V==0.8

parse_utils/page_parser.py

@@ -52,3 +52,25 @@ def extract_dict(self, config, item=None, is_list=None):
                     continue
 
         return _item
+
+    def extract_dict_from_json(self, config, item=None, is_list=None):
+        """
+        extracts json data
+        """
+        if not item:
+            _item = dict()
+        else:
+            _item = {** item }
+        for _k, _pathlist in config.items():
+            if _pathlist[0].__class__ != list:
+                _pathlist = [_pathlist]
+            for _paths in _pathlist:
+                tmp = self._selector
+                for _path in _paths:
+                    tmp = tmp.get(_path)
+                    if tmp is None:
+                        break
+                if tmp:
+                    _item[_k] = tmp
+                    break
+        return _item

setup.py

@@ -5,7 +5,7 @@
 
 setuptools.setup(
     name="parse-utils",
-    version="0.7",
+    version="0.9",
     author="Yogendra Tamang",
     author_email="48yogen@gmail.com",
     description="Page Parser Utils For scraping, List index update",

test.py

@@ -9,12 +9,39 @@
     </body>
 </html>
 '''
-config = {
-    'header': ['//p[@id="header"]/text()'],
-    'content': ['//p[@class="content"]'],
+json_data = {
+    'name': 'Yogendra',
+    'address': {
+        'country': 'Nepal',
+        'city': 'Pokhara',
+    }
 }
-pparser = PageParser(html_data)
-item = pparser.extract_dict(config)
-_item = pparser.extract_dict(config, is_list=True)
-print(item)
-print(_item)
+
+
+def test_html_parser():
+    '''
+    '''
+    config = {
+        'header': ['//p[@id="header"]/text()'],
+        'content': ['//p[@class="content"]'],
+    }
+    pparser = PageParser(html_data)
+    item = pparser.extract_dict(config)
+    _item = pparser.extract_dict(config, is_list=True)
+    print(item)
+    print(_item)
+
+def test_json_parser():
+    '''
+    '''
+    config = {
+        'header': ['name'],
+        'city': ['address', 'city'],
+    }
+    jparser = PageParser(json_data, selector=True)
+    item = jparser.extract_dict_from_json(config)
+    print(item)
+
+if __name__ == '__main__':
+    test_html_parser()
+    test_json_parser()