Sync to trunk.

recipes/birmingham_post.recipe

@@ -9,14 +9,14 @@ class AdvancedUserRecipe1306097511(BasicNewsRecipe):
     __author__ = 'Dave Asbury'
     cover_url = 'http://profile.ak.fbcdn.net/hprofile-ak-snc4/161987_9010212100_2035706408_n.jpg'
     oldest_article = 2
-    max_articles_per_feed = 12
+    max_articles_per_feed = 20
     linearize_tables = True
     remove_empty_feeds = True
     remove_javascript     = True
     no_stylesheets = True
     auto_cleanup = True
     language = 'en_GB'
-
+    compress_news_images = True
     cover_url = 'http://profile.ak.fbcdn.net/hprofile-ak-snc4/161987_9010212100_2035706408_n.jpg'
 
     masthead_url        = 'http://www.trinitymirror.com/images/birminghampost-logo.gif'

recipes/countryfile.recipe

@@ -7,13 +7,14 @@ class AdvancedUserRecipe1325006965(BasicNewsRecipe):
     #cover_url = 'http://www.countryfile.com/sites/default/files/imagecache/160px_wide/cover/2_1.jpg'
     __author__ = 'Dave Asbury'
     description           = 'The official website of Countryfile Magazine'
-    # last updated 8/12/12
+    # last updated 19/10/12
     language = 'en_GB'
     oldest_article = 30
     max_articles_per_feed = 25
     remove_empty_feeds = True
     no_stylesheets = True
     auto_cleanup = True
+    compress_news_images = True
     ignore_duplicate_articles = {'title', 'url'}
     #articles_are_obfuscated = True
     #article_already_exists = False

recipes/daily_mirror.recipe

@@ -13,9 +13,9 @@ class AdvancedUserRecipe1306061239(BasicNewsRecipe):
 
     masthead_url = 'http://www.nmauk.co.uk/nma/images/daily_mirror.gif'
 
-
+    compress_news_images = True
     oldest_article = 1
-    max_articles_per_feed = 1
+    max_articles_per_feed = 12
     remove_empty_feeds = True
     remove_javascript     = True
     no_stylesheets = True

recipes/financial_times_uk.recipe

@@ -8,6 +8,7 @@ import datetime
 from calibre.ptempfile import PersistentTemporaryFile
 from calibre import strftime
 from calibre.web.feeds.news import BasicNewsRecipe
+from collections import OrderedDict
 
 class FinancialTimes(BasicNewsRecipe):
     title                 = 'Financial Times (UK)'
@@ -93,7 +94,7 @@ class FinancialTimes(BasicNewsRecipe):
             try:
                 urlverified = self.browser.open_novisit(url).geturl() # resolve redirect.
             except:
-                continue 
+                continue
             title = self.tag_to_string(item)
             date = strftime(self.timefmt)
             articles.append({
@@ -105,29 +106,28 @@ class FinancialTimes(BasicNewsRecipe):
         return articles
 
     def parse_index(self):
-        feeds = []
+        feeds = OrderedDict()
         soup = self.index_to_soup(self.INDEX)
-        dates= self.tag_to_string(soup.find('div', attrs={'class':'btm-links'}).find('div'))
+        #dates= self.tag_to_string(soup.find('div', attrs={'class':'btm-links'}).find('div'))
-        self.timefmt = ' [%s]'%dates
+        #self.timefmt = ' [%s]'%dates
-        wide = soup.find('div',attrs={'class':'wide'})
+
-        if not wide:
+        for column in soup.findAll('div', attrs = {'class':'feedBoxes clearfix'}):
-           return feeds
+            for section in column. findAll('div', attrs = {'class':'feedBox'}):
-        allsections = wide.findAll(attrs={'class':lambda x: x and 'footwell' in x.split()})
+                section_title=self.tag_to_string(section.find('h4'))
-        if not allsections:
+                for article in section.ul.findAll('li'):
-           return feeds
+                    articles = []
-        count = 0
+                    title=self.tag_to_string(article.a)
-        for item in allsections:
+                    url=article.a['href']
-            count = count + 1
+                    articles.append({'title':title, 'url':url, 'description':'', 'date':''})
-            if self.test and count > 2:
+
-               return feeds
+                    if articles:
-            fitem = item.h3
+                        if section_title not in feeds:
-            if not fitem:
+                            feeds[section_title] = []
-               fitem = item.h4
+                        feeds[section_title] += articles
-            ftitle = self.tag_to_string(fitem)   
+
-            self.report_progress(0, _('Fetching feed')+' %s...'%(ftitle))
+
-            feedarts = self.get_artlinks(item.ul)
+        ans = [(key, val) for key, val in feeds.iteritems()]
-            feeds.append((ftitle,feedarts))
+        return ans
-        return feeds
 
