CODEWITHSUNDEEP
python
ILAR
ILAR

Reputation: 13

Error TypeError: 'NoneType' object is not iterab

def parse():
    html = get_html(URL)
    if html.status_code == 200:
        phones = []
        pages_count = pages(html.text)
        for page in range(1, pages_count + 1):
            print(f'Parsing a page {page} from {pages_count}...')
            html = get_html(URL, params={'p': page})
            phones.extend(get_content(html.text))
        print(phones)
    else:
        print('Error')

Hi, I want to list items, but I get an error

  File "C:/Users/User/PycharmProjects/Parser/parser.py", line 52, in <module>
    parse()
  File "C:/Users/User/PycharmProjects/Parser/parser.py", line 46, in parse
    phones.extend(get_content(html.text))
TypeError: 'NoneType' object is not iterab

This is all the code:

import requests
from bs4 import BeautifulSoup

URL = 'https://comfy.ua/smartfon/'
HEADERS = {'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:71.0) Gecko/20100101 Firefox/71.0',
           'accept': '*/*'}


def get_html(url, params=None):
    r = requests.get(url, headers=HEADERS, params=params)
    return r


def pages(html):
    soup = BeautifulSoup(html, 'html.parser')
    pagination = soup.find_all('li', class_='pager__number')
    if pagination:
        return int(pagination[-2].get_text())
    else:
        return 1


def get_content(html):
    soup = BeautifulSoup(html, 'html.parser')
    items = soup.find_all('div', class_="product-item__i")

    phone = []
    for item in items:
        phone.append({
            'title': item.find('p', class_="product-item__name").get_text(strip=True),
            'link': item.find('a', class_="product-item__name-link js-gtm-product-title").get('href'),
            'price': item.find('div', class_="price-box__content-i").get_text(strip=True).replace(u'\xa0', u' ')
        })
    print(phone)


def parse():
    html = get_html(URL)
    if html.status_code == 200:
        phones = []
        pages_count = pages(html.text)
        for page in range(1, pages_count + 1):
            print(f'Parsing a page {page} from {pages_count}...')
            html = get_html(URL, params={'p': page})
            phones.extend(get_content(html.text))
        print(phones)
    else:
        print('Error')


parse()

I get an empty list, but should get the phones. Also i get an error.

Upvotes: 0

Views: 40

Answers (1)

Arthur Tacca
Arthur Tacca

Reputation: 9978

phones.extend(get_content(html.text))
TypeError: 'NoneType' object is not iterab

This error is telling you that you're trying to iterate over None. Since extend() takes an iterable, this is therefore telling you that get_content() is returning None. This often happens when a function returns nothing at all: no return statement is equivalent to return None in Python.

Sure enough, your code for get_content() doesn't have a return statement. You need to add it:

def get_content(html):
    soup = BeautifulSoup(html, 'html.parser')
    items = soup.find_all('div', class_="product-item__i")

    phone = []
    for item in items:
        phone.append({
            'title': item.find('p', class_="product-item__name").get_text(strip=True),
            'link': item.find('a', class_="product-item__name-link js-gtm-product-title").get('href'),
            'price': item.find('div', class_="price-box__content-i").get_text(strip=True).replace(u'\xa0', u' ')
        })
    print(phone)
    return phone  #   <--- add this

Upvotes: 1

Related Questions