X-Git-Url: http://git.cielonegro.org/gitweb.cgi?a=blobdiff_plain;f=youtube_dl%2Futils.py;h=6e982157c4811b9db43642af3b9ee90d8ab5e376;hb=921a14559277cfb2ead84b613c02d0251aeeb9ab;hp=a19656000d738530cfaa6d13450442385332a202;hpb=9e6dd238761e6628d7bd0b6bdb7a997604de3757;p=youtube-dl.git

diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py
index a19656000..6e982157c 100644
--- a/youtube_dl/utils.py
+++ b/youtube_dl/utils.py
@@ -11,16 +11,12 @@ import sys
 import zlib
 import urllib2
 import email.utils
+import json
 
 try:
 	import cStringIO as StringIO
 except ImportError:
 	import StringIO
-		
-try:
-	import json
-except ImportError: # Python <2.6, use trivialjson (https://github.com/phihag/trivialjson):
-	import trivialjson as json
 
 std_headers = {
 	'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64; rv:5.0.1) Gecko/20100101 Firefox/5.0.1',
@@ -73,7 +69,7 @@ def htmlentity_transform(matchobj):
 	# Unknown entity in name, return its literal representation
 	return (u'&%s;' % entity)
 
-
+HTMLParser.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 IDParser(HTMLParser.HTMLParser):
 	"""Modified HTMLParser that isolates a tag with the specified id"""
 	def __init__(self, id):
@@ -83,8 +79,17 @@ class IDParser(HTMLParser.HTMLParser):
 		self.depth = {}
 		self.html = None
 		self.watch_startpos = False
+		self.error_count = 0
 		HTMLParser.HTMLParser.__init__(self)
 
+	def error(self, message):
+		print self.getpos()
+		if self.error_count > 10 or self.started:
+			raise HTMLParser.HTMLParseError(message, self.getpos())
+		self.rawdata = '\n'.join(self.html.split('\n')[self.getpos()[0]:]) # skip one line
+		self.error_count += 1
+		self.goahead(1)
+
 	def loads(self, html):
 		self.html = html
 		self.feed(html)