我用这个简短的脚本来检查亚马逊猫砂的价格,如果它低于9美元,请提醒我。它每六个小时检查一次。该脚本以9 MB的速度启动,但在几天内以某种方式爬升到16 MB。
from random import random
from requests import get
from time import sleep
from datetime import datetime
def ReadAsin():
def find_item(text, start, end):
start_index = text.index(start)
end_index = text[start_index + len(start):].index(end)
return text[start_index + len(start):][:end_index]
headers = {
'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/42.0.2311.90 Safari/537.36'}
AsinList = ['B001N02JXW','B01N9VEMP6']
# extracted_data = []
while True:
for i in AsinList:
url = "http://www.amazon.de/dp/"+i
# print("Processing: ",url)
r = get(url,headers=headers)
sleep(5 * random())
try:
title = ''
price = find_item(r.text, '<span id="priceblock_ourprice" class="a-size-medium a-color-price">EUR ', '</span>')
title = find_item(r.text, '<meta name="title" content=', 'Amazon.de')
except:
pass
else:
price = float(price.replace(',','.'))
if price < 9:
now = datetime.now()
print(now.strftime("%Y-%m-%d %H:%M:%S"),': ',title,'EUR',price)
sleep(60 * 60 * 6)
if __name__ == "__main__":
ReadAsin()