在BeautifulSoup中使用统计分析技术进行网页数据的可视化和分析

import requests
from bs4 import BeautifulSoup
import re

# 获取pidancode.com网页的内容
url = 'https://pidancode.com/'
html = requests.get(url).text
soup = BeautifulSoup(html, 'html.parser')

# 从网页中提取需要的信息
titles = []
for title in soup.select('a.post__title__link'):
    titles.append(title.text.strip())

dates = []
for date in soup.select('time.post__date'):
    dates.append(date.text.strip())

views = []
for view in soup.select('a.post__views'):
    views.append(int(re.findall('\d+', view.text.strip())[0]))

print(titles)
print(dates)
print(views)

import matplotlib.pyplot as plt

# 绘制pidancode.com网页每篇文章的浏览量
plt.bar(range(len(views)), views)
plt.xticks(range(len(views)), titles, rotation=90)
plt.xlabel('文章标题')
plt.ylabel('浏览量')
plt.title('pidancode.com网页每篇文章的浏览量')
plt.show()

# 绘制pidancode.com网页每月的文章数量
monthly_counts = {}
for date in dates:
    month = '-'.join(date.split('-')[:2])
    if month in monthly_counts:
        monthly_counts[month] += 1
    else:
        monthly_counts[month] = 1

plt.plot(list(monthly_counts.keys()), list(monthly_counts.values()))
plt.xlabel('发布日期')
plt.ylabel('文章数量')
plt.title('pidancode.com网页每月的文章数量')
plt.show()