Day10.如何给⽑不易的歌曲做词云展示

wc = WordCloud(
    background_color='white',  # 设置背景颜⾊
    mask=backgroud_Image,  # 设置背景图⽚
    font_path='./SimHei.ttf',  # 设置字体，针对中⽂的情况需要设置中⽂字体，否则显示乱码
    max_words=100,  # 设置最⼤的字数
    stopwords=STOPWORDS,  # 设置停⽤词
    max_font_size=150,  # 设置字体最⼤值
    width=2000,  # 设置画布的宽度
    height=1200,  # 设置画布的⾼度
    random_state=30  # 设置多少种随机状态，即多少种颜⾊
)

import matplotlib.pyplot as plt
plt.imshow(wordcloud)
plt.axis("off")
plt.show()

fromwordcloudimportWordCloudimport matplotlib.pyplot as plt
import jieba
from PIL import Image
import numpy as np

f = '数据可视化概述\
数据可视化基础语法\
五种常见图形绘制\
五种扩展图形绘制\
可视化基础数据分析-NumPy入门指南(一)\
数据分析-NumPy入门指南(二)\
数据挖掘初探：亲和性分析-商品推荐\
利用pandas做数据处理(一)\
利用pandas做数据处理(二)\
十分钟掌握python操作excel秘诀\
数据采集-爬虫\
数据清洗\
数据集成与转换\
数据可视化：给毛不易的歌词做词云展示'

# ⽣成词云
def create_word_cloud(f):
    print('根据词频计算词云')
text = ' '.join(jieba.cut(f, cut_all=False, HMM=True))
wc = WordCloud(
    font_path="C:\Windows\Fonts\SimHei.ttf",
    max_words=100,
    width=2000,
    height=1200,
)
wordcloud = wc.generate(text)
# 写词云图⽚
wordcloud.to_file("wordcloud.jpg")
# 显示词云⽂件
plt.imshow(wordcloud)
plt.axis("off")
plt.show()

# ⽹易云⾳乐 通过歌⼿ID，⽣成该歌⼿的词云
import requests
import sys
import re
import os
from wordcloud import WordCloud,STOPWORDS
import matplotlib.pyplot as plt
import jieba
from PIL import Image
import numpy as np
from lxml import etree

headers = {
    'Referer': 'http://music.163.com',
    'Host': 'music.163.com',
    'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8',
    'User-Agent': 'Chrome/10'
    }

# 得到某⼀⾸歌的歌词
def get_song_lyric(headers, lyric_url):
    res = requests.request('GET', lyric_url, headers=headers)
    if 'lrc' in res.json():
        lyric = res.json()['lrc']['lyric']
        new_lyric = re.sub(r'[\d:.[\]]', '', lyric)
        return new_lyric
    else:
        return ''
        print(res.json())

def remove_stop_words(f):
    stop_words = {"作词", "作曲", "编曲", "Arranger", "录⾳", "混⾳", "⼈声", "Vocal", "弦乐", "Keyboard", "键盘", "编辑","不易","" }
    for stop_words in stop_words:
        f = f.replace(stop_words, '')
    return f

# ⽣成词云
def create_word_cloud(f):
    print('根据词频，开始⽣成词云!')
    f = remove_stop_words(f)
    cut_text = " ".join(jieba.cut(f, cut_all=False, HMM=True))
    wc = WordCloud(
        font_path="C:\Windows\Fonts\FZSTK.TTF",
        max_words=100,
        width=2000,
        height=1200,
    )
    print(cut_text)
    wordcloud = wc.generate(cut_text)
    # 写词云图⽚
    wordcloud.to_file("wordcloud.jpg")
    # 显示词云⽂件
    plt.imshow(wordcloud)
    plt.axis("off")
    plt.show()


# 得到指定歌⼿⻚⾯ 热⻔前50的歌曲ID，歌曲名
def get_songs(artist_id):
    page_url = 'https://music.163.com/artist?id=' + artist_id
    # 获取⽹⻚HTML
    res = requests.request('GET', page_url, headers=headers)
    # ⽤XPath解析 前50⾸热⻔歌曲
    html = etree.HTML(res.text)
    href_xpath = "//*[@id='hotsong-list']//a/@href"
    name_xpath = "//*[@id='hotsong-list']//a/text()"
    hrefs = html.xpath(href_xpath)
    names = html.xpath(name_xpath)
    # 设置热⻔歌曲的ID，歌曲名称
    song_ids = []
    song_names = []
    for href, name in zip(hrefs, names):
        song_ids.append(href[9:])
        song_names.append(name)
        print(href, ' ', name)
    return song_ids, song_names
# 设置歌⼿ID，⽑不易为12138269
artist_id = '12138269'
[song_ids, song_names] = get_songs(artist_id)
# 所有歌词
all_word = ''
# 获取每⾸歌歌词
for (song_id, song_name) in zip(song_ids, song_names):
    # 歌词API URL
    lyric_url = 'http://music.163.com/api/song/lyric?os=pc&id=' + song_id + '&lv=-1&kv=-1&tv=-1'
    lyric = get_song_lyric(headers, lyric_url)
    all_word = all_word + ' ' + lyric
    print(song_name)
# 根据词频 ⽣成词云
create_word_cloud(all_word)