（一）Selenium获取歌曲评论并生成词云图

1 前期准备

指定词云图形状的图片，不指定默认生成的词云形状矩形。对应文件：云朵.png

设置好中文停用词，可以直接在网上搜，然后复制粘贴到txt格式文件中。对应文件： 停用词.txt

设置中文字体。对应文件：msyh.ttc

2 编写代码

获取评论的代码如下 wy.py

from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver import ChromeOptions  # 反检测
import time
import re

# 抓取某首歌的评论
option = ChromeOptions()
option.add_experimental_option("excludeSwitches", ["enable-automation"])
driver = webdriver.Chrome(options=option)
driver.maximize_window()
# 设置隐形加载时间为10s
driver.implicitly_wait(10)
driver.get("https://music.163.com/#/song?id=2015332584")
# 切换到iframe内
driver.switch_to.frame('g_iframe')
# 滚轮滚动
driver.execute_script('document.documentElement.scrollTop = document.documentElement.scrollHeight')

for page in range(1, 16):
    print(f'正在获取第{page}页评论.......')
    div_list = driver.find_elements(By.CSS_SELECTOR, '.itm')
    for div in div_list:
        comments = div.find_element(By.XPATH, './div[2]/div[1]/div').text
        # print(comments)
        comment = re.findall('.*?：(.*)', comments, re.S)[0]  # 注意冒号为中文冒号
        # print(comment)
        with open('./wyy评论.txt', 'a', encoding='utf-8') as fp:
            fp.write(comment + '\n')
    print(f'第{page}页评论获取成功！')
    # 点击下一页
    driver.find_element(By.CSS_SELECTOR, 'div.u-page .znxt').click()
    time.sleep(1)
driver.close()
driver.quit()

接着针对该评论生成词云图的代码如下 词云图.py

import wordcloud as wc
import jieba
from PIL import Image
import numpy as np

with open('./wyy评论.txt', 'r', encoding='utf-8') as fp:
    content = fp.read()
res = jieba.lcut(content)
text = " ".join(res)

# 设置词云的形状
mask = np.array(Image.open("云朵.png"))
# 设置停用词
stopwords = set([line.strip() for line in open('停用词.txt', 'r', encoding='utf-8').readlines()])
word_cloud = wc.WordCloud(font_path="msyh.ttc", mask=mask, stopwords=stopwords)
word_cloud.generate(text)
word_cloud.to_file("output.png")

3 效果

生成的词云图：

该程序涉及的所有文件