python b站 排行_python爬取b站排行榜视频信息

1 import xlrd#读取excel

2 import xlwt#写入excel

3 importrequests4 importlinecache5 importwordcloud6 importjieba7 importmatplotlib.pyplot as plt8 from bs4 importBeautifulSoup9

10 if __name__=="__main__":11 f = xlwt.Workbook(encoding='utf-8') #创建工作簿

12 sheet1 = f.add_sheet(u'sheet1') #创建sheet

13 row0 = [u'ID',u'name',u'av',u'play_num',u'comment_num']14 #生成第一行

15 for i inrange(0,len(row0)):16 sheet1.write(0,i,row0[i])17 yun=""

18

19 n=0#ID编号

20 target='https://www.bilibili.com/ranking/all/160/0/3'#b站

21 user_agent = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/54.0.2840.99 Safari/537.36'

22 headers = {'User-Agent':user_agent}23

24 req=requests.get(url=target)25 html=req.text26 html=html.replace('
',' ').replace('
',' ').replace('/>','>')27 bf=BeautifulSoup(html,"html.parser")28

29 texts=bf.find('ul',class_='rank-list')30 texts_div=texts.find_all('div',class_='info')31 #print(texts_div)

32 for item intexts_div:33 n=n+1

34 item_name=item.find('a').text#标题

35 yun+=str(item_name)36 item_href=item.find('a')['href']#链接

37 h=item_href.rfind('/')38 item_href=item_href[h+1:]39 item_refer=item.find_all('span',class_='data-box')40 item_refer1=item_refer[0].text41 item_refer2=item_refer[1].text42 #print('{} {} {} {}\n'.format(item_name,item_href,item_refer1,item_refer2))

43 mid=[n,item_name,item_href,item_refer1,item_refer2]44 #print(mid)

45 for i in range(len(row0)):#写入excel

46 sheet1.write(n,i,mid[i])47 f.save('demo1.xls') #保存文件

48

49 #结巴分词，生成字符串，wordcloud无法直接生成正确的中文词云

50 cut_text = " ".join(jieba.cut(yun))51 wc =wordcloud.WordCloud(52 #设置字体，不然会出现口字乱码，文字的路径是电脑的字体一般路径，可以换成别的

53 font_path="C:/Windows/Fonts/simfang.ttf",54 #设置了背景，宽高

55 background_color="white",width=1000,height=880).generate(cut_text)56

57 plt.imshow(wc, interpolation="bilinear")58 plt.axis("off")59 plt.show()60 print("Done!")