unescape HTML entities in media titles

src/you_get/common.py

@@ -11,7 +11,7 @@ import platform
 import threading
 
 from .version import __version__
-from .util import log, legitimize, sogou_proxy_server
+from .util import log, legitimize, sogou_proxy_server, unescape
 
 dry_run = False
 force = False
@@ -523,6 +523,7 @@ def download_urls(urls, title, ext, total_size, output_dir = '.', refer = None,
             traceback.print_exc(file = sys.stdout)
             pass
     
+    title = unescape(title)
     title = legitimize(title)
     
     filename = '%s.%s' % (title, ext)
@@ -727,7 +728,7 @@ def print_info(site_info, title, type, size):
         type_info = "Unknown type (%s)" % type
     
     print("Video Site:", site_info)
-    print("Title:     ", tr(title))
+    print("Title:     ", unescape(tr(title)))
     print("Type:      ", type_info)
     print("Size:      ", round(size / 1048576, 2), "MiB (" + str(size) + " Bytes)")
     print()

src/you_get/util/__init__.py

@@ -3,3 +3,4 @@
 from .fs import *
 from .log import *
 from .sogou_proxy import *
+from .strings import *

src/you_get/util/strings.py

@@ -0,0 +1,20 @@
+try:
+  # py 3.4
+  from html import unescape
+except ImportError:
+  import re
+  from html.entities import entitydefs
+
+  def unescape(string):
+    '''HTML entity decode'''
+    string = re.sub(r'&#[^;]+;', _sharp2uni, string)
+    string = re.sub(r'&[^;]+;', lambda m: entitydefs[m.group(0)[1:-1]], string)
+    return string
+
+  def _sharp2uni(m):
+    '''&#...; ==> unicode'''
+    s = m.group(0)[2:].rstrip(';；')
+    if s.startswith('x'):
+      return chr(int('0'+s, 16))
+    else:
+      return chr(int(s))