爬虫虾米音乐

思路

• 找到歌单的歌曲列表 
• 
• 找到MP3超链接（虾米的链接需要进行凯撒解码） 
• 
• 解码后，直接二进制写进文件即可

代码

• 获取超链接

import time

import requests
from lxml import etree
from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.support.ui import WebDriverWait

from utils.kaisha import str2url

browser = webdriver.Chrome()
browser.set_window_size(800, 800)
wait = WebDriverWait(browser, 10)


def index_page():
    url = 'https://www.xiami.com/chart/index/c/103/type/0?spm=a1z1s.2943549.6827461.1.a26OKv'
    browser.get(url)
    # 等待元素加载完成
    wait.until(EC.presence_of_element_located((By.XPATH, '//tr[@class="songwrapper"]')))

    # 获得页面的html
    html = browser.page_source
    return html


def pares_page(html):
    # 转换属性
    etree_html = etree.HTML(html)
    # 获得所有歌曲标签mp3地址
    data_mp3_list = etree_html.xpath('//tr[@class="songwrapper"]/@data-mp3')
    # 获得歌曲名
    data_mp3_name = etree_html.xpath('//tr[@class="songwrapper"]//strong/a/text()')
    # 循环歌曲标签mp3地址
    for index in range(len(data_mp3_list)):
        # 凯撒密码解码
        mp3_url = str2url(data_mp3_list[index])
        # 组合名字
        mp3_name = './song/' + data_mp3_name[index] +'.mp3'
        headers = {"User-Agent": "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; 360SE)",}
        response = requests.get(mp3_url, headers=headers)
        # 写进文件
        with open(mp3_name, 'wb') as f:
            f.write(response.content)
        print(mp3_name)
        time.sleep(2)


def main():
    # 获得歌单页面
    page_source = index_page()
    # 下载
    pares_page(page_source)


if __name__ == '__main__':
    main()

• 凯撒解码

from urllib import parse

def str2url(s):

    num_loc = s.find('h')
    rows = int(s[0:num_loc])
    strlen = len(s) - num_loc
    cols = int(strlen/rows)
    right_rows = strlen % rows
    new_s = list(s[num_loc:])
    output = ''
    for i in range(len(new_s)):
        x = i % rows
        y = i / rows
        p = 0
        if x <= right_rows:
            p = x * (cols + 1) + y
        else:
            p = right_rows * (cols + 1) + (x - right_rows) * cols + y
        output += new_s[int(p)]
    return parse.unquote(output).replace('^', '0')