- #-*- coding: utf-8 -*-
- import urllib.request
- import re
- from _io import open
- def yunpan_search():
- url = "https://www.zhihu.com/explore"
- req = 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'
- })
- opener = urllib.request.urlopen(req)
- html = opener.read()
- html = html.decode('utf-8')
- rex = '(?<=<textarea class="content hidden">\\n).*?(?=<span class="answer-date-link-wrap">)'
- m = re.findall(rex,html,re.S)
- f = open('/root/Desktop/zhihu.txt','w')
- for i in m:
- f.write(i)
- f.write('\\n\\n')
- f.close()
- print("抓取成功!")
- file = open('/root/Desktop/zhihu.txt','r+')
- fullfile = file.readlines()
- text = []
- p = re.compile(r'\\w*', re.L)
- pp = re.compile(r"(&;)*")
- for line in fullfile:
- lines = p.sub('',line)
- liness = pp.sub('',lines)
- text.append(liness)
- file.seek(0)
- file.truncate(0)
- file.writelines(text)
- file.close()
- print("处理成功!")
- if __name__=='__main__':
- yunpan_search()
- #该片段来自于http://www.codesnippet.cn/detail/1301201614421.html
来源: http://www.codesnippet.cn/detail/1301201614421.html