词频脚本-网页抓取

Question

此脚本查找包含文章的子页面的地址，并从中收集数据。如何使用计数器找到10个最常见的单词及其编号。 2.查找每个作者的10个最常见的单词及其编号？

我看到了一些示例，但是在这些示例中，抓取代码完全不同，我不知道如何使用它们

残废代码：

import requests
from bs4 import BeautifulSoup as bs
from selenium import webdriver
from collections import Counter
import psycopg2 as pg2
from sqlalchemy.dialects.postgresql import psycopg2

url = 'https://teonite.com/blog/page/{}/index.html'
all_links = []

headers = {
    'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8',
    'User-Agent': 'Mozilla/5.0'
}
with requests.Session() as s:
    r = s.get('https://teonite.com/blog/')
    soup = bs(r.content, 'lxml')
    article_links = ['https://teonite.com' + item['href'][2:] for item in soup.select('.post-content a')]
    all_links.append(article_links)
    num_pages = int(soup.select_one('.page-number').text.split('/')[1])

    for page in range(2, num_pages + 1):
        r = s.get(url.format(page))
        soup = bs(r.content, 'lxml')
        article_links = ['https://teonite.com' + item['href'][2:] for item in soup.select('.post-content a')]
        all_links.append(article_links)

    all_links = [item for i in all_links for item in i]

    d = webdriver.Chrome()

    contents = []
    authors = []

    for article in all_links:
        d.get(article)
        soup = bs(d.page_source, 'lxml')
        [t.extract() for t in soup(['style', 'script', '[document]', 'head', 'title'])]
        visible_text = soup.getText()
        content = soup.find('section', attrs={'class': 'post-content'})
        contents.append(content)
        author = soup.find('span', attrs={'class': 'author-content'})
        authors.append(author)
        unique_authors = list(set(authors))
        unique_contents = list(set(contents))


        try:
            print(soup.select_one('.post-title').text)
        except:
            print(article)
            print(soup.select_one('h1').text)
            break  # for debugging
    d.quit()

    # POSTGRESQL CONNECTION
    # 1. Connect to local database using psycopg2

    import psycopg2

    hostname = 'balarama.db.elephantsql.com'
    username = 'yagoiucf'
    password = 'jXoWgxxxxxxxxxxxxxxxxxxxHo'
    database = 'yagoiucf'

    conn = psycopg2.connect(host='balarama.db.elephantsql.com', user='yagoiucf',
                            password='jxxxxxxx8HxxxxxxxxxxxMHo', dbname='yagoiucf')
    conn.close()