while True:
print ("test")
sleep(3)
try:
doc = html.fromstring(page.content)
XPATH_NAME = '//h1[@id="title"]//text()'
XPATH_SALE_PRICE = '//span[contains(@id,"priceblock_ourprice") or contains(@id,"saleprice")]/text()'
XPATH_ORIGINAL_PRICE = '//td[contains(text(),"List Price") or contains(text(),"M.R.P") or contains(text(),"Price")]/following-sibling::td/text()'
XPATH_CATEGORY = '//a[@class="a-link-normal a-color-tertiary"]//text()'
XPATH_AVAILABILITY = '//div[@id="availability"]//text()'
RAW_NAME = doc.xpath(XPATH_NAME)
RAW_SALE_PRICE = doc.xpath(XPATH_SALE_PRICE)
RAW_CATEGORY = doc.xpath(XPATH_CATEGORY)
RAW_ORIGINAL_PRICE = doc.xpath(XPATH_ORIGINAL_PRICE)
RAw_AVAILABILITY = doc.xpath(XPATH_AVAILABILITY)
print(RAW_SALE_PRICE)
NAME = ' '.join(''.join(RAW_NAME).split()) if RAW_NAME else None
SALE_PRICE = ' '.join(''.join(RAW_SALE_PRICE).split()).strip() if RAW_SALE_PRICE else None
CATEGORY = ' > '.join([i.strip() for i in RAW_CATEGORY]) if RAW_CATEGORY else None
ORIGINAL_PRICE = ''.join(RAW_ORIGINAL_PRICE).strip() if RAW_ORIGINAL_PRICE else None
AVAILABILITY = ''.join(RAw_AVAILABILITY).strip() if RAw_AVAILABILITY else None
print(SALE_PRICE)
if not ORIGINAL_PRICE:
ORIGINAL_PRICE = SALE_PRICE
data = {
'NAME': NAME,
'SALE_PRICE': SALE_PRICE,
'CATEGORY': CATEGORY,
'ORIGINAL_PRICE': ORIGINAL_PRICE,
'AVAILABILITY': AVAILABILITY,
'URL': url,
}
return data
except Exception as e:
print
e
这很好用。但是当我插入
if SALE_PRICE.startswith('EUR'):
SALE_PRICE = SALE_PRICE.replace('EUR ', '')
在Lins上,我将RAW变量剥离为普通变量(NAME,SALE_PRICE)之后,我将以infitine循环结尾-为什么?
答案 0 :(得分:0)
查看行:
DateTime
在此可以为SALE_PRICE分配一个DateTimeOffsets
值。
添加行时,有时会尝试对None值执行SALE_PRICE = ' '.join(''.join(RAW_SALE_PRICE).split()).strip() if RAW_SALE_PRICE else None
。这将导致异常。在您的exception子句中,您不会中断循环,它将永远持续下去。
在您的例外条款中添加None
或.startswith
。
答案 1 :(得分:0)
在try循环之外进行try catch块,换句话说,将其嵌套在try中,诸如此类
try:
while(true):
#All your code
except Exception as e:
print e