问在Python3中从网站中找到最常用的单词

EN

import requests
from bs4 import BeautifulSoup
from collections import Counter
from string import punctuation

r = requests.get("http://en.wikipedia.org/wiki/Wolfgang_Amadeus_Mozart")

soup = BeautifulSoup(r.content)

text = (''.join(s.findAll(text=True))for s in soup.findAll('p'))

c = Counter((x.rstrip(punctuation).lower() for y in text for x in y.split()))
print (c.most_common()) # prints most common words staring at most common.

[('the', 279), ('and', 192), ('in', 175), ('of', 168), ('his', 140), ('a', 124), ('to', 103), ('mozart', 82), ('was', 77), ('he', 70), ('with', 53), ('as', 50), ('for', 40), ("mozart's", 39), ('on', 35), ('from', 34), ('at', 31), ('by', 31), ('that', 26), ('is', 23), ('k.', 21), ('an', 20), ('had', 20), ('were', 20), ('but', 19), ('which',.............

print ([x for x in c if c.get(x) > 5]) # words appearing more than 5 times

['there', 'but', 'both', 'wife', 'for', 'musical', 'salzburg', 'it', 'more', 'first', 'this', 'symphony', 'wrote', 'one', 'during', 'mozart', 'vienna', 'joseph', 'in', 'later', 'salzburg,', 'other', 'such', 'last', 'needed]', 'only', 'their', 'including', 'by', 'music,', 'at', "mozart's", 'mannheim,', 'composer', 'and', 'are', 'became', 'four', 'premiered', 'time', 'did', 'the', 'not', 'often', 'is', 'have', 'began', 'some', 'success', 'court', 'that', 'performed', 'work', 'him', 'leopold', 'these', 'while', 'been', 'new', 'most', 'were', 'father', 'opera', 'as', 'who', 'classical', 'k.', 'to', 'of', 'has', 'many', 'was', 'works', 'which', 'early', 'three', 'family', 'on', 'a', 'when', 'had', 'december', 'after', 'he', 'no.', 'year', 'from', 'great', 'period', 'music', 'with', 'his', 'composed', 'minor', 'two', 'number', '1782', 'an', 'piano']

text = '''INSERT TEXT HERE'''.split() #Where you see "INSERT TEXT HERE", that's where the text goes.
#also note the .split() method at the end. This converts the text into a list, splitting every word in between the spaces. 
#for example, "red dog food".split() would be ['red','dog','food']
overusedwords = [] #this is where the words that are used 5 or more times are going to be held.
for i in text: #this will iterate through every single word of the text
    if text.count(i) >= 5 and overusedwords.count(i) == 0: #(1. Read below)
        overusedwords.append(i) #this adds the word to the list of words used 5 or more times
if len(overusedwords) > 0: #if there are no words used 5 or more times, it doesn't print anything useless.
    print('The overused words are:')
    for i in overusedwords:
        print(i)
else:
    print('No words used 5 or more times.') #just in case there are no words used 5 or more times