Dekker1/Fourmi
Archived
1
0
Fork 0
Code

Parse is runnable now.

Browse Source
This commit is contained in:
Bas Vb 2014-04-16 00:35:19 +02:00
parent 91ed053ac5
commit 1ca3593ae1
1 changed files with 8 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
FourmiCrawler/parsers/WikipediaParser.py
View File

@ -18,14 +18,20 @@ class WikipediaParser(Parser):
items = [] items = []
item = Result() item = Result()
item['attribute']="Melting point" item['attribute']="Melting point"
item['value']="value1" # sel.xpath('//tr[contains(@href, "/wiki/Melting_point")]/text()').extract() item['value']= sel.xpath('//tr/td/a[@title="Melting point"]/../../td[2]/text()').extract() # ('//tr[contains(@href, "/wiki/Melting_point")]/text()').extract()
item['source']= "Wikipedia" item['source']= "Wikipedia"
items.append(item) items.append(item)
print item['attribute'] print item['attribute']
print item['value'] print item['value']
print item['source'] print item['source']
print "test"
return items return items
def getmeltingpoint(self, sel):
item=Result()
item['attribute']="Melting point"
item['value']= sel.xpath('//tr/td/a[@title="Melting point"]/../../td[2]/text()').extract() # ('//tr[contains(@href, "/wiki/Melting_point")]/text()').extract()
item['source']= "Wikipedia"
return item
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)