Python3 Error: TypeError: Can't convert 'bytes' object to str implicitly

Question

I am working on exercise 41 in learnpythonthehardway and keep getting the error:

  Traceback (most recent call last):
  File ".\url.py", line 72, in <module>
    question, answer = convert(snippet, phrase)
  File ".\url.py", line 50, in convert
    result = result.replace("###", word, 1)
TypeError: Can't convert 'bytes' object to str implicitly

I am using python3 while the books uses python2, so I have made some changes. Here is the script:

#!/usr/bin/python
# Filename: urllib.py

import random
from random import shuffle
from urllib.request import urlopen
import sys

WORD_URL = "http://learncodethehardway.org/words.txt"
WORDS = []

PHRASES = {
            "class ###(###):":
                "Make a class named ### that is-a ###.",
            "class ###(object):\n\tdef __init__(self, ***)" :
                "class ### has-a __init__ that takes self and *** parameters.",
            "class ###(object):\n\tdef ***(self, @@@)":
                "class ### has-a funciton named *** that takes self and @@@ parameters.",
            "*** = ###()":
                "Set *** to an instance of class ###.",
            "***.*** = '***'":
                "From *** get the *** attribute and set it to '***'."
}

# do they want to drill phrases first
PHRASE_FIRST = False
if len(sys.argv) == 2 and sys.argv[1] == "english":
    PHRASE_FIRST = True

# load up the words from the website
for word in urlopen(WORD_URL).readlines():
    WORDS.append(word.strip())

def convert(snippet, phrase):
    class_names = [w.capitalize() for w in
                    random.sample(WORDS, snippet.count("###"))]
    other_names = random.sample(WORDS, snippet.count("***"))
    results = []
    param_names = []

    for i in range(0, snippet.count("@@@")):
        param_count = random.randint(1,3)
        param_names.append(', '.join(random.sample(WORDS, param_count)))

    for sentence in snippet, phrase:
        result = sentence[:]

        # fake class names
        for word in class_names:
            result = result.replace("###", word, 1)

        # fake other names
        for word in other_names:
            result = result.replace("***", word, 1)

        # fake parameter lists
        for word in param_names:
            result = result.replace("@@@", word, 1)

        results.append(result)

    return results

# keep going until they hit CTRL-D
try:
    while True:
        snippets = list(PHRASES.keys())
        random.shuffle(snippets)

        for snippet in snippets:
            phrase = PHRASES[snippet]
            question, answer = convert(snippet, phrase)
            if PHRASE_FIRST:
                question, answer = answer, question

            print(question)

            input("> ")
            print("ANSWER: {}\n\n".format(answer))
except EOFError:
    print("\nBye")

What exactly am I doing wrong here? Thanks!

Answer 1

urlopen() returns a bytes object, to perform string operations over it you should convert it to str first.

for word in urlopen(WORD_URL).readlines():
    WORDS.append(word.strip().decode('utf-8')) # utf-8 works in your case

To get the correct charset : How to download any(!) webpage with correct charset in python?