Merge into python3 support from Vetal4444

See

	https://github.com/vetal4444/python-goose/tree/python_3
	grangier#220

Conflicts:
	goose/text.py

Author: Lol4to

.travis.yml

@@ -3,9 +3,10 @@ language: python
 python:
     - 2.6
     - 2.7
+    - 3.4
 
 install:
-    - pip install -r requirements.txt --use-mirrors
+    - pip install jieba
     - python setup.py install
 
 script: python setup.py test

goose/__init__.py

@@ -21,7 +21,6 @@
 limitations under the License.
 """
 import os
-import platform
 from tempfile import mkstemp
 
 from goose.version import version_info, __version__
@@ -64,9 +63,12 @@ def crawl(self, crawl_candiate):
         try:
             crawler = Crawler(self.config)
             article = crawler.crawl(crawl_candiate)
-        except (UnicodeDecodeError, ValueError):
-            self.config.parser_class = parsers[0]
-            return self.crawl(crawl_candiate)
+        except (UnicodeDecodeError, ValueError) as e:
+            if parsers:
+                self.config.parser_class = parsers[0]
+                return self.crawl(crawl_candiate)
+            else:
+                raise e
         return article
 
     def initialize(self):

goose/cleaners.py

@@ -20,6 +20,8 @@
 See the License for the specific language governing permissions and
 limitations under the License.
 """
+from __future__ import unicode_literals
+
 from goose.utils import ReplaceSequence
 
 

goose/configuration.py

@@ -22,6 +22,9 @@
 """
 import os
 import tempfile
+
+import six
+
 from goose.text import StopWords
 from goose.parsers import Parser
 from goose.parsers import ParserSoup
@@ -30,10 +33,12 @@
 HTTP_DEFAULT_TIMEOUT = 30
 
 AVAILABLE_PARSERS = {
-    'lxml': Parser,
-    'soup': ParserSoup,
+    'lxml': Parser
 }
 
+if six.PY2:
+    AVAILABLE_PARSERS['soup'] = ParserSoup
+
 
 class Configuration(object):
 

goose/extractors/content.py

@@ -260,7 +260,7 @@ def update_score(self, node, addToScore):
         if score_string:
             current_score = int(score_string)
 
-        new_score = current_score + addToScore
+        new_score = current_score + int(addToScore)
         self.parser.setAttribute(node, "gravityScore", str(new_score))
 
     def update_node_count(self, node, add_to_count):

goose/extractors/images.py

@@ -23,7 +23,7 @@
 import re
 import os
 
-from urlparse import urlparse, urljoin
+from six.moves.urllib.parse import urlparse, urljoin
 
 from goose.extractors import BaseExtractor
 from goose.image import Image

goose/extractors/metas.py

@@ -22,8 +22,8 @@
 """
 
 import re
-from urlparse import urljoin
-from urlparse import urlparse
+
+from six.moves.urllib.parse import urlparse, urljoin
 
 from goose.extractors import BaseExtractor
 

goose/image.py

@@ -46,7 +46,7 @@ def __init__(self):
         self.extraction_type = "NA"
 
         # stores how many bytes this image is.
-        self.bytes = long(0)
+        self.bytes = 0
 
     def get_src(self):
         return self.src
@@ -87,7 +87,7 @@ def set_mime_type(self, mime_type):
 class LocallyStoredImage(object):
 
     def __init__(self, src='', local_filename='',
-        link_hash='', bytes=long(0), file_extension='', height=0, width=0):
+                 link_hash='', bytes=0, file_extension='', height=0, width=0):
         self.src = src
         self.local_filename = local_filename
         self.link_hash = link_hash

goose/network.py

@@ -20,7 +20,12 @@
 See the License for the specific language governing permissions and
 limitations under the License.
 """
-import urllib2
+import six
+
+try:
+    from urllib2 import urlopen, Request
+except ImportError:
+    from urllib.request import urlopen, Request
 
 
 class HtmlFetcher(object):
@@ -39,18 +44,14 @@ def get_url(self):
 
     def get_html(self, url):
         # utf-8 encode unicode url
-        if isinstance(url, unicode):
+        if isinstance(url, six.text_type) and six.PY2:
             url = url.encode('utf-8')
 
         # set request
-        self.request = urllib2.Request(
-                        url,
-                        headers=self.headers)
+        self.request = Request(url, headers=self.headers)
         # do request
         try:
-            self.result = urllib2.urlopen(
-                            self.request,
-                            timeout=self.config.http_timeout)
+            self.result = urlopen(self.request, timeout=self.config.http_timeout)
         except Exception:
             self.result = None
 

goose/outputformatters.py

@@ -20,7 +20,8 @@
 See the License for the specific language governing permissions and
 limitations under the License.
 """
-from HTMLParser import HTMLParser
+from six.moves.html_parser import HTMLParser
+
 from goose.text import innerTrim