Beispiel #1
0
from challenge import get_price
 
url = "http://hughes.sieve.com.br:9090/level1/"
xpath = "//div/text()"
print get_price(url, xpath)
Beispiel #2
0
from challenge import get_price
 
url = "http://hughes.sieve.com.br:9090/level2/"
xpath = "//div/text()"
print get_price(url, xpath, use_cookie=True)
Beispiel #3
0
from challenge import get_price
 

def get_yes_link(r):
    from lxml import html
    import requests
    xpath = "//a[contains(text(), 'Sim')]/@href"
    subpath = html.fromstring(r.text).xpath(xpath)[0]
    url = "http://hughes.sieve.com.br:9090%s" % subpath
    g = requests.get(url)
    # yes, i agree it's not elegant, =P
    # TODO: check how to treat response headers properly, e.g. Set-Cookie:18=+; Path=/
    return requests.get('http://hughes.sieve.com.br:9090/level3/', cookies=g.cookies).text


url = "http://hughes.sieve.com.br:9090/level3/"
xpath = "//p/text()"
print get_price(url, xpath, after_fetch=get_yes_link)
Beispiel #4
0
import challenge


urls = open('challenge.in', 'r+')
xpath = "//p[@class='sale price']//span[@class='amount']/text()"
unv_xpath = "//div[@class='unavailProd']"
for url in urls.readlines():
    url = url.strip()
    print "Getting price from [%s]" % url
    print challenge.get_price(url, xpath, unv_xpath)