sync with Kovid's branch

recipes/aktualne.cz.recipe

@@ -0,0 +1,69 @@
+# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai
+from __future__ import unicode_literals
+from calibre.web.feeds.recipes import BasicNewsRecipe
+import re
+
+class aktualneRecipe(BasicNewsRecipe):
+    __author__  = 'bubak'
+    title = u'aktualne.cz'
+    publisher = u'Centrum holdings'
+    description = 'aktuálně.cz'
+    oldest_article = 1
+    max_articles_per_feed = 20
+
+    feeds = [
+            (u'Domácí', u'http://aktualne.centrum.cz/feeds/rss/domaci/?photo=0'),
+            (u'Zprávy', u'http://aktualne.centrum.cz/feeds/rss/zpravy/?photo=0'),
+            (u'Praha', u'http://aktualne.centrum.cz/feeds/rss/domaci/regiony/praha/?photo=0'),
+            (u'Ekonomika', u'http://aktualne.centrum.cz/feeds/rss/ekonomika/?photo=0'),
+            (u'Finance', u'http://aktualne.centrum.cz/feeds/rss/finance/?photo=0'),
+            (u'Blogy a názory', u'http://blog.aktualne.centrum.cz/export-all.php')
+            ]
+
+
+    language = 'cs'
+    cover_url = 'http://img.aktualne.centrum.cz/design/akt4/o/l/logo-akt-ciste.png'
+    remove_javascript = True
+    no_stylesheets = True
+
+    remove_attributes = []
+    remove_tags_before  = dict(name='h1', attrs={'class':['titulek-clanku']})
+    filter_regexps = [r'img.aktualne.centrum.cz']
+    remove_tags = [dict(name='div',   attrs={'id':['social-bookmark']}),
+                dict(name='div', attrs={'class':['box1', 'svazane-tagy']}),
+                dict(name='div', attrs={'class':'itemcomment id0'}),
+                dict(name='div', attrs={'class':'hlavicka'}),
+                dict(name='div', attrs={'class':'hlavni-menu'}),
+                dict(name='div', attrs={'class':'top-standard-brand-obal'}),
+                dict(name='div', attrs={'class':'breadcrumb'}),
+                dict(name='div', attrs={'id':'start-standard'}),
+                dict(name='div', attrs={'id':'forum'}),
+                dict(name='span', attrs={'class':'akce'}),
+                dict(name='span', attrs={'class':'odrazka vetsi'}),
+                dict(name='div', attrs={'class':'boxP'}),
+                dict(name='div', attrs={'class':'box2'})]
+    preprocess_regexps = [
+            (re.compile(r'<div class="(contenttitle"|socialni-site|wiki|facebook-promo|facebook-like-button"|meta-akce).*', re.DOTALL|re.IGNORECASE), lambda match: '</body>'),
+            (re.compile(r'<div class="[^"]*poutak-clanek-trojka".*', re.DOTALL|re.IGNORECASE), lambda match: '</body>')]
+
+    keep_only_tags = []
+
+    visited_urls = {}
+    def get_article_url(self, article):
+        url = BasicNewsRecipe.get_article_url(self, article)
+        if url in self.visited_urls:
+            self.log.debug('Ignoring duplicate: ' + url)
+            return None
+        else:
+            self.visited_urls[url] = True
+            self.log.debug('Accepting: ' + url)
+            return url
+
+    def encoding(self, source):
+        if source.newurl.find('blog.aktualne') >= 0:
+            enc = 'utf-8'
+        else:
+            enc = 'iso-8859-2'
+        self.log.debug('Called encoding ' + enc + " " + str(source.newurl))
+        return source.decode(enc, 'replace')
+

recipes/antyweb.recipe

@@ -0,0 +1,48 @@
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class AntywebRecipe(BasicNewsRecipe):
+    encoding = 'utf-8'
+    __license__ = 'GPL v3'
+    __author__ = u'Artur Stachecki <artur.stachecki@gmail.com>'
+    language = 'pl'
+    version = 1
+    title = u'Antyweb'
+    category = u'News'
+    description = u'Blog o internecie i nowych technologiach'
+    cover_url=''
+    remove_empty_feeds= True
+    auto_cleanup = False
+    no_stylesheets=True
+    use_embedded_content = False
+    oldest_article = 1
+    max_articles_per_feed = 100
+    remove_javascript = True
+    simultaneous_downloads = 3
+
+    keep_only_tags =[]
+    keep_only_tags.append(dict(name = 'h1', attrs = { 'class' : 'mm-article-title'}))
+    keep_only_tags.append(dict(name = 'div', attrs = {'class' : 'mm-article-content'}))
+
+
+    remove_tags =[]
+    remove_tags.append(dict(name = 'h2', attrs = {'class' : 'widgettitle'}))
+    remove_tags.append(dict(name = 'img', attrs = {'class' : 'alignleft'}))
+    remove_tags.append(dict(name = 'div', attrs = {'class' : 'float: right;margin-left:1em;margin-bottom: 0.5em;padding-bottom: 3px; width: 72px;'}))
+    remove_tags.append(dict(name = 'img', attrs = {'src' : 'http://antyweb.pl/wp-content/uploads/2011/09/HOSTERSI_testy_pasek600x30.gif'}))
+    remove_tags.append(dict(name = 'div', attrs = {'class' : 'podwpisowe'}))
+
+
+    extra_css = '''
+                    body {font-family: verdana, arial, helvetica, geneva, sans-serif ;}
+                       '''
+
+    feeds          = [
+                            (u'Artykuly', u'feed://feeds.feedburner.com/Antyweb?format=xml'),
+                     ]
+    def preprocess_html(self, soup):
+        for alink in soup.findAll('a'):
+            if alink.string is not None:
+               tstr = alink.string
+               alink.replaceWith(tstr)
+	return soup

