Codeforces科学刷题指南，一图一表便够了

1: import re
2: import urllib.request
3: from bs4 import BeautifulSoup
4: import os
5: import csv
6: import time
  

 1: #%% retrieve the problem set
 2: def spider(url):
 3:     response = urllib.request.urlopen(url)
 4:     soup = BeautifulSoup(response.read())
 5:     pattern = {'name': 'tr'}
 6:     content = soup.findAll(**pattern)
 7:     for row in content:
 8: 	item = row.findAll('td')
 9: 	try:
10: 	    # get the problem id
11: 	    id = item[0].find('a').string.strip()
12: 	    col2 = item[1].findAll('a')
13: 	    # get the problem title
14: 	    title = col2[0].string.strip()
15: 	    # get the problem tags
16: 	    tags = [foo.string.strip() for foo in col2[1:]]
17: 	    # get the number of AC submissions
18: 	    solved = re.findall('x(\d+)', str(item[3].find('a')))[0]
19: 	    # update the problem info
20: 	    codeforces[id] = {'title':title, 'tags':tags, 'solved':solved, 'accepted':0,}
21: 	except:
22: 	    continue
23:     return soup
24: 
25: codeforces = {}
26: wait = 15 # wait time to avoid the blocking of spider
27: last_page = 33 # the total page number of problem set page
28: url = ['http://codeforces.com/problemset/page/%d' % page for page in range(1,last_page+1)]
29: for foo in url:
30:     print('Processing URL %s' % foo)
31:     spider(foo)
32:     print('Wait %f seconds' % wait)
33:     time.sleep(wait)
  

 1: #%% mark the accepted problems
 2: def accepted(url):
 3:     response = urllib.request.urlopen(url)
 4:     soup = BeautifulSoup(response.read())
 5:     pattern = {'name':'table', 'class':'status-frame-datatable'}
 6:     table = soup.findAll(**pattern)[0]
 7:     pattern = {'name': 'tr'}
 8:     content = table.findAll(**pattern)
 9:     for row in content:
10: 	try:
11: 	    item = row.findAll('td')
12: 	    # check whether this problem is solved
13: 	    if 'Accepted' in str(row):
14: 		id = item[3].find('a').string.split('-')[0].strip()
15: 		codeforces[id]['accepted'] = 1
16: 	except:
17: 	    continue
18:     return soup
19: 
20: wait = 15 # wait time to avoid the blocking of spider
21: last_page = 10 # the total page number of user submission
22: handle = 'Greenwicher' # please input your handle
23: url = ['http://codeforces.com/submissions/%s/page/%d' % (handle, page) for page in range(1, last_page+1)]
24: for foo in url:
25:     print('Processing URL %s' % foo)
26:     accepted(foo)
27:     print('Wait %f seconds' % wait)
28:     time.sleep(wait)
  

 1: #%% output the problem set to csv files
 2: root = os.getcwd()
 3: with open(os.path.join(root,"CodeForces-ProblemSet.csv"),"w", encoding="utf-8") as f_out:
 4:     f_csv = csv.writer(f_out)
 5:     f_csv.writerow(['ID', 'Title', 'Tags', 'Solved', 'Accepted'])
 6:     for id in codeforces:
 7: 	title = codeforces[id]['title']
 8: 	tags = ', '.join(codeforces[id]['tags'])
 9: 	solved = codeforces[id]['solved']
10: 	accepted = codeforces[id]['accepted']
11: 	f_csv.writerow([id, title, tags, solved, accepted])
12:     f_out.close()
  

 1: #%% analyze the problem set
 2: # initialize the difficult and tag list
 3: difficult_level = {}
 4: tags_level = {}
 5: for id in codeforces:
 6:     difficult = re.findall('([A-Z])', id)[0]
 7:     tags = codeforces[id]['tags']
 8:     difficult_level[difficult] = difficult_level.get(difficult, 0) + 1
 9:     for tag in tags:
10: 	tags_level[tag] = tags_level.get(tag, 0) + 1
11: import operator
12: tag_level = sorted(tags_level.items(), key=operator.itemgetter(1))[::-1]
13: tag_list = [foo[0] for foo in tag_level]
14: difficult_level = sorted(difficult_level.items(), key=operator.itemgetter(0))
15: difficult_list = [foo[0] for foo in difficult_level]
16: 
17: # initialize the 2D relationships matrix
18: # matrix_solved: the number of AC submission for each tag in each difficult level
19: # matrix_freq: the number of tag frequency for each diffiicult level
20: matrix_solved, matrix_freq = [[[0] * len(difficult_list) for _ in range(len(tag_list))] for _ in range(2)]
21: 
22: 
23: # construct the 2D relationships matrix
24: for id in codeforces:
25:     difficult = re.findall('([A-Z])', id)[0]
26:     difficult_id = difficult_list.index(difficult)
27:     tags = codeforces[id]['tags']
28:     solved = codeforces[id]['solved']
29:     for tag in tags:
30: 	tag_id = tag_list.index(tag)
31: 	matrix_solved[tag_id][difficult_id] += int(solved)
32: 	matrix_freq[tag_id][difficult_id] += 1