     def preprocess_html(self, soup):
         items = ['promo-box','promo-title',
@@ -174,9 +174,6 @@ class FinancialTimes(BasicNewsRecipe):
             count += 1
         tfile = PersistentTemporaryFile('_fa.html')
         tfile.write(html)
-        tfile.close()        
+        tfile.close()
         self.temp_files.append(tfile)
         return tfile.name
-
-    def cleanup(self):
-        self.browser.open('https://registration.ft.com/registration/login/logout?location=')

recipes/hbr.recipe

@@ -1,6 +1,4 @@
 from calibre.web.feeds.news import BasicNewsRecipe
-import re
-from datetime import date, timedelta
 
 class HBR(BasicNewsRecipe):
 
@@ -11,16 +9,11 @@ class HBR(BasicNewsRecipe):
     timefmt                = ' [%B %Y]'
     language = 'en'
     no_stylesheets = True
-    # recipe_disabled = ('hbr.org has started requiring the use of javascript'
-    #         ' to log into their website. This is unsupported in calibre, so'
-    #         ' this recipe has been disabled. If you would like to see '
-    #         ' HBR supported in calibre, contact hbr.org and ask them'
-    #         ' to provide a javascript free login method.')
 
     LOGIN_URL = 'https://hbr.org/login?request_url=/'
     LOGOUT_URL = 'https://hbr.org/logout?request_url=/'
 
-    INDEX = 'http://hbr.org/archive-toc/BR'
+    INDEX = 'http://hbr.org'
 
     keep_only_tags = [dict(name='div', id='pageContainer')]
     remove_tags = [dict(id=['mastheadContainer', 'magazineHeadline',
@@ -57,22 +50,6 @@ class HBR(BasicNewsRecipe):
         if url.endswith('/ar/1'):
             return url[:-1]+'pr'
 
-    def hbr_get_toc(self):
-        # return self.index_to_soup(open('/t/toc.html').read())
-
-        today = date.today()
-        future = today + timedelta(days=30)
-        past = today - timedelta(days=30)
-        for x in [x.strftime('%y%m') for x in (future, today, past)]:
-            url = self.INDEX + x
-            soup = self.index_to_soup(url)
-            if (not soup.find(text='Issue Not Found') and not soup.find(
-                text="We're Sorry.  There was an error processing your request")
-                and 'Exception: java.io.FileNotFoundException' not in
-                unicode(soup)):
-                return soup
-        raise Exception('Could not find current issue')
-
     def hbr_parse_toc(self, soup):
         feeds = []
         current_section = None
@@ -105,23 +82,19 @@ class HBR(BasicNewsRecipe):
 
                 articles.append({'title':title, 'url':url, 'description':desc,
                     'date':''})
+
+        if current_section is not None and articles:
+            feeds.append((current_section, articles))
         return feeds
 
     def parse_index(self):
-        soup = self.hbr_get_toc()
+        soup0 = self.index_to_soup('http://hbr.org/magazine')
-        # open('/t/hbr.html', 'wb').write(unicode(soup).encode('utf-8'))
+        datencover = soup0.find('ul', attrs={'id':'magazineArchiveCarousel'}).findAll('li')[-1]
+        #find date & cover
+        self.cover_url=datencover.img['src']
+        dates=self.tag_to_string(datencover.img['alt'])
+        self.timefmt = u' [%s]'%dates
+        soup = self.index_to_soup(self.INDEX + soup0.find('div', attrs = {'class':'magazine_page'}).a['href'])
         feeds = self.hbr_parse_toc(soup)
         return feeds
 
