Created
January 14, 2010 00:24
-
-
Save sarcilav/276731 to your computer and use it in GitHub Desktop.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| #!/usr/bin/python | |
| import urllib2 | |
| import os | |
| import sys | |
| url = str(sys.argv[1]) | |
| htmlfile = "en.html" | |
| urlread = lambda url: urllib2.urlopen(url).read() | |
| s_parameters = "<td class=\"statText\">Parameters:</td>\n" | |
| s_returns = "<td class=\"statText\">Returns:</td>\n" | |
| s_previous = "<td class=\"statText\">" | |
| s_post = "</td>" | |
| s_html_eat_previous = "<tr><td class=\"statText\"><pre>" | |
| s_html_eat_post = "</pre></td></tr>" | |
| s_return = "Returns: " | |
| #Toma el tipo del input y la string que lo representa y retorna la forma apropiada | |
| def eat_that(type, s): | |
| s.replace("\n","") | |
| s_ans = "" | |
| if(type == "int"): | |
| return s.replace(" ","") | |
| elif(type == "double"): | |
| return s.replace(" ","") | |
| elif(type == "String"): | |
| return s[s.find("\"")+1:len(s)-1] | |
| else : | |
| s = s.replace("{","") | |
| s = s.replace("}","") | |
| list = s.split(",") | |
| s_ans += str(len(list)) +"\n" | |
| s_type = type.replace("[]","") | |
| for i in list: | |
| s_ans += eat_that(s_type,i) | |
| s_ans += "\n" | |
| return s_ans[0:len(s_ans)-1] | |
| #Toma el html del enunciado del problema , la string que indica los parametros y retorna | |
| #un vector de 2 posiciones la primera la string de la entrada y la segunda la string de la salida | |
| def eat_cases(html,param, returns): | |
| param = param.replace(" ","") | |
| params = param.split(",") | |
| n_params = len(params) | |
| returns = returns.replace(" ","") | |
| n_returns = 1 | |
| s_in = "" | |
| s_out = "" | |
| i_index = html.find(s_html_eat_previous) | |
| cnt = 0 | |
| p = 0 | |
| while(i_index >= 0): | |
| cnt += 1 | |
| i_index += len(s_html_eat_previous) | |
| j_index = html.find(s_html_eat_post,i_index) | |
| if( cnt % (n_params + n_returns) == 0): | |
| s_out += eat_that(returns,html[i_index+len(s_return):j_index]) | |
| s_out += "\n" | |
| else : | |
| s_in += eat_that(params[p % n_params],html[i_index:j_index] ) | |
| s_in +="\n" | |
| p += 1 | |
| i_index = html.find(s_html_eat_previous,j_index) | |
| return [s_in,s_out] | |
| #Toma el html partido de la pagina inicial y busca los directorios y los crea | |
| def deep_and_parse( val ): | |
| i_first = val.find("\"") | |
| i_second = val.find("\"",i_first + 1) | |
| dir = val[i_first + 1:i_second] | |
| try: | |
| os.makedirs(dir) | |
| except OSError: | |
| pass | |
| html = urlread(url+dir+htmlfile) | |
| i_params = html.find(s_parameters) + len (s_parameters) + len(s_previous) | |
| j_params = html.find(s_post,i_params) | |
| i_returns = html.find(s_returns) + len(s_returns) + len(s_previous) | |
| j_returns = html.find(s_post,i_returns) | |
| print html[i_params:j_params] | |
| print html[i_returns:j_returns] | |
| list = eat_cases(html, html[i_params:j_params], html[i_returns:j_returns]) | |
| file = open(dir+"in","w") | |
| file.writelines(list[0]) | |
| file.close() | |
| file = open(dir+"out","w") | |
| file.writelines(list[1]) | |
| file.close() | |
| list = urlread(url).split("alt=\"[DIR]\"") #importa de 2 en adelante | |
| list = list[2:len(list)] | |
| for i in list: | |
| deep_and_parse(i) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment