聲明：本文僅作為學(xué)習(xí)愛好者編寫，請勿商業(yè)和惡意攻擊源網(wǎng)站，本文所有解釋權(quán)歸作者
本文沒有使用爬蟲框架，僅用了三個Python的常用庫
本文適合新手參考，文章里面有大量注釋為理解提供便利

            
              # 爬喜馬拉雅
import requests
from lxml import etree
import os
headers = {
    "User-Agent": "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.181 Safari/537.36",
    'Referer':'https://www.ximalaya.com/'
}
# 設(shè)置url 我們先搞第一頁，注意默認p1是省略的               總歌單      單歌曲
# https://www.ximalaya.com/youshengshu/14968275/83332135
# 如果要爬取別的區(qū)塊的內(nèi)容，則修改下面的url就可以了
url = "https://www.ximalaya.com/youshengshu/p1/"
# 列表頁函數(shù)
def listing(url):
    #直接請求
    response = requests.get(url=url, headers=headers).text
    # 生成解析對象
    etrees = etree.HTML(response)
    # 解析頁面 獲取當(dāng)前頁的歌曲地址
    page_listing_url = etrees.xpath('//div[@class="sound-list _yo5_"]/ul/li/div[@class="text _yo5_"]/a/@href')
    # 獲取歌曲名稱
    page_listing_name = etrees.xpath('//div[@id="anchor_sound_list"]/div/ul/li/div[@class="text _yo5_"]/a/span/text()')
    # 獲取總的名字
    all_name = etrees.xpath('//div[@class="info _J460"]/h1/text()')[0]
    # 遍歷歌曲url不是傳到詳情頁 而是傳到外鏈頁   https://link.hhtjim.com/ximalaya/203837977.mp3
    file_path = "./%s/"%all_name
    if not os.path.exists(file_path):
        os.mkdir(file_path)
        for i,j in enumerate(page_listing_url):
            for k,v in enumerate(page_listing_name):
                if i == k:
                    # 分割i ,拿出歌曲id
                    song_id = j.split("/")[-1]
                    # 拼接路由
                    url = "https://link.hhtjim.com/ximalaya/" + song_id + ".mp3"
                    # 傳給外鏈頁url,返回歌曲內(nèi)容
                    content = linking(url)
                    with open(file_path + v + ".mp3","wb") as f:
                        f.write(content)
                    print("%s，%s下載成功"%(all_name,v))
    # 獲取下一頁的列表，有下一頁則遞歸
    next_url = etrees.xpath('//div[@class="pagination _yo5_"]/nav/ul/li[@class="page-next page-item _dN2"]/a/@href')
    if next_url:
        # 拼接路由
        url = "https://www.ximalaya.com" + next_url[0]
        # 遞歸調(diào)用
        listing(url)
    else:
        pass
# 外鏈頁函數(shù)
def linking(url):
    response = requests.get(url=url,headers=headers).content
    return response
# 分類首頁函數(shù)
def category_index(url):
    # 發(fā)送請求
    response = requests.get(url=url,headers=headers).text
    # 生成解析對象
    etrees = etree.HTML(response)
    # 解析頁面 獲取當(dāng)前頁的歌單地址
    # page_url_list = etrees.xpath('//div[@class="content"]/ul/li/div/a[@class="album-title line-1 lg bold _qie"]/@href')
    page_url_list = etrees.xpath('//div[@class="content"]/ul/li/div/a[@class="album-title line-1 lg bold _qie"]/@href')
    print(page_url_list)
    # page_name_list = etrees.xpath('//div[@class="content"]/ul/li/div/a/span/text()')
    # 獲取之后遍歷，直接把url傳到列表頁
    for i in page_url_list:
        # 拼接url傳值    /youshengshu/25407248/   https://www.ximalaya.com/youshengshu/25407248/
        url = "https://www.ximalaya.com" + i
        listing(url)
    # 判斷是否還有下一頁   /youshengshu/p2/
    next_url = etrees.xpath('//div[@class="pagination-wrap"]/nav/ul/li[@class="page-next page-item _dN2"]/a/@href')
    if next_url:
        # 拼接路由
        url = "https://www.ximalaya.com" + next_url[0]
        # 遞歸調(diào)用
        category_index(url)
    else:
        pass
# 調(diào)用分類首頁函數(shù)
category_index(url)