more python3 cleanups

ox/cache.py

@@ -10,6 +10,7 @@ import os
 from six import BytesIO
 import time
 from six.moves import urllib
+from six import PY2
 import sqlite3
 
 from .utils import json
@@ -24,6 +25,7 @@ COMPRESS_TYPES = (
     'text/html',
     'text/plain',
     'text/xml',
+    'application/json',
     'application/xhtml+xml',
     'application/x-javascript',
     'application/javascript',
@@ -203,7 +205,7 @@ class SQLiteCache(Cache):
             elif value == 'data':
                 if row[1] == 1:
                     r = zlib.decompress(r)
-                else:
+                elif PY2:
                     r = str(r)
             break
 

ox/net.py

@@ -104,9 +104,8 @@ def save_url(url, filename, overwrite=False):
         if not os.path.exists(dirname):
             os.makedirs(dirname)
         data = read_url(url)
-        f = open(filename, 'w')
+        with open(filename, 'wb') as f:
             f.write(data)
-        f.close()
 
 def oshash(url):
     def get_size(url):

ox/web/imdb.py

@@ -9,7 +9,6 @@ import unicodedata
 from six.moves import urllib
 from six import string_types
 
-
 from .. import find_re, strip_tags, decode_html
 from .. import cache
 

ox/web/itunes.py

@@ -2,7 +2,7 @@
 # encoding: utf-8
 from __future__ import print_function
 import re
-import urllib
+from six.moves import urllib
 
 from ox.cache import read_url
 from ox.html import decode_html, strip_tags

ox/web/metacritic.py

@@ -1,7 +1,8 @@
 # -*- coding: utf-8 -*-
 # vi:si:et:sw=4:sts=4:ts=4
 import re
-from urllib import quote
+
+from six.movies.urllib.parse import quote
 from lxml.html import document_fromstring
 
 from ox.cache import read_url

ox/web/mininova.py

@@ -3,7 +3,7 @@
 from datetime import datetime
 import re
 import socket
-from urllib import quote
+from six.movies.urllib.parse import quote
 
 from ox.cache import read_url
 from ox import find_re, cache, strip_tags, decode_html, get_torrent_info, int_value, normalize_newlines

ox/web/thepiratebay.py

@@ -2,9 +2,8 @@
 # vi:si:et:sw=4:sts=4:ts=4
 from datetime import datetime
 import re
-import socket
-from urllib import quote, urlencode
-from urllib2 import URLError
+
+from six.movies.urllib.parse import quote
 
 from ox import find_re, cache, strip_tags, decode_html, get_torrent_info, normalize_newlines
 from ox.normalize import normalize_imdbid

ox/web/twitter.py

@@ -2,7 +2,7 @@
 # vi:si:et:sw=4:sts=4:ts=4
 import re
 from datetime import datetime
-from urllib import quote
+from six.movies.urllib.parse import quote
 
 import lxml.html
 import ox

ox/web/vimeo.py

@@ -1,27 +1,17 @@
 # -*- coding: utf-8 -*-
 # vi:si:et:sw=4:sts=4:ts=4
-import re
-from StringIO import StringIO
-import xml.etree.ElementTree as ET
+
+import json
 
 from ox.cache import read_url
-from ox import find_string, find_re
 
 
 def get_data(id):
-    url = 'http://www.vimeo.com/moogaloop/load/clip:%s' %id
-    xml = read_url(url)
-    tree = ET.parse(StringIO(xml))
-    request_signature = tree.find('request_signature').text
-    request_signature_expires = tree.find('request_signature_expires').text
+    url = 'http://vimeo.com/api/v2/video/%s.json' % id
+    data = json.loads(read_url(url).decode('utf-8'))[0]
 
-    data = {}
-    video_url = "http://www.vimeo.com/moogaloop/play/clip:%s/%s/%s/?q=" % \
-                              (id, request_signature, request_signature_expires)
-    data['video_sd'] = video_url + 'sd'
-    data['video_hd'] = video_url + 'hd'
-    video = tree.find('video')
-    for key in ('caption', 'width', 'height', 'duration', 'thumbnail'):
-        data[key] = video.find(key).text
+    url = 'http://player.vimeo.com/video/%s/config?autoplay=0&byline=0&bypass_privacy=1&context=clip.main&default_to_hd=1&portrait=0' % id    
+    info = json.loads(read_url(url).decode('utf-8'))
+    data['video'] = info['request']['files']['h264']
     return data