X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Futils.py;h=c8308ba3a3b7e3473e53423b45c7950b57eb5aef;hb=bccdac68749e7a39a47dd0e1ad0ec9c177657de6;hp=89234b39df9cdfe3edbce0420fee5ec5b67c4575;hpb=c88270271e65be591f7e194b71728256644b8684;p=youtube-dl

diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py
index 89234b39d..c8308ba3a 100644
--- a/youtube_dl/utils.py
+++ b/youtube_dl/utils.py
@@ -39,6 +39,7 @@ from .compat import (
     compat_chr,
     compat_etree_fromstring,
     compat_html_entities,
+    compat_html_entities_html5,
     compat_http_client,
     compat_kwargs,
     compat_parse_qs,
@@ -75,7 +76,7 @@ def register_socks_protocols():
 compiled_regex_type = type(re.compile(''))
 
 std_headers = {
-    'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64; rv:10.0) Gecko/20150101 Firefox/44.0 (Chrome)',
+    'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64; rv:10.0) Gecko/20150101 Firefox/47.0 (Chrome)',
     'Accept-Charset': 'ISO-8859-1,utf-8;q=0.7,*;q=0.7',
     'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
     'Accept-Encoding': 'gzip, deflate',
@@ -456,12 +457,19 @@ def orderedSet(iterable):
     return res
 
 
-def _htmlentity_transform(entity):
+def _htmlentity_transform(entity_with_semicolon):
     """Transforms an HTML entity to a character."""
+    entity = entity_with_semicolon[:-1]
+
     # Known non-numeric HTML entity
     if entity in compat_html_entities.name2codepoint:
         return compat_chr(compat_html_entities.name2codepoint[entity])
 
+    # TODO: HTML5 allows entities without a semicolon. For example,
+    # '&Eacuteric' should be decoded as 'Éric'.
+    if entity_with_semicolon in compat_html_entities_html5:
+        return compat_html_entities_html5[entity_with_semicolon]
+
     mobj = re.match(r'#(x[0-9a-fA-F]+|[0-9]+)', entity)
     if mobj is not None:
         numstr = mobj.group(1)
@@ -486,7 +494,7 @@ def unescapeHTML(s):
     assert type(s) == compat_str
 
     return re.sub(
-        r'&([^;]+);', lambda m: _htmlentity_transform(m.group(1)), s)
+        r'&([^;]+;)', lambda m: _htmlentity_transform(m.group(1)), s)
 
 
 def get_subprocess_encoding():
@@ -1893,6 +1901,16 @@ def dict_get(d, key_or_keys, default=None, skip_false_values=True):
     return d.get(key_or_keys, default)
 
 
+def try_get(src, getter, expected_type=None):
+    try:
+        v = getter(src)
+    except (AttributeError, KeyError, TypeError, IndexError):
+        pass
+    else:
+        if expected_type is None or isinstance(v, expected_type):
+            return v
+
+
 def encode_compat_str(string, encoding=preferredencoding(), errors='strict'):
     return string if isinstance(string, compat_str) else compat_str(string, encoding, errors)
 
@@ -2020,6 +2038,9 @@ def mimetype2ext(mt):
 
     ext = {
         'audio/mp4': 'm4a',
+        # Per RFC 3003, audio/mpeg can be .mp1, .mp2 or .mp3. Here use .mp3 as
+        # it's the most popular one
+        'audio/mpeg': 'mp3',
     }.get(mt)
     if ext is not None:
         return ext