recipes/bankier_pl.recipe

@@ -0,0 +1,50 @@
+#!/usr/bin/env  python
+
+__license__ = 'GPL v3'
+__author__ = 'teepel <teepel44@gmail.com>'
+
+'''
+bankier.pl
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class bankier(BasicNewsRecipe):
+    title          = u'Bankier.pl'
+    __author__ = 'teepel <teepel44@gmail.com>'
+    language       = 'pl'
+    description ='Polski portal finansowy. Informacje o: gospodarka, inwestowanie, finanse osobiste, prowadzenie firmy, kursy walut, notowania akcji, fundusze.'
+    masthead_url='http://www.bankier.pl/gfx/hd-mid-02.gif'
+    INDEX='http://bankier.pl/'
+    remove_empty_feeds= True
+    oldest_article = 1
+    max_articles_per_feed = 100
+    remove_javascript=True
+    no_stylesheets=True
+    simultaneous_downloads = 5
+
+    keep_only_tags =[]
+    keep_only_tags.append(dict(name = 'div', attrs = {'align' : 'left'}))
+
+    remove_tags =[]
+    remove_tags.append(dict(name = 'table', attrs = {'cellspacing' : '2'}))
+    remove_tags.append(dict(name = 'div', attrs = {'align' : 'center'}))
+    remove_tags.append(dict(name = 'img', attrs = {'src' : '/gfx/hd-mid-02.gif'}))
+    #remove_tags.append(dict(name = 'a', attrs = {'target' : '_blank'}))
+    #remove_tags.append(dict(name = 'br', attrs = {'clear' : 'all'}))
+
+    feeds          = [
+            (u'Wiadomości dnia', u'http://feeds.feedburner.com/bankier-wiadomosci-dnia'),
+            (u'Finanse osobiste', u'http://feeds.feedburner.com/bankier-finanse-osobiste'),
+            (u'Firma', u'http://feeds.feedburner.com/bankier-firma'),
+            (u'Giełda', u'http://feeds.feedburner.com/bankier-gielda'),
+            (u'Rynek walutowy', u'http://feeds.feedburner.com/bankier-rynek-walutowy'),
+            (u'Komunikaty ze spółek', u'http://feeds.feedburner.com/bankier-espi'),
+         ]
+    def print_version(self, url):
+        segment = url.split('.')
+        urlPart = segment[2]
+        segments = urlPart.split('-')
+        urlPart2 = segments[-1]
+        return 'http://www.bankier.pl/wiadomosci/print.html?article_id=' + urlPart2
+

recipes/blesk.recipe

@@ -0,0 +1,55 @@
+# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai
+from __future__ import unicode_literals
+from calibre.web.feeds.recipes import BasicNewsRecipe
+import re
+
+class bleskRecipe(BasicNewsRecipe):
+    __author__  = 'bubak'
+    title = u'Blesk'
+    publisher = u''
+    description = 'blesk.cz'
+    oldest_article = 1
+    max_articles_per_feed = 20
+    use_embedded_content = False
+
+    feeds = [
+            (u'Zprávy', u'http://www.blesk.cz/rss/7'),
+            (u'Blesk', u'http://www.blesk.cz/rss/1'),
+            (u'Sex a tabu', u'http://www.blesk.cz/rss/2'),
+            (u'Celebrity', u'http://www.blesk.cz/rss/5'),
+            (u'Cestování', u'http://www.blesk.cz/rss/12')
+            ]
+
+
+    #encoding = 'iso-8859-2'
+    language = 'cs'
+    cover_url = 'http://img.blesk.cz/images/blesk/blesk-logo.png'
+    remove_javascript = True
+    no_stylesheets = True
+    extra_css             = """
+                            """
+
+    remove_attributes = []
+    remove_tags_before  = dict(name='div', attrs={'id':['boxContent']})
+    remove_tags_after  = dict(name='div', attrs={'class':['artAuthors']})
+    remove_tags = [dict(name='div',   attrs={'class':['link_clanek']}),
+                dict(name='div',   attrs={'id':['partHeader']}),
+                dict(name='div',   attrs={'id':['top_bottom_box', 'lista_top']})]
+    preprocess_regexps = [(re.compile(r'<div class="(textovytip|related)".*', re.DOTALL|re.IGNORECASE), lambda match: '</body>')]
+
+    keep_only_tags = [dict(name='div', attrs={'class':'articleContent'})]
+
+    visited_urls = {}
+    def get_article_url(self, article):
+        url = BasicNewsRecipe.get_article_url(self, article)
+        if url in self.visited_urls:
+            self.log.debug('Ignoring duplicate: ' + url)
+            return None
+        else:
+            self.visited_urls[url] = True
+            self.log.debug('Accepting: ' + url)
+            return url
+
+
+
+

