Dekker1/Fourmi
Archived
1
0
Fork 0
Code

minor edits (comments etc.)

Browse Source
This commit is contained in:
Bas Vb 2014-04-16 15:27:36 +02:00
parent 34c3a8b4d6
commit 74aa446f40
1 changed files with 3 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
FourmiCrawler/parsers/WikipediaParser.py
View File

@ -33,13 +33,12 @@ class WikipediaParser(Parser):
item['value'] = prop_values[i].extract().encode('utf-8') item['value'] = prop_values[i].extract().encode('utf-8')
item['source'] = "Wikipedia" item['source'] = "Wikipedia"
items.append(item) items.append(item)
#print "new: " + item['attribute'] print "new: " + item['attribute']
#print item['value'] print item['value']
items=filter(lambda a: a['value']!='', items) items=filter(lambda a: a['value']!='', items) #remove items with an empty value
print items print items
return items return items
def new_compound_request(self, compound): def new_compound_request(self, compound):
return Request(url=self.website[:-1] + compound, callback=self.parse) return Request(url=self.website[:-1] + compound, callback=self.parse)