[ustream] Simplify channel extraction

[youtube-dl] / youtube_dl / utils.py

diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py
index b3d0f64ea9162876f5cd3d517ef77a9b631c781e..768c6207df5e32728c95ccc4a1cfa5e05d9088c3 100644 (file)
--- a/youtube_dl/utils.py
+++ b/youtube_dl/utils.py
@@ -213,7 +213,7 @@ if sys.version_info >= (2,7):
     def find_xpath_attr(node, xpath, key, val):
         """ Find the xpath xpath[@key=val] """
         assert re.match(r'^[a-zA-Z]+$', key)
-        assert re.match(r'^[a-zA-Z@\s]*$', val)
+        assert re.match(r'^[a-zA-Z0-9@\s]*$', val)
         expr = xpath + u"[@%s='%s']" % (key, val)
         return node.find(expr)
 else:
@@ -249,7 +249,17 @@ def htmlentity_transform(matchobj):
     return (u'&%s;' % entity)
 
 compat_html_parser.locatestarttagend = re.compile(r"""<[a-zA-Z][-.a-zA-Z0-9:_]*(?:\s+(?:(?<=['"\s])[^\s/>][^\s/=>]*(?:\s*=+\s*(?:'[^']*'|"[^"]*"|(?!['"])[^>\s]*))?\s*)*)?\s*""", re.VERBOSE) # backport bugfix
-class AttrParser(compat_html_parser.HTMLParser):
+class BaseHTMLParser(compat_html_parser.HTMLParser):
+    def __init(self):
+        compat_html_parser.HTMLParser.__init__(self)
+        self.html = None
+
+    def loads(self, html):
+        self.html = html
+        self.feed(html)
+        self.close()
+
+class AttrParser(BaseHTMLParser):
     """Modified HTMLParser that isolates a tag with the specified attribute"""
     def __init__(self, attribute, value):
         self.attribute = attribute
@@ -257,10 +267,9 @@ class AttrParser(compat_html_parser.HTMLParser):
         self.result = None
         self.started = False
         self.depth = {}
-        self.html = None
         self.watch_startpos = False
         self.error_count = 0
-        compat_html_parser.HTMLParser.__init__(self)
+        BaseHTMLParser.__init__(self)
 
     def error(self, message):
         if self.error_count > 10 or self.started:
@@ -269,11 +278,6 @@ class AttrParser(compat_html_parser.HTMLParser):
         self.error_count += 1
         self.goahead(1)
 
-    def loads(self, html):
-        self.html = html
-        self.feed(html)
-        self.close()
-
     def handle_starttag(self, tag, attrs):
         attrs = dict(attrs)
         if self.started:
@@ -334,6 +338,38 @@ def get_element_by_attribute(attribute, value, html):
         pass
     return parser.get_result()
 
+class MetaParser(BaseHTMLParser):
+    """
+    Modified HTMLParser that isolates a meta tag with the specified name 
+    attribute.
+    """
+    def __init__(self, name):
+        BaseHTMLParser.__init__(self)
+        self.name = name
+        self.content = None
+        self.result = None
+
+    def handle_starttag(self, tag, attrs):
+        if tag != 'meta':
+            return
+        attrs = dict(attrs)
+        if attrs.get('name') == self.name:
+            self.result = attrs.get('content')
+
+    def get_result(self):
+        return self.result
+
+def get_meta_content(name, html):
+    """
+    Return the content attribute from the meta tag with the given name attribute.
+    """
+    parser = MetaParser(name)
+    try:
+        parser.loads(html)
+    except compat_html_parser.HTMLParseError:
+        pass
+    return parser.get_result()
+
 
 def clean_html(html):
     """Clean an HTML snippet into a readable string"""