使用 python 进行字数统计

我用Python写了一个字数统计代码。

我想从以下页面获取每个单词的文本和频率：

问题是我的程序给了我除以每节经文的字数，但我希望它不除。

请帮助我。

import requests
from bs4 import BeautifulSoup
import operator


def start(url):
    word_list = []
    source_code = requests.get(url).text  
    soup = BeautifulSoup(source_code, "html.parser")
    for bible_text in soup.findAll('font', {'class': 'tk4l'}):
        content = bible_text.get_text()   
        words = content.lower().split() 
        for each_word in words:
            word_list.append(each_word)
        clean_up_list(word_list)


def clean_up_list(word_list):
    clean_word_list = []
    for word in word_list:                                  
        symbols = "~!@#$%^&*()_+`{}|\"?><`-=\][';/.,']"
        for i in range(0, len(symbols)):
            word = word.replace(symbols[i], "")               
        if len(word) > 0:     
            clean_word_list.append(word)
    create_dictionary(clean_word_list)


def create_dictionary(clean_word_list):
    word_count = {}
    for word in clean_word_list:
        if word in word_count:
            word_count[word] += 1
        else:
            word_count[word] = 1  
    for key, value in sorted(word_count.items(),key=operator.itemgetter(0)):
        print(key, value)                  


start('http://www.holybible.or.kr/B_NIV/cgi/bibleftxt.php?VR=NIV&VL=1&CN=1&CV=99')

你正在构建一个新的word_count每节经文的字典，然后打印出来word_count只为这节经文。相反，您只需要一个实例word_count.

Update：代码还有其他问题，另外您应该使用正则表达式来删除所有非字母数字字符，另外您应该使用collections.Counter，因为它使您的代码变得更短，而且，作为一个很好的副作用，让您可以检索最常见的单词：

import requests
import re
from bs4 import BeautifulSoup
from collections import Counter


def parse(url):
    html = requests.get(url).text
    soup = BeautifulSoup(html, "html.parser")
    count = Counter()
    for bible_text in soup.findAll('font', {'class': 'tk4l'}):
        text = re.sub("[^\w0-9 ]", "", bible_text.get_text().lower())
        count.update(text.split(" "))
    return count

word_count = parse('http://www.holybible.or.kr/B_NIV/cgi/bibleftxt.php?VR=NIV&VL=1&CN=1&CV=99')
print(word_count.most_common(10))

Output:

[('the', 83), ('and', 71), ('god', 30), ('was', 29), ('to', 22), ('it', 17), ('of', 16), ('there', 16), ('that', 15), ('in', 15)]