Dekker1/Fourmi
Archived
1
0
Fork 0
Code

regex

Browse Source
This commit is contained in:
Bas Vb 2014-04-16 17:01:35 +02:00
parent 873231439c
commit be63315ca2
1 changed files with 4 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
FourmiCrawler/parsers/WikipediaParser.py
View File

@ -2,6 +2,7 @@ from scrapy.http import Request
from parser import Parser from parser import Parser
from scrapy.selector import Selector from scrapy.selector import Selector
from FourmiCrawler.items import Result from FourmiCrawler.items import Result
import re
class WikipediaParser(Parser): class WikipediaParser(Parser):
@ -45,7 +46,9 @@ class WikipediaParser(Parser):
def cleanitems(self, items): def cleanitems(self, items):
for item in items: for item in items:
print item['value'] value=item['value']
if re.match('3(...)', value):
print value
return items return items
def getboilingpoint(self, sel): def getboilingpoint(self, sel):