some HTMLParser bugfixes

This commit is contained in:
Filippo Valsorda 2012-04-13 22:09:24 +02:00
parent 9e6dd23876
commit 9beb5af82e
4 changed files with 14 additions and 5 deletions

Binary file not shown.

Binary file not shown.

View file

@ -359,8 +359,8 @@ class YoutubeIE(InfoExtractor):
pass
# description
video_description = get_element_by_id("eow-description", video_webpage)
if video_description: video_description = clean_html(video_description.decode('utf8'))
video_description = get_element_by_id("eow-description", video_webpage.decode('utf8'))
if video_description: video_description = clean_html(video_description)
else: video_description = ''
# closed captions
@ -1055,8 +1055,8 @@ class VimeoIE(InfoExtractor):
video_thumbnail = config["video"]["thumbnail"]
# Extract video description
video_description = get_element_by_id("description", webpage)
if video_description: video_description = clean_html(video_description.decode('utf8'))
video_description = get_element_by_id("description", webpage.decode('utf8'))
if video_description: video_description = clean_html(video_description)
else: video_description = ''
# Extract upload date

View file

@ -73,7 +73,7 @@ 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 +83,17 @@ 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)