Project: Text Analyzer

[rubberwoden]

Thank you for reading this thread. I need help creating my Text Analyzer. I have been going at it for a few days now. I will present the class I am making along with the instructions given and a help file and of course the current error message. Of course I am not looking for anyone to do the whole thing for me, have to learn after all, so I will take the help step by step. I am working on Jupiter Notebook via Anaconda. I am fairly certain it is something super simple, that I am not putting my finger on it. I know the help file has builtins.object in the parenthesis after the class textanalyzer, but you get an object not found error when it's in. I know one thing that is confusing me is in some places in the help and instructions the type is typed out as "_src_type" and other places it is "src_type".

---

Instructions & Help
The easiest way to share this is via google drive
Instructions
Help

---

The Text Analyzer

import requests, re
from bs4 import BeautifulSoup
from collections import Counter
import statistics as stats
import string
#above was created by the school
#create your class here
class TextAnalyzer():   
    def __init__(self, src, _src_type = 'discover'):
        self.src = src
        self._src_type = _src_type
        if src == 'discover':
            if re.match(r"^http", src, re.I):
                _src_type = 'url'
            elif re.search(r"txt&", src, re.I):
                _src_type = 'path'
            else:
                _src_type = 'text'
        elif src == 'url':
            _src_type = 'url'
        elif src == 'path':
            _src_type = 'path'
        else:
            _src_type = 'text'

     
    #def char_distribution(self, casesensitive=False, letters_only=False):

    #def common_words(self, minlen=1, maxlen=100, count=10, casesensitive=False):

    #def plot_char_distribution(self, casesensitive=False, letters_only=False):
        
    #def plot_common_words(self, minlen=1, maxlen=100, count=10, casesensitive=False):
        
    #def reset_content(self):
        
    #def set_content_to_tag(self, tag, tag_id=None):

---

The Tester

import unittest

url = 'https://www.webucator.com/how-to/address-by-bill-clinton-1997.cfm'
path = 'pride-and-prejudice.txt'
text = '''The outlook wasn't brilliant for the Mudville Nine that day;
the score stood four to two, with but one inning more to play.
And then when Cooney died at first, and Barrows did the same,
a sickly silence fell upon the patrons of the game.'''

class TestTextAnalyzer(unittest.TestCase):
    def test_discover_url(self):
        ta = TextAnalyzer(url)
        self.assertEqual(ta._src_type, 'url')
    def test_discover_path(self):
        ta = TextAnalyzer(path)
        self.assertEqual(ta._src_type, 'path')
    def test_discover_text(self):
        ta = TextAnalyzer(text)
        self.assertEqual(ta._src_type, 'text')
'''
    def test_set_content_to_tag(self):
        ta = TextAnalyzer(url)
        ta.set_content_to_tag('div','content-main')
        self.assertEqual(ta._content[0:25], '\n\nAddress by Bill Clinton')
    def test_reset_content(self):
        ta = TextAnalyzer(url)
        ta.set_content_to_tag('div','content-main')
        ta.reset_content()
        self.assertEqual(ta._content[0], '<')
    def test_common_words(self):
        ta = TextAnalyzer(path, src_type='path')
        common_words = ta.common_words(minlen=5, maxlen=10)
        liz = common_words[0]
        self.assertEqual(liz[0],'ELIZABETH')
    def test_avg_word_length(self):
        ta = TextAnalyzer(text, src_type='text')
        self.assertEqual(ta.avg_word_length, 4.16)
    def test_word_count(self):
        ta = TextAnalyzer(text, src_type='text')
        self.assertEqual(ta.word_count, 45)
    def test_distinct_word_count(self):
        ta = TextAnalyzer(text, src_type='text')
        self.assertEqual(ta.distinct_word_count, 38)
    def test_char_distribution(self):
        ta = TextAnalyzer(text, src_type='text')
        char_dist = ta.char_distribution(letters_only=True)
        self.assertEqual(char_dist[1][1], 20)
    def test_positivity(self):
        ta = TextAnalyzer(text, src_type='text')
        positivity = ta.positivity
        self.assertEqual(positivity, -44)
'''        
suite = unittest.TestLoader().loadTestsFromTestCase(TestTextAnalyzer)
unittest.TextTestRunner().run(suite)

---

Current Error

Error:
FFF
======================================================================
FAIL: test_discover_path (__main__.TestTextAnalyzer)
----------------------------------------------------------------------
Traceback (most recent call last):
  File "<ipython-input-6-46dd30f19dcd>", line 16, in test_discover_path
    self.assertEqual(ta._src_type, 'path')
AssertionError: 'discover' != 'path'
- discover
+ path


======================================================================
FAIL: test_discover_text (__main__.TestTextAnalyzer)
----------------------------------------------------------------------
Traceback (most recent call last):
  File "<ipython-input-6-46dd30f19dcd>", line 19, in test_discover_text
    self.assertEqual(ta._src_type, 'text')
AssertionError: 'discover' != 'text'
- discover
+ text


======================================================================
FAIL: test_discover_url (__main__.TestTextAnalyzer)
----------------------------------------------------------------------
Traceback (most recent call last):
  File "<ipython-input-6-46dd30f19dcd>", line 13, in test_discover_url
    self.assertEqual(ta._src_type, 'url')
AssertionError: 'discover' != 'url'
- discover
+ url


----------------------------------------------------------------------
Ran 3 tests in 0.002s

FAILED (failures=3)