(feat): Refactored code for python3 compatibility

articleDateExtractor/__init__.py

@@ -1,6 +1,7 @@
 __author__ = 'Ran Geva'
 
-import urllib2,re, json
+from six.moves import urllib
+import re, json
 from dateutil.parser import parse
 try:
     from bs4 import BeautifulSoup
@@ -38,16 +39,16 @@ def _extractFromLDJson(parsedHTML):
 
         try:
             jsonDate = parseStrDate(data['datePublished'])
-        except Exception, e:
+        except Exception as e:
             pass
 
         try:
             jsonDate = parseStrDate(data['dateCreated'])
-        except Exception, e:
+        except Exception as e:
             pass
 
 
-    except Exception, e:
+    except Exception as e:
         return None
 
 
@@ -205,18 +206,18 @@ def _extractFromHTMLTag(parsedHTML):
 
 def extractArticlePublishedDate(articleLink, html = None):
 
-    print "Extracting date from " + articleLink
+    print("Extracting date from " + articleLink)
 
     articleDate = None
 
     try:
         articleDate = _extractFromURL(articleLink)
 
         if html is None:
-            request = urllib2.Request(articleLink)
+            request = urllib.request.Request(articleLink)
             # Using a browser user agent, decreases the change of sites blocking this request - just a suggestion
             # request.add_header('User-Agent', 'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/41.0.2228.0 Safari/537.36')
-            html = urllib2.build_opener().open(request).read()
+            html = urllib.request.build_opener().open(request).read()
 
         parsedHTML = BeautifulSoup(html,"lxml")
 
@@ -230,8 +231,8 @@ def extractArticlePublishedDate(articleLink, html = None):
         articleDate = possibleDate
 
     except Exception as e:
-        print "Exception in extractArticlePublishedDate for " + articleLink
-        print e.message, e.args
+        print("Exception in extractArticlePublishedDate for " + articleLink)
+        print(e.message, e.args)
 
 
 
@@ -242,4 +243,4 @@ def extractArticlePublishedDate(articleLink, html = None):
 
 if __name__ == '__main__':
     d = extractArticlePublishedDate("http://techcrunch.com/2015/11/30/atlassian-share-price/")
-    print d
+    print(d)

setup.py

@@ -1,12 +1,8 @@
-from codecs import open
-
 try:
     from setuptools import setup
 except ImportError:
     from distutils.core import setup
 
-with open('README.md', 'r', 'utf-8') as f:
-    readme = f.read()
 
 setup(
     name='articleDateExtractor',
@@ -17,18 +13,17 @@
     url='https://github.com/Webhose/article-date-extractor',
     license='MIT',
     description='Automatically extracts and normalizes an online article or blog post publication date',
-    long_description=readme,
     install_requires=[
-        "BeautifulSoup >= 3.2.1",
-        "python-dateutil >= 2.4.2"
+        "beautifulsoup4>=4.5.3",
+        "python-dateutil>=2.6.0",
+        "six>=1.10.0"
     ],
     classifiers=(
         'Development Status :: 4 - Beta',
         'Intended Audience :: Developers',
         'Natural Language :: English',
         'License :: OSI Approved :: MIT License',
         'Programming Language :: Python',
-        'Programming Language :: Python :: 2.6',
-        'Programming Language :: Python :: 2.7'
+        'Programming Language :: Python :: 3.5'
         )
-)
+)