aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorDaniel Stenberg <daniel@haxx.se>2005-01-31 18:22:40 +0000
committerDaniel Stenberg <daniel@haxx.se>2005-01-31 18:22:40 +0000
commit883343ba63a376ce9326149b0476262993d73b08 (patch)
treefd484d8fbcd94b13611dbef9283eb2f92afc9005
parent16b5dc710fe2ddfdb80571bc6a20d652c9ce230b (diff)
HTML <head> parsing (with libxml) example code by Lars Nilsson.
Diffstat
-rw-r--r--docs/examples/Makefile.am2
-rw-r--r--docs/examples/htmltitle.cc297
2 files changed, 298 insertions, 1 deletions
diff --git a/docs/examples/Makefile.am b/docs/examples/Makefile.am
index 34ac520a7..f9b2939c4 100644
--- a/docs/examples/Makefile.am
+++ b/docs/examples/Makefile.am
@@ -10,7 +10,7 @@ EXTRA_DIST = README curlgtk.c sepheaders.c simple.c postit2.c \
post-callback.c multi-app.c multi-double.c multi-single.c \
multi-post.c fopen.c simplepost.c makefile.dj curlx.c https.c \
multi-debugcallback.c fileupload.c getinfo.c ftp3rdparty.c debug.c \
- anyauthput.c
+ anyauthput.c htmltitle.cc
all:
@echo "done"
diff --git a/docs/examples/htmltitle.cc b/docs/examples/htmltitle.cc
new file mode 100644
index 000000000..7d0cc4c3c
--- /dev/null
+++ b/docs/examples/htmltitle.cc
@@ -0,0 +1,297 @@
+/*****************************************************************************
+ * _ _ ____ _
+ * Project ___| | | | _ \| |
+ * / __| | | | |_) | |
+ * | (__| |_| | _ <| |___
+ * \___|\___/|_| \_\_____|
+ *
+ * $Id$
+ */
+
+// Get a web page, parse it with libxml.
+//
+// Written by Lars Nilsson
+//
+// GNU C++ compile command line suggestion (edit paths accordingly):
+//
+// g++ -Wall -I/opt/curl/include -I/opt/libxml/include/libxml2 htmltitle.cc \
+// -o htmltitle -L/opt/curl/lib -L/opt/libxml/lib -lcurl -lxml2
+
+#include <stdio.h>
+#include <string.h>
+#include <stdlib.h>
+#include <string>
+#include <curl/curl.h>
+#include <libxml/HTMLparser.h>
+
+//
+// Case-insensitive string comparison
+//
+
+#ifdef _MSC_VER
+#define COMPARE(a, b) (!stricmp((a), (b)))
+#else
+#define COMPARE(a, b) (!strcasecmp((a), (b)))
+#endif
+
+//
+// libxml callback context structure
+//
+
+struct Context
+{
+ Context(): addTitle(false) { }
+
+ bool addTitle;
+ std::string title;
+};
+
+//
+// libcurl variables for error strings and returned data
+
+static char errorBuffer[CURL_ERROR_SIZE];
+static std::string buffer;
+
+//
+// libcurl write callback function
+//
+
+static int writer(char *data, size_t size, size_t nmemb,
+ std::string *writerData)
+{
+ if (writerData == NULL)
+ return 0;
+
+ writerData->append(data, size*nmemb);
+
+ return size * nmemb;
+}
+
+//
+// libcurl connection initialization
+//
+
+static bool init(CURL *&conn, char *url)
+{
+ CURLcode code;
+
+ conn = curl_easy_init();
+
+ if (conn == NULL)
+ {
+ fprintf(stderr, "Failed to create CURL connection\n");
+
+ exit(EXIT_FAILURE);
+ }
+
+ code = curl_easy_setopt(conn, CURLOPT_ERRORBUFFER, errorBuffer);
+ if (code != CURLE_OK)
+ {
+ fprintf(stderr, "Failed to set error buffer [%d]\n", code);
+
+ return false;
+ }
+
+ code = curl_easy_setopt(conn, CURLOPT_URL, url);
+ if (code != CURLE_OK)
+ {
+ fprintf(stderr, "Failed to set URL [%s]\n", errorBuffer);
+
+ return false;
+ }
+
+ code = curl_easy_setopt(conn, CURLOPT_FOLLOWLOCATION, 1);
+ if (code != CURLE_OK)
+ {
