Remove superfluous encodings

[youtube-dl] / youtube_dl / utils.py

diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py
index 66833827003320278a46b45ccb404ad2d0da2898..0aa350e648d154f9356d81b76a583deeb7ca4623 100644 (file)
--- a/youtube_dl/utils.py
+++ b/youtube_dl/utils.py
@@ -2,7 +2,7 @@
 # -*- coding: utf-8 -*-
 
 import gzip
-import HTMLParser
+import io
 import locale
 import os
 import re
@@ -11,11 +11,6 @@ import zlib
 import email.utils
 import json
 
-try:
-       import cStringIO as StringIO
-except ImportError:
-       import StringIO
-
 try:
        import urllib.request as compat_urllib_request
 except ImportError: # Python 2
@@ -38,9 +33,24 @@ except ImportError: # Python 2
 
 try:
        import html.entities as compat_html_entities
-except NameError: # Python 2
+except ImportError: # Python 2
        import htmlentitydefs as compat_html_entities
 
+try:
+       import html.parser as compat_html_parser
+except ImportError: # Python 2
+       import HTMLParser as compat_html_parser
+
+try:
+       import http.client as compat_http_client
+except ImportError: # Python 2
+       import httplib as compat_http_client
+
+try:
+       from urllib.parse import parse_qs as compat_parse_qs
+except ImportError: # Python 2
+       from urlparse import parse_qs as compat_parse_qs
+
 try:
        compat_str = unicode # Python 2
 except NameError:
@@ -51,7 +61,6 @@ try:
 except NameError:
        compat_chr = chr
 
-
 std_headers = {
        'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64; rv:10.0) Gecko/20100101 Firefox/10.0',
        'Accept-Charset': 'ISO-8859-1,utf-8;q=0.7,*;q=0.7',
@@ -73,6 +82,13 @@ def preferredencoding():
 
        return pref
 
+if sys.version_info < (3,0):
+       def compat_print(s):
+               print(s.encode(preferredencoding(), 'xmlcharrefreplace'))
+else:
+       def compat_print(s):
+               assert type(s) == type(u'')
+               print(s)
 
 def htmlentity_transform(matchobj):
        """Transforms an HTML entity to a character.
@@ -99,8 +115,8 @@ 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 +126,11 @@ 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 +186,7 @@ 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()
 
@@ -396,12 +412,12 @@ class YoutubeDLHandler(compat_urllib_request.HTTPHandler):
                old_resp = resp
                # gzip
                if resp.headers.get('Content-encoding', '') == 'gzip':
-                       gz = gzip.GzipFile(fileobj=StringIO.StringIO(resp.read()), mode='r')
+                       gz = gzip.GzipFile(fileobj=io.BytesIO(resp.read()), mode='r')
                        resp = self.addinfourl_wrapper(gz, old_resp.headers, old_resp.url, old_resp.code)
                        resp.msg = old_resp.msg
                # deflate
                if resp.headers.get('Content-encoding', '') == 'deflate':
-                       gz = StringIO.StringIO(self.deflate(resp.read()))
+                       gz = io.BytesIO(self.deflate(resp.read()))
                        resp = self.addinfourl_wrapper(gz, old_resp.headers, old_resp.url, old_resp.code)
                        resp.msg = old_resp.msg
                return resp