python 3.4 get content of page - charmap error

Vote count:

0

i using python 3.3.4 and try to get content of web page. but i have a error. my sample site is:

http://p30download.com

whene i write content to file, everything is good but when i print data, i give an error

my error:

UnicodeEncodeError: 'charmap' codec can't encode characters in position 341-342:
 character maps to <undefined>

and my code:

#!/usr/bin/python
# -*- coding: utf-8 -*-

import codecs
import urllib.request
import re
from sys import argv

__author__ = 'Moein'

totalPages = 100
UrlList = []

emails = []
numbers = []
toUtf8 = codecs.getencoder('UTF8')


class Robot:
    def __init__(self):
        self.getURLContent(UrlList.pop(0))
        pass

    def getURLContent(self, url):
        request = urllib.request.Request(url)
        response = urllib.request.urlopen(request)
        content = response.read().decode('utf-8')

        print(content)

        f = open('f:/1.txt', 'w', encoding='utf-8')
        f.write(content);
        f.close()

        pass

    def getPageURLs(self, page):
        pass

    def getPageNumbers(self, page):
        pass

    def getPageEmails(self, page):
        r = re.compile(r'[^@]+@[^@]+\.[^@]+')
        return r.findall(page)
        pass


# get arg
arg_names = ['command', 'x', 'y', 'operation', 'option']
args = dict(zip(arg_names, argv))

# set arg to list
UrlList.append(args['x'])

robot = Robot()

asked 1 min ago

Moein

23

python 3.4 get content of page - charmap error