Python 爬虫 小练习

获得某易云音乐 对应歌单下的所有歌曲的歌曲、专辑图片、歌手图片、lrc歌词

import requests
from bs4 import BeautifulSoup
from selenium import webdriver
from selenium.webdriver.chrome.options import Options
import urllib.request
import json
import re

headers = {
    'Referer': 'http://music.163.com/',
    'Host': 'music.163.com',
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/62.0.3202.75 Safari/537.36',
    'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8',
}
play_url = 'http://music.163.com/playlist?id=752199922'

chrome_options = Options()
chrome_options.add_argument('--headless')
chrome_options.add_argument('--disable-gpu')
browser = webdriver.Chrome('D:/chromedriver_win32/chromedriver.exe', chrome_options=chrome_options) # 下载的chromedriver_win32的路径
browser.get(play_url)
browser.switch_to.frame('contentFrame')

trList = browser.find_element_by_class_name('m-table ').find_element_by_css_selector('tbody').find_elements_by_tag_name(
    'tr')
assets = []
for i in range(len(trList)):
    asset = []
    tdList = trList[i].find_elements_by_tag_name('td')
    musicID = str(tdList[1].find_element_by_tag_name('a').get_attribute('href')).split('?')[1]
    musicName = tdList[1].find_element_by_tag_name('a').find_element_by_tag_name('b').get_attribute('title')
    singer = tdList[3].find_elements_by_tag_name('a')
    singerList = []
    for j in range(len(singer)):
        singerUrl = singer[j].get_attribute('href')
        singerList.append(singerUrl)
    albumUrl = tdList[4].find_element_by_tag_name('a').get_attribute('href')
    musicUrl = 'http://music.163.com/song/media/outer/url?' + musicID + '.mp3'
    lyricUrl = 'http://music.163.com/api/song/lyric?' + musicID + '&lv=1&kv=1&tv=-1'
    asset.append(musicName)
    asset.append(musicUrl)
    asset.append(lyricUrl)
    asset.append(albumUrl)
    asset.append(singerList)
    assets.append(asset)

for i in assets:
    # 歌曲名称 歌曲下载地址 歌词lrc下载地址 专辑地址
    musicName = i[0]
    musicDownUrl = i[1]
    lrcDownUrl = i[2]
    albumUrl = i[3]
    singerUrl = i[4]
    try:
        # 下载歌曲
        urllib.request.urlretrieve(musicDownUrl, 'D:/歌曲/%s.mp3' % musicName)

        # 下载歌词
        html = requests.get(lrcDownUrl, headers=headers).text
        json_obj = json.loads(html)
        try:
            lrc = json_obj['lrc']['lyric']
            with open('D:歌词/{}.lrc'.format(musicName), 'a', encoding='utf-8') as fp:
                fp.write(lrc)
        except KeyError as e:
            pass

        # 下载专辑图片
        html = requests.get(albumUrl, headers=headers).text
        img = re.findall(r'<meta property="og:image" content="(.*?)" />', html, re.DOTALL)[0]
        req = requests.get(img)
        with open('D:/专辑图片/{}.jpg'.format(musicName), 'wb') as fp:
            fp.write(req.content)

        # 下载专辑图片
        html = requests.get(albumUrl, headers=headers).text
        img = re.findall(r'<meta property="og:image" content="(.*?)" />', html, re.DOTALL)[0]
        req = requests.get(img)
        albumName = re.findall(r'meta property="og:title" content="(.*?)" />', html, re.DOTALL)[0]
        with open('D:/专辑图片/{}.jpg'.format(albumName), 'wb') as fp:
            fp.write(req.content)

        # 下载歌手图片
        for k in singerUrl:
            html = requests.get(k, headers=headers).text
            img = re.findall(r'<meta property="og:image" content="(.*?)" />', html, re.DOTALL)[0]
            req = requests.get(img)
            singerName = re.findall(r'<meta name="keywords" content="(.*?)" />', html, re.DOTALL)[0]

            with open('D:/歌手图片/{}.jpg'.format(singerName), 'wb') as fp:
                fp.write(req.content)
        print('下载成功')
    except:
        print('下载失败')

只不过感觉下载速度有点慢，才60个资源就下了好久，不知道是不是用了chromedriver的原因