fixed encoding issue

[radio.git] / mp3tohtml.py

diff --git a/mp3tohtml.py b/mp3tohtml.py
index 5f8ca2d..221269a 100755 (executable)
--- a/mp3tohtml.py
+++ b/mp3tohtml.py
@@ -8,14 +8,39 @@
 # Last version of this tool can be get from the GIT repository:
 # http://git.wpitchoune.net/radio.git
 #
-# (c) 2015 Jean-Philippe Orsini  <jeanfi@gmail.com>
+# (c) 2016 Jean-Philippe Orsini  <jeanfi@gmail.com>
 
-import glob
-import sys
 import eyeD3
+import glob
 import os.path
+import re
+import sys
+
+def fma_copyright_to_html(path, copyright):
+    if copyright == "":
+        sys.stderr.write(path + ": no FMA copyright.\n")
+        return ""
+
+    p = re.compile("(.*): (.*)")
+    m = p.match(copyright)
+    if m is not None:
+        name = m.group(1)
+        name = name.replace("Creative Commons", "CC")
+        name = name.replace("Attribution", "BY")
+        name = name.replace("NonCommercial", "NC")
+        name = name.replace("Noncommercial", "NC")
+        name = name.replace("NoDerivatives", "ND")
+        name = name.replace("ShareAlike", "SA")
+        name = name.replace("Share Alike", "SA")
+        name = name.replace("United States", "US")
+        return "<a href=\"" + m.group(2) + "\">" + name + "</a>"
+    else:
+        sys.stderr.write(path + ": invalid FMA copyright: "
+                         + copyright + ".\n");
+        return copyright
 
 if len(sys.argv) != 2:
+    sys.stderr.write("Usage: mp3tohtml.py <mp3_dir>\n")
     exit(1)
 
 header_path = os.path.dirname(sys.argv[0]) + "/header.tpl"
@@ -32,27 +57,38 @@ for f in files:
 
     print "\t<tr>"
 
-    try:
-        artist = tag.getArtist()
-        print "\t\t<td>" + artist + "</td>"
-    except UnicodeEncodeError:
-        print "\t\t<td></td>"
-
-    try:
-        print "\t\t<td>" + tag.getAlbum() + "</td>"
-    except UnicodeEncodeError:
-        print "\t\t<td></td>"
+    print "\t\t<td>" + tag.getArtist().encode("UTF8") + "</td>\n"
+    print "\t\t<td>" + tag.getAlbum().encode("UTF-8") + "</td>"
+    print "\t\t<td>" + tag.getTitle().encode("UTF-8") + "</td>"
 
-    try:
-        print "\t\t<td>" + tag.getTitle() + "</td>"
-    except UnicodeEncodeError:
-        print "\t\t<td></td>"
-
-    print "\t\t<td>"
     comments = tag.getComments()
+    strComments = ""
     for c in comments:
-        print c.comment
-    print "\t\t</td>"
+        strComments += c.comment
+
+    p = re.compile("URL: (.*)\r\nComments: (.*)\r\nCurators?: (.*)\r\nCopyright: (.*)")
+    m = p.match(strComments)
+
+    if m is None:
+        url = ""
+        curator = ""
+        copyright = ""
+    else:
+        if m.group(2) == "http://freemusicarchive.org/":
+            strComments = ""
+            url = "<a href=\"" + m.group(1) + "\">FMA</a>"
+        else:
+            strComments =  m.group(2)
+            url = "<a href=\"" + m.group(1) + "\">source</a>"
+
+        curator = m.group(3)
+
+        copyright = fma_copyright_to_html(f, m.group(4))
+
+    print "\t\t<td>" + url + "</td>"
+    print "\t\t<td>" + curator + "</td>"
+    print "\t\t<td>" + copyright + "</td>"
+    print "\t\t<td>" + strComments + "</td>"
 
     print "\t</tr>"