PY3: use six for robotparser and urlparse

extras/scrapy-ws.py

@@ -13,7 +13,7 @@ command).
 
 from __future__ import print_function
 import sys, optparse, urllib, json
-from urlparse import urljoin
+from six.moves.urllib.parse import urljoin
 
 from scrapy.utils.jsonrpc import jsonrpc_client_call, JsonRpcError
 

scrapy/commands/deploy.py

@@ -8,7 +8,7 @@ import time
 import urllib2
 import netrc
 import json
-from urlparse import urlparse, urljoin
+from six.moves.urllib.parse import urlparse, urljoin
 from subprocess import Popen, PIPE, check_call
 
 from w3lib.form import encode_multipart

scrapy/contrib/downloadermiddleware/httpproxy.py

@@ -1,7 +1,7 @@
 import base64
 from urllib import getproxies, unquote, proxy_bypass
 from urllib2 import _parse_proxy
-from urlparse import urlunparse
+from six.moves.urllib.parse import urlunparse
 
 from scrapy.utils.httpobj import urlparse_cached
 from scrapy.exceptions import NotConfigured

scrapy/contrib/downloadermiddleware/redirect.py

@@ -1,4 +1,4 @@
-from urlparse import urljoin
+from six.moves.urllib.parse import urljoin
 
 from scrapy import log
 from scrapy.http import HtmlResponse

scrapy/contrib/downloadermiddleware/robotstxt.py

@@ -4,7 +4,7 @@ enable this middleware and enable the ROBOTSTXT_OBEY setting.
 
 """
 
-import robotparser
+from six.moves.urllib import robotparser
 
 from scrapy import signals, log
 from scrapy.exceptions import NotConfigured, IgnoreRequest

scrapy/contrib/feedexport.py

@@ -7,7 +7,7 @@ See documentation in docs/topics/feed-exports.rst
 import sys, os, posixpath
 from tempfile import TemporaryFile
 from datetime import datetime
-from urlparse import urlparse
+from six.moves.urllib.parse import urlparse
 from ftplib import FTP
 
 from zope.interface import Interface, implements

scrapy/contrib/linkextractors/htmlparser.py

@@ -3,7 +3,7 @@ HTMLParser-based link extractor
 """
 
 from HTMLParser import HTMLParser
-from urlparse import urljoin
+from six.moves.urllib.parse import urljoin
 
 from w3lib.url import safe_url_string
 

scrapy/contrib/linkextractors/lxmlhtml.py

@@ -3,7 +3,7 @@ Link extractor based on lxml.html
 """
 
 import re
-from urlparse import urlparse, urljoin
+from six.moves.urllib.parse import urlparse, urljoin
 
 import lxml.etree as etree
 

scrapy/contrib/linkextractors/regex.py

@@ -1,5 +1,5 @@
 import re
-from urlparse import urljoin
+from six.moves.urllib.parse import urljoin
 
 from w3lib.html import remove_tags, remove_entities, replace_escape_chars
 

scrapy/contrib/linkextractors/sgml.py

@@ -1,7 +1,7 @@
 """
 SGMLParser-based Link extractors
 """
-from urlparse import urljoin
+from six.moves.urllib.parse import urljoin
 import warnings
 from sgmllib import SGMLParser
 

scrapy/contrib/pipeline/files.py

@@ -7,7 +7,7 @@ import os
 import os.path
 import rfc822
 import time
-import urlparse
+from six.moves.urllib.parse import urlparse
 from collections import defaultdict
 from cStringIO import StringIO
 import six
@@ -167,7 +167,7 @@ class FilesPipeline(MediaPipeline):
         if os.path.isabs(uri):  # to support win32 paths like: C:\\some\dir
             scheme = 'file'
         else:
-            scheme = urlparse.urlparse(uri).scheme
+            scheme = urlparse(uri).scheme
         store_cls = self.STORE_SCHEMES[scheme]
         return store_cls(uri)
 

scrapy/core/downloader/handlers/ftp.py

@@ -29,7 +29,7 @@ In case of status 200 request, response.headers will come with two keys:
 """
 
 import re
-from urlparse import urlparse
+from six.moves.urllib.parse import urlparse
 from cStringIO import StringIO
 
 from twisted.internet import reactor

scrapy/core/downloader/handlers/http11.py

@@ -4,7 +4,7 @@ import re
 
 from time import time
 from cStringIO import StringIO
-from urlparse import urldefrag
+from six.moves.urllib.parse import urldefrag
 