recipes/buchreport.recipe

@@ -0,0 +1,45 @@
+from calibre.web.feeds.recipes import BasicNewsRecipe
+
+'''Calibre recipe to convert the RSS feeds of the Buchreport to an ebook.'''
+
+class Buchreport(BasicNewsRecipe) :
+    __author__    = 'a.peter'
+    __copyright__ = 'a.peter'
+    __license__   = 'GPL v3'
+    description   = 'Buchreport'
+    version       = 4
+    title         = u'Buchreport'
+    timefmt       = ' [%d.%m.%Y]'
+    encoding      = 'cp1252'
+    language      = 'de'
+
+
+    extra_css = 'body  { margin-left: 0.00em; margin-right: 0.00em; } \
+                     article, articledate, articledescription { text-align: left; } \
+                     h1 { text-align: left; font-size: 140%; font-weight: bold; } \
+                     h2 { text-align: left; font-size: 100%; font-weight: bold; font-style: italic; } \
+                     h3 { text-align: left; font-size: 100%; font-weight: regular; font-style: italic; } \
+                     h4, h5, h6 { text-align: left; font-size: 100%; font-weight: bold; }'
+
+    oldest_article = 7.0
+    no_stylesheets = True
+    remove_javascript = True
+    use_embedded_content = False
+    publication_type = 'newspaper'
+
+    remove_tags_before = dict(name='h2')
+    remove_tags_after =  [
+                          dict(name='div', attrs={'style':["padding-top:10px;clear:both"]})
+                         ]
+    remove_tags =        [
+                          dict(name='div', attrs={'style':["padding-top:10px;clear:both"]}),
+                          dict(name='iframe'),
+                          dict(name='img')
+                         ]
+
+    feeds = [
+             (u'Buchreport', u'http://www.buchreport.de/index.php?id=5&type=100')
+            ]
+
+    def get_masthead_url(self):
+        return 'http://www.buchreport.de/fileadmin/template/img/buchreport_logo.jpg'

recipes/business_standard.recipe

@@ -1,5 +1,5 @@
 __license__   = 'GPL v3'
-__copyright__ = '2009-2010, Darko Miletic <darko.miletic at gmail.com>'
+__copyright__ = '2009-2012, Darko Miletic <darko.miletic at gmail.com>'
 '''
 www.business-standard.com
 '''
@@ -14,10 +14,12 @@ class BusinessStandard(BasicNewsRecipe):
     max_articles_per_feed  = 100
     no_stylesheets         = True
     use_embedded_content   = False
+    auto_cleanup           = False
     encoding               = 'cp1252'
     publisher              = 'Business Standard Limited'
     category               = 'news, business, money, india, world'
     language               = 'en_IN'
+    masthead_url           = 'http://feeds.business-standard.com/images/logo_08.jpg'    
 
     conversion_options = {
                              'comments'        : description
@@ -26,7 +28,7 @@ class BusinessStandard(BasicNewsRecipe):
                             ,'publisher'       : publisher
                             ,'linearize_tables': True
                          }
-    keep_only_tags=[dict(attrs={'class':'TableClas'})]
+    #keep_only_tags=[dict(name='td', attrs={'class':'TableClas'})]
     remove_tags = [
                      dict(name=['object','link','script','iframe','base','meta'])
                     ,dict(attrs={'class':'rightDiv2'})
@@ -45,3 +47,8 @@ class BusinessStandard(BasicNewsRecipe):
               ,(u'Management & Mktg'   , u'http://feeds.business-standard.com/rss/7_0.xml'   )
               ,(u'Opinion'             , u'http://feeds.business-standard.com/rss/5_0.xml'   )
             ]
+
+    def print_version(self, url):
+        l, s, tp = url.rpartition('/')
+        t, k, autono = l.rpartition('/')
+        return 'http://www.business-standard.com/india/printpage.php?autono=' + autono + '&tp=' + tp

recipes/ceska_pozice.recipe

@@ -0,0 +1,68 @@
+# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai
+from __future__ import unicode_literals
+from calibre.web.feeds.recipes import BasicNewsRecipe
+
+class ceskaPoziceRecipe(BasicNewsRecipe):
+    __author__  = 'bubak'
+    title = u'Česká pozice'
+    description = 'Česká pozice'
+    oldest_article = 2
+    max_articles_per_feed = 20
+
+    feeds = [
+        (u'Všechny články', u'http://www.ceskapozice.cz/rss.xml'),
+        (u'Domov', u'http://www.ceskapozice.cz/taxonomy/term/16/feed'),
+        (u'Chrono', u'http://www.ceskapozice.cz/chrono/feed'),
+        (u'Evropa', u'http://www.ceskapozice.cz/taxonomy/term/17/feed')
+            ]
+
+
+    language = 'cs'
+    cover_url = 'http://www.ceskapozice.cz/sites/default/files/cpozice_logo.png'
+    remove_javascript = True
+    no_stylesheets = True
+    domain = u'http://www.ceskapozice.cz'
+    use_embedded_content = False
+
+
+    remove_tags = [dict(name='div',   attrs={'class':['block-ad', 'region region-content-ad']}),
+               dict(name='ul',   attrs={'class':'links'}),
+               dict(name='div',   attrs={'id':['comments', 'back-to-top']}),
+               dict(name='div',   attrs={'class':['next-page', 'region region-content-ad']}),
+           dict(name='cite')]
+
+    keep_only_tags = [dict(name='div',   attrs={'id':'content'})]
+
+    visited_urls = {}
+    def get_article_url(self, article):
+        url = BasicNewsRecipe.get_article_url(self, article)
+        if url in self.visited_urls:
+            self.log.debug('Ignoring duplicate: ' + url)
+            return None
+        else:
+            self.visited_urls[url] = True
+            self.log.debug('Accepting: ' + url)
+            return url
+
+    def preprocess_html(self, soup):
+        self.append_page(soup, soup.body, 3)
+        return soup
+
+    def append_page(self, soup, appendtag, position):
+        pager = soup.find('div', attrs={'class':'paging-bottom'})
+        if pager:
+            nextbutton = pager.find('li', attrs={'class':'pager-next'})
+            if nextbutton:
+                nexturl = self.domain + nextbutton.a['href']
+                soup2 = self.index_to_soup(nexturl)
+                texttag = soup2.find('div', attrs={'class':'main-body'})
+                for it in texttag.findAll('div', attrs={'class':'region region-content-ad'}):
+                    it.extract()
+                    for it in texttag.findAll('cite'):
+                        it.extract()
+                        newpos = len(texttag.contents)
+                        self.append_page(soup2, texttag, newpos)
+                        texttag.extract()
+                        appendtag.insert(position, texttag)
+                        pager.extract()
+

