Merge branch 'release/0.3.1'

FourmiCrawler/pipelines.py

@@ -5,6 +5,22 @@
 import re
 from scrapy.exceptions import DropItem
 
+class RemoveNonePipeline(object):
+
+    def __init__(self):
+        self.known_values = set()
+
+    def process_item(self, item, spider):
+        """
+        Processing the items so None values are replaced by empty strings
+        :param item: The incoming item
+        :param spider: The spider which scraped the spider
+        :return: :raise DropItem: Returns the item if unique or drops them if it's already known
+        """
+        for key in item:
+            if item[key] is None:
+                item[key] = ""
+        return item
 
 class DuplicatePipeline(object):
 

FourmiCrawler/settings.py

@@ -11,8 +11,9 @@ BOT_NAME = 'FourmiCrawler'
 SPIDER_MODULES = ['FourmiCrawler']
 NEWSPIDER_MODULE = 'FourmiCrawler'
 ITEM_PIPELINES = {
-    'FourmiCrawler.pipelines.AttributeSelectionPipeline': 100,
-    'FourmiCrawler.pipelines.DuplicatePipeline': 200,
+    "FourmiCrawler.pipelines.RemoveNonePipeline": 100,
+    'FourmiCrawler.pipelines.AttributeSelectionPipeline': 200,
+    'FourmiCrawler.pipelines.DuplicatePipeline': 300,
 }
 FEED_URI = 'results.json'
 FEED_FORMAT = 'jsonlines'

fourmi.py

@@ -80,7 +80,7 @@ def search(docopt_arguments, source_loader):
 
 
 if __name__ == '__main__':
-    arguments = docopt.docopt(__doc__, version='Fourmi - V0.3.0')
+    arguments = docopt.docopt(__doc__, version='Fourmi - V0.3.1')
     loader = SourceLoader()
 
     if arguments["--include"]: