Python实例---爬去酷狗音乐

项目一：获取酷狗TOP 100

http://www.kugou.com/yy/rank/home/1-8888.html

排名

文件&&歌手

时长

效果：

附源码：

import time
import json
from bs4 import BeautifulSoup
import requests


class Kugou(object):
    def __init__(self):
        self.header = {
            "User-Agent": 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:60.0) Gecko/20100101 Firefox/60.0'
        }

    def getInfo(self, url):
        html = requests.get(url, headers=self.header)
        soup = BeautifulSoup(html.text, 'html.parser')
        # print(soup.prettify())
        ranks = soup.select('.pc_temp_num')
        titles = soup.select('.pc_temp_songlist > ul > li > a')  # 层层标签查找
        times = soup.select('.pc_temp_time')
        for rank, title, songTime in zip(ranks, titles, times):
            data = {
                # rank 全打印就是带HTML标签的
                'rank': rank.get_text().strip(),
                'title': title.get_text().split('-')[1].strip(),
                'singer': title.get_text().split('-')[0].strip(),
                'songTime': songTime.get_text().strip()
            }
            s = str(data)
            print('rank:%2s	' % data['rank'], 'title:%2s	' % data['title'], 'singer:%2s	' %data['singer'], 'songTime:%2s	' % data['songTime'])
            with open('hhh.txt', 'a', encoding='utf8') as f:
               f.writelines(s + '
')

if __name__ == '__main__':
    urls = [
        'http://www.kugou.com/yy/rank/home/{}-8888.html'.format(str(i)) for i in range(30)
    ]

    kugou = Kugou()
    for url in urls:
        kugou.getInfo(url)
        time.sleep(1)

部分代码解析

--------------------------------------------------------------------
urls = ['http://www.kugou.com/yy/rank/home/{}-8888.html'.format(str(i)) for i in range(1, 5)]
for i in urls:
    print(i)

结果打印：
	http://www.kugou.com/yy/rank/home/1-8888.html
	http://www.kugou.com/yy/rank/home/2-8888.html
	http://www.kugou.com/yy/rank/home/3-8888.html
	http://www.kugou.com/yy/rank/home/4-8888.html
--------------------------------------------------------------------
for rank, title, songTime in zip(ranks, titles, times):
    data = {
        # rank 全打印就是带HTML标签的
        'rank': rank.get_text().strip(),
        'title': title.get_text().split('-')[0].strip(),
        'singer': title.get_text().split('-')[1].strip(),
        'songTime': songTime.get_text()
    }
    print(data['rank'])
    print(data['title'])
    print(data['singer'])
    print(data['songTime'])
	
结果打印：
    1
    飞驰于你
    许嵩
    4: 04
--------------------------------------------------------------------   
for rank, title, songTime in zip(ranks, titles, times):
	data = {
		# rank 全打印就是带HTML标签的
		'rank': rank,
		'title': title,
		'songTime': songTime
	}
	print(data['rank'])
	print(data['title'])
	print(data['songTime'])
结果打印：
<span class="pc_temp_num">
	<strong>1</strong>
</span>
<a class="pc_temp_songname" data-active="playDwn" data-index="0" hidefocus="true" href="http://www.kugou.com/song/pjn5xaa.html" title="许嵩 - 飞驰于你">许嵩 - 飞驰于你</a>
<span class="pc_temp_time">	4:04 </span>

项目二：搜索曲目获取URL

根据关键字搜索后的结果：

http://songsearch.kugou.com/song_search_v2?callback=jQuery191034642999175022426_1489023388639&keyword=%E5%9B%AD%E6%B8%B8%E4%BC%9A&page=1&pagesize=30&userid=-1&clientver=&platform=WebFilter&tag=em&filter=2&iscorrection=1&privilege_filter=0&_=1489023388641%27

# encoding=utf-8
# Time    : 2018/4/27
# Email   : z2615@163.com
# Software: PyCharm
# Language: Python 3
import requests
import json


class KgDownLoader(object):
    def __init__(self):
        self.search_url = 'http://songsearch.kugou.com/song_search_v2?callback=jQuery191034642999175022426_1489023388639&keyword={}&page=1&pagesize=30&userid=-1&clientver=&platform=WebFilter&tag=em&filter=2&iscorrection=1&privilege_filter=0&_=1489023388641'

        # .format('园游会')
        self.play_url = 'http://www.kugou.com/yy/index.php?r=play/getdata&hash={}'
        self.song_info = {
            '歌名': None,
            '演唱者': None,
            '专辑': None,
            'filehash': None,
            'mp3url': None
        }

    def get_search_data(self, keys):
        search_file = requests.get(self.search_url.format(keys))
        search_html = search_file.content.decode().replace(')', '').replace(
            'jQuery191034642999175022426_1489023388639(', '')
        views = json.loads(search_html)
        for view in views['data']['lists']:
            song_name = view['SongName'].replace('<em>', '').replace('</em>', '')
            album_name = view['AlbumName'].replace('<em>', '').replace('</em>', '')
            sing_name = view['SingerName'].replace('<em>', '').replace('</em>', '')
            file_hash = view['FileHash']
            new_info = {
                '歌名': song_name,
                '演唱者': sing_name,
                '专辑': album_name if album_name else None,
                'filehash': file_hash,
                'mp3url': None
            }
            self.song_info.update(new_info)
            yield self.song_info

    def get_mp3_url(self, filehash):
        mp3_file = requests.get(self.play_url.format(filehash)).content.decode()
        mp3_json = json.loads(mp3_file)
        real_url = mp3_json['data']['play_url']
        self.song_info['mp3url'] = real_url
        yield self.song_info

    def save_mp3(self, song_name, real_url):
        with open(song_name + ".mp3", "wb")as fp:
            fp.write(requests.get(real_url).content)


if __name__ == '__main__':
    kg = KgDownLoader()
    mp3_info = kg.get_search_data(input('请输入歌名：'))
    for x in mp3_info:
        mp3info = kg.get_mp3_url(x['filehash'])
        for i in mp3info:
            print(i)

项目三：搜索下载歌曲

代码仅供学习参考

from selenium import webdriver

from bs4 import BeautifulSoup

import urllib.request

from selenium.webdriver.common.action_chains import ActionChains

input_string = input('>>>please input the search key:')

#input_string="你就不要想起我"

driver = webdriver.Chrome()

driver.get('http://www.kugou.com/')


a=driver.find_element_by_xpath('/html/body/div[1]/div[1]/div[1]/div[1]/input') #输入搜索内容/html/body/div[1]/div[1]/div[1]/div[1]/input

a.send_keys(input_string)

driver.find_element_by_xpath('/html/body/div[1]/div[1]/div[1]/div[1]/div/i').click() #点击搜索/html/body/div[1]/div[1]/div[1]/div[1]/div/i

for handle in driver.window_handles:#方法二，始终获得当前最后的窗口，所以多要多次使用

    driver.switch_to_window(handle)

#result_url = driver.current_url


#driver = webdriver.Firefox()

#driver.maximize_window()

#driver.get(result_url)

#j=driver.find_element_by_xpath('/html/body/div[4]/div[1]/div[2]/ul[2]/li[2]/div[1]/a').get_attribute('title')测试

#print(j)

soup = BeautifulSoup(driver.page_source,'lxml')

PageAll = len(soup.select('ul.list_content.clearfix > li'))

print(PageAll)

for i in range(1,PageAll+1):

    j=driver.find_element_by_xpath('/html/body/div[4]/div[1]/div[2]/ul[2]/li[%d]/div[1]/a'%i).get_attribute('title')

    print('%d.'%i + j)

choice=input("请输入你要下载的歌曲（输入序号）：")

#global mname

#mname=driver.find_element_by_xpath('/html/body/div[4]/div[1]/div[2]/ul[2]/li[%d]/div[1]/a'%choice).get_attribute('title')#歌曲名

a=driver.find_element_by_xpath('/html/body/div[4]/div[1]/div[2]/ul[2]/li[%s]/div[1]/a'%choice)#定位

b=driver.find_element_by_xpath('/html/body/div[4]/div[1]/div[2]/ul[2]/li[%s]/div[1]/a'%choice).get_attribute('title')

actions=ActionChains(driver)#selenium中定义的一个类

actions.move_to_element(a)#将鼠标移动到指定位置

actions.click(a)#点击

actions.perform()

#wait(driver)?

#driver = webdriver.Firefox()

#driver.maximize_window()

#driver.get(result_url)

#windows = driver.window_handles

#driver.switch_to.window(windows[-1])

#handles = driver.window_handles

for handle in driver.window_handles:#方法二，始终获得当前最后的窗口，所以多要多次使用

    driver.switch_to_window(handle)

Local=driver.find_element_by_xpath('//*[@id="myAudio"]').get_attribute('src')

print(driver.find_element_by_xpath('//*[@id="myAudio"]').get_attribute('src'))

def cbk(a, b, c):

    per = 100.0 * a * b / c

    if per > 100:

        per = 100

    print('%.2f%%' % per)

soup=BeautifulSoup(b)

name=soup.get_text()

path='D:\%s.mp3'%name

urllib.request.urlretrieve(Local, path, cbk)

print('finish downloading %s.mp3' % name + '

')