Dekker1/Fourmi
Archived
1
0
Fork 0
Code

added comment to parse_searchrequest and added optional todo for extract()[0] usage

Browse Source
This commit is contained in:
RTB 2014-04-18 17:33:00 +02:00
parent 3c5dbc44dc
commit 63fb9f4733
1 changed files with 4 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
FourmiCrawler/parsers/ChemSpider.py
View File

@ -5,6 +5,9 @@ from scrapy.selector import Selector
from FourmiCrawler.items import Result from FourmiCrawler.items import Result
import re import re
# TODO: Maybe clean up usage of '.extract()[0]', because it will raise an
# IndexError exception if the xpath matches nothing
class ChemSpider(Parser): class ChemSpider(Parser):
"""ChemSpider scraper for synonyms and properties """ChemSpider scraper for synonyms and properties
@ -187,6 +190,7 @@ somewhere.
return properties return properties
def parse_searchrequest(self, response): def parse_searchrequest(self, response):
"""Parse the initial response of the ChemSpider Search API """
sel = Selector(response) sel = Selector(response)
log.msg('chemspider parse_searchrequest', level=log.DEBUG) log.msg('chemspider parse_searchrequest', level=log.DEBUG)
sel.register_namespace('cs', 'http://www.chemspider.com/') sel.register_namespace('cs', 'http://www.chemspider.com/')