from bs4 import BeautifulSoup
import time
#import requests
import urllib.request,re
#import pandas as pd
#import numpy as np
import csv
def crawlcontents():
url = 'https://www.tripadvisor.com/ShowTopic-g983296-i13236-k11538516-Rent_from_LOTTE_standard_or_mystery_option-Jeju_Island.html'
html = urllib.request.urlopen(url).read().decode()
# print(html)
soup = BeautifulSoup(html,'html.parser')
# print(soup)
div = soup.select_one('#SHOW_TOPIC > div.balance > div.firstPostBox > div > div > div.postRightContent > div.postcontent > div.postBody')
div.select_one('script').decompose()
postcontent = div.text.strip()
postcontent = re.sub(r'\n+', ' ',postcontent)
print(postcontent)
crawlcontents()
vendredi 25 mai 2018
python 'NoneType' object has no attribute 'decompose'
Inscription à :
Publier les commentaires (Atom)
Aucun commentaire:
Enregistrer un commentaire