Dekker1/Fourmi
Archived
1
0
Fork 0
Code

Parse is runnable now.

Browse Source
This commit is contained in:
Bas Vb 2014-04-08 14:59:09 +02:00
parent e10ac12d04
commit f9799c30d8
1 changed files with 4 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
FourmiCrawler/parsers/WikipediaParser.py
View File

@ -8,20 +8,18 @@ class WikipediaParser(Parser):
website = "http://en.wikipedia.org/wiki/*" website = "http://en.wikipedia.org/wiki/*"
__spider = None __spider = None
print "test1"
#def __init__(self, csid): #def __init__(self, csid):
# self.website = "http://en.wikipedia.org/wiki/{id}".format(id=csid) # self.website = "http://en.wikipedia.org/wiki/{id}".format(id=csid)
def parse(self, response): def parse(self, response):
print "test1" print response.url
#self.log('A response from %s just arrived!' % response.url) #self.log('A response from %s just arrived!' % response.url)
#def parse(): sel = Selector(response)
sel = Selector("http://en.wikipedia.org/wiki/Methane")
items = [] items = []
item = Result() item = Result()
item['attribute']="Melting point" item['attribute']="Melting point"
item['value']=site.xpath('//tr[contains(@href, "/wiki/Melting_point")]/text()').extract() item['value']="value1" # sel.xpath('//tr[contains(@href, "/wiki/Melting_point")]/text()').extract()
item['source']= self.website item['source']= "Wikipedia"
items.append(item) items.append(item)
print item['attribute'] print item['attribute']
print item['value'] print item['value']