recipes/ceske_noviny.recipe

@@ -0,0 +1,30 @@
+# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai
+from __future__ import unicode_literals
+from calibre.web.feeds.recipes import BasicNewsRecipe
+
+class ceskenovinyRecipe(BasicNewsRecipe):
+    __author__  = 'bubak'
+    title = u'České Noviny'
+    description = 'ceskenoviny.cz'
+    oldest_article = 1
+    max_articles_per_feed = 20
+
+    feeds = [
+            (u'Domácí', u'http://www.ceskenoviny.cz/sluzby/rss/domov.php')
+            #,(u'Hlavní události', u'http://www.ceskenoviny.cz/sluzby/rss/index.php')
+            #,(u'Přehled zpráv', u'http://www.ceskenoviny.cz/sluzby/rss/zpravy.php')
+            #,(u'Ze světa', u'http://www.ceskenoviny.cz/sluzby/rss/svet.php')
+            #,(u'Kultura', u'http://www.ceskenoviny.cz/sluzby/rss/kultura.php')
+            #,(u'IT', u'http://www.ceskenoviny.cz/sluzby/rss/pocitace.php')
+            ]
+
+
+    language = 'cs'
+    cover_url = 'http://i4.cn.cz/grafika/cn_logo-print.gif'
+    remove_javascript = True
+    no_stylesheets = True
+
+    remove_attributes = []
+    filter_regexps = [r'img.aktualne.centrum.cz']
+
+    keep_only_tags = [dict(name='div', attrs={'id':'clnk'})]

recipes/cesky_rozhlas_6.recipe

@@ -0,0 +1,26 @@
+# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai
+from __future__ import unicode_literals
+from calibre.web.feeds.recipes import BasicNewsRecipe
+
+class cro6Recipe(BasicNewsRecipe):
+    __author__  = 'bubak'
+    title = u'Český rozhlas 6'
+    description = 'Český rozhlas 6'
+    oldest_article = 1
+    max_articles_per_feed = 20
+
+    feeds = [
+            (u'Český rozhlas 6', u'http://www.rozhlas.cz/export/cro6/')
+            ]
+
+
+    language = 'cs'
+    cover_url = 'http://www.rozhlas.cz/img/e5/logo/cro6.png'
+    remove_javascript = True
+    no_stylesheets = True
+
+    remove_attributes = []
+    remove_tags = [dict(name='div',   attrs={'class':['audio-play-all', 'poradHeaders', 'actions']}),
+               dict(name='p', attrs={'class':['para-last']})]
+
+    keep_only_tags = [dict(name='div', attrs={'id':'article'})]

recipes/demagog.cz.recipe

@@ -0,0 +1,39 @@
+# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai
+from __future__ import unicode_literals
+from calibre.web.feeds.recipes import BasicNewsRecipe
+import re
+
+class demagogRecipe(BasicNewsRecipe):
+    __author__  = 'bubak'
+    title = u'Demagog.cz'
+    publisher = u''
+    description = 'demagog.cz'
+    oldest_article = 6
+    max_articles_per_feed = 20
+    use_embedded_content = False
+    remove_empty_feeds = True
+
+    feeds = [
+            (u'Aktuality', u'http://demagog.cz/rss')
+            ]
+
+
+    #encoding = 'iso-8859-2'
+    language = 'cs'
+    cover_url = 'http://demagog.cz/content/images/demagog.cz.png'
+    remove_javascript = True
+    no_stylesheets = True
+    extra_css             = """
+				.vyrok_suhrn{margin-top:50px; }
+				.vyrok{margin-bottom:30px; }
+                            """
+
+    remove_tags = [dict(name='a', attrs={'class':'vyrok_odovodnenie_tgl'}),
+		dict(name='img', attrs={'class':'vyrok_fotografia'})]
+    remove_tags_before = dict(name='h1')
+    remove_tags_after = dict(name='div', attrs={'class':'vyrok_text_after'})
+    preprocess_regexps = [(re.compile(r'(<div class="vyrok_suhrn">)', re.DOTALL|re.IGNORECASE), lambda match: '\1<hr>')]
+
+
+
+

recipes/denik.cz.recipe

@@ -0,0 +1,36 @@
+# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai
+from __future__ import unicode_literals
+from calibre.web.feeds.recipes import BasicNewsRecipe
+
+class ceskyDenikRecipe(BasicNewsRecipe):
+    __author__  = 'bubak'
+    title = u'denik.cz'
+    publisher = u''
+    description = u'Český deník'
+    oldest_article = 1
+    max_articles_per_feed = 20
+    use_embedded_content = False
+    remove_empty_feeds = True
+
+    feeds = [
+           (u'Z domova', u'http://www.denik.cz/rss/z_domova.html')
+            ,(u'Pražský deník - Moje Praha', u'http://prazsky.denik.cz/rss/zpravy_region.html')
+            #,(u'Zahraničí', u'http://www.denik.cz/rss/ze_sveta.html')
+            #,(u'Kultura', u'http://www.denik.cz/rss/kultura.html')
+            ]
+
+
+    #encoding = 'iso-8859-2'
+    language = 'cs'
+    cover_url = 'http://g.denik.cz/images/loga/denik.png'
+    remove_javascript = True
+    no_stylesheets = True
+    extra_css             = """
+                            """
+
+    remove_tags = []
+    keep_only_tags = [dict(name='div', attrs={'class':'content'})]
+    #remove_tags_before = dict(name='h1')
+    remove_tags_after = dict(name='p', attrs={'class':'clanek-autor'})
+
+

