Dekker1/Fourmi
Archived
1
0
Fork 0
Code

Able to parse the weblinks to other databases, one example done

Browse Source
This commit is contained in:
Bas Vb 2014-04-16 10:37:57 +02:00
parent cd1637b0fe
commit d778050f36
1 changed files with 6 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
FourmiCrawler/parsers/WikipediaParser.py
View File

@ -23,7 +23,7 @@ class WikipediaParser(Parser):
meltingpoint = self.getmeltingpoint(sel) meltingpoint = self.getmeltingpoint(sel)
items.append(meltingpoint) items.append(meltingpoint)
boilingpoint = self.getboilingpoint(sel) boilingpoint = self.getboilingpoint(sel)
print boilingpoint chemlink = self.getchemspider(sel)
items.append(boilingpoint) items.append(boilingpoint)
return items return items
@ -42,4 +42,9 @@ class WikipediaParser(Parser):
item['attribute']="Boiling point" item['attribute']="Boiling point"
item['value']= sel.xpath('//tr/td/a[@title="Boiling point"]/../../td[2]/text()').extract() # ('//tr[contains(@href, "/wiki/Melting_point")]/text()').extract() item['value']= sel.xpath('//tr/td/a[@title="Boiling point"]/../../td[2]/text()').extract() # ('//tr[contains(@href, "/wiki/Melting_point")]/text()').extract()
item['source']= "Wikipedia" item['source']= "Wikipedia"
return item
def getchemspider(self, sel):
item=sel.xpath('//tr/td/a[@title="ChemSpider"]/../../td[2]/span/a/@href').extract() # ('//tr[contains(@href, "/wiki/Melting_point")]/text()').extract()
print item
return item return item