Hello all. I'm new to Python, but have been playing around with it for a few
weeks now, following tutorials, etc. I've spun off on my own and am trying to
do some basic web scraping. I've used Firebug/View XPath in Firefox for some
help with the XPaths, however, I still am receiving errors when I try to run
this script. If you could help, it would be greatly appreciated!
from scrapy.spider import BaseSpider
from scrapy.selector import HtmlXPathSelector
from cbb_info.items import CbbInfoItem, Field
class GameInfoSpider(BaseSpider):
name = "game_info"
allowed_domains = ["www.sbrforum.com"]
start_urls = [
'http://www.sbrforum.com/betting-odds/ncaa-basketball/',
]
def parse(self, response):
hxs = HtmlXPathSelector(response)
toplevels = hxs.select("//div[@class='eventLine-value']")
items = []
for toplevels in toplevels:
item = CbbInfoItem()
item ["teams"] =
toplevels.select("/span[@class='team-name'/text()").extract()
item ["lines"] = toplevels.select("/div[@rel='19']").extract()
item.append(item)
return items
--
http://mail.python.org/mailman/listinfo/python-list
