爬虫爬取网易云歌单

from urllib import parse
from lxml import etree
from urllib3 import disable_warnings
import requests
import csv
class Wangyiyun(object):
 
    def __init__(self, **kwargs):
        # 歌单的歌曲风格
        self.types = kwargs[‘types‘]
        # 歌单的发布类型
        self.years = kwargs[‘years‘]
        # 这是当前爬取的页数
        self.pages = pages
        # 这是请求的url参数（页数）
        self.limit = 35
        self.offset = 35 * self.pages - self.limit
        # 这是请求的url
        self.url = "https://music.163.com/discover/playlist/?"
 
 
    # 设置请求头部信息(可扩展：不同的User - Agent)
    def set_header(self):
        self.header = {
            "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/73.0.3683.103 Safari/537.36",
            "Referer": "https://music.163.com/",
            "Upgrade-Insecure-Requests": ‘1‘,
        }
        return self.header
 
    # 设置请求表格信息
    def set_froms(self):
        self.key = parse.quote(self.types)
        self.froms = {
            "cat": self.key,
            "order": self.years,
            "limit": self.limit,
            "offset": self.offset,
        }
        return self.froms
 
    # 解析代码，获取有用的数据
    def parsing_codes(self):
        page = etree.HTML(self.code)
        # 标题
        self.title = page.xpath(‘//div[@class="u-cover u-cover-1"]/a[@title]/@title‘)
        # 作者
        self.author = page.xpath(‘//p/a[@class="nm nm-icn f-thide s-fc3"]/text()‘)
        # 阅读量
        self.listen = page.xpath(‘//span[@class="nb"]/text()‘)
        # 歌单链接
        self.link = page.xpath(‘//div[@class="u-cover u-cover-1"]/a[@href]/@href‘)
        # 将数据保存为csv文件 
        data=list(zip(self.title,self.author,self.listen,self.link))
        with open(‘yinyue.csv‘,‘a‘,encoding=‘utf-8‘,newline=‘‘) as f:
            writer=csv.writer(f)
            #writer.writerow(header)
            writer.writerows(data)
    # 获取网页源代码
    def get_code(self):
        disable_warnings()
        self.froms[‘cat‘]=self.types
        disable_warnings()
        self.new_url = self.url+parse.urlencode(self.froms)
        self.code = requests.get(
            url = self.new_url,
            headers = self.header,
            data = self.froms,
            verify = False,
        ).text
 
    # 爬取多页时刷新offset
    def multi(self ,page):
        self.offset = self.limit * page - self.limit
 
 
if __name__ == ‘__main__‘:
    # 歌单的歌曲风格
    types = "说唱"
    # 歌单的发布类型:最热=hot，最新=new
    years = "hot"
    # 指定爬取的页数
    pages = 10
    # 通过pages变量爬取指定页面
    music = Wangyiyun(
        types = types,
        years = years,
    )
    for i in range(pages):
        page = i+1              # 因为没有第0页
        music.multi(page)       # 爬取多页时指定，传入当前页数，刷新offset
        music.set_header()      # 调用头部方法，构造请求头信息
        music.set_froms()       # 调用froms方法，构造froms信息
        music.get_code()        # 获取当前页面的源码
        music.parsing_codes()   # 处理源码，获取指定数据
        

import pandas as pd
#读取文件
data=pd.read_csv(r"yinyue.csv",encoding = "utf-8")
data.columns=(‘title‘,‘author‘,‘listen_num‘,‘link‘)  
data


#删除没有万单位的行
data = data[data["listen_num"].str[-1] == "万"]
data


#删除万单位
data[‘listen_num‘] = data[‘listen_num‘].str.strip("万").apply(int)
data


#删除重复值
data=data.drop_duplicates()
data.head()



data.describe()


#按播放数量进行降序排序
data = data.sort_values(‘listen_num‘,ascending = False).head(10)
data


#绘制柱状图
import seaborn as sns
import pandas as pd
import matplotlib.pyplot as plt
import matplotlib
#绘制柱状图查看top50歌单的播放量分布
plt.hist(data[‘listen_num‘],bins=50)
plt.show()


#绘制饼状图
plt.rcParams[‘font.sans-serif‘] = [‘SimHei‘]#解决乱码问题
df_score = data[‘listen_num‘].value_counts() #统计评分情况
plt.title("播放数量占比图") #设置饼图标题
plt.pie(df_score.values,labels = df_score.index,autopct=‘%1.1f%%‘) #绘图
#autopct表示圆里面的文本格式，在python里%操作符可用于格式化字符串操作
plt.show()


#绘制直方图查看播放数量的分布
sns.distplot(data[‘listen_num‘])

data.to_csv("./wangyiyun.csv")
data