抓取 题目描述 生成 解题报告 模板 python

BGround

Code

# -*- coding: utf-8 -*-

import requests, time, re
import HTMLParser

def getPage(html, url, headers, params = {}, timeout = 5, verify = True):
response = html.get(url = url, headers = headers, params = params, timeout = timeout, verify = verify)
page = response.content
return page

def search(string, page, flags = 0):
pattern = re.compile(string, flags = flags)
results = re.findall(pattern, page)
return results

def format(string):
results = HTMLParser.HTMLParser().unescape(re.compile(r'<[^>]+>', re.S).sub('', re.sub('</strong>|</h2>', '\n---\n', re.sub('<strong>|<h2>', '\n##', string.decode('UTF-8')))))
return results

def main():
html = requests.session()
headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/49.0.2623.22 Safari/537.36 SE 2.X MetaSr 1.0'}
probid = raw_input('id: ')
url = 'https://www.luogu.org/problem/show?pid=%s#sub' % probid
PD = search(r"<div class=\"lg-article am-g\">(.+?)<div class=\'lg-article-sub am-g\' id=\"sub\"></div>", getPage(html, url, headers), flags = re.S)[0]
with open('/home/olahiuj/文档/progs/oi/luogu%s.cpp' % probid, 'r') as file:
content = '''
%s

## Analysis
---

## Code
---
` ``
%s
` ``
''' % (re.sub('    ', '', format(PD).encode('UTF-8')), file.read().encode('UTF-8'))
with open('/home/olahiuj/文档/LPD/luogu%s.md' % probid, 'w') as file:
file.write(content)
print 'Problem %s is Done!' % probid

if __name__ == '__main__':
main()