recipes/denik_referendum.recipe

@@ -0,0 +1,28 @@
+# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai
+from __future__ import unicode_literals
+from calibre.web.feeds.recipes import BasicNewsRecipe
+
+class denikReferendumRecipe(BasicNewsRecipe):
+    __author__  = 'bubak'
+    title = u'Den\u00edk Referendum'
+    publisher = u''
+    description = ''
+    oldest_article = 1
+    max_articles_per_feed = 20
+
+    feeds = [
+            (u'Deník Referendum', u'http://feeds.feedburner.com/DenikReferendum')
+            ]
+
+
+    #encoding = 'iso-8859-2'
+    language = 'cs'
+    remove_javascript = True
+    no_stylesheets = True
+    use_embedded_content = False
+    remove_attributes = []
+    remove_tags_after  = dict(name='div', attrs={'class':['text']})
+    remove_tags = [dict(name='div', attrs={'class':['box boxLine', 'box noprint', 'box']}),
+          dict(name='h3', attrs={'class':'head alt'})]
+
+    keep_only_tags = [dict(name='div',   attrs={'id':['content']})]

recipes/editoriali.recipe

@@ -7,6 +7,7 @@ class AdvancedUserRecipe1332847053(BasicNewsRecipe):
     title          = u'Editoriali'
     __author__      = 'faber1971'
     description = 'Leading articles on Italy by the best Italian editorials'
+    language = 'it'
 
     oldest_article = 1
     max_articles_per_feed = 100

recipes/f1_ultra.recipe

@@ -0,0 +1,35 @@
+from calibre.web.feeds.news import BasicNewsRecipe
+import re
+
+class f1ultra(BasicNewsRecipe):
+    title = u'Formuła 1 - F1 ultra'
+    __license__ = 'GPL v3'
+    __author__ = 'MrStefan <mrstefaan@gmail.com>, Artur Stachecki <artur.stachecki@gmail.com>'
+    language = 'pl'
+    description =u'Formuła 1, Robert Kubica, F3, GP2 oraz inne serie wyścigowe.'
+    masthead_url='http://www.f1ultra.pl/templates/f1ultra/images/logo.gif'
+    remove_empty_feeds= True
+    oldest_article = 1
+    max_articles_per_feed = 100
+    remove_javascript=True
+    no_stylesheets=True
+
+    keep_only_tags =[(dict(name = 'div', attrs = {'id' : 'main'}))]
+    remove_tags_after =[dict(attrs = {'style' : 'margin-top:5px;margin-bottom:5px;display: inline;'})]
+    remove_tags =[(dict(attrs = {'class' : ['buttonheading', 'avPlayerContainer', 'createdate']}))]
+    remove_tags.append(dict(attrs = {'title' : ['PDF', 'Drukuj', 'Email']}))
+    remove_tags.append(dict(name = 'form', attrs = {'method' : 'post'}))
+    remove_tags.append(dict(name = 'hr', attrs = {'size' : '2'}))
+    
+    preprocess_regexps = [(re.compile(r'align="left"'), lambda match: ''),
+		          (re.compile(r'align="right"'), lambda match: ''),
+		          (re.compile(r'width=\"*\"'), lambda match: ''),
+        		  (re.compile(r'\<table .*?\>'), lambda match: '')]
+  
+
+    extra_css = '''.contentheading { font-size: 1.4em; font-weight: bold; }
+	           img { display: block; clear: both;}
+	        '''
+    remove_attributes = ['width','height','position','float','padding-left','padding-right','padding','text-align']
+
+    feeds = [(u'F1 Ultra', u'http://www.f1ultra.pl/index.php?option=com_rd_rss&id=1&Itemid=245')]

recipes/foreign_policy.recipe

@@ -8,6 +8,7 @@ from calibre.web.feeds.news import BasicNewsRecipe
 
 class AdvancedUserRecipe1349086293(BasicNewsRecipe):
     title          = u'Foreign Policy'
+    language = 'en'
     __author__            = 'Darko Miletic'
     description           = 'International News'
     publisher             = 'Washingtonpost.Newsweek Interactive, LLC'

recipes/gazeta_pl_krakow.recipe

@@ -8,7 +8,6 @@ krakow.gazeta.pl
 '''
 
 from calibre.web.feeds.news import BasicNewsRecipe
-import re
 
 class gw_krakow(BasicNewsRecipe):
     title          = u'Gazeta.pl Kraków'

recipes/gazeta_pl_warszawa.recipe

@@ -8,7 +8,6 @@ warszawa.gazeta.pl
 '''
 
 from calibre.web.feeds.news import BasicNewsRecipe
-import re
 
 class gw_wawa(BasicNewsRecipe):
     title          = u'Gazeta.pl Warszawa'

recipes/ihned.cz.recipe

@@ -0,0 +1,36 @@
+# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai
+from __future__ import unicode_literals
+from calibre.web.feeds.recipes import BasicNewsRecipe
+
+class ihnedRecipe(BasicNewsRecipe):
+    __author__  = 'bubak'
+    title = u'iHNed.cz'
+    publisher = u''
+    description = 'ihned.cz'
+    oldest_article = 1
+    max_articles_per_feed = 20
+    use_embedded_content = False
+
+    feeds = [
+            (u'Zprávy', u'http://zpravy.ihned.cz/?m=rss'),
+            (u'Hospodářské noviny', u'http://hn.ihned.cz/?p=500000_rss'),
+            (u'Byznys', u'http://byznys.ihned.cz/?m=rss'),
+            (u'Life', u'http://life.ihned.cz/?m=rss'),
+            (u'Dialog', u'http://dialog.ihned.cz/?m=rss')
+            ]
+
+
+    #encoding = 'iso-8859-2'
+    language = 'cs'
+    cover_url = 'http://rss.ihned.cz/img/0/0_hp09/ihned.cz.gif'
+    remove_javascript = True
+    no_stylesheets = True
+    extra_css             = """
+                            """
+
+    remove_attributes = []
+    remove_tags_before  = dict(name='div', attrs={'id':['heading']})
+    remove_tags_after  = dict(name='div', attrs={'id':['next-authors']})
+    remove_tags = [dict(name='ul',   attrs={'id':['comm']}),
+                dict(name='div',   attrs={'id':['r-big']}),
+                dict(name='div',   attrs={'class':['tools tools-top']})]

