diff --git a/src/main/java/org/archive/format/text/charset/CharsetDetector.java b/src/main/java/org/archive/format/text/charset/CharsetDetector.java
index ae71b5fa..690f8b99 100644
--- a/src/main/java/org/archive/format/text/charset/CharsetDetector.java
+++ b/src/main/java/org/archive/format/text/charset/CharsetDetector.java
@@ -60,7 +60,8 @@ public abstract class CharsetDetector {
 	private final static String META_CONTENT_ATTR_PATTERN_STRING = "\\b" + 
 		META_CONTENT_ATTRIBUTE + "\\s*=\\s*(" + ANY_ATTR_VALUE + ")(?:\\s|>)?";
 	private final static String META_HTTP_EQUIV_ATTR_PATTERN_STRING = "\\b" + 
-		META_HTTP_EQUIV_ATTRIBUTE + "\\s*=\\s*(" + ANY_ATTR_VALUE + ")(?:\\s|>)?";
+		META_HTTP_EQUIV_ATTRIBUTE + "\\s*=\\s*(" + META_CONTENT_TYPE + "|" +
+		ANY_ATTR_VALUE + ")(?:\\s|>)?";
 
 	
 	
@@ -230,7 +231,6 @@ public static String findMetaContentType(String pageSample) {
 	protected String getCharsetFromBytes(byte buffer[], int len) 
 	throws IOException {
 		String charsetName = null;
-
 	    UniversalDetector detector = new UniversalDetector(null);
 		detector.handleData(buffer, 0, len);
 		detector.dataEnd();
diff --git a/src/main/java/org/archive/resource/html/HTMLResourceFactory.java b/src/main/java/org/archive/resource/html/HTMLResourceFactory.java
index 935843f1..afb1c850 100644
--- a/src/main/java/org/archive/resource/html/HTMLResourceFactory.java
+++ b/src/main/java/org/archive/resource/html/HTMLResourceFactory.java
@@ -1,9 +1,16 @@
 package org.archive.resource.html;
 
+import java.io.BufferedInputStream;
 import java.io.IOException;
 import java.io.InputStream;
 import java.io.UnsupportedEncodingException;
 
+import org.apache.commons.logging.Log;
+import org.apache.commons.logging.LogFactory;
+import org.archive.format.http.HttpHeaders;
+import org.archive.format.json.JSONUtils;
+import org.archive.format.text.charset.CharsetDetector;
+import org.archive.format.text.charset.StandardCharsetDetector;
 import org.archive.format.text.html.CDATALexer;
 import org.archive.format.text.html.LexParser;
 import org.archive.resource.MetaData;
@@ -13,17 +20,48 @@
 import org.archive.resource.ResourceParseException;
 import org.htmlparser.lexer.Page;
 import org.htmlparser.util.ParserException;
+import org.json.JSONException;
+import org.json.JSONObject;
 
 public class HTMLResourceFactory implements ResourceFactory {
 
+	public static final Log LOG = LogFactory.getLog(HTMLResourceFactory.class);
+
+	protected static final int CHARSET_GUESS_CHUNK_SIZE = 8192;
+	protected static final String HTTP_HEADER_PATH = "Envelope.Payload-Metadata.HTTP-Response-Metadata.Headers";
+
+	protected CharsetDetector charSetDetector = new StandardCharsetDetector();
+
+
 	public Resource getResource(InputStream is, MetaData parentMetaData,
 			ResourceContainer container) throws ResourceParseException, IOException {
 		HTMLMetaData hmd = new HTMLMetaData(parentMetaData);
 		ExtractingParseObserver epo = new ExtractingParseObserver(hmd);
 		LexParser parser = new LexParser(epo);
 		CDATALexer lex = new CDATALexer();
-		// TODO: figure out charset:
+
+		// guess charset based on HTTP header and sniffed content chunk
 		String charset = "UTF-8";
+		is = new BufferedInputStream(is, CHARSET_GUESS_CHUNK_SIZE);
+		byte[] chunk = new byte[CHARSET_GUESS_CHUNK_SIZE];
+		is.mark(0);
+		int chunkSize = is.read(chunk, 0, CHARSET_GUESS_CHUNK_SIZE);
+		is.reset();
+		if (chunkSize > 0) {
+			JSONObject headers = JSONUtils.extractObject(hmd.getTopMetaData(), HTTP_HEADER_PATH);
+			HttpHeaders httpHeaders = new HttpHeaders();
+			if (headers.has("Content-Type")) {
+				try {
+					httpHeaders.add("Content-Type", headers.getString("Content-Type"));
+				} catch (JSONException e) { }
+			}
+			try {
+				charset = charSetDetector.getCharset(chunk, chunkSize, httpHeaders);
+			} catch (Exception e) {
+				LOG.error("Failed to guess charset: " + e.getMessage());
+			}
+		}
+
 		Page page;
 		try {
 			page = new Page(is, charset);