vcs.maemo.org Git - feedingit/blob - src/rss.py

   1 #!/usr/bin/env python2.5
   2
   3 #
   4 # Copyright (c) 2007-2008 INdT.
   5 # This program is free software: you can redistribute it and/or modify
   6 # it under the terms of the GNU Lesser General Public License as published by
   7 # the Free Software Foundation, either version 3 of the License, or
   8 # (at your option) any later version.
   9 #
  10 #  This program is distributed in the hope that it will be useful,
  11 #  but WITHOUT ANY WARRANTY; without even the implied warranty of
  12 #  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  13 #  GNU Lesser General Public License for more details.
  14 #
  15 #  You should have received a copy of the GNU Lesser General Public License
  16 #  along with this program.  If not, see <http://www.gnu.org/licenses/>.
  17 #
  18
  19 # ============================================================================
  20 # Name        : FeedingIt.py
  21 # Author      : Yves Marcoz
  22 # Version     : 0.4.1
  23 # Description : Simple RSS Reader
  24 # ============================================================================
  25
  26 from os.path import isfile
  27 from os.path import isdir
  28 from os import remove
  29 import pickle
  30 import md5
  31 import feedparser
  32 import time
  33 import urllib2
  34
  35 #CONFIGDIR="/home/user/.feedingit/"
  36
  37 def getId(string):
  38     return md5.new(string).hexdigest()
  39
  40 class Feed:
  41     # Contains all the info about a single feed (articles, ...), and expose the data
  42     def __init__(self, name, url):
  43         self.entries = []
  44         self.readItems = {}
  45         self.countUnread = 0
  46         self.name = name
  47         self.url = url
  48         self.updateTime = "Never"
  49
  50     def saveFeed(self, configdir):
  51         file = open(configdir+getId(self.name), "w")
  52         pickle.dump(self, file )
  53         file.close()
  54
  55     def updateFeed(self, configdir, expiryTime=24):
  56         # Expiry time is in hours
  57         tmp=feedparser.parse(self.url)
  58         # Check if the parse was succesful (number of entries > 0, else do nothing)
  59         if len(tmp["entries"])>0:
  60            #reversedEntries = self.getEntries()
  61            #reversedEntries.reverse()
  62            tmpIds = []
  63            for entry in tmp["entries"]:
  64                tmpIds.append(self.getUniqueId(-1, entry))
  65            for entry in self.getEntries():
  66                currentTime = time.time()
  67                expiry = float(expiryTime) * 3600.
  68                if entry.has_key("updated_parsed"):
  69                    articleTime = time.mktime(entry["updated_parsed"])
  70                    if currentTime - articleTime < expiry:
  71                        id = self.getUniqueId(-1, entry)
  72                        if not id in tmpIds:
  73                            tmp["entries"].append(entry)
  74
  75            self.entries = tmp["entries"]
  76            self.countUnread = 0
  77            # Initialize the new articles to unread
  78            tmpReadItems = self.readItems
  79            self.readItems = {}
  80            for index in range(self.getNumberOfEntries()):
  81                if not tmpReadItems.has_key(self.getUniqueId(index)):
  82                    self.readItems[self.getUniqueId(index)] = False
  83                else:
  84                    self.readItems[self.getUniqueId(index)] = tmpReadItems[self.getUniqueId(index)]
  85                if self.readItems[self.getUniqueId(index)]==False:
  86                   self.countUnread = self.countUnread + 1
  87            del tmp
  88            self.updateTime = time.asctime()
  89            self.saveFeed(configdir)
  90
  91     def setEntryRead(self, index):
  92         if self.readItems[self.getUniqueId(index)]==False:
  93             self.countUnread = self.countUnread - 1
  94             self.readItems[self.getUniqueId(index)] = True
  95
  96     def isEntryRead(self, index):
  97         return self.readItems[self.getUniqueId(index)]
  98
  99     def getTitle(self, index):
 100         return self.entries[index]["title"]
 101
 102     def getLink(self, index):