-    def get_cover_url(self):
-        cover_url = None
-        index = 'http://hbr.org/current'
-        soup = self.index_to_soup(index)
-        link_item = soup.find('img', alt=re.compile("Current Issue"), src=True)
-
-        if link_item:
-           cover_url = 'http://hbr.org' + link_item['src']
-
-        return cover_url
-
-

recipes/metro_uk.recipe

@@ -6,10 +6,10 @@ import time
 
 class AdvancedUserRecipe1306097511(BasicNewsRecipe):
     title          = u'Metro UK'
-    description = 'News as provided by The Metro -UK'
+    description = 'News from The Metro, UK'
     #timefmt = ''
-    __author__ = 'fleclerc & Dave Asbury'
+    __author__ = 'Dave Asbury'
-    #last update 20/1/13
+    #last update 4/4/13
     #cover_url = 'http://profile.ak.fbcdn.net/hprofile-ak-snc4/276636_117118184990145_2132092232_n.jpg'
 
     cover_url = 'https://twimg0-a.akamaihd.net/profile_images/1638332595/METRO_LETTERS-01.jpg'
@@ -22,7 +22,7 @@ class AdvancedUserRecipe1306097511(BasicNewsRecipe):
 
     language = 'en_GB'
     masthead_url        = 'http://e-edition.metro.co.uk/images/metro_logo.gif'
-
+    compress_news_images = True
     def parse_index(self):
 		articles = {}
 		key = None

recipes/nme.recipe

@@ -12,6 +12,7 @@ class AdvancedUserRecipe1306061239(BasicNewsRecipe):
     max_articles_per_feed = 20
     #auto_cleanup = True
     language = 'en_GB'
+    compress_news_images = True
 
     def get_cover_url(self):
         soup = self.index_to_soup('http://www.nme.com/component/subscribe')
@@ -27,7 +28,7 @@ class AdvancedUserRecipe1306061239(BasicNewsRecipe):
             br.open_novisit(cov2)
             cover_url = str(cov2)
         except:
-                cover_url = 'http://tawanda3000.files.wordpress.com/2011/02/nme-logo.jpg'
+            cover_url = 'http://tawanda3000.files.wordpress.com/2011/02/nme-logo.jpg'
         return cover_url
 
     masthead_url   = 'http://tawanda3000.files.wordpress.com/2011/02/nme-logo.jpg'

recipes/the_sun.recipe

@@ -20,7 +20,7 @@ class AdvancedUserRecipe1325006965(BasicNewsRecipe):
     no_stylesheets = True
 
     ignore_duplicate_articles = {'title','url'}
-
+    compress_news_images = True
 
     extra_css  = '''
     body{ text-align: justify; font-family:Arial,Helvetica,sans-serif; font-size:11px; font-size-adjust:none; font-stretch:normal; font-style:normal; font-variant:normal; font-weight:normal;}

setup/iso_639/ca.po

@@ -12,13 +12,13 @@ msgstr ""
 "Report-Msgid-Bugs-To: Debian iso-codes team <pkg-isocodes-"
 "devel@lists.alioth.debian.org>\n"
 "POT-Creation-Date: 2011-11-25 14:01+0000\n"
-"PO-Revision-Date: 2013-03-27 13:07+0000\n"
+"PO-Revision-Date: 2013-03-28 13:01+0000\n"
 "Last-Translator: Ferran Rius <frius64@hotmail.com>\n"
 "Language-Team: Catalan <linux@softcatala.org>\n"
 "MIME-Version: 1.0\n"
 "Content-Type: text/plain; charset=UTF-8\n"
 "Content-Transfer-Encoding: 8bit\n"
-"X-Launchpad-Export-Date: 2013-03-28 04:41+0000\n"
+"X-Launchpad-Export-Date: 2013-03-29 04:36+0000\n"
 "X-Generator: Launchpad (build 16546)\n"
 "Language: ca\n"
 
