在学习python爬虫,准备把爬到的数据写到JSON文件中时,发现报错
原代码
#coding:utf-8
import json
from bs4 import BeautifulSoup
import requests
user_agent = 'Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:55.0) Gecko/20100101 Firefox/55.0'
headers = {'User-Agent':user_agent}
r = requests.get('http://seputu.com',headers=headers)
soup = BeautifulSoup(r.text, 'html.parser',from_encoding='utf-8')
content = []
for mulu in soup.find_all(class_="mulu"):
h2 = mulu.find('h2')
if h2 != None:
h2_title = h2.string
list = []
for a in mulu.find(class_="box").find_all('a'):
href = a.get('href')
box_title = a.get('title')
list.append({'href':href,'bot_title':box_title})
content.append({'title':h2_title,'content'