现如今,音乐伴随着我们的生活。已经成为了我们的生活习惯一部分,听音乐的场景有很多,例如做作业、上班出勤的路上、午休小寝时……为此我们都会对最近新出的流行歌曲和热度飙升比较快的歌曲感兴趣。为此我选这个主题作为课题。
名称:QQ音乐流行、飙升排行榜数据爬取
内容:通过访问QQ音乐的web官网,爬取相对应榜单的信息。最后保存下来做可视化分析。
设计方案思路:
首先,用request进行访问页面。
其次,用xtree来获取页面内容。
最后,文件操作进行数据的保存。
技术难点:在于分排行榜单进行爬取,工程量较大。
页面分析:
内容导航型
爬取目标特征分析(Htmls分析):
排名、热度、歌曲时间:
歌曲名:
歌手:
节点查找方法:
QQ_muc_pop = html.xpath("//*[@id='app']/div/div[2]/div[2]/div[3]/ul[2]/li[{}]/div/div[1]/text()".format(pop)) QQ_muc_up = html.xpath("//*[@id='app']/div/div[2]/div[2]/div[3]/ul[2]/li[{}]/div/div[2]/text()".format(pop)) QQ_muc_name = html.xpath("//*[@id='app']/div/div[2]/div[2]/div[3]/ul[2]/li[{}]/div/div[3]/span/a[2]/text()".format(pop)) QQ_muc_singer = html.xpath("//*[@id='app']/div/div[2]/div[2]/div[3]/ul[2]/li[{}]/div/div[4]/a/text()".format(pop)) QQ_muc_time = html.xpath("//*[@id='app']/div/div[2]/div[2]/div[3]/ul[2]/li[{}]/div/div[5]/text()".format(pop))
遍历方法:通过for循环控制标签导航,进行遍历筛出
数据爬取与采集:
1 import requests 2 from bs4 import BeautifulSoup 3 import time 4 import random 5 import sys 6 import re 7 from tqdm import tqdm 8 from lxml import etree 9 10 USER_AGENTS = [ 11 'Mozilla/5.0 (Windows NT 6.2; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/32.0.1667.0 Safari/537.36' 12 'Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/31.0.1650.16 Safari/537.36' 13 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/31.0.1623.0 Safari/537.36' 14 'Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/30.0.1599.17 Safari/537.36' 15 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/29.0.1547.62 Safari/537.36' 16 'Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/29.0.1547.2 Safari/537.36' 17 'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/28.0.1468.0 Safari/537.36' 18 'Mozilla/5.0 (Windows NT 6.2) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/28.0.1467.0 Safari/537.36' 19 'Mozilla/5.0 (Windows NT 6.2) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/28.0.1464.0 Safari/537.36' 20 'Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/27.0.1500.55 Safari/537.36' 21 'Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/27.0.1453.93 Safari/537.36' 22 'Mozilla/5.0 (Windows NT 6.1; rv:27.3) Gecko/20130101 Firefox/27.3' 23 'Mozilla/5.0 (Windows NT 6.2; Win64; x64; rv:27.0) Gecko/20121011 Firefox/27.0' 24 'Mozilla/5.0 (Windows NT 6.1; Win64; x64; rv:25.0) Gecko/20100101 Firefox/25.0' 25 'Mozilla/5.0 (Windows NT 6.0; WOW64; rv:24.0) Gecko/20100101 Firefox/24.0' 26 'Mozilla/5.0 (Windows NT 6.2; rv:22.0) Gecko/20130405 Firefox/23.0' 27 'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:23.0) Gecko/20130406 Firefox/23.0' 28 'Mozilla/5.0 (Windows NT 6.1; Win64; x64; rv:23.0) Gecko/20131011 Firefox/23.0' 29 'Mozilla/5.0 (Windows NT 6.2; rv:22.0) Gecko/20130405 Firefox/22.0' 30 'Mozilla/5.0 (Windows NT 6.1; Win64; x64; rv:22.0) Gecko/20130328 Firefox/22.0' 31 'Mozilla/5.0 (Windows NT 6.1; rv:22.0) Gecko/20130405 Firefox/22.0' 32 'Mozilla/5.0 (Microsoft Windows NT 6.2.9200.0); rv:22.0) Gecko/20130405 Firefox/22.0' 33 'Mozilla/5.0 (Windows NT 6.2; Win64; x64; rv:16.0.1) Gecko/20121011 Firefox/21.0.1' 34 'Mozilla/5.0 (Windows NT 6.1; Win64; x64; rv:16.0.1) Gecko/20121011 Firefox/21.0.1' 35 'Mozilla/5.0 (Windows NT 6.2; Win64; x64; rv:21.0.0) Gecko/20121011 Firefox/21.0.0' 36 'Mozilla/5.0 (Windows NT 6.2; WOW64; rv:21.0) Gecko/20130514 Firefox/21.0' 37 ] 38 39 headers = { 40 'User-Agent':random.choice(USER_AGENTS), 41 # 'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:89.0) Gecko/20100101 Firefox/89.0', 42 'Connection':'keep-alive', 43 'Accept-Language':'zh-CN,zh;q=0.8,zh-TW;q=0.7,zh-HK;q=0.5,en-US;q=0.3,en;q=0.2' 44 } 45 46 # QQ音乐飙升榜 47 def QQ_muc_up(): 48 # 请求访问 49 url = 'https://y.qq.com/n/ryqq/toplist/62' 50 res = requests.get(url,headers=headers) 51 res.encoding = 'utf-8' 52 # print(res) 53 html = etree.HTML(res.text) 54 # print(html) 55 # 创建保存文件 56 # 创建文件 57 file = open("QQ_muc_up.csv", "a") 58 file.write( 59 "QQ_muc_pop" + "," + "QQ_muc_up" + "," + "QQ_muc_name" + "," + "QQ_muc_singer" + "," + "QQ_muc_time" + '\n') 60 file = file.close() 61 # 排名QQ_muc_pop、飙升指数QQ_muc_up、歌名QQ_muc_name、歌手QQ_muc_singer、歌曲时间QQ_muc_time 62 pop = 1 63 for i in range(1,21): 64 QQ_muc_pop = html.xpath("//*[@id='app']/div/div[2]/div[2]/div[3]/ul[2]/li[{}]/div/div[1]/text()".format(pop)) 65 for item in QQ_muc_pop: 66 QQ_muc_pop = item 67 QQ_muc_up = html.xpath("//*[@id='app']/div/div[2]/div[2]/div[3]/ul[2]/li[{}]/div/div[2]/text()".format(pop)) 68 for item in QQ_muc_up: 69 QQ_muc_up = item.strip('%') 70 QQ_muc_up = int(QQ_muc_up) 71 QQ_muc_name = html.xpath("//*[@id='app']/div/div[2]/div[2]/div[3]/ul[2]/li[{}]/div/div[3]/span/a[2]/text()".format(pop)) 72 for item in QQ_muc_name: 73 QQ_muc_name = item 74 QQ_muc_singer = html.xpath("//*[@id='app']/div/div[2]/div[2]/div[3]/ul[2]/li[{}]/div/div[4]/a/text()".format(pop)) 75 for item in QQ_muc_singer: 76 QQ_muc_singer = item 77 QQ_muc_time = html.xpath("//*[@id='app']/div/div[2]/div[2]/div[3]/ul[2]/li[{}]/div/div[5]/text()".format(pop)) 78 for item in QQ_muc_time: 79 QQ_muc_time = item 80 pop += 1 81 # 保存数据 82 with open('QQ_muc_up.csv', "a", encoding='utf-8') as file1: 83 file1.writelines(QQ_muc_pop + "," + str(QQ_muc_up) + "," + QQ_muc_name + "," + QQ_muc_singer + "," + QQ_muc_time + '\n') 84 print('歌名:',QQ_muc_name,'\n','排名:',QQ_muc_pop,'\n','飙升指数:',QQ_muc_up,'\n','歌手名:',QQ_muc_singer,'\n','时长',QQ_muc_time) 85 86 #QQ音乐流行榜 