+ fprintf(stderr, "Failed to set redirect option [%s]\n", errorBuffer);
+
+ return false;
+ }
+
+ code = curl_easy_setopt(conn, CURLOPT_WRITEFUNCTION, writer);
+ if (code != CURLE_OK)
+ {
+ fprintf(stderr, "Failed to set writer [%s]\n", errorBuffer);
+
+ return false;
+ }
+
+ code = curl_easy_setopt(conn, CURLOPT_WRITEDATA, &buffer);
+ if (code != CURLE_OK)
+ {
+ fprintf(stderr, "Failed to set write data [%s]\n", errorBuffer);
+
+ return false;
+ }
+
+ return true;
+}
+
+//
+// libxml start element callback function
+//
+
+static void startElement(void *voidContext,
+ const xmlChar *name,
+ const xmlChar **attributes)
+{
+ Context *context = (Context *)voidContext;
+
+ if (COMPARE((char *)name, "TITLE"))
+ {
+ context->title = "";
+ context->addTitle = true;
+ }
+}
+
+//
+// libxml end element callback function
+//
+
+static void endElement(void *voidContext,
+ const xmlChar *name)
+{
+ Context *context = (Context *)voidContext;
+
+ if (COMPARE((char *)name, "TITLE"))
+ context->addTitle = false;
+}
+
+//
+// Text handling helper function
+//
+
+static void handleCharacters(Context *context,
+ const xmlChar *chars,
+ int length)
+{
+ if (context->addTitle)
+ context->title.append((char *)chars, length);
+}
+
+//
+// libxml PCDATA callback function
+//
+
+static void characters(void *voidContext,
+ const xmlChar *chars,
+ int length)
+{
+ Context *context = (Context *)voidContext;
+
+ handleCharacters(context, chars, length);
+}
+
+//
+// libxml CDATA callback function
+//
+
+static void cdata(void *voidContext,
+ const xmlChar *chars,
+ int length)
+{
+ Context *context = (Context *)voidContext;
+
+ handleCharacters(context, chars, length);
+}
+
+//
+// libxml SAX callback structure
+//
+
+static htmlSAXHandler saxHandler =
+{
+ NULL,
+ NULL,
+ NULL,
+ NULL,
+ NULL,
+ NULL,
+ NULL,
+ NULL,
+ NULL,
+ NULL,
+ NULL,
+ NULL,
+ NULL,
+ NULL,
+ startElement,
+ endElement,
+ NULL,
+ characters,
+ NULL,
+ NULL,
+ NULL,
+ NULL,
+ NULL,
+ NULL,
+ NULL,
+ cdata,
+ NULL
+};
+
+//
+// Parse given (assumed to be) HTML text and return the title
+//
+
+static void parseHtml(const std::string &html,
+ std::string &title)
+{
+ htmlParserCtxtPtr ctxt;
+ Context context;
+
+ ctxt = htmlCreatePushParserCtxt(&saxHandler, &context, "", 0, "",
+ XML_CHAR_ENCODING_NONE);
+
+ htmlParseChunk(ctxt, html.c_str(), html.size(), 0);
+ htmlParseChunk(ctxt, "", 0, 1);
+
+ htmlFreeParserCtxt(ctxt);
+
+ title = context.title;
+}
+
+int main(int argc, char *argv[])
+{
+ CURL *conn = NULL;
+ CURLcode code;
+ std::string title;
+
+ // Ensure one argument is given
+
+ if (argc != 2)
+ {
+ fprintf(stderr, "Usage: %s <url>\n", argv[0]);
+
+ exit(EXIT_FAILURE);
+ }
+
+ // Initialize CURL connection
+
+ if (!init(conn, argv[1]))
+ {
+ fprintf(stderr, "Connection initializion failed\n");
+
+ exit(EXIT_FAILURE);
+ }
+
+ // Retrieve content for the URL
+
+ code = curl_easy_perform(conn);
+ if (code != CURLE_OK)
+ {
+ fprintf(stderr, "Failed to get '%s' [%s]\n", argv[1], errorBuffer);
+
+ exit(EXIT_FAILURE);
+ }
+
+ // Parse the (assumed) HTML code
+
+ parseHtml(buffer, title);
+
+ // Display the extracted title
+
+ printf("Title: %s\n", title.c_str());
+
+ return EXIT_SUCCESS;
+}
generated by cgit v1.2.3 (git 2.25.1) at 2024-06-30 12:21:54 +0000