- from bs4 import BeautifulSoup
- import urllib,urllib.request
- import re
- print("请输入要爬取的url:")
- url=input()
- picnum=0
- while url!='-1':
- urlhd=urllib.request.Request( url, headers = {
- 'Connection': 'Keep-Alive',
- 'Accept': 'text/html, application/xhtml+xml, */*',
- 'Accept-Language': 'en-US,en;q=0.8,zh-Hans-CN;q=0.5,zh-Hans;q=0.3',
- 'User-Agent': 'Mozilla/5.0 (Windows NT 6.3; WOW64; Trident/7.0; rv:11.0) like Gecko'
- })
- page= urllib.request.urlopen(urlhd)
- soup=BeautifulSoup(page,'html.parser',from_encoding='utf-8')
- title=soup.find_all(id='title')
- lrc=soup.find_all(class_='lrc_main')
- lrc=str(lrc)
- title=str(title)
- p = re.compile('<[^>]+>')
- lrc=p.sub("",lrc)
- title=p.sub("",title)
- print(title)
- with open(str(picnum)+'.txt','w')as f:
- f.write(lrc)
- picnum+=1
- print("请输入要爬取的url:")
- url=input()
- #该片段来自于http://www.codesnippet.cn/detail/2311201615164.html
来源: http://www.codesnippet.cn/detail/2311201615164.html