmlXPathObjectPtr
-get_nodes_xpath_expression (
-		const xmlDocPtr document,
-		char *xpath) {
+get_nodes_xpath_expression (const xmlDocPtr document, char *xpath) {
 	xmlXPathContextPtr context;
 	xmlXPathObjectPtr result;