87 def QQ_muc_fasion(): 88 # 请求访问 89 url = 'https://y.qq.com/n/ryqq/toplist/4' 90 res = requests.get(url,headers=headers) 91 res.encoding = 'utf-8' 92 # print(res) 93 html = etree.HTML(res.text) 94 # print(html) 95 # 创建保存文件 96 # 创建文件 97 file = open("QQ_muc_fasion.csv", "a") 98 file.write( 99 "QQ_muc_pop" + "," + "QQ_muc_up" + "," + "QQ_muc_name" + "," + "QQ_muc_singer" + "," + "QQ_muc_time" + '\n') 100 file = file.close() 101 # 排名QQ_muc_pop、飙升指数QQ_muc_up、歌名QQ_muc_name、歌手QQ_muc_singer、歌曲时间QQ_muc_time 102 pop = 1 103 for i in range(1,21): 104 QQ_muc_pop = html.xpath("//*[@id='app']/div/div[2]/div[2]/div[3]/ul[2]/li[{}]/div/div[1]/text()".format(pop)) 105 for item in QQ_muc_pop: 106 QQ_muc_pop = item 107 QQ_muc_up = html.xpath("//*[@id='app']/div/div[2]/div[2]/div[3]/ul[2]/li[{}]/div/div[2]/text()".format(pop)) 108 for item in QQ_muc_up: 109 QQ_muc_up = item.strip('%') 110 QQ_muc_up = int(QQ_muc_up) 111 QQ_muc_name = html.xpath("//*[@id='app']/div/div[2]/div[2]/div[3]/ul[2]/li[{}]/div/div[3]/span/a[2]/text()".format(pop)) 112 for item in QQ_muc_name: 113 QQ_muc_name = item 114 QQ_muc_singer = html.xpath("//*[@id='app']/div/div[2]/div[2]/div[3]/ul[2]/li[{}]/div/div[4]/a/text()".format(pop)) 115 for item in QQ_muc_singer: 116 QQ_muc_singer = item 117 QQ_muc_time = html.xpath("//*[@id='app']/div/div[2]/div[2]/div[3]/ul[2]/li[{}]/div/div[5]/text()".format(pop)) 118 for item in QQ_muc_time: 119 QQ_muc_time = item 120 pop += 1 121 # 保存数据 122 with open('QQ_muc_fasion.csv', "a", encoding='utf-8') as file1: 123 file1.writelines( 124 QQ_muc_pop + "," + str(QQ_muc_up) + "," + QQ_muc_name + "," + QQ_muc_singer + "," + QQ_muc_time + '\n') 125 print('歌名:',QQ_muc_name,'\n','排名:',QQ_muc_pop,'\n','飙升指数:',QQ_muc_up,'\n','歌手名:',QQ_muc_singer,'\n','时长',QQ_muc_time) 126 127 if __name__ == '__main__': 128 print('-------------------start----------------------') 129 print('正在爬取QQ音乐飙升榜单') 130 QQ_muc_up() 131 print('-------------------分界线----------------------') 132 print('正在爬取QQ音乐流行榜单') 133 QQ_muc_fasion() 134 print('--------------------end------------------------')
数据清洗:
import pandas as pd import numpy as np Fasion = pd.read_csv(r'D:\HW\QQ_muc_fasion.csv',error_bad_lines=False) Up = pd.read_csv(r'D:\HW\QQ_muc_up.csv',error_bad_lines=False) Fasion
# 重复值处理 Fasion = Fasion.drop_duplicates() Up = Up.drop_duplicates() # Nan处理 Fasion = Fasion.dropna(axis = 0) Up = Up.dropna(axis = 0) # 删除无效行 del Up['QQ_muc_time'] del Fasion['QQ_muc_time']
import matplotlib.pyplot as plt # 可视化分析 # y的点击数单位为万 x = Fasion['QQ_muc_name'] y = Fasion['QQ_muc_up'] z = Up['QQ_muc_up'] plt.rcParams['font.sans-serif']=['SimHei'] #用来正常显示中文标签 plt.rcParams['axes.unicode_minus']=False plt.plot(x,y,'-',color = 'r',label="热度") plt.xticks(rotation=90) plt.legend(loc = "best")#图例 plt.title("QQ音乐流行榜单趋势图") plt.xlabel("歌曲名",)#横坐标名字 plt.ylabel("热度")#纵坐标名字 plt.show()
