错误 TypeError: 'NoneType' object is not iterab

Question

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')

嗨，我想列出项目，但出现错误

  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

这是所有代码：

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)

我得到一个空列表，但应该拿到电话。我也收到一个错误。

Answer 1

phones.extend(get_content(html.text))TypeError: 'NoneType' object is not iterab此错误告诉您您正在尝试迭代None. 由于extend()需要一个可迭代对象，因此这告诉您get_content()正在返回None。当函数什么都不返回时经常会发生这种情况：没有 return 语句等同于return NonePython。果然，您的代码get_content()没有返回语句。您需要添加它：def get_content(html):&nbsp; &nbsp; soup = BeautifulSoup(html, 'html.parser')&nbsp; &nbsp; items = soup.find_all('div', class_="product-item__i")&nbsp; &nbsp; phone = []&nbsp; &nbsp; for item in items:&nbsp; &nbsp; &nbsp; &nbsp; phone.append({&nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; 'title': item.find('p', class_="product-item__name").get_text(strip=True),&nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; 'link': item.find('a', class_="product-item__name-link js-gtm-product-title").get('href'),&nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; 'price': item.find('div', class_="price-box__content-i").get_text(strip=True).replace(u'\xa0', u' ')&nbsp; &nbsp; &nbsp; &nbsp; })&nbsp; &nbsp; print(phone)&nbsp; &nbsp; return phone&nbsp; #&nbsp; &nbsp;<--- add this