@@ -1884,7 +1884,7 @@ msgstr "Awera"
 
 #. name for aws
 msgid "Awyu; South"
-msgstr "Awyu meridional"
+msgstr "Awyu; meridional"
 
 #. name for awt
 msgid "Araweté"
@@ -1892,7 +1892,7 @@ msgstr "Araweté"
 
 #. name for awu
 msgid "Awyu; Central"
-msgstr "Awyu central"
+msgstr "Awyu; Central"
 
 #. name for awv
 msgid "Awyu; Jair"
@@ -4052,7 +4052,7 @@ msgstr "Buginès"
 
 #. name for buh
 msgid "Bunu; Younuo"
-msgstr "Bunu; Younuo"
+msgstr "Bunu; Younou"
 
 #. name for bui
 msgid "Bongili"
@@ -4308,7 +4308,7 @@ msgstr "Bwa"
 
 #. name for bwx
 msgid "Bunu; Bu-Nao"
-msgstr "Bunu; Bu-Nao"
+msgstr "Bunu; Bu Nao"
 
 #. name for bwy
 msgid "Bwamu; Cwi"
@@ -19804,7 +19804,7 @@ msgstr "Minoà"
 
 #. name for omo
 msgid "Utarmbung"
-msgstr ""
+msgstr "Utarmbung"
 
 #. name for omp
 msgid "Manipuri; Old"
@@ -20344,7 +20344,7 @@ msgstr "Pear"
 
 #. name for pcc
 msgid "Bouyei"
-msgstr ""
+msgstr "Buyí"
 
 #. name for pcd
 msgid "Picard"
@@ -20456,11 +20456,11 @@ msgstr "Pengo"
 
 #. name for peh
 msgid "Bonan"
-msgstr ""
+msgstr "Bonan"
 
 #. name for pei
 msgid "Chichimeca-Jonaz"
-msgstr ""
+msgstr "Chichimec"
 
 #. name for pej
 msgid "Pomo; Northern"
@@ -20484,7 +20484,7 @@ msgstr "Persa Antic"
 
 #. name for pep
 msgid "Kunja"
-msgstr ""
+msgstr "Kunja"
 
 #. name for peq
 msgid "Pomo; Southern"
@@ -20536,7 +20536,7 @@ msgstr "Pagi"
 
 #. name for pgk
 msgid "Rerep"
-msgstr ""
+msgstr "Rerep"
 
 #. name for pgl
 msgid "Irish; Primitive"
@@ -20624,7 +20624,7 @@ msgstr "Pima Baix"
 
 #. name for pib
 msgid "Yine"
-msgstr ""
+msgstr "Yine"
 
 #. name for pic
 msgid "Pinji"
@@ -20660,7 +20660,7 @@ msgstr "Pijao"
 
 #. name for pil
 msgid "Yom"
-msgstr ""
+msgstr "Yom"
 
 #. name for pim
 msgid "Powhatan"
@@ -20760,7 +20760,7 @@ msgstr "Llenguatge de signes pakistaní"
 
 #. name for pkt
 msgid "Maleng"
-msgstr ""
+msgstr "Maleng"
 
 #. name for pku
 msgid "Paku"
@@ -20768,7 +20768,7 @@ msgstr "Paku"
 
 #. name for pla
 msgid "Miani"
-msgstr ""
+msgstr "Miani"
 
 #. name for plb
 msgid "Polonombauk"
@@ -20804,7 +20804,7 @@ msgstr "Polci"
 
