Generating Word Cloud and Pie Chart from News Articles Using Python

This article demonstrates how to scrape a news webpage, extract its text, perform Chinese word segmentation, count word frequencies, and visualize the top ten words using a word cloud and a pie chart.

Solution steps: 1) Crawl all text from the news article; 2) Split the text into individual characters; 3) Count occurrences and select the ten most frequent characters; 4) Generate visualizations.

Below is the complete Python script used for the process:

import jieba as jieba
import requests
from bs4 import BeautifulSoup
from pyecharts.charts import WordCloud, Pie

if __name__ == "__main__":
    headers = {
        "user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/111.0.0.0 Safari/537.36"
    }
    url = "https://new.qq.com/rain/a/20230315A08LAK00"
    res_html = requests.get(url, headers=headers).text
    soup = BeautifulSoup(res_html, "lxml")
    txt = soup.select(".content-article")[0].text
    words = jieba.lcut(txt)

    counts = {}
    for word in words:
        if len(word) == 1:
            continue
        else:
            counts[word] = counts.get(word, 0) + 1

    sort_data = sorted(counts.items(), key=lambda a: a[1], reverse=True)[:10]

    wc = WordCloud()
    wc.add("", sort_data, word_size_range=[20, 100])
    wc.render("1.html")

    pip = Pie()
    pip.add(
        series_name="次数",
        data_pair=sort_data
    )
    pip.render("2.html")

The generated word cloud and pie chart are displayed in the article, illustrating the most frequent words in the news content.

At the end of the article, a QR code is provided for readers to claim free Python course materials and additional resources.