#!/usr/local/bin/python from urllib2 import build_opener, HTTPCookieProcessor, Request from urllib import urlencode, urlretrieve from BeautifulSoup import BeautifulSoup, BeautifulStoneSoup import re import time import subprocess #os import cgitb; #cgitb.enable(display=0, logdir="/tmp") model_summary_page = "Extracted_model_log" #specify the root URL of the wiki url_root = 'http://www.yeastpheromonemodel.org' #the folder where the html documents will be stored date = time.strftime("%Y_%m_%d_%Hh%Mm%Ss") docFolder = date + '/' docPath = '/data/www/html/alpha/ModelDocs/' retcode = subprocess.call(["mkdir", docPath + docFolder]) #Build opener opener = build_opener(HTTPCookieProcessor) #Authenticate - note that I took the password out of the authentication... f=opener.open(Request(url_root + "/index.php?title=Special:Uerlogin",urlencode(dict(wpName="Wiki parser",wpPassword="",action="submitlogin")))) f.close() #Edit the Extracted model log page f=opener.open(url_root + "/index.php?title=" + model_summary_page + "&action=edit") #Read the HTML contents into a string of text doc = f.read() f.close() soup = BeautifulSoup(doc) editForm = soup.find("form", id="editform") new_text = "==Model " + date + "==" new_text = new_text + "\n*It takes about 20 minutes for the model file and all the documentation to be produced, so if the links do not work yet, please be patient." new_text = new_text + "\n*Model documentation: " + url_root + '/ModelDocs/' + docFolder new_text = new_text + "\n*Main model page: " + url_root + '/ModelDocs/' + docFolder + "Yeast_pheromone_response_model.html" new_text = new_text + "\n*Model file: " + url_root + '/ModelDocs/' + docFolder + "model-" + date + ".bngl" new_text = new_text + "\n*Zip file of documentation: " + url_root + '/ModelDocs/' + docFolder + date + ".zip" new_text = new_text + "\n\n" + editForm.textarea.string wpSection = editForm.find(attrs={"name":"wpSection"}) wpSection["value"] = new_text inputs = editForm.findAll("input") data = {'wpTextbox1' : wpSection["value"], 'wpSummary' : "", 'wpMinoredit' : "1", 'wpSave' : "Save page", 'wpEditToken' : editForm.find(attrs={"name":"wpEditToken"})["value"], 'wpAutoSummary':editForm.find(attrs={"name":"wpAutoSummary"})["value"], 'wpStarttime':editForm.find(attrs={"name":"wpStarttime"})["value"], 'wpEdittime':editForm.find(attrs={"name":"wpEdittime"})["value"]} urldata = urlencode(data) f=opener.open(url_root + "/index.php?title=" + model_summary_page + "&action=submit", urldata) f.close() print 'Content-Type: text/html\n\n' # HTML is following print '\n' print '' print '' f = open(docPath + docFolder + "logfile.log", "w") pid = subprocess.Popen(["./wiki_parser_v2.py", date], stdout = f, stderr = f).pid f.close()