 #. name for plk
 msgid "Shina; Kohistani"
-msgstr ""
+msgstr "Shina; Kohistani"
 
 #. name for pll
 msgid "Palaung; Shwe"
@@ -20852,7 +20852,7 @@ msgstr "Palawà; Brooke"
 
 #. name for ply
 msgid "Bolyu"
-msgstr ""
+msgstr "Bolyu"
 
 #. name for plz
 msgid "Paluan"
@@ -20896,7 +20896,7 @@ msgstr "Algonquí Carolina"
 
 #. name for pml
 msgid "Lingua Franca"
-msgstr ""
+msgstr "Aljamia"
 
 #. name for pmm
 msgid "Pomo"
@@ -20924,7 +20924,7 @@ msgstr "Piemontès"
 
 #. name for pmt
 msgid "Tuamotuan"
-msgstr ""
+msgstr "Tuamotu"
 
 #. name for pmu
 msgid "Panjabi; Mirpur"
@@ -20972,7 +20972,7 @@ msgstr "Penrhyn"
 
 #. name for pni
 msgid "Aoheng"
-msgstr ""
+msgstr "Aoheng"
 
 #. name for pnm
 msgid "Punan Batu 1"
@@ -21008,7 +21008,7 @@ msgstr "Pontic"
 
 #. name for pnu
 msgid "Bunu; Jiongnai"
-msgstr ""
+msgstr "Bunu; Jiongnai"
 
 #. name for pnv
 msgid "Pinigura"
@@ -21100,7 +21100,7 @@ msgstr "Potavatomi"
 
 #. name for pov
 msgid "Crioulo; Upper Guinea"
-msgstr ""
+msgstr "Crioll guineà"
 
 #. name for pow
 msgid "Popoloca; San Felipe Otlaltepec"
@@ -21128,7 +21128,7 @@ msgstr "Paipai"
 
 #. name for ppk
 msgid "Uma"
-msgstr ""
+msgstr "Uma"
 
 #. name for ppl
 msgid "Pipil"
@@ -21144,7 +21144,7 @@ msgstr "Papapana"
 
 #. name for ppo
 msgid "Folopa"
-msgstr ""
+msgstr "Folopa"
 
 #. name for ppp
 msgid "Pelende"
@@ -21180,7 +21180,7 @@ msgstr "Malecite-Passamaquoddy"
 
 #. name for prb
 msgid "Lua'"
-msgstr ""
+msgstr "Lua"
 
 #. name for prc
 msgid "Parachi"
@@ -21220,7 +21220,7 @@ msgstr "Llenguatge de signes peruà"
 
 #. name for prm
 msgid "Kibiri"
-msgstr ""
+msgstr "Kibiri"
 
 #. name for prn
 msgid "Prasuni"
@@ -21272,7 +21272,7 @@ msgstr "Llenguatge de signes de Providencia"
 
 #. name for psa
 msgid "Awyu; Asue"
-msgstr ""
+msgstr "Awyu; Asue"
 
 #. name for psc
 msgid "Persian Sign Language"
@@ -21328,7 +21328,7 @@ msgstr "Llenguatge de signes portuguès"
 
 #. name for pss
 msgid "Kaulong"
-msgstr ""
+msgstr "Kaulong"
 
 #. name for pst
 msgid "Pashto; Central"
@@ -21376,11 +21376,11 @@ msgstr "Pìamatsina"
 
 #. name for ptt
 msgid "Enrekang"
-msgstr ""
+msgstr "Enrekang"
 
 #. name for ptu
 msgid "Bambam"
-msgstr ""
+msgstr "Bambam"
 
 #. name for ptv
 msgid "Port Vato"
@@ -29584,7 +29584,7 @@ msgstr ""
 
 #. name for yir
 msgid "Awyu; North"
-msgstr ""
+msgstr "Awyu; Septentrional"
 
 #. name for yis
 msgid "Yis"