recipes/insider.recipe

@@ -0,0 +1,59 @@
+# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai
+from __future__ import unicode_literals
+import re
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class insider(BasicNewsRecipe):
+    __author__  = 'bubak'
+    title      = 'Insider'
+    language = 'cs'
+
+    remove_tags        = [dict(name='div', attrs={'class':'article-related-content'})
+                 ,dict(name='div', attrs={'class':'calendar'})
+                 ,dict(name='span', attrs={'id':'labelHolder'})
+    ]
+
+    no_stylesheets = True
+    keep_only_tags = [dict(name='div', attrs={'class':['doubleBlock textContentFormat']})]
+
+    preprocess_regexps = [(re.compile(r'T.mata:.*', re.DOTALL|re.IGNORECASE), lambda m: '</body>')]
+    needs_subscription = True
+
+    def get_browser(self):
+        br = BasicNewsRecipe.get_browser()
+        br.open('http://www.denikinsider.cz/')
+        br.select_form(nr=0)
+        br['login-name'] = self.username
+        br['login-password'] = self.password
+        res = br.submit()
+        raw = res.read()
+        if u'Odhlásit se' not in raw:
+            raise ValueError('Failed to login to insider.cz'
+                             'Check your username and password.')
+        return br
+
+    def parse_index(self):
+        articles = []
+
+        soup = self.index_to_soup('http://www.denikinsider.cz')
+        titles = soup.findAll('span', attrs={'class':'homepageArticleTitle'})
+        if titles is None:
+            raise ValueError('Could not find category content')
+
+        articles = []
+        seen_titles = set([])
+        for title in titles:
+            if title.string in seen_titles:
+                continue
+            article = title.parent
+            seen_titles.add(title.string)
+            url = article['href']
+            if url.startswith('/'):
+                url = 'http://www.denikinsider.cz/'+url
+            self.log('\tFound article:', title, 'at', url)
+            articles.append({'title':title.string, 'url':url, 'description':'',
+                            'date':''})
+        return [(self.title, articles)]
+
+

recipes/kudy_z_nudy.recipe

@@ -0,0 +1,32 @@
+# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai
+from __future__ import unicode_literals
+from calibre.web.feeds.recipes import BasicNewsRecipe
+
+class kudyznudyRecipe(BasicNewsRecipe):
+    __author__  = 'bubak'
+    title = u'Kudy z nudy'
+    publisher = u''
+    description = 'kudyznudy.cz'
+    oldest_article = 3
+    max_articles_per_feed = 20
+    use_embedded_content = False
+
+    feeds = [
+            (u'Praha nejnovější', u'http://www.kudyznudy.cz/RSS/Charts.aspx?Type=Newest&Lang=cs-CZ&RegionId=1')
+            ]
+
+
+    #encoding = 'iso-8859-2'
+    language = 'cs'
+    cover_url = 'http://www.kudyznudy.cz/App_Themes/KzN/Images/Containers/Header/HeaderLogoKZN.png'
+    remove_javascript = True
+    no_stylesheets = True
+    extra_css             = """
+                            """
+
+    remove_attributes = []
+    remove_tags_before  = dict(name='div', attrs={'class':['C_WholeContentPadding']})
+    remove_tags_after  = dict(name='div', attrs={'class':['SurroundingsContainer']})
+    remove_tags = [dict(name='div',   attrs={'class':['Details', 'buttons', 'SurroundingsContainer', 'breadcrumb']})]
+
+    keep_only_tags = []

recipes/lidovky.recipe

@@ -0,0 +1,40 @@
+# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai
+from __future__ import unicode_literals
+from calibre.web.feeds.recipes import BasicNewsRecipe
+import re
+
+class lnRecipe(BasicNewsRecipe):
+    __author__  = 'bubak'
+    title = u'lidovky'
+    publisher = u''
+    description = 'lidovky.cz'
+    oldest_article = 1
+    max_articles_per_feed = 20
+
+    feeds = [
+            (u'Události', u'http://www.lidovky.cz/export/rss.asp?r=ln_domov'),
+            (u'Svět', u'http://www.lidovky.cz/export/rss.asp?r=ln_zahranici'),
+            (u'Byznys', u'http://www.lidovky.cz/export/rss.asp?c=ln_byznys'),
+            (u'Věda', u'http://www.lidovky.cz/export/rss.asp?r=ln_veda'),
+            (u'Názory', u'http://www.lidovky.cz/export/rss.asp?r=ln_nazory'),
+            (u'Relax', u'http://www.lidovky.cz/export/rss.asp?c=ln_relax')
+            ]
+
+
+    #encoding = 'iso-8859-2'
+    language = 'cs'
+    cover_url = 'http://g.lidovky.cz/o/lidovky_ln3b/lidovky-logo.png'
+    remove_javascript = True
+    no_stylesheets = True
+    use_embedded_content = False
+    remove_attributes = []
+    remove_tags_before  = dict(name='div', attrs={'id':['content']})
+    remove_tags_after  = dict(name='div', attrs={'class':['authors']})
+    preprocess_regexps = [(re.compile(r'<div id="(fb-root)".*', re.DOTALL|re.IGNORECASE), lambda match: '</body>')]
+
+    keep_only_tags = []
+
+
+
+
+

