from selenium import webdriver  # 導(dǎo)入瀏覽器的功能
import re   # 正則表達(dá)式模塊, 內(nèi)置
import time   # 時間模塊, 程序延遲

driver = webdriver.Chrome()

driver.get('https://music.163.com/#/song?id=488249475')
# selenium無法直接獲取到嵌套頁面里面的數(shù)據(jù)
driver.switch_to.frame(0)  # switch_to.frame()  切換到嵌套網(wǎng)頁
driver.implicitly_wait(10)  # 讓瀏覽器加載的時候, 等待渲染頁面

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

divs = driver.find_elements_by_css_selector('.itm') 
# 所有div  css語法: 定位到 html 數(shù)據(jù)/xpath/正則
for div in divs:
    cnt = div.find_element_by_css_selector('.cnt.f-brk').text
    cnt = re.findall('：(.*)', cnt)[0]  # 中英文有區(qū)別
    print(cnt)

for page in range(10):  # 控制翻頁  速度太快
    # 翻頁 , 找到下一頁標(biāo)簽, 點(diǎn)擊?
    driver.find_element_by_css_selector('.znxt').click()
    time.sleep(1)
# selenium  欲速則不達(dá)

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

import jieba  # 中文分詞庫  pip install jieba
import wordcloud  # 制作詞云圖的模塊  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('分詞結(jié)果:', txt_list)

string_ = ' '.join(txt_list)  # 1 + 1 = 2   字符串的基本語法
print('合并分詞:', string_)

wc = wordcloud.WordCloud(
    width=1000,  # 圖片的寬
    height=800,  # 圖片的高
    background_color='white',  # 圖片的背景色
    font_path='msyh.ttc',  # 微軟雅黑
    scale=15,  # 詞云圖默認(rèn)的字體大小
    # mask=img,  # 指定詞云圖的圖片
    # 停用詞< 語氣詞, 助詞,....
    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_)  # 繪制詞云圖
wc.to_file('out.png')  # 保存詞云圖
print('詞云圖繪制完成...')