from BeautifulSoup import BeautifulSoup
import mechanize
import re
def price_walmart_match(keyword):
url = "http://www.walmart.com/search/?query="+keyword
br = mechanize.Browser()
br.set_handle_robots(False)
br.open(url)
html = br.response().read()
result_soup = BeautifulSoup(html)
found_results = result_soup.findAll('div' , attrs={'class':'js-tile tile-landscape'})
all_results=[]
for result in found_results:
title = result.find('a' , attrs={'class':'js-product-title'})
links = result.find('a' , href=True)
before_decimal= str(result.find('span', attrs={'class':'price price-display'})).split('<span class="sup">$</span>')[1].split('<span class="visuallyhidden">')[0]
after_decimal= str(result.find('span', attrs={'class':'price price-display'})).split('</span><span class="sup">')[1].split('</span>')[0]
prices = before_decimal+'.'+after_decimal
inArray = [float(prices), "http://www.walmart.com"+links['href']]
all_results.append(inArray)
print(all_result)
很抱歉,这是完整代码,我收到错误。
答案 0 :(得分:0)
那是因为页面中提到的课程不。 尝试表示常量的查询字词。