Python抓取JSON比较文件

Question

Here is my python code, it searchs the webpage two times for getting product details and save data in .json files. It should check if the key in the new file changes and print what changed, but i'm getting the following error.

Error :

 Traceback (most recent call last):
    File "x.py", line 84, in <module>
    compare()
    File "x.py", line 76, in compare
    for key in b.keys():
    AttributeError: 'NoneType' object has no attribute 'keys'

Code:

#!/usr/bin/env python
# -*- coding: utf-8 -*-
import cfscrape
import requests
from bs4 import BeautifulSoup as bs
import re
from pprint import pprint
import json

s = requests.Session()
s = cfscrape.create_scraper()

products = []
products1 = []

def x():
    r = s.get("https://www.oneblockdown.it/it/calzature-sneakers", headers={"User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_11_2) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/48.0.2564.103 Safari/537.36"})
    soup = bs(r.content, "html.parser")

    js = [x.text for x in soup.find_all('script', {'type': 'text/javascript'}) if "var preloadedItems =" in x.text][0]
    js = js.replace('var preloadedItems = ', '')
    js = js[:js.find("}];")]+"}]".strip()
    data = json.loads(js)
    for product in data:
        product_id = product["id"]
        product_title = product["title"]
        product_link = product["permalink"]
        product_price = product["displayPrice"]
        product_available = product["isAvailable"]
        product_size = product["attributes"]
        products.append({
            "product_id": product_id,
            "product_title": product_title,
            "product_link": product_link,
            "product_price": product_price,
            "product_available": product_available,
            "product_size": product_size
        })

    with open('data.json', 'w') as f:
        json.dump(products, f, indent = 4)
        f.close()

def y():
    r1 = s.get("https://www.oneblockdown.it/it/calzature-sneakers", 
    headers={"User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_11_2) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/48.0.2564.103 Safari/537.36"})
    soup = bs(r1.content, "html.parser")

    js = [x.text for x in soup.find_all('script', {'type': 'text/javascript'}) if "var preloadedItems =" in x.text][0]
    js = js.replace('var preloadedItems = ', '')
    js = js[:js.find("}];")]+"}]".strip()
    data1 = json.loads(js)
    for product in data1:
        product_id = product["id"]
        product_title = product["title"]
        product_link = product["permalink"]
        product_price = product["displayPrice"]
        product_available = product["isAvailable"]
        product_size = product["attributes"]
        products1.append({
            "product_id": product_id,
            "product_title": product_title,
            "product_link": product_link,
            "product_price": product_price,
            "product_available": product_available,
            "product_size": product_size
        })

    with open('data1.json', 'w') as f:
        json.dump(products, f, indent = 4)
        f.close()


def compare():
    while True:
        a = x()
        b = y()
        for key in b.keys():
            value = b[key]
            if key not in a:
                print(key, value)
            else:
                if a[key] != value:
                    print("for key {} values are different".format(key))

compare()

I've choose this method but i don't know if there is a better one for this purpose.

Answer 1

You are not returning anything from x() and y() methods. Hence, a and b are of the type None .

Most likely you would want to remove the products list from x() and y() , so add a return statement in the method.

Like:

return products