 103         return self.entries[index]["link"]
 104
 105     def getDate(self, index):
 106         try:
 107             return self.entries[index]["updated_parsed"]
 108         except:
 109             return time.localtime()
 110
 111     def getUniqueId(self, index, entry=None):
 112         if index >=0:
 113             entry = self.entries[index]
 114         if entry.has_key("updated_parsed"):
 115             return getId(time.strftime("%a, %d %b %Y %H:%M:%S",entry["updated_parsed"]) + entry["title"])
 116         elif entry.has_key("link"):
 117             return getId(entry["link"] + entry["title"])
 118         else:
 119             return getId(entry["title"])
 120
 121     def getUpdateTime(self):
 122         return self.updateTime
 123
 124     def getEntries(self):
 125         try:
 126             return self.entries
 127         except:
 128             return []
 129
 130     def getNumberOfUnreadItems(self):
 131         return self.countUnread
 132
 133     def getNumberOfEntries(self):
 134         return len(self.entries)
 135
 136     def getItem(self, index):
 137         try:
 138             return self.entries[index]
 139         except:
 140             return []
 141
 142     def getContent(self, index):
 143         entry = self.entries[index]
 144         if entry.has_key('content'):
 145             content = entry.content[0].value
 146         else:
 147             content = entry.get('summary', '')
 148         return content
 149
 150     def getArticle(self, index):
 151         self.setEntryRead(index)
 152         entry = self.entries[index]
 153         title = entry.get('title', 'No title')
 154         #content = entry.get('content', entry.get('summary_detail', {}))
 155         content = self.getContent(index)
 156
 157         link = entry.get('link', 'NoLink')
 158         if entry.has_key("updated_parsed"):
 159             date = time.strftime("%a, %d %b %Y %H:%M:%S",entry["updated_parsed"])
 160         elif entry.has_key("published_parsed"):
 161             date = time.strftime("%a, %d %b %Y %H:%M:%S", entry["published_parsed"])
 162         else:
 163             date = ""
 164         #text = '''<div style="color: black; background-color: white;">'''
 165         text = '<meta http-equiv="Content-Type" content="text/html; charset=UTF-8"/>'
 166         text += '<div><a href=\"' + link + '\">' + title + "</a>"
 167         text += "<BR /><small><i>Date: " + date + "</i></small></div>"
 168         text += "<BR /><BR />"
 169         text += content
 170         return text
 171
 172 class ArchivedArticles(Feed):
 173     def addArchivedArticle(self, title, link, updated_parsed, configdir):
 174         entry = {}
 175         entry["title"] = title
 176         entry["link"] = link
 177         entry["downloaded"] = False
 178         entry["summary"] = '<a href=\"' + link + '\">' + title + "</a>"
 179         entry["updated_parsed"] = updated_parsed
 180         self.entries.append(entry)
 181         self.readItems[self.getUniqueId(len(self.entries)-1)] = False
 182         self.countUnread = self.countUnread + 1
 183         self.saveFeed(configdir)
 184         #print entry
 185
 186     def updateFeed(self, configdir, expiryTime=24):
 187         for entry in self.getEntries():
 188             if not entry["downloaded"]:
 189                 try:
 190                     f = urllib2.urlopen(entry["link"])
 191                     entry["summary"] = f.read()
 192                     f.close()
 193                     entry["downloaded"] = True
 194                     entry["time"] = time.time()
 195                 except:
 196                     pass
 197             currentTime = time.time()
 198             expiry = float(expiryTime) * 3600
 199             if currentTime - entry["time"] > expiry:
 200                 self.entries.remove(entry)
 201         self.saveFeed(configdir)
 202
 203     def getArticle(self, index):
 204         self.setEntryRead(index)
 205         content = self.getContent(index)
 206         return content
 207
 208
 209 class Listing:
 210     # Lists all the feeds in a dictionary, and expose the data
 211     def __init__(self, configdir):
 212         self.configdir = configdir
 213         self.feeds = {}
