aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/utils.py
diff options
context:
space:
mode:
authorPhilipp Hagemeister <phihag@phihag.de>2012-11-28 00:06:28 +0100
committerPhilipp Hagemeister <phihag@phihag.de>2012-11-28 00:06:28 +0100
commita8156c1d2e4b2a7ac5e034c247c6fccaca15a21d (patch)
treef0b113599e29f837d0719398d1e01c9df54a28b5 /youtube_dl/utils.py
parent3e669f369f886dff8fa8272f3bfa37be6360a0ba (diff)
Python 3 version of HTMLParser
Diffstat (limited to 'youtube_dl/utils.py')
-rw-r--r--youtube_dl/utils.py16
1 files changed, 10 insertions, 6 deletions
diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py
index 668338270..c4917012b 100644
--- a/youtube_dl/utils.py
+++ b/youtube_dl/utils.py
@@ -2,7 +2,6 @@
# -*- coding: utf-8 -*-
import gzip
-import HTMLParser
import locale
import os
import re
@@ -42,6 +41,11 @@ except NameError: # Python 2
import htmlentitydefs as compat_html_entities
try:
+ import html.parser as compat_html_parser
+except NameError: # Python 2
+ import HTMLParser as compat_html_parser
+
+try:
compat_str = unicode # Python 2
except NameError:
compat_str = str
@@ -99,8 +103,8 @@ 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):
+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 IDParser(compat_html_parser.HTMLParser):
"""Modified HTMLParser that isolates a tag with the specified id"""
def __init__(self, id):
self.id = id
@@ -110,11 +114,11 @@ class IDParser(HTMLParser.HTMLParser):
self.html = None
self.watch_startpos = False
self.error_count = 0
- HTMLParser.HTMLParser.__init__(self)
+ compat_html_parser.HTMLParser.__init__(self)
def error(self, message):
if self.error_count > 10 or self.started:
- raise HTMLParser.HTMLParseError(message, self.getpos())
+ raise compat_html_parser.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)
@@ -170,7 +174,7 @@ def get_element_by_id(id, html):
parser = IDParser(id)
try:
parser.loads(html)
- except HTMLParser.HTMLParseError:
+ except compat_html_parser.HTMLParseError:
pass
return parser.get_result()