Dekker1/Fourmi
Archived
1
0
Fork 0
Code

Updated the wikipedia parser as an rightful subclass of Parser

Browse Source
This commit is contained in:
Jip J. Dekker 2014-04-08 11:40:30 +02:00
parent f3807c3018
commit 4b0c4acf96
1 changed files with 8 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
FourmiCrawler/parsers/WikipediaParser.py
View File

@ -1,11 +1,12 @@
import parser from scrapy.http import Request
from parser import Parser
from scrapy.selector import Selector from scrapy.selector import Selector
from FourmiCrawler.items import Result from FourmiCrawler.items import Result
class WikipediaParser: class WikipediaParser(Parser):
website = "http://en.wikipedia.org/wiki/Methane" website = "http://en.wikipedia.org/wiki/*"
__spider = "WikipediaParser" __spider = None
print "test1" print "test1"
#def __init__(self, csid): #def __init__(self, csid):
@ -27,3 +28,6 @@ class WikipediaParser:
print item['source'] print item['source']
print "test" print "test"
return items return items
def new_compound_request(self, compound):
return Request(url=self.website[:-1] + compound, callback=self.parse)