Python爬取网易云歌曲评论实现词云图

from selenium import webdriver  # 导入浏览器的功能
import re   # 正则表达式模块, 内置
import time   # 时间模块, 程序延迟

driver = webdriver.Chrome()

driver.get('https://music.163.com/#/song?id=488249475')
# selenium无法直接获取到嵌套页面里面的数据
driver.switch_to.frame(0)  # switch_to.frame()  切换到嵌套网页
driver.implicitly_wait(10)  # 让浏览器加载的时候, 等待渲染页面

js = 'document.documentElement.scrollTop = document.documentElement.scrollHeight'
driver.execute_script(js)

divs = driver.find_elements_by_css_selector('.itm') 
# 所有div  css语法: 定位到 html 数据/xpath/正则
for div in divs:
    cnt = div.find_element_by_css_selector('.cnt.f-brk').text
    cnt = re.findall('：(.*)', cnt)[0]  # 中英文有区别
    print(cnt)

for page in range(10):  # 控制翻页  速度太快
    # 翻页 , 找到下一页标签, 点击?
    driver.find_element_by_css_selector('.znxt').click()
    time.sleep(1)
# selenium  欲速则不达

with open('contend.txt', mode='a', encoding='utf-8') as f:
    f.write(cnt + '\n')

import jieba  # 中文分词库  pip install jieba
import wordcloud  # 制作词云图的模块  pip install wordcloud
import imageio

with open('contend.txt', mode='r', encoding='utf-8') as f:
    txt = f.read()
print(txt)

txt_list = jieba.lcut(txt)
print('分词结果:', txt_list)

string_ = ' '.join(txt_list)  # 1 + 1 = 2   字符串的基本语法
print('合并分词:', string_)

wc = wordcloud.WordCloud(
    width=1000,  # 图片的宽
    height=800,  # 图片的高
    background_color='white',  # 图片的背景色
    font_path='msyh.ttc',  # 微软雅黑
    scale=15,  # 词云图默认的字体大小
    # mask=img,  # 指定词云图的图片
    # 停用词< 语气词, 助词,....
    stopwords=set([line.strip() for line in open('cn_stopwords.txt', mode='r', encoding='utf-8').readlines()] )
)
print('正在绘制词云图...')
wc.generate(string_)  # 绘制词云图
wc.to_file('out.png')  # 保存词云图
print('词云图绘制完成...')