Dekker1/Fourmi
Archived
1
0
Fork 0
Code

synonyms are now scraped

Browse Source
This commit is contained in:
RTB 2014-05-17 19:32:20 +02:00
parent b46c7a309d
commit 472aae86be
1 changed files with 6 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
FourmiCrawler/sources/NIST.py
View File

@ -79,6 +79,12 @@ class NIST(Source):
ul = sel.xpath('body/ul[li/strong="IUPAC Standard InChI:"]')
li = ul.xpath('li')
raw_synonyms = ul.xpath('li[strong="Other names:"]/text()').extract()
for synonym in raw_synonyms[0].strip().split(';\n'):
log.msg('NIST synonym: %s' % synonym, level=log.DEBUG)
self.ignore_list.update(synonym)
self._spider.get_synonym_requests(synonym)
data = {}
raw_formula = ul.xpath('li[strong/a="Formula"]//text()').extract()