recipes/metropol_tv.recipe

@@ -0,0 +1,29 @@
+# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai
+from __future__ import unicode_literals
+from calibre.web.feeds.recipes import BasicNewsRecipe
+
+class metropolRecipe(BasicNewsRecipe):
+    __author__  = 'bubak'
+    title = u'Metropol TV'
+    publisher = u''
+    description = 'metropol.cz'
+    oldest_article = 1
+    max_articles_per_feed = 20
+    use_embedded_content = False
+
+    feeds = [
+            (u'Metropolcv.cz', u'http://www.metropol.cz/rss/')
+            ]
+
+
+    #encoding = 'iso-8859-2'
+    language = 'cs'
+    cover_url = 'http://www.metropol.cz/public/css/../images/logo/metropoltv.png'
+    remove_javascript = True
+    no_stylesheets = True
+    extra_css             = """
+                            """
+
+    remove_attributes = []
+
+    keep_only_tags = [dict(name='div', attrs={'id':['art-full']})]

recipes/myapple_pl.recipe

@@ -0,0 +1,49 @@
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class MyAppleRecipe(BasicNewsRecipe):
+    __license__ = 'GPL v3'
+    __author__ = u'Artur Stachecki <artur.stachecki@gmail.com>'
+    language = 'pl'
+    version = 1
+
+    title = u'MyApple.pl'
+    category = u'News'
+    description = u' Największy w Polsce serwis zajmujący się tematyką związaną z Apple i wszelkimi produktami tej firmy.'
+    cover_url=''
+    remove_empty_feeds= True
+    no_stylesheets=True
+    oldest_article = 7
+    max_articles_per_feed = 100000
+    recursions = 0
+
+    no_stylesheets = True
+    remove_javascript = True
+    simultaneous_downloads = 3
+
+    keep_only_tags =[]
+    keep_only_tags.append(dict(name = 'div', attrs = {'id' : 'article_content'}))
+
+    remove_tags =[]
+    remove_tags.append(dict(name = 'div', attrs = {'class' : 'article_author_date_comment_container'}))
+    remove_tags.append(dict(name = 'div', attrs = {'class' : 'fullwidth'}))
+    remove_tags.append(dict(name = 'div', attrs = {'class' : 'cmslinks'}))
+    remove_tags.append(dict(name = 'div', attrs = {'class' : 'googleads-468'}))
+    remove_tags.append(dict(name = 'div', attrs = {'id' : 'comments'}))
+
+
+    extra_css = '''
+                    body {font-family: verdana, arial, helvetica, geneva, sans-serif ;}
+                    td.contentheading{font-size: large; font-weight: bold;}
+                    '''
+
+    feeds          = [
+                            ('News', 'feed://myapple.pl/external.php?do=rss&type=newcontent&sectionid=1&days=120&count=10'),
+                          ]
+
+    def preprocess_html(self, soup):
+        for alink in soup.findAll('a'):
+            if alink.string is not None:
+               tstr = alink.string
+               alink.replaceWith(tstr)
+        return soup

recipes/nadacni_fond_proti_korupci.recipe

@@ -0,0 +1,30 @@
+# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai
+from __future__ import unicode_literals
+from calibre.web.feeds.recipes import BasicNewsRecipe
+
+class nfpkRecipe(BasicNewsRecipe):
+    __author__  = 'bubak'
+    title = u'Nadační fond proti korupci'
+    publisher = u''
+    description = 'nfpk.cz'
+    oldest_article = 7
+    max_articles_per_feed = 20
+    use_embedded_content = False
+    remove_empty_feeds = True
+
+    feeds = [
+            (u'Aktuality', u'http://feeds.feedburner.com/nfpk')
+            ]
+
+
+    #encoding = 'iso-8859-2'
+    language = 'cs'
+    cover_url = 'http://www.nfpk.cz/_templates/nfpk/_images/logo.gif'
+    remove_javascript = True
+    no_stylesheets = True
+    extra_css             = """
+                            """
+
+    remove_attributes = []
+    keep_only_tags = [dict(name='div', attrs={'id':'content'})]
+

recipes/nepszabadsag.recipe

@@ -0,0 +1,56 @@
+# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai
+from __future__ import unicode_literals
+'''
+Fetch Népszabadság
+'''
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class nepszabadsag(BasicNewsRecipe):
+    title = u'N\u00e9pszabads\u00e1g'
+    description = ''
+    __author__ = 'bubak'
+    use_embedded_content   = False
+    timefmt = ' [%d %b %Y]'
+    oldest_article = 2
+    max_articles_per_feed = 20
+    no_stylesheets = True
+    language = 'hu'
+    #delay = 1
+    #timeout = 10
+    simultaneous_downloads = 5
+
+    #encoding = 'utf-8'
+    remove_javascript = True
+    cover_url = 'http://nol.hu/_design/image/logo_nol_live.jpg'
+
+    feeds = [
+             (u'Belföld', u'http://nol.hu/feed/belfold.rss')
+             #,(u'Külföld', u'http://nol.hu/feed/kulfold.rss')
+             #,(u'Gazdaság', u'http://nol.hu/feed/gazdasag.rss')
+             #,(u'Kultúra', u'http://nol.hu/feed/kult.rss')
+             ]
+
+    extra_css = '''
+    		'''
+
+    remove_attributes = []
+    remove_tags_before  = dict(name='div', attrs={'class':['d-source']})
+    remove_tags_after  = dict(name='div', attrs={'class':['tags']})
+    remove_tags = [dict(name='div',   attrs={'class':['h']}),
+			dict(name='tfoot')]
+
+
+    keep_only_tags = [dict(name='table', attrs={'class':'article-box'})]
+
+    # NS sends an ad page sometimes but not frequently enough, TBD
+    def AAskip_ad_pages(self, soup):
+        if ('advertisement' in soup.find('title').string.lower()):
+            href = soup.find('a').get('href')
+            self.log.debug('Skipping to: ' + href)
+            new = self.browser.open(href).read().decode('utf-8', 'ignore')
+            #ipython(locals())
+            self.log.debug('Finished: ' + href)
+            return new
+        else:
+            return None
+

