Forum: Uppgift, cron-script

 
import pyexpat, email.Utils, time
 
# Don't get values from the file before these posisions have been found         
date_start = 0
title_start = 0
desc_start = 0
item_start = 0
 
def start_element(name, attrs):
    global date_start, title_start, desc_start, item_start
    if name == 'item':
        item_start = 1
    elif name == 'pubDate':
        date_start = 1
    elif name == 'title':
        title_start = 1
    elif name == 'description':
        desc_start = 1
 
def char_data(data):
    global date_start, title_start, desc_start, item_start
 
    if item_start == 1:
        print 'Ok!'
        # Get date, using email function to parse date string                   
        if date_start == 1:
            dt = email.Utils.parsedate(data)
            print 'Timestamp: "', str(time.mktime(dt)),'"'
            date_start = 0
        # Get title of item                                                     
        elif title_start == 1:
            print 'Title: "', data, '"'
            title_start = 0
        # Get description of item                                               
        elif desc_start == 1:
            print 'Description: "', data, '"'
            desc_start = 0
 
p = pyexpat.ParserCreate()
 
f = file('/home/independence/python/data/rss.xml')
 
p.StartElementHandler = start_element
p.CharacterDataHandler = char_data
 
p.ParseFile(f)
 

#!/usr/bin/env python
# -*- coding: utf-8 -*-
from xml.sax import make_parser
from xml.sax.handler import ContentHandler
import urllib
 
BASEURL = "http://marcusson.no-ip.com"
# This one really should start with a slash (shouldn't max days be less
# than 90?):
RSSURL = "/timeline?milestone=on&ticket=on&changeset=on&wiki=on&max=1&daysback=90&format=rss"
 
 
# XML parsing classes:
 
class Projectparser(ContentHandler):
    '''Get the href-part of a link. This is used to get a list of projects'''
    projectlist = []
    def startElement(self, name, attrs):
        if name == "a":
            if attrs.has_key("href"):
                self.projectlist.append(attrs.get("href"))
 
class RSSParser(ContentHandler):
    '''Get an item from an RSS feed. If more than one item is found,
    this will go kaboom'''
    class ItemStruct(object):
        '''A simple structure for storing item data'''
        title = ""
        date = ""
        link = ""
        description = ""
    def __init__(self):
        self.item = self.ItemStruct()
        self.is_item = False
        self.is_title = False
        self.is_date = False
        self.is_link = False
        self.is_description = False
    def startElement(self, name, attrs):
        if self.is_description: #descriptions can contain XML tags.
            self.item.description += "<%s" % (name,)
            for attr in attrs.keys():
                self.item.description += " %s=\"%s\"" % (attr, attrs.get(attr))
            self.item.description += ">\n"
        elif name == "item":
            self.is_item = True
        elif self.is_item == True:
            if name == "title":
                self.is_title = True
            elif name == "pubDate":
                self.is_date = True
            elif name == "link":
                self.is_link = True
            elif name == "description":
                self.is_description = True
 
    def endElement(self, name):
        if name == "item":
            self.is_item = False
        elif self.is_item == True:
            if name == "title":
                self.is_title = False
            elif name == "pubDate":
                self.is_date = False
            elif name == "link":
                self.is_link = False
            elif name == "description":
                self.is_description = False
            elif self.is_description == True:
                self.item.description += "</%s>" % (name,)
 
    def characters(self, ch):
        if self.is_title:
            self.item.title += ch
        elif self.is_date:
            self.item.date += ch
        elif self.is_link:
            self.item.link += ch
        elif self.is_description:
            self.item.description += ch
 
project = urllib.urlopen("http://marcusson.no-ip.com/projects/")
 
# The HTML is validating XML in this case (if indy brakes this
# assumtion, he'll have to fix it himself), and thus we can parse it as
# XML
parser = make_parser()
projectparser = Projectparser()
parser.setContentHandler(projectparser)
parser.parse(project)
 
# Now, parse the RSS the very same way:
for project in projectparser.projectlist:
    url = BASEURL+project+RSSURL
    rssobject = urllib.urlopen(url)
    rssparser = RSSParser()
    parser.setContentHandler(rssparser)
    parser.parse(rssobject)
    projectname = project.split("/")[2]
    print "<h1>%s</h1>" % (projectname,)
    if rssparser.item.date:
        if rssparser.item.link:
            print "<a href=\"%s\"><h2>%s</h2></a>" % (rssparser.item.link,
                                                      rssparser.item.title)
        else:
            print "<h2>%s</h2>" % (rssparser.item.title,)
        print "<p>%s</p>" % (rssparser.item.date,)
        if rssparser.item.description:
            if rssparser.item.description.startswith("<p"):
                print rssparser.item.description
            else:
                print "<p>%s</p>" % (rssparser.item.description,)
    else:
        print u"<p>%s har inte gjort några uppdateringar på senaste tiden</p>" % (projectname,)