fixed flake8 issues

Author: Sumesh Murali

selectorlib/formatter.py

@@ -4,7 +4,8 @@ class Formatter:
     """
 
     def format(self, text: str):
-        """Override this function in inherited subclass. return text after formatting"""
+        """Override this function in inherited subclass.
+         return text after formatting"""
         return text
 
     @property

selectorlib/selectorlib.py

@@ -8,7 +8,9 @@
 
 def extract_field(element, item_type, attribute=None, formatter=None):
     if item_type == 'Text':
-        texts = [i.strip() for i in element.xpath('.//text()').getall() if i.strip()]
+        texts = [
+            i.strip() for i in element.xpath('.//text()').getall() if i.strip()
+        ]
         content = " ".join(texts)
     elif item_type == 'Link':
         content = element.xpath('.//@href').get()
@@ -68,7 +70,8 @@ def extract(self, html: str, base_url: str = None):
         """
         Args:
             html: html string
-            base_url (str, optional): specifying the base_url will make all extracted Links absolute
+            base_url (str, optional): specifying the base_url will make all
+             extracted Links absolute
         Returns:
             dict: extracted data from given html string
 
@@ -80,7 +83,9 @@ def extract(self, html: str, base_url: str = None):
             sel.root.make_links_absolute()
         fields_data = {}
         for selector_name, selector_config in self.config.items():
-            fields_data[selector_name] = self._extract_selector(selector_config, sel)
+            fields_data[selector_name] = self._extract_selector(
+                selector_config, sel
+            )
         return fields_data
 
     def _extract_selector(self, field_config, parent_parser):
@@ -105,7 +110,9 @@ def _extract_selector(self, field_config, parent_parser):
                 if 'attribute' in field_config:
                     kwargs['attribute'] = field_config['attribute']
                 if 'format' in field_config:
-                    kwargs['formatter'] = self.formatters[field_config['format']]
+                    kwargs['formatter'] = self.formatters[
+                        field_config['format']
+                    ]
                 value = extract_field(element, item_type, **kwargs)
 
             if field_config.get('multiple') is not True:
@@ -119,7 +126,10 @@ def _get_child_item(self, field_config, element):
         children_config = field_config['children']
         child_item = {}
         for field in children_config:
-            child_value = self._extract_selector(children_config[field], element)
+            child_value = self._extract_selector(
+                children_config[field],
+                element
+            )
             child_item[field] = child_value
         return child_item
 

setup.py

@@ -34,7 +34,8 @@
         'Programming Language :: Python :: 3.6',
         'Programming Language :: Python :: 3.7',
     ],
-    description="A library to read a YML file with Xpath or CSS Selectors and extract data from HTML pages using them",
+    description="A library to read a YML file with Xpath or CSS Selectors"
+                " and extract data from HTML pages using them",
     entry_points={
         'console_scripts': [
             'selectorlib=selectorlib.cli:main',

tests/test_selectorlib.py

@@ -65,7 +65,10 @@ def extract_field_test_html():
 def test_content(html, input_yaml, output_yaml):
     base_url = "https://scrapeme.live/shop/Bulbasaur/"
     formatters = formatter.Formatter.get_all()
-    extractor = selectorlib.Extractor.from_yaml_string(input_yaml, formatters=formatters)
+    extractor = selectorlib.Extractor.from_yaml_string(
+        input_yaml,
+        formatters=formatters
+    )
     output = extractor.extract(html, base_url=base_url)
     assert output == yaml.safe_load(output_yaml)
 
@@ -90,8 +93,13 @@ def test_empty_selector_in_children(
                "/B004K4CIKC/ref=sr_1_3?qid=1563864262&refinements=p_89:NIKE" \
                "&s=apparel&sr=1-3"
     formatters = formatter.Formatter.get_all()
-    extractor = selectorlib.Extractor.from_yaml_string(empty_selector_yaml, formatters=formatters)
-    output = extractor.extract(amazon_nike_product_page_html, base_url=base_url)
+    extractor = selectorlib.Extractor.from_yaml_string(
+        empty_selector_yaml, formatters=formatters
+    )
+    output = extractor.extract(
+        amazon_nike_product_page_html,
+        base_url=base_url
+    )
     assert output == json.loads(amazon_nike_product_page_output)