from selenium import webdriver
import re 
import time  

driver = webdriver.Chrome()

driver.get('https://music.163.com/#/song?id=569213220')

driver.implicitly_wait(10)  # 隱式等待  瀏覽器渲染頁面  智能化等待
driver.maximize_window()  # 最大化瀏覽器

driver.switch_to.frame(0)

# document.documentElement.scrollTop  指定頁面的高度
# document.documentElement.scrollHeight  獲取頁面的高度
# document.documentElement.scrollTop  指定頁面的高度
# document.documentElement.scrollHeight  獲取頁面的高度
js = 'document.documentElement.scrollTop = document.documentElement.scrollHeight'
driver.execute_script(js)

for click in range(10):
    divs = driver.find_elements_by_css_selector('.itm')
    for div in divs:
        cnt = div.find_element_by_css_selector('.cnt.f-brk').text
        cnt = cnt.replace('\n', ' ') # 替換換行符
        cnt = re.findall('：(.*)', cnt)[0]
        
        with open('contend.txt', mode='a', encoding='utf-8') as f:
            f.write(cnt + '\n')

    # 找到下一頁標(biāo)簽點(diǎn)擊
    driver.find_element_by_css_selector('.znxt').click()
    time.sleep(1)


input('程序阻塞.')

driver.quit()

import jieba  # 中文分詞庫
import wordcloud  # 詞云圖庫
import imageio  # 圖像模塊


file = open('contend.txt', mode='r', encoding='utf-8')
txt = file.read()
# print(txt)
txt_list = jieba.lcut(txt)
print('分詞結(jié)果',txt_list)

string = ' '.join(txt_list)
print('合并分詞:', string)

"""制作詞云圖"""
# 讀取圖像
img = imageio.imread('音樂.png')


# 設(shè)置詞云圖
wc = wordcloud.WordCloud(
    width=1000, # 詞云圖的寬
    height=700, # 圖片的高
    background_color= 'black', # 詞云圖背景顏色
    font_path='msyh.ttc',  # 詞云字體, 微軟雅黑, 系統(tǒng)自帶
    scale=10, # 字體大小
    # mask=img,
    stopwords=set([line.strip() for line in open('cn_stopwords.txt', mode='r',
                                                 encoding='utf-8').readlines()])
)

print('正在繪制詞云圖')
wc.generate(string)
wc.to_file('output2.png')
print('詞云圖制作成功...')