CODEWITHSUNDEEP
pythonjson
Vincenzo
Vincenzo

Reputation: 53

TypeError(f'Object of type {o.__class__.__name__} ' TypeError: Object of type bytes is not JSON serializable

I'm trying to write JSON data contained in an array in a file but I'm not able to solve the issue reported in the title. Here my code:

import json

from bs4 import BeautifulSoup
import requests

url = 'http://ethans_fake_twitter_site.surge.sh/'
response = requests.get(url, timeout=5)
content = BeautifulSoup(response.content, "html.parser")
tweetArr = []
for tweet in content.findAll('div', attrs={"class": "tweetcontainer"}):
    tweetObject = {
        "author": tweet.find('h2', attrs={"class": "author"}).text.encode('utf-8'),
        "date": tweet.find('h5', attrs={"class": "dateTime"}).text.encode('utf-8'),
        "tweet": tweet.find('p', attrs={"class": "content"}).text.encode('utf-8'),
        "likes": tweet.find('p', attrs={"class": "likes"}).text.encode('utf-8'),
        "shares": tweet.find('p', attrs={"class": "shares"}).text.encode('utf-8')
    }
    tweetArr.append(tweetObject)

#print(tweetArr)

with open('twitterData.json', 'w') as outfile:
    json.dump(tweetArr, outfile)

This is the tweetArr content:

[{'author': b'jimmyfallon', 'date': b'17/01/2017 13:47', 'tweet': b'Tonight: @MichaelKeaton, @ninadobrev, music from @The_xx, and more! #FallonTonight', 'likes': b'Likes  184', 'shares': b'Shares  42'}, {'author': b'jimmyfallon', 'date': b'17/01/2017 12:55', 'tweet': b'.@michaelstrahan and @BryceDHoward take on @questlove and I in an intense game of Pyramid  #FallonTonight', 'likes': b'Likes  402', 'shares': b'Shares  60'},....}]

Upvotes: 5

Views: 25742

Answers (1)

marcos
marcos

Reputation: 4510

Just remove the .encode('utf-8') part, it doesn't make any sense.

import json

from bs4 import BeautifulSoup
import requests

url = 'http://ethans_fake_twitter_site.surge.sh/'
response = requests.get(url, timeout=5)
content = BeautifulSoup(response.content, "html.parser")
tweetArr = []
for tweet in content.findAll('div', attrs={"class": "tweetcontainer"}):
    tweetObject = {
        "author": tweet.find('h2', attrs={"class": "author"}).text,
        "date": tweet.find('h5', attrs={"class": "dateTime"}).text,
        "tweet": tweet.find('p', attrs={"class": "content"}).text,
        "likes": tweet.find('p', attrs={"class": "likes"}).text,
        "shares": tweet.find('p', attrs={"class": "shares"}).text
    }
    tweetArr.append(tweetObject)

with open('twitterData.json', 'w') as outfile:
    json.dump(tweetArr, outfile)

Upvotes: 3

Related Questions