import zephyr
import feedparser
import pycurl
+from BeautifulSoup import BeautifulSoup
"""Screen scrapes jira.mit.edu. Supposedly. Doesn't actually work yet.
self.lastResult = ''
c.perform()
return self.lastResult
+ def getPage(self, url):
+ return Page(url, self.get(url), self)
+
+class Page(object):
+ def __init__(self, url, contents, browser):
+ self.url = url
+ self.soup = BeautifulSoup(contents)
+ self.browser = browser
+ def submitForm(self, name, args ={}):
+ form = self.soup.find(name='form', attrs={"name": name})
+ if form == None: return False
+ dest = form.get('action', self.url)
+ # this has a lot of edge-cases that don't work
+ inputs = form.findAll(name='input')
+ vals = {}
+ for input in inputs:
+ vals[input[name]] = input[value]
+ for k,v in args.items():
+ vals[k] = v
+ return self.browser.getPage()
+
b = Browser(
SSLCERT = "cert.pem",
SSL_VERIFYPEER = 0,
COOKIEJAR = "jirabot.cookie",
FOLLOWLOCATION = 1,
+ AUTOREFERER = 1,
+ HTTPHEADER = ["Accept-Language: en-us,en;q=0.5"],
)
b.get("https://jira.mit.edu/jira/secure/Dashboard.jspa")
-print b.get("https://jira.mit.edu/jira/secure/mit_login.jsp?os_destination=/secure/Dashboard.jspa")
+page = b.getPage("https://jira.mit.edu/jira/secure/mit_login.jsp?os_destination=/secure/Dashboard.jspa")
+
+print page.submitForm('wayfForm1')
#c.setopt(c.URL, "https://jira.mit.edu/jira/sr/jira.issueviews:searchrequest-rss/temp/SearchRequest.xml?&pid=10185&updated%3Aprevious=-1w&sorter/field=updated&sorter/order=DESC&tempMax=1000")
--- /dev/null
+import httplib
+import mechanize
+
+def make_cert_handler(key_file=None, cert_file=None):
+ if cert_file is None:
+ cert_file = key_file
+
+ class HTTPSCertConnection(httplib.HTTPSConnection):
+ def __init__(self, host):
+ httplib.HTTPSConnection.__init__(self, host,
+ key_file=key_file,
+ cert_file=cert_file)
+
+ class HTTPSCertHandler(mechanize.HTTPSHandler):
+ def https_open(self, req):
+ return self.do_open(HTTPSCertConnection, req)
+
+ return HTTPSCertHandler
+
+cj = mechanize.CookieJar()
+
+cert_handler = make_cert_handler("cert.pem")
+opener = mechanize.build_opener(mechanize.HTTPRedirectHandler, cert_handler, mechanize.HTTPCookieProcessor(cj))
+mechanize.install_opener(opener)
+
+b = mechanize.Browser()
+b.set_handle_robots(False)
+b.addheaders = [("Accept-Language", "en-us,en;q=0.5"),]
+b.open("https://jira.mit.edu/jira/secure/Dashboard.jsp://jira.mit.edu/jira/secure/Dashboard.jspa")
+b.follow_link(text="MIT Touchstone")
--- /dev/null
+import urllib2
+import httplib
+
+cert_file = "cert.pem"
+key_file = cert_file
+
+class HTTPSCertConnection(httplib.HTTPSConnection):
+ def __init__(self, host):
+ httplib.HTTPSConnection.__init__(self, host, None, key_file, cert_file)
+
+class HTTPSCertHandler(urllib2.HTTPSHandler):
+ def do_open(self, http_class, req):
+ if http_class is httplib.HTTPSConnection:
+ http_class = HTTPSCertConnection
+ return urllib2.HTTPSHandler.do_open(self, http_class, req)
+
+opener = urllib2.build_opener(urllib2.HTTPRedirectHandler, HTTPSCertHandler)
+urllib2.install_opener(opener)
+
+#req = urllib2.Request(url='https://geofft.scripts.mit.edu:444/detect.php')
+#f = urllib2.urlopen(req)
+#print f.read()
+
+req = urllib2.Request(url='https://jira.mit.edu/jira/secure/mit_login.jsp?os_destination=/secure/Dashboard.jspa')
+print urllib2.urlopen(req).read()
+