 from zope.interface import implements
 from twisted.internet import defer, reactor, protocol

scrapy/core/downloader/webclient.py

@@ -1,5 +1,5 @@
 from time import time
-from urlparse import urlparse, urlunparse, urldefrag
+from six.moves.urllib.parse import urlparse, urlunparse, urldefrag
 
 from twisted.web.client import HTTPClientFactory
 from twisted.web.http import HTTPClient

scrapy/http/request/form.py

@@ -5,7 +5,8 @@ This module implements the FormRequest class which is a more covenient class
 See documentation in docs/topics/request-response.rst
 """
 
-import urllib, urlparse
+import urllib
+from six.moves.urllib.parse import urljoin
 import lxml.html
 import six
 from scrapy.http.request import Request
@@ -43,7 +44,7 @@ class FormRequest(Request):
 def _get_form_url(form, url):
     if url is None:
         return form.action or form.base_url
-    return urlparse.urljoin(form.base_url, url)
+    return urljoin(form.base_url, url)
 
 def _urlencode(seq, enc):
     values = [(unicode_to_str(k, enc), unicode_to_str(v, enc))

scrapy/linkextractor.py

@@ -3,7 +3,7 @@ Common code and definitions used by Link extractors (located in
 scrapy.contrib.linkextractor).
 """
 import re
-from urlparse import urlparse
+from six.moves.urllib.parse import urlparse
 
 from scrapy.utils.url import url_is_from_any_domain
 from scrapy.utils.url import canonicalize_url, url_is_from_any_domain, url_has_any_extension

scrapy/tests/test_contrib_feedexport.py

@@ -1,4 +1,5 @@
-import os, urlparse
+import os
+from six.moves.urllib.parse import urlparse
 from cStringIO import StringIO
 
 from zope.interface.verify import verifyObject
@@ -84,7 +85,7 @@ class S3FeedStorageTest(unittest.TestCase):
         file = storage.open(Spider("default"))
         file.write("content")
         yield storage.store(file)
-        u = urlparse.urlparse(uri)
+        u = urlparse(uri)
         key = connect_s3().get_bucket(u.hostname, validate=False).get_key(u.path)
         self.failUnlessEqual(key.get_contents_as_string(), "content")
 

scrapy/tests/test_engine.py

@@ -11,7 +11,8 @@ module with the ``runserver`` argument::
 """
 
 from __future__ import print_function
-import sys, os, re, urlparse
+import sys, os, re
+from six.moves.urllib.parse import urlparse
 
 from twisted.internet import reactor, defer
 from twisted.web import server, static, util
@@ -117,7 +118,7 @@ class CrawlerRun(object):
         return "http://localhost:%s%s" % (self.portno, path)
 
     def getpath(self, url):
-        u = urlparse.urlparse(url)
+        u = urlparse(url)
         return u.path
 
     def item_scraped(self, item, spider, response):

scrapy/tests/test_http_cookies.py

@@ -1,4 +1,4 @@
-from urlparse import urlparse
+from six.moves.urllib.parse import urlparse
 from unittest import TestCase
 
 from scrapy.http import Request, Response

scrapy/tests/test_http_request.py

@@ -1,7 +1,7 @@
 import cgi
 import unittest
 import xmlrpclib
-from urlparse import urlparse
+from six.moves.urllib.parse import urlparse
 
 from scrapy.http import Request, FormRequest, XmlRpcRequest, Headers, HtmlResponse
 

scrapy/tests/test_spidermiddleware_offsite.py

@@ -5,7 +5,7 @@ from scrapy.spider import Spider
 from scrapy.contrib.spidermiddleware.offsite import OffsiteMiddleware
 from scrapy.utils.test import get_crawler
 
-from urlparse import urlparse
+from six.moves.urllib.parse import urlparse
 
 class TestOffsiteMiddleware(TestCase):
 

scrapy/tests/test_urlparse_monkeypatches.py

@@ -1,4 +1,4 @@
-from urlparse import urlparse
+from six.moves.urllib.parse import urlparse
 import unittest
 
 

scrapy/tests/test_utils_httpobj.py

@@ -1,5 +1,5 @@
 import unittest
-import urlparse
+from six.moves.urllib.parse import urlparse
 
 from scrapy.http import Request
 from scrapy.utils.httpobj import urlparse_cached
@@ -13,7 +13,7 @@ class HttpobjUtilsTest(unittest.TestCase):
         req1a = urlparse_cached(request1)
         req1b = urlparse_cached(request1)
         req2 = urlparse_cached(request2)
-        urlp = urlparse.urlparse(url)
+        urlp = urlparse(url)
 
         assert req1a == req2
         assert req1a == urlp

scrapy/tests/test_utils_response.py

@@ -1,6 +1,6 @@
 import os
 import unittest
-import urlparse
+from six.moves.urllib.parse import urlparse
 
 from scrapy.http import Response, TextResponse, HtmlResponse
 from scrapy.utils.response import response_httprepr, open_in_browser, get_meta_refresh
@@ -24,7 +24,7 @@ class ResponseUtilsTest(unittest.TestCase):
         url = "http:///www.example.com/some/page.html"
         body = "<html> <head> <title>test page</title> </head> <body>test body</body> </html>"
         def browser_open(burl):
-            path = urlparse.urlparse(burl).path
+            path = urlparse(burl).path
             if not os.path.exists(path):
                 path = burl.replace('file://', '')
             bbody = open(path).read()

scrapy/tests/test_webclient.py

@@ -3,7 +3,7 @@ from twisted.internet import defer
 Tests borrowed from the twisted.web.client tests.
 """
 import os
-from urlparse import urlparse
+from six.moves.urllib.parse import urlparse
 
 from twisted.trial import unittest
 from twisted.web import server, static, error, util

scrapy/utils/httpobj.py

@@ -2,7 +2,7 @@
 
 import weakref
 
-from urlparse import urlparse
+from six.moves.urllib.parse import urlparse
 
 _urlparse_cache = weakref.WeakKeyDictionary()
 def urlparse_cached(request_or_response):

scrapy/utils/request.py

@@ -6,7 +6,7 @@ scrapy.http.Request objects
 from __future__ import print_function
 import hashlib
 import weakref
-from urlparse import urlunparse
+from six.moves.urllib.parse import urlunparse
 
 from twisted.internet.defer import Deferred
 from w3lib.http import basic_auth_header

scrapy/utils/testsite.py

@@ -1,5 +1,5 @@
 from __future__ import print_function
-import urlparse
+from six.moves.urllib.parse import urljoin
 
 from twisted.internet import reactor
 from twisted.web import server, resource, static, util
@@ -14,7 +14,7 @@ class SiteTest(object):
         self.site.stopListening()
 
     def url(self, path):
-        return urlparse.urljoin(self.baseurl, path)
+        return urljoin(self.baseurl, path)
 
 def test_site():
     r = resource.Resource()

scrapy/utils/url.py

@@ -6,7 +6,7 @@ Some of the functions that used to be imported from this module have been moved
 to the w3lib.url module. Always import those from there instead.
 """
 import posixpath
-import urlparse
+from six.moves.urllib.parse import ParseResult, urlunparse, urldefrag, urlparse
 import urllib
 import cgi
 
@@ -59,7 +59,7 @@ def canonicalize_url(url, keep_blank_values=True, keep_fragments=False,
     query = urllib.urlencode(keyvals)
     path = safe_url_string(_unquotepath(path)) or '/'
     fragment = '' if not keep_fragments else fragment
-    return urlparse.urlunparse((scheme, netloc.lower(), path, params, query, fragment))
+    return urlunparse((scheme, netloc.lower(), path, params, query, fragment))
 
 
 def _unquotepath(path):
@@ -72,8 +72,8 @@ def parse_url(url, encoding=None):
     """Return urlparsed url from the given argument (which could be an already
     parsed url)
     """
-    return url if isinstance(url, urlparse.ParseResult) else \
-        urlparse.urlparse(unicode_to_str(url, encoding))
+    return url if isinstance(url, ParseResult) else \
+        urlparse(unicode_to_str(url, encoding))
 
 
 def escape_ajax(url):
@@ -99,7 +99,7 @@ def escape_ajax(url):
     >>> escape_ajax("www.example.com/ajax.html")
     'www.example.com/ajax.html'
     """
-    defrag, frag = urlparse.urldefrag(url)
+    defrag, frag = urldefrag(url)
     if not frag.startswith('!'):
         return url
     return add_or_replace_parameter(defrag, '_escaped_fragment_', frag[1:])