plt.rcParams['font.sans-serif']=['SimHei'] #用来正常显示中文标签 plt.rcParams['axes.unicode_minus']=False plt.plot(x,z,'-',color = 'b',label="热度") plt.xticks(rotation=90) plt.legend(loc = "best")#图例 plt.title("QQ音乐飙升榜趋势图") plt.xlabel("歌曲名",)#横坐标名字 plt.ylabel("热度")#纵坐标名字 plt.show()
# 柱状图 plt.bar(x,y,alpha=0.2, width=0.4, color='b', lw=3) plt.rcParams['font.sans-serif']=['SimHei'] #用来正常显示中文标签 plt.title("QQ音乐流行榜单柱状图") plt.xticks(rotation=90) plt.xlabel("歌曲名",)#横坐标名字 plt.ylabel("热度")#纵坐标名字 plt.show()
# 柱状图 plt.bar(x,z,alpha=0.2, width=0.4, color='g', lw=3) plt.rcParams['font.sans-serif']=['SimHei'] #用来正常显示中文标签 plt.title("QQ音乐飙升榜单柱状图") plt.xticks(rotation=90) plt.xlabel("歌曲名",)#横坐标名字 plt.ylabel("热度")#纵坐标名字 plt.show()
# 水平图 plt.barh(x,y, alpha=0.2, height=0.4, color='y',label="热度指数", lw=3) plt.title("QQ音乐流行榜单水平图") plt.legend(loc = "best")#图例 plt.xlabel("热度",)#横坐标名字 plt.ylabel("歌曲名")#纵坐标名字 plt.show()
# 水平图 plt.barh(x,z, alpha=0.2, height=0.4, color='pink',label="热度指数", lw=3) plt.title("QQ音乐飙升榜单水平图") plt.legend(loc = "best")#图例 plt.xlabel("热度",)#横坐标名字 plt.ylabel("歌曲名")#纵坐标名字 plt.show()
# 散点图 plt.scatter(x,y,color='pink',marker='o',s=40,edgecolor='black',alpha=0.5) plt.xticks(rotation=90) plt.title("QQ音乐流行榜单散点图") plt.xlabel("歌曲名",)#横坐标名字 plt.ylabel("热度")#纵坐标名字 plt.show()
# 散点图 plt.scatter(x,z,color='gray',marker='o',s=40,edgecolor='black',alpha=0.5) plt.xticks(rotation=90) plt.title("QQ音乐飙升榜单散点图") plt.xlabel("歌曲名",)#横坐标名字 plt.ylabel("热度")#纵坐标名字 plt.show()
# 盒图 plt.boxplot(z) plt.title("QQ音乐飙升榜单量盒图") plt.show()
# 盒图 plt.boxplot(y) plt.title("QQ音乐流行榜单量盒图") plt.show()
云词:
import pandas as pd import numpy as np import wordcloud as wc from PIL import Image import matplotlib.pyplot as plt bk = np.array(Image.open("QQ.jpg")) mask = bk Fasion = pd.read_csv(r'D:\HW\QQ_muc_fasion.csv',error_bad_lines=False) Up = pd.read_csv(r'D:\HW\QQ_muc_up.csv',error_bad_lines=False) word_cloud = wc.WordCloud( width=1000, # 词云图宽 height=1000, # 词云图高 mask = mask, background_color='white', # 词云图背景颜色,默认为白色 font_path='msyhbd.ttc', # 词云图 字体(中文需要设定为本机有的中文字体) max_font_size=400, # 最大字体,默认为200 random_state=50, # 为每个单词返回一个PIL颜色 ) text = Fasion['QQ_muc_singer'] Fasion = [] for i in text: Fasion.append(i) text = " ".join(Fasion) word_cloud.generate(text) plt.imshow(word_cloud) plt.show()
text = Up['QQ_muc_singer'] Up = [] for i in text: Up.append(i) text = " ".join(Up) word_cloud.generate(text) plt.imshow(word_cloud) plt.show()
在设计过程中,我收获到了如何编写爬虫程序,如何把网页想要爬取的内容提取出来,云词怎么画出来。改进的地方可能是编写代码经验不足吧,写代码的时候比较吃力。希望我自己在以后的就业或者提升中花费多些时间、精力来提升这一短板。