python_爬取音乐部落

本文介绍了一个使用Python实现的Luoo音乐爬虫项目。该爬虫能够抓取音乐列表和专辑信息,并下载对应的音乐文件到本地指定路径。文章详细展示了如何通过发送HTTP请求获取网页内容、解析HTML数据提取所需信息,以及如何处理音乐下载流程。

摘要生成于 C知道 ,由 DeepSeek-R1 满血版支持, 前往体验 >

#有点瑕疵不想改的了
import requests
from bs4 import BeautifulSoup
import bs4
import os
def getHtmlText(url):
    try:
        r=requests.get(url)
        r.raise_for_status()
        r.encoding='utf-8'
        return r.text
    except:
        return '连接异常'

def getMusic_list(html,musiclist):

    soup = BeautifulSoup(html,'html.parser')
    alist = soup.find('div',attrs={'class':'pagenav-wrapper'}).children
    for a in alist:
        if isinstance(a, bs4.element.Tag):
            musicdict = {}
            a_href = a['href']
            a_text = a.text
            musicdict[a_href] = a_text
            musiclist.append(musicdict)

def  music_style(num,musiclist):
    msg = ''
    if num.isdigit():
        num = int(num)
        if num<len(musiclist):
            page = input("你想听得页数")
            a_href = list(musiclist[num].keys())[0]+'?p=%s'%page
            msg = getHtmlText(a_href)
            return msg
        else:
            msg = '超过最大目录'
            return msg
    else:
        msg = '请输入正确的数字'
        return msg

def style_info(style_html,albumlist):
    soup = BeautifulSoup(style_html,'html.parser')
    for div_vollist in soup.select('.vol-list'):
        a = div_vollist("a",attrs={'class':'cover-wrapper'})
        if a ==[]:
            return "超过最大页数"

    for a_title in a:
        music_album = {}
        music_album[a_title['title']] = a_title['href']
        albumlist.append(music_album)

def music_loads(num, albumlist,artistlist):
    msg = ''
    if num.isdigit():
        num = int(num)
        if num < len(musiclist):
            url = list(albumlist[num].values())[0]
            html = getHtmlText(url)
            soup = BeautifulSoup(html, 'html.parser')

            vol_num=soup.select('.vol-number')[0].text+"|"+soup.select('.vol-title')[0].text
            for class_player in soup.select(".player-wrapper"):
                name = class_player.select('.name')[0].text
                artist = class_player.select('.artist')[0].text
                artistlist[name]=artist
                print(name+"||"+artist)
            return  vol_num
        else:
            msg = '超过最大目录'
            return msg

def loding(artistlist,vol_num):
    url_num,url_root=vol_num.split('|')
    url="http://mp3-cdn2.luoo.net/low/luoo/radio{}/"
    root = "D://Music//%s//"%url_root
    patha=[]
    for k_name, v_artist in artistlist.items():
        paths=root+str(k_name)+str(".mp3")
        patha.append(paths)
    if not os.path.exists(root):
        os.mkdir(root)
    for i,p in enumerate(patha):
        url1=" "
        if not os.path.exists(p):
            if i<9:
                a=str(i+1)+".mp3"
                url1=url.format(str(url_num))+"0"+a
                print(url1)
                r = requests.get(url1)
                with open(p,"wb") as f:
                    f.write(r.content)
            else :
                a = str(i + 1) + ".mp3"
                url1 = url.format(str(url_num))+a
                print(url1)
                r = requests.get(url1)
                with open(p, "wb") as f:
                    f.write(r.content)

if __name__ == '__main__':
    artistlist={}
    info = "{0:^10}\t{1:{2}^5}"
    musiclist=[]
    albumlist=[]
    url="http://www.luoo.net/music/"
    html = getHtmlText(url)
    getMusic_list(html, musiclist)
    for index,i in enumerate(musiclist):
        print(info.format(index,list(i.values())[0],chr(12288)))
    num = input("请输入你想听得类型序号")
    style_html = music_style(num, musiclist)
    if style_html == '请输入正确的数字' or style_html == '超过最大目录':
        print(style_html)
    else:
        style_html = style_html
        style_info(style_html,albumlist)
        for index, i in enumerate(albumlist):
            print(info.format(index,list(i.keys())[0],chr(12288)))

        num = input("请输入你想听得类型序号")
        vol_num=music_loads(num, albumlist,artistlist)
        loding(artistlist, vol_num)

好的,这里提供一个简单的爬取猎聘大数据岗位相关信息的Python代码,具体步骤如下: 1. 导入所需库:requests、bs4、pandas 2. 定义一个函数,用于爬取指定页面的数据,并将数据转换为DataFrame格式 3. 定义一个循环语句,用于爬取多个页面的数据 4. 将所有爬取到的数据合并为一个DataFrame,并保存为Excel文件 代码如下: ```python import requests from bs4 import BeautifulSoup import pandas as pd # 定义一个函数,用于爬取指定页面的数据,并将数据转换为DataFrame格式 def get_data(url): headers = { 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.3'} response = requests.get(url, headers=headers) soup = BeautifulSoup(response.content, 'lxml') job_list = soup.find_all('div', class_='job-info') data = [] for job in job_list: job_title = job.find('h3').text.strip() company = job.find('p', class_='company-name').text.strip() salary = job.find('span', class_='text-warning').text.strip() location = job.find('p', class_='area').text.strip() experience = job.find('p', class_='experience').text.strip() education = job.find('p', class_='education').text.strip() job_desc = job.find('p', class_='temptation').text.strip() data.append([job_title, company, salary, location, experience, education, job_desc]) df = pd.DataFrame(data, columns=['职位名称', '公司名称', '薪资', '工作地点', '工作经验', '教育程度', '职位描述']) return df # 定义一个循环语句,用于爬取多个页面的数据 result = pd.DataFrame() for i in range(1, 11): url = 'https://www.liepin.com/zhaopin/?key=大数据&d_sfrom=search_fp&headckid=8cfa3a6d7e4f2f4d&flushckid=1&d_pageSize=40&d_curPage={}'.format(i) df = get_data(url) result = pd.concat([result, df], ignore_index=True) # 将所有爬取到的数据合并为一个DataFrame,并保存为Excel文件 result.to_excel('大数据岗位.xlsx', index=False) print('数据已保存!') ``` 其中,for循环语句中的range(1, 11)表示爬取10页数据,可以根据需要进行修改。另外,最后一行代码将所有爬取到的数据保存为Excel文件,文件名为“大数据岗位.xlsx”,可以根据需要进行修改。
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值