python爬取歌词并生成词云图

最新推荐文章于 2024-09-03 16:47:21 发布

larrino

最新推荐文章于 2024-09-03 16:47:21 发布

阅读量4k

点赞数 5

分类专栏： python 文章标签： python

本文链接：https://blog.csdn.net/qq_39317214/article/details/80572744

版权

python 专栏收录该内容

2 篇文章 0 订阅

订阅专栏

第一部分：爬取数据

# 第一部分：爬取数据
import requests
import re
import os
import json
from bs4 import BeautifulSoup

#发起响应
def get_html(url):
    headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/60.0.3112.101 Safari/537.36'}
    try:
        response = requests.get(url, headers=headers)
        html = response.content
        return html
    except:
        print('request error')
        pass

#函数：按照歌曲id，提取歌词内容
def download_by_music_id(music_id):
    lrc_url = 'http://music.163.com/api/song/lyric?'+'id='+str(music_id) + '&lv=1&kv=1&tv=-1'
    r = requests.get(lrc_url)
    json_obj = r.text
    j = json.loads(json_obj)
    try:
        lrc = j['lrc']['lyric']
        pat = re.compile(r'\[.*\]')
        lrc = re.sub(pat, "",lrc)
        lrc = lrc.strip()
        return lrc
    except:
        pass

#函数：按照歌手id，发起请求，解析网页，提取歌曲id
def get_music_ids_by_musician_id(singer_id):
    singer_url = 'http://music.163.com/artist?id={}'.format(singer_id)
    r = get_html(singer_url)
    soupObj = BeautifulSoup(r,'lxml')
    song_ids = soupObj.find('textarea').text
    jobj = json.loads(song_ids)
    ids = {}
    for item in jobj:
        print(item['id'])
        ids[item['name']] = item['id']
    return ids

# 创建文件夹，在文件夹下存储每首歌的歌词
# os.mkdir创建目录，os.chdir改变当前工作目录到指定的路径
def download_lyric(uid):
    try:
        os.mkdir(str(uid))
    except:
        pass

    os.chdir(str(uid))
    music_ids = get_music_ids_by_musician_id(uid)
    for key in music_ids:
        text = download_by_music_id(music_ids[key])
        file = open(key+'.txt', 'a')
        file.write(key+'\n')
        file.write(str(text))
        file.close()

if __name__ == '__main__':
    download_lyric(6731)

第二部分：词频分析

利用jieba分词包进行分词，用set()去掉每首歌里的重复的词（比如在一首歌里出现北京北京北京北京只按1次算）,同时去掉停用词（如的、和、吗等无意义的虚词），统计词频，然后以词云图显示。

# 第二部分：词频分析

import os
from collections import Counter
import  jieba
from wordcloud import WordCloud
import matplotlib.pyplot as plt
from scipy.misc import imread
from pylab import mpl

#第一步：定义停用词库
def stopwordslist(filepath):
    stopwords = [line.strip() for line in open(filepath, 'r').readlines()]
    return stopwords
stopwords=stopwordslist('C:/Users/chen/PycharmProjects/stoplist.txt')

# 第二步：读取文件，分词，生成all_words列表，用停用词检查后生成新的all_words_new
all_words=[]
outstr = ''
for filename in os.listdir('6731'):
    with open('6731/'+filename) as f:
        lyrics=f.read()
        data=jieba.cut(lyrics)
        all_words.extend(set(data))
for word in all_words:
    if word not in stopwords:
        if word != '\t':
            outstr += word
            outstr += " "
all_words_new= outstr.split(" ") #转成列表
#第三步：对all_words中的词计数，并按照词频排序
count=Counter(all_words_new)
result=sorted(count.items(), key=lambda x: x[1], reverse=True)
print(result)
#第四步，词云显示
#将频率变成字典
word_dic=dict(count.items())
# 使matplotlib模块能显示中文
mpl.rcParams['font.sans-serif'] = ['SimHei'] # 指定默认字体
mpl.rcParams['axes.unicode_minus'] = False # 解决保存图像是负号'-'显示为方块的问题
color_mask=imread('xinxing.jpg') #背景图
cloud=WordCloud(
    font_path='C:\Windows\Fonts\SIMYOU.TTF',
    width=600,
    height=480,
    background_color='black',
    mask=color_mask,
    max_words=350,
    max_font_size=150)
world_cloud=cloud.fit_words(word_dic)
world_cloud.to_file('zhaolei.jpg')

第三部分：成果