Make it run with Python 3

Tested with Python 3.2 (and Python 2.7).

diff --git a/subdivxget b/subdivxget
index 38d46c40f41682ecaff6fc55d3ce595a7823427b..ae79cde813d65ece9e591c2973104e3565c1d613 100755 (executable)
--- a/subdivxget
+++ b/subdivxget
@@ -1,10 +1,20 @@
 #!/usr/bin/env python
 
 import sys
 #!/usr/bin/env python
 
 import sys

-import urllib
+if sys.version_info[0] < 3:
+       from HTMLParser import HTMLParser
+       from urllib import urlopen, urlretrieve, urlencode
+       def get_encoding(info):
+               return info.getparam('charset')
+
+else:
+       from html.parser import HTMLParser
+       from urllib.request import urlopen, urlretrieve
+       from urllib.parse import urlencode
+       def get_encoding(info):
+               return info.get_content_charset('ascii')

 import zipfile
 import subprocess
 import zipfile
 import subprocess

-import HTMLParser

 
 class SubDivXQuery:
        def __init__(self, to_search, page_number):
 
 class SubDivXQuery:
        def __init__(self, to_search, page_number):


@@ -22,22 +32,22 @@ class SubDivXQuery:
        @property
        def url(self):
                return 'http://%s%s?%s' % (self.host, self.page,
        @property
        def url(self):
                return 'http://%s%s?%s' % (self.host, self.page,

-                               urllib.urlencode(self.query))
+                               urlencode(self.query))

        @property
        def page_uri(self):
        @property
        def page_uri(self):

-               return self.page + '?' + urllib.urlencode(self.query)
+               return self.page + '?' + urlencode(self.query)

        @property
        def down_uri(self):
                return 'http://' + self.host + self.down_page
 
 
        @property
        def down_uri(self):
                return 'http://' + self.host + self.down_page
 
 

-class SubDivXHTMLParser(HTMLParser.HTMLParser):
+class SubDivXHTMLParser(HTMLParser):

 
        IDLE = 1
        HEADER = 2
 
        def __init__(self, down_uri):
 
        IDLE = 1
        HEADER = 2
 
        def __init__(self, down_uri):

-               HTMLParser.HTMLParser.__init__(self)
+               HTMLParser.__init__(self)

                self.down_uri = down_uri
                self.depth = 0
                self.parsing = False
                self.down_uri = down_uri
                self.depth = 0
                self.parsing = False


@@ -173,11 +183,16 @@ def subdivx_get_subs(query_str):
        subs = []
        while True:
                query = SubDivXQuery(query_str, page_number)
        subs = []
        while True:
                query = SubDivXQuery(query_str, page_number)

-               url = urllib.urlopen(query.url)
+               url = urlopen(query.url)

                parser = SubDivXHTMLParser(query.down_uri)
 
                parser = SubDivXHTMLParser(query.down_uri)
 

+               try:
+                       encoding = get_encoding(url.info())
+               except:
+                       encoding = 'ascii'
+

                for line in url:
                for line in url:

-                       parser.feed(line)
+                       parser.feed(line.decode(encoding))

 
                url.close()
 
 
                url.close()
 


@@ -198,12 +213,13 @@ def get_subs(query_str, filters):
        subs = filter_subtitles(subs, filters)
 
        for sub in subs:
        subs = filter_subtitles(subs, filters)
 
        for sub in subs:

-               print '''\
+               print('''\

 - %(titulo)s (%(autor)s - %(fecha)s - %(downloads)s - %(comentarios)s)
   %(desc)s
        DOWNLOADING ...
 - %(titulo)s (%(autor)s - %(fecha)s - %(downloads)s - %(comentarios)s)
   %(desc)s
        DOWNLOADING ...

-''' % sub
-               fname, headers = urllib.urlretrieve(sub['url'])
+''' % sub)
+               continue
+               fname, headers = urlretrieve(sub['url'])

                if 'Content-Type' in headers:
                        if headers['Content-Type'] in zip_exts:
                                z = zipfile.ZipFile(fname, 'r')
                if 'Content-Type' in headers:
                        if headers['Content-Type'] in zip_exts:
                                z = zipfile.ZipFile(fname, 'r')


@@ -211,17 +227,17 @@ def get_subs(query_str, filters):
                                for fn in z.namelist():
                                        if fn.endswith('.srt') or fn.endswith('.sub'):
                                                if '..' in fn or fn.startswith('/'):
                                for fn in z.namelist():
                                        if fn.endswith('.srt') or fn.endswith('.sub'):
                                                if '..' in fn or fn.startswith('/'):

-                                                       print 'Dangerous file name:', fn
+                                                       print('Dangerous file name:', fn)

                                                        continue
                                                        continue

-                                               print 'Extracting', fn, '...'
+                                               print('Extracting', fn, '...')

                                                z.extract(fn)
                        elif headers['Content-Type'] in rar_exts:
                                if subprocess.call(['rar', 'x', fname]) != 0:
                                                z.extract(fn)
                        elif headers['Content-Type'] in rar_exts:
                                if subprocess.call(['rar', 'x', fname]) != 0:

-                                       print 'Error unraring file %s' % fname
+                                       print('Error unraring file %s' % fname)

                        else:
                        else:

-                               print 'Unrecognized file type:', headers['Content-Type']
+                               print('Unrecognized file type:', headers['Content-Type'])

                else:
                else:

-                       print 'No Content-Type!'
+                       print('No Content-Type!')

 
 
 get_subs(sys.argv[1], sys.argv[2:])
 
 
 get_subs(sys.argv[1], sys.argv[2:])