Fix standard search method. Results where "li" tags and now they are "div" tags.

Author: abenassi

.gitignore

@@ -71,3 +71,4 @@ target/
 *.egg-info
 *.dmp
 *.zip
+.DS_Store

google/.DS_Store

@@ -14,10 +14,15 @@ def __init__(self):
         self.value = None  # Result value (eg. 157300.0)
         self.from_value = None  # Initial value (eg. 157.3)
         self.unit = None  # Result unit (eg. u'grams') (NOT implemented yet)
-        self.from_unit = None  # Initial unit (eg. u'kilograms') (NOT implemented yet)
-        self.expr = None  # Initial expression (eg. u'157.3 grams') (NOT implemented yet)
-        self.result = None  # Result expression  (eg. u'157300 kilograms') (NOT implemented yet)
-        self.fullstring = None  # Complete expression (eg. u'157.3 kilograms = 157300 grams') (NOT implemented yet)
+        # Initial unit (eg. u'kilograms') (NOT implemented yet)
+        self.from_unit = None
+        # Initial expression (eg. u'157.3 grams') (NOT implemented yet)
+        self.expr = None
+        # Result expression  (eg. u'157300 kilograms') (NOT implemented yet)
+        self.result = None
+        # Complete expression (eg. u'157.3 kilograms = 157300 grams') (NOT
+        # implemented yet)
+        self.fullstring = None
 
     def __repr__(self):
         return unidecode(self.value)

google/modules/calculator.py

@@ -62,10 +62,10 @@ def search(query, pages=1, lang='en', void=True):
 
         if html:
             soup = BeautifulSoup(html, "html.parser")
-            lis = soup.findAll("li", attrs={"class": "g"})
-            
+            divs = soup.findAll("div", attrs={"class": "g"})
+
             j = 0
-            for li in lis:
+            for li in divs:
                 res = GoogleResult()
 
                 res.page = i
@@ -90,7 +90,7 @@ def search(query, pages=1, lang='en', void=True):
 def _get_name(li):
     """Return the name of a google search."""
     a = li.find("a")
-    #return a.text.encode("utf-8").strip()
+    # return a.text.encode("utf-8").strip()
     if a is not None:
         return a.text.strip()
     return None
@@ -136,7 +136,7 @@ def _get_description(li):
     if sdiv:
         stspan = sdiv.find("span", attrs={"class": "st"})
         if stspan is not None:
-        #return stspan.text.encode("utf-8").strip()
+            # return stspan.text.encode("utf-8").strip()
             return stspan.text.strip()
     else:
         return None

google/modules/standard_search.py

@@ -4,7 +4,7 @@
 from selenium import webdriver
 import urllib2
 from functools import wraps
-#import requests
+# import requests
 from urllib import urlencode
 
 

google/modules/utils.py

@@ -4,6 +4,9 @@
 from google import currency, images
 from mock import Mock
 import os
+import vcr
+
+BASE_DIR = os.path.dirname(__file__)
 
 
 def load_html_file(path):
@@ -26,6 +29,11 @@ def test_decorated(self):
     return test_decorator
 
 
+# HELPERS
+def get_dir_vcr(name):
+    return os.path.join(BASE_DIR, "vcr_cassetes", name)
+
+
 class GoogleTest(unittest.TestCase):
 
     @load_html_file("html_files")
@@ -85,14 +93,11 @@ def test_convert_currency(self, html_f):
         euros = google.convert_currency(5.0, "USD", "EUR")
         self.assertGreater(euros, 0.0)
 
-    @load_html_file("html_files")
-    def test_standard_search(self, html_f):
+    # @load_html_file("html_files")
+    @vcr.use_cassette("test_standard_search.yaml")
+    def test_standard_search(self):
         """Test method to search in google."""
 
-        # replace method to get html from a test html file
-        google.standard_search.get_html = \
-            Mock(return_value=html_f.read().decode('utf8'))
-
         search = google.search("github")
         self.assertNotEqual(len(search), 0)
 
@@ -150,15 +155,17 @@ def test_get_images_req_url(self):
 
     def test_repr(self):
         res = images.ImageResult()
-        assert repr(res) == 'ImageResult(index=None, page=None, domain=None, link=None)'
+        assert repr(
+            res) == 'ImageResult(index=None, page=None, domain=None, link=None)'
         res.page = 1
         res.index = 11
         res.name = 'test'
         res.thumb = 'test'
         res.format = 'test'
         res.domain = 'test'
         res.link = 'http://aa.com'
-        assert repr(res) == 'ImageResult(index=11, page=1, domain=test, link=http://aa.com)'
+        assert repr(
+            res) == 'ImageResult(index=11, page=1, domain=test, link=http://aa.com)'
 
     def test_download(self):
         pass

google/tests/test_google.py

@@ -0,0 +1,25 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+
+"""Tests helper methods."""
+
+from __future__ import unicode_literals
+from __future__ import print_function
+from __future__ import with_statement
+import unittest
+import nose
+
+from google.modules.utils import _get_search_url
+
+
+class UtilsTestCase(unittest.TestCase):
+    """Tests for helper methods."""
+
+    def test_get_search_url(self):
+        url = _get_search_url("apple", 0, 10, "en")
+        exp_url = "http://www.google.com/search?q=apple&start=0&num=10&nl=en"
+        self.assertEqual(url, exp_url)
+
+
+if __name__ == '__main__':
+    nose.run(defaultTest=__name__)