diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index 30160d59d..9a2e54d14 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -13,6 +13,7 @@ from ..utils import ( compat_urllib_parse, compat_urllib_request, compat_urlparse, + compat_xml_parse_error, ExtractorError, HEADRequest, @@ -241,10 +242,10 @@ class GenericIE(InfoExtractor): # Is it an RSS feed? try: - doc = xml.etree.ElementTree.fromstring(webpage) + doc = xml.etree.ElementTree.fromstring(webpage.encode('utf-8')) if doc.tag == 'rss': return self._extract_rss(url, video_id, doc) - except xml.etree.ElementTree.ParseError: + except compat_xml_parse_error: pass # it's tempting to parse this further, but you would diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py index 057cd20d1..471516b8f 100644 --- a/youtube_dl/utils.py +++ b/youtube_dl/utils.py @@ -174,6 +174,11 @@ try: except NameError: compat_chr = chr +try: + from xml.etree.ElementTree import ParseError as compat_xml_parse_error +except ImportError: # Python 2.6 + from xml.parsers.expat import ExpatError as compat_xml_parse_error + def compat_ord(c): if type(c) is int: return c else: return ord(c)