docs: Fix a few typos

goose/__init__.py

@@ -87,7 +87,7 @@ def initialize(self):
             )
 
         # test to write a dummy file to the directory
-        # to check is directory is writtable
+        # to check is directory is writable
         level, path = mkstemp(dir=self.config.local_storage_path)
         try:
             f = os.fdopen(level, "w")

goose/configuration.py

@@ -49,7 +49,7 @@ def __init__(self):
         # interface to build your own
         self.enable_image_fetching = True
 
-        # set this valriable to False if you want to force
+        # set this variable to False if you want to force
         # the article language. OtherWise it will attempt to
         # find meta language and use the correct stopwords dictionary
         self.use_meta_language = True

goose/extractors/content.py

@@ -149,7 +149,7 @@ def is_boostable(self, node):
         it should be connected to other paragraphs,
         at least for the first n paragraphs so we'll want to make sure that
         the next sibling is a paragraph and has at
-        least some substatial weight to it
+        least some substantial weight to it
         """
         para = "p"
         steps_away = 0
@@ -181,7 +181,7 @@ def walk_siblings(self, node):
 
     def add_siblings(self, top_node):
         # in case the extraction used known attributes
-        # we don't want to add sibilings
+        # we don't want to add siblings
         if self.is_articlebody(top_node):
             return top_node
         baselinescore_siblings_para = self.get_siblings_score(top_node)

goose/extractors/title.py

@@ -47,8 +47,8 @@ def clean_title(self, title):
             title = pattern.sub("", title).strip()
 
         # split the title in words
-        # TechCrunch | my wonderfull article
-        # my wonderfull article | TechCrunch
+        # TechCrunch | my wonderful article
+        # my wonderful article | TechCrunch
         title_words = title.split()
 
         # check for an empty title

goose/text.py

@@ -137,7 +137,7 @@ class StopWordsChinese(StopWords):
     Chinese segmentation
     """
     def __init__(self, language='zh'):
-        # force zh languahe code
+        # force zh language code
         super(StopWordsChinese, self).__init__(language='zh')
 
     def candiate_words(self, stripped_input):
@@ -153,7 +153,7 @@ class StopWordsArabic(StopWords):
     Arabic segmentation
     """
     def __init__(self, language='ar'):
-        # force ar languahe code
+        # force ar language code
         super(StopWordsArabic, self).__init__(language='ar')
 
     def remove_punctuation(self, content):

tests/extractors/images.py

@@ -204,12 +204,12 @@ def test_detail(self):
         for k, v in self.expected_results.items():
             self.assertEqual(getattr(image_detail, k), v)
 
-        # test image_detail get_ methode
+        # test image_detail get_ method
         for k, v in self.expected_results.items():
             attr = 'get_%s' % k
             self.assertEqual(getattr(image_detail, attr)(), v)
 
-        # test image_detail set_ methode
+        # test image_detail set_ method
         expected_results = {
             'width': 10,
             'height': 10,