quick and dirty script to transfer passed proposals from the iuf committee to a github repository. Requires python 2.x

issues.py

#!/usr/bin/python
# -*- coding: <utf-8> -*-
import getopt
import sys
import urllib2
from urllib2 import URLError, HTTPError
import base64
import json
import getpass
from BeautifulSoup import BeautifulSoup, Tag
import HTMLParser

html_parser = HTMLParser.HTMLParser()



class Issue(object):
    '''
    Example:
      "title": "Found a bug",
      "body": "I'm having a problem with this.",
      "assignee": "octocat",
      "milestone": 1,
      "labels": [
        "Label1",
        "Label2"
      ]
    '''
    def __init__(self, title, body, *args, **kwargs):
        
        self.title = html_parser.unescape(title)
        self.body = html_parser.unescape(body)
        self.labels = []
        self.milestone = None

def getHTML(url):
    '''return html sources of a webpage'''
    f = urllib2.urlopen(url)
    html = f.read()
    return html

def parseProposals(html):
    '''
    given the html parse it and extract proposal names, ids and text.
    Return a list of proposal objects.
    '''
    soup = BeautifulSoup(html)
    proposals = soup.findAll('h2')
    issues = []
    for section in proposals: #proposal titles are in h2 headings
        propnum, title = section.text.split(":", 1)
        propurl = "http://rulebook.unicycling.org/proposals/%s" % propnum.split()[-1]
        title = "Apply proposal: %s" % title
        issue = Issue(title, "%s (see: %s)\n" % (propnum.strip(), propurl))
        issue.labels.append("committeeproposal")
        #FIXME: miletsone number should be retrieved dynamically
        issue.milestone = 1
        issues.append(issue)
        #get first proposal node below the h2 heading
        proposal = None
        h3s = section.findNextSiblings("h3")
        nextNode = h3s[3] # the proposal heading
        while True:
            tag_name = ""
            nextNode = nextNode.nextSibling
            try:
                tag_name = nextNode.name
            except AttributeError:
                tag_name = ""
                continue
            if tag_name == "p":
                contents = nextNode.contents
                # join all text elements separated by newlines, ignore Tags
                text = "\n".join([item for item in contents if not isinstance(item, Tag)])
                issue.body += html_parser.unescape("\n%s" % text)
            else:
                break
    return issues



def postIssue(issue, destination, user, password):
    '''posts the issue object serialized to json via the github api v3'''
    headers = {
        'Connection': 'keep-alive',
        'User-Agent': 'IUF',
        'Content-type': 'application/json; charset=UTF-8',
        'Accept': 'application/json, */*',
    }
    data = json.dumps(issue.__dict__)
    base64str = base64.encodestring("%s:%s" % (user, password)).replace("\n", "")
    req = urllib2.Request(destination, data, headers) 
    req.add_header("Authorization", "Basic %s" % base64str)
    try:
        response = urllib2.urlopen(req)
        return True
    except URLError as err:
        print err.reason
        return False
    except HTTPError as err:
        print err.code
        print err.reason
        return False


def main(argv):
    #url with passed proposals
    url = "http://rulebook.unicycling.org/proposals/passed"
    #get destination repository
    destination = raw_input("destination repository in the form 'user/repository': ")
    destination = 'https://api.github.com/repos/%s/issues' % destination
    print destination
    #get credentials
    user = raw_input("username on github: ")
    print "enter password for %s" % user
    pw = getpass.getpass()
    #parse proposals and post issues
    html = getHTML(url)
    issues = parseProposals(html)
    failed = []
    for issue in issues:
        success = postIssue(issue, destination, user, pw)
        if(not success):
            failed.append(issue)
    if(len(failed) > 0):
        print "The following proposals could not be added as issues:"
    for issue in failed:
        print failed.title

if __name__ == "__main__":
    main(sys.argv[1:])