爬虫大作业

Posted 2020-11-01 黄俊熙

 

打开酷我新歌排行榜，网址是http://www.kuwo.cn/bang/index

 

 

代码：

用requests库和BeautifulSoup库，爬取酷我新歌榜当前页面的每首的曲目、作者、歌词、排行、链接等，将获取歌曲详情的代码定义成一个函数 

musicUrl=\'http://www.kuwo.cn/yinyue/41185134?catalog=yueku2016\'
url=\'http://www.kuwo.cn/bang/index\'
gequ = {}
quan={}
def getNewsDetail(musicUrl ,pm):
    resd = requests.get(musicUrl)
    resd.encoding = \'utf-8\'
    soupd = BeautifulSoup(resd.text, \'html.parser\')
    info = soupd.select(\'p\')[1].text
    panduan = soupd.select(\'p\')[4].text
    # pinlun =  soupd.select(\'.title_\').text
    if (info.find("返回")>0):
        print(\'版权保护\')
        return 1
    else:




        gequ[\'曲目\']= gequ1=soupd.select(\'#lrcName\')[0].text
                            # for tit in  gequ[\'曲目\']:
                            #     print(tit.text)
        gequ[\'歌手\']=asinger=soupd.select(\'.artist\')[0].text
                            # for singer in asinger:
                            # print(\'歌手：\'+asinger[0].text)
                                 # return atit
        if(panduan.find("歌词")>0):
            gequ[\'歌词\']=\'none\'
        else:
            gequ[\'歌词\'] = ageci = soupd.select(\'#llrcId\')[0].text
                            # for geci in ageci:
                            #    print(geci.text)
        gequ[\'排名\'] =pm
        f = open(\'quan2.txt\', \'a\',encoding=\'utf-8\')
        f.write(gequ1 + \' \' + str(pm) + \'\\n\')
        f.close()






    return gequ
# gequ=getNewsDetail(musicUrl)
# print(gequ)

def getListPage(musicsurl):

    res = requests.get(url)
    res.encoding = \'utf-8\'
    soupq = BeautifulSoup(res.text,\'html.parser\')
    i=1
    p=200

    for music in soupq.select(\'.listMusic\'):
         for music in music.select(\'.name\'):
             for music in music.select(\'a\'):
               musicUrl=music[\'href\']
               i=i-1
               pm=p+i
               # set(pm)
               print(musicUrl)
               # print(pm)
               # list.append(getNewsDetail(musicUrl))
               print(getNewsDetail(musicUrl,pm))

    return 1

getListPage(url)

 

生成词云：

abel_mask = np.array(Image.open("C:\\\\timg.jpg"))
f=open(\'quan2.txt\',\'r\',encoding=\'utf-8\').read()
font=r\'C:\\Windows\\Fonts\\simkai.ttf\'
wordcloud=WordCloud(background_color="white",width=1000,height=860,margin=2,font_path=font,mask=abel_mask).generate(f)
image_colors = ImageColorGenerator(abel_mask)
plt.imshow(wordcloud)

plt.axis("off")
plt.show()
wordcloud.to_file(\'timg1.jpg\')