How to add exception to skip AttributeError in my code? - python-3.x

Question

I was trying to skip AttributeError in my code because there is always atrribute error while crawling, especially when trying to get the value of title, and content. I have tried to put "except AttributeError" somewhere but never work. Could anybody help me? I am using python 3.6
from bs4 import BeautifulSoup
import requests
import pymysql.cursors
urls2 = []
result = requests.get("http://desaku.bandungkab.go.id/desaonline/")
src = result.content
soup = BeautifulSoup(src, 'lxml')
links = soup.find_all('a')
urls = []
for link in links:
if "www" in link.text:
url = link.attrs['href']
urls.append(url)
num1=len(urls)
b=0
while b<10:
result2 = requests.get(urls[b])
src2 = result2.content
soup = BeautifulSoup(src2, 'lxml')
links2 = soup.find_all('a')
for link in links2:
if "selengkapnya" in link.text:
url2 = link.attrs['href']
urls2.append(url2)
b+=1
num=len(urls2)
i=0
while i<num:
html = requests.get(urls2[i])
src = html.content
soup = BeautifulSoup(src, 'lxml')
recordList = soup.findAll("div", {"class": "artikel", })
recordlist = soup.find_all('div', attrs={'class':'sampul2'})
connection = pymysql.connect(host='localhost',
user='root',
password='',
db='bs4-test',
charset='utf8mb4',
cursorclass=pymysql.cursors.DictCursor)
try:
with connection.cursor() as cursor:
for record in recordList:
#except AttributeError:
#continue #WHERE TO PUT THIS EXCEPTION,TO SKIP ATRRIBUTEERRROR?
title = record.find("h2", {"class": "judul", }).get_text().strip()
date = record.find('i').next_sibling.next_sibling.next_sibling.replace('\t\t\t\t\t\t\t', '')
content = record.find("div", {"class":"teks"}).get_text().strip()
image = record.img['src']
cover = record.img['src']
sql = "INSERT INTO `artikel` (`jdl`, `tgl`, `kon`, `gambar`, `sampul`) VALUES (%s, %s, %s, %s, %s)"
cursor.execute(sql, (title, date, content, image, cover))
connection.commit()
print ("Record inserted successfully into table")
finally:
connection.close()
print("MySQL connection is closed")
i+=1

Answer 1

Just an example: if it is an url then append the url, if not then append null. Usually you would want the length of all lists to be the same, so that finally you could put them in a dataframe.
import numpy as np
links = soup.find_all('a')
urls = []
for link in links:
try:
url = link['href']
urls.append(url)
except:
urls.append(np.nan)