使用BeautifulSoup时出现“ NoneType”错误

Question

Below is my code...

from bs4 import BeautifulSoup

import requests


for count in range(1,2):


    r = requests.get('http://manufacturer.indiatradepage.com/all/a_a_enterprises/' + str(count) + '/',headers={'User-Agent': 'Googlebot'})

    soup = BeautifulSoup(r.text,'lxml')

    data = soup.find('div',class_='container_main')

    for links in data.find_all('div',class_='com_countainer'):
        for link in links.find_all('a')[0:1]:
            l = link['href']
            r = requests.get(l)
            soup = BeautifulSoup(r.text,'lxml')

            data = soup.find('td',{"id":"intro_txt"})
            table1 = data.find('table',{"style":"max-height: 400px !important"})

            body1 = table1.find('div',class_='f_body')


            table2 = data.find('div',{"id":"f3_1"})

            div = table2.find('div',class_='f_body')


            body2 = div.find('div',{"style":"text-transform:capitalize; "})

            print body2.text + body1.text

im getting this below error.

Traceback (most recent call last): File "C:/Python27/indiatradepage_try.py", line 19, in body1 = table1.find('div',class_='f_body') AttributeError: 'NoneType' object has no attribute 'find'

due to below error, my code is breaking everytime.

Answer 1

You can handle that by not trying to use attribute .find on a NoneType object, which is what you are trying to do at body1 = table1.find('div',class_='f_body') , and also probably at table2 = data.find('div',{"id":"f3_1"})

You can do something like this, that will check if the table is None, and if it is, instead of .find , print out that it's not there and then continue looping.

from bs4 import BeautifulSoup

import requests


for count in range(1,2):

    r = requests.get('http://manufacturer.indiatradepage.com/all/a_a_enterprises/' + str(count) + '/',headers={'User-Agent': 'Googlebot'})

    soup = BeautifulSoup(r.text,'lxml')

    data = soup.find('div',class_='container_main')

    for links in data.find_all('div',class_='com_countainer'):
        for link in links.find_all('a')[0:1]:
            l = link['href']
            r = requests.get(l)
            soup = BeautifulSoup(r.text,'lxml')

            data = soup.find('td',{"id":"intro_txt"})
            table1 = data.find('table',{"style":"max-height: 400px !important"})

            if table1 != None:
                body1 = table1.find('div',class_='f_body').text
            else:
                body1 = ' table1 no present '


            table2 = data.find('div',{"id":"f3_1"})
            if table2 != None:
                div = table2.find('div',class_='f_body')
                body2 = div.find('div',{"style":"text-transform:capitalize; "}).text
            else:
                body2 = ' table2 not present '

            print (body2 + body1)