 214         if isfile(self.configdir+"feeds.pickle"):
 215             file = open(self.configdir+"feeds.pickle")
 216             self.listOfFeeds = pickle.load(file)
 217             file.close()
 218         else:
 219             self.listOfFeeds = {getId("Slashdot"):{"title":"Slashdot", "url":"http://rss.slashdot.org/Slashdot/slashdot"}, }
 220         if self.listOfFeeds.has_key("font"):
 221             del self.listOfFeeds["font"]
 222         if self.listOfFeeds.has_key("feedingit-order"):
 223             self.sortedKeys = self.listOfFeeds["feedingit-order"]
 224         else:
 225             self.sortedKeys = self.listOfFeeds.keys()
 226             if "font" in self.sortedKeys:
 227                 self.sortedKeys.remove("font")
 228             self.sortedKeys.sort(key=lambda obj: self.getFeedTitle(obj))
 229         for key in self.sortedKeys:
 230             try:
 231                 self.loadFeed(key)
 232             except:
 233                 self.sortedKeys.remove(key)
 234         #self.saveConfig()
 235
 236     def addArchivedArticle(self, key, index):
 237         title = self.getFeed(key).getTitle(index)
 238         link = self.getFeed(key).getLink(index)
 239         date = self.getFeed(key).getDate(index)
 240         if not self.listOfFeeds.has_key(getId("Archived Articles")):
 241             self.listOfFeeds[getId("Archived Articles")] = {"title":"Archived Articles", "url":""}
 242             self.sortedKeys.append(getId("Archived Articles"))
 243             self.feeds[getId("Archived Articles")] = ArchivedArticles("Archived Articles", "")
 244             self.saveConfig()
 245
 246         self.getFeed(getId("Archived Articles")).addArchivedArticle(title, link, date, self.configdir)
 247
 248     def loadFeed(self, key):
 249             if isfile(self.configdir+key):
 250                 file = open(self.configdir+key)
 251                 self.feeds[key] = pickle.load(file)
 252                 file.close()
 253             else:
 254                 title = self.listOfFeeds[key]["title"]
 255                 url = self.listOfFeeds[key]["url"]
 256                 self.feeds[key] = Feed(title, url)
 257
 258     def updateFeeds(self, expiryTime=24):
 259         for key in self.getListOfFeeds():
 260             self.feeds[key].updateFeed(self.configdir, expiryTime)
 261
 262     def updateFeed(self, key, expiryTime=24):
 263         self.feeds[key].updateFeed(self.configdir, expiryTime)
 264
 265     def getFeed(self, key):
 266         return self.feeds[key]
 267
 268     def getFeedUpdateTime(self, key):
 269         return self.feeds[key].getUpdateTime()
 270
 271     def getFeedNumberOfUnreadItems(self, key):
 272         return self.feeds[key].getNumberOfUnreadItems()
 273
 274     def getFeedTitle(self, key):
 275         return self.listOfFeeds[key]["title"]
 276
 277     def getFeedUrl(self, key):
 278         return self.listOfFeeds[key]["url"]
 279
 280     def getListOfFeeds(self):
 281         return self.sortedKeys
 282
 283     def addFeed(self, title, url):
 284         if not self.listOfFeeds.has_key(getId(title)):
 285             self.listOfFeeds[getId(title)] = {"title":title, "url":url}
 286             self.sortedKeys.append(getId(title))
 287             self.saveConfig()
 288             self.feeds[getId(title)] = Feed(title, url)
 289
 290     def removeFeed(self, key):
 291         del self.listOfFeeds[key]
 292         self.sortedKeys.remove(key)
 293         del self.feeds[key]
 294         if isfile(self.configdir+key):
 295            remove(self.configdir+key)
 296
 297     def saveConfig(self):
 298         self.listOfFeeds["feedingit-order"] = self.sortedKeys
 299         file = open(self.configdir+"feeds.pickle", "w")
 300         pickle.dump(self.listOfFeeds, file)
 301         file.close()
 302
 303     def moveUp(self, key):
 304         index = self.sortedKeys.index(key)
 305         self.sortedKeys[index] = self.sortedKeys[index-1]
 306         self.sortedKeys[index-1] = key
 307
 308     def moveDown(self, key):
 309         index = self.sortedKeys.index(key)
 310         index2 = (index+1)%len(self.sortedKeys)
 311         self.sortedKeys[index] = self.sortedKeys[index2]
 312         self.sortedKeys[index2] = key