其实呢就是从1到1147把所有的contest的题目的html下载下来,这样就可以离线刷题了(离线刷题,最为致命)结合我之前的文章 震惊! 某男子一夜之间竟把codeforces题库刷穿 改吧改吧 可以顺便 把AC代码和部分数据下载下来,为什么我不贴出来那部分呢? 因为我懒啊~~~
# coding=utf-8 import os import random import re import time import threading import urllib.request from urllib import request user_agent = [ 'Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_8; en-us) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 ' 'Safari/534.50', 'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-us) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50', 'Mozilla/5.0 (Windows NT 10.0; WOW64; rv:38.0) Gecko/20100101 Firefox/38.0', 'Mozilla/5.0 (Windows NT 10.0; WOW64; Trident/7.0; .NET4.0C; .NET4.0E; .NET CLR 2.0.50727; .NET CLR 3.0.30729; ' '.NET CLR 3.5.30729; InfoPath.3; rv:11.0) like Gecko', 'Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Trident/5.0)', 'Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.0; Trident/4.0)', 'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.0)', 'Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1)', 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10.6; rv:2.0.1) Gecko/20100101 Firefox/4.0.1', 'Mozilla/5.0 (Windows NT 6.1; rv:2.0.1) Gecko/20100101 Firefox/4.0.1', 'Opera/9.80 (Macintosh; Intel Mac OS X 10.6.8; U; en) Presto/2.8.131 Version/11.11', 'Opera/9.80 (Windows NT 6.1; U; en) Presto/2.8.131 Version/11.11', 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_0) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 ' 'Safari/535.11', 'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Maxthon 2.0)', 'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; TencentTraveler 4.0)', 'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1)', 'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; The World)', 'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Trident/4.0; SE 2.X MetaSr 1.0; SE 2.X MetaSr 1.0; .NET CLR ' '2.0.50727; SE 2.X MetaSr 1.0)', 'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; 360SE)', 'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Avant Browser)', 'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1)', 'Mozilla/5.0 (iPhone; U; CPU iPhone OS 4_3_3 like Mac OS X; en-us) AppleWebKit/533.17.9 (KHTML, like Gecko) ' 'Version/5.0.2 Mobile/8J2 Safari/6533.18.5', 'Mozilla/5.0 (iPod; U; CPU iPhone OS 4_3_3 like Mac OS X; en-us) AppleWebKit/533.17.9 (KHTML, like Gecko) ' 'Version/5.0.2 Mobile/8J2 Safari/6533.18.5', 'Mozilla/5.0 (iPad; U; CPU OS 4_3_3 like Mac OS X; en-us) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 ' 'Mobile/8J2 Safari/6533.18.5', 'Mozilla/5.0 (Linux; U; Android 2.3.7; en-us; Nexus One Build/FRF91) AppleWebKit/533.1 (KHTML, like Gecko) ' 'Version/4.0 Mobile Safari/533.1', 'MQQBrowser/26 Mozilla/5.0 (Linux; U; Android 2.3.7; zh-cn; MB200 Build/GRJ22; CyanogenMod-7) AppleWebKit/533.1 (' 'KHTML, like Gecko) Version/4.0 Mobile Safari/533.1', 'Opera/9.80 (Android 2.3.4; Linux; Opera Mobi/build-1107180945; U; en-GB) Presto/2.8.149 Version/11.10', 'Mozilla/5.0 (Linux; U; Android 3.0; en-us; Xoom Build/HRI39) AppleWebKit/534.13 (KHTML, like Gecko) Version/4.0 ' 'Safari/534.13', 'Mozilla/5.0 (BlackBerry; U; BlackBerry 9800; en) AppleWebKit/534.1+ (KHTML, like Gecko) Version/6.0.0.337 Mobile ' 'Safari/534.1+', 'Mozilla/5.0 (hp-tablet; Linux; hpwOS/3.0.0; U; en-US) AppleWebKit/534.6 (KHTML, like Gecko) wOSBrowser/233.70 ' 'Safari/534.6 TouchPad/1.0', 'Mozilla/5.0 (SymbianOS/9.4; Series60/5.0 NokiaN97-1/20.0.019; Profile/MIDP-2.1 Configuration/CLDC-1.1) ' 'AppleWebKit/525 (KHTML, like Gecko) BrowserNG/7.1.18124', 'Mozilla/5.0 (compatible; MSIE 9.0; Windows Phone OS 7.5; Trident/5.0; IEMobile/9.0; HTC; Titan)', 'UCWEB7.0.2.37/28/999', 'NOKIA5700/ UCWEB7.0.2.37/28/999', 'Openwave/ UCWEB7.0.2.37/28/999', 'Mozilla/4.0 (compatible; MSIE 6.0; ) Opera/UCWEB7.0.2.37/28/999', ] def gethtml(url): header = {'User-Agent': random.choice(user_agent)} req = request.Request(url, headers=header) try: html = request.urlopen(req).read() except urllib.request.HTTPError: with open(r'./codeforces/fail.txt', 'a+') as f: f.write('\n' + url) f.close() return False html = html.decode('utf-8') return html def save(out, a, b): try: html=gethtml(out) with open( './codeforces/' + a + '/' + a + b + '.html','w',encoding='utf-8') as f: f.write(html) except (urllib.request.HTTPError, IOError): with open(r'./codeforces/fail.txt', 'a+') as _f: _f.write('\n' + out) _f.close() else: print('solved:' + out) def solve(a): url = 'https://codeforces.com/contest/' + a html = gethtml(url) if not html: return links = re.findall('<a href="/contest/' + a + '/problem/(.+?)"><!--', html) setlinks = set(links) links = list(setlinks) links.sort() if not os.path.exists("codeforces/%s" % a): os.mkdir("codeforces/%s" % a) for b in links: if len(b) < 3: out = 'https://codeforces.com/contest/' + a + '/problem/' + b save(out, a, b) time.sleep(3) if not os.path.exists('codeforces'): os.mkdir("codeforces") #f = int(input('from:')) f=1 for a in range(f, 1147): #solve(str(a)) threading.Thread(target=solve, args=(str(a),)).start() time.sleep(20)