Dekker1/Fourmi
Archived
1
0
Fork 0
Code

added scraping of synonyms labeled as 'synonym_cn'

Browse Source
This commit is contained in:
RTB 2014-04-18 13:36:33 +02:00
parent a4a21f2578
commit bf4a5bb41f
1 changed files with 3 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
FourmiCrawler/parsers/ChemSpider.py
View File

@ -74,6 +74,9 @@ class ChemSpider(Parser):
def parse_synonyms(self, sel):
requests = []
synonyms = []
for syn in sel.xpath('//p[@class="syn"][span[@class="synonym_cn"]]'):
name = syn.xpath('span[@class="synonym_cn"]/text()').extract()[0]
synonyms.append(self.new_synonym(syn, name, 'expert'))
for syn in sel.xpath('//p[@class="syn"][strong]'):
name = syn.xpath('strong/text()').extract()[0]
synonyms.append(self.new_synonym(syn, name, 'expert'))