recipes/neviditelny_pes.recipe

@@ -0,0 +1,32 @@
+# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai
+from __future__ import unicode_literals
+from calibre.web.feeds.recipes import BasicNewsRecipe
+
+class pesRecipe(BasicNewsRecipe):
+    __author__  = 'bubak'
+    title = u'Neviditelný pes'
+    publisher = u''
+    description = u'Neviditelný pes'
+    oldest_article = 1
+    max_articles_per_feed = 20
+    use_embedded_content = False
+    remove_empty_feeds = True
+
+    feeds = [
+            (u'Neviditelný pes', u'http://neviditelnypes.lidovky.cz/export/rss.asp?c=pes_neviditelny')
+            ]
+
+
+    #encoding = 'iso-8859-2'
+    language = 'cs'
+    cover_url = 'http://g.zpravy.cz/o/pes/logo_pes.jpg'
+    remove_javascript = True
+    no_stylesheets = True
+    extra_css             = """
+                            """
+
+    remove_tags = []
+    remove_tags_before = dict(name='div', attrs={'id':'art-full'})
+    remove_tags_after = dict(name='div', attrs={'id':'authors'})
+
+

recipes/novinky.cz.recipe

@@ -0,0 +1,50 @@
+# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai
+from __future__ import unicode_literals
+from calibre.web.feeds.recipes import BasicNewsRecipe
+
+class novinkyRecipe(BasicNewsRecipe):
+    __author__  = 'bubak'
+    title = u'novinky.cz'
+    publisher = u'seznam.cz'
+    description = 'novinky.cz'
+    oldest_article = 1
+    max_articles_per_feed = 20
+
+    feeds = [
+            (u'Domácí', u'http://www.novinky.cz/rss2/domaci/'),
+            (u'Praha', u'http://www.novinky.cz/rss2/vase-zpravy/praha/'),
+            (u'Ekonomika', u'http://www.novinky.cz/rss2/ekonomika/'),
+            (u'Finance', u'http://www.novinky.cz/rss2/finance/'),
+            ]
+
+
+    #encoding = 'utf-8'
+    language = 'cs'
+    cover_url = 'http://www.novinky.cz/static/images/logo.gif'
+    remove_javascript = True
+    no_stylesheets = True
+
+    remove_tags = [dict(name='div',   attrs={'id':['pictureInnerBox']}),
+        dict(name='div',   attrs={'id':['discussionEntry']}),
+        dict(name='span',   attrs={'id':['mynews-hits', 'mynews-author']}),
+        dict(name='div',   attrs={'class':['related']}),
+        dict(name='div',   attrs={'id':['multimediaInfo']})]
+    remove_tags_before  = dict(name='div',attrs={'class':['articleHeader']})
+    remove_tags_after  = dict(name='div',attrs={'class':'related'})
+
+    keep_only_tags = []
+
+    # This source has identical articles under different links
+    # which are redirected to the common url. I've found
+    # just this API method that has the real URL
+    visited_urls = {}
+    def encoding(self, source):
+        url = source.newurl
+        if url in self.visited_urls:
+            self.log.debug('Ignoring duplicate: ' + url)
+            return None
+        else:
+            self.visited_urls[url] = True
+            self.log.debug('Accepting: ' + url)
+            return source.decode('utf-8', 'replace')
+

recipes/parlamentni_listy.recipe

@@ -0,0 +1,38 @@
+# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai
+from __future__ import unicode_literals
+from calibre.web.feeds.recipes import BasicNewsRecipe
+import re
+
+class plRecipe(BasicNewsRecipe):
+    __author__  = 'bubak'
+    title = u'Parlamentn\u00ed Listy'
+    publisher = u''
+    description = ''
+    oldest_article = 1
+    max_articles_per_feed = 20
+
+    feeds = [
+            (u'Parlamentní listy.cz', u'http://www.parlamentnilisty.cz/export/rss.aspx')
+            ]
+
+
+    #encoding = 'iso-8859-2'
+    language = 'cs'
+    cover_url = 'http://www.parlamentnilisty.cz/design/listy-logo2.png'
+    remove_javascript = True
+    no_stylesheets = True
+    use_embedded_content = False
+    remove_attributes = []
+    remove_tags = [dict(name='div', attrs={'class':['articledetailboxin','crumbs', 'relatedarticles articledetailbox']}),
+          dict(name='div', attrs={'class':['socialshare-1 noprint', 'socialshare-2 noprint']}),
+          dict(name='div', attrs={'id':'widget'}),
+          dict(name='div', attrs={'class':'article-discussion-box noprint'})]
+    preprocess_regexps = [(re.compile(r'<(span|strong)[^>]*>\s*Ptejte se politik.*', re.DOTALL|re.IGNORECASE), lambda match: '</body>')]
+
+    keep_only_tags = [dict(name='div',   attrs={'class':['article-detail']})]
+
+
+
+
+
+

recipes/piratska_strana.recipe

@@ -0,0 +1,40 @@
+# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai
+from __future__ import unicode_literals
+from calibre.web.feeds.recipes import BasicNewsRecipe
+
+class cpsRecipe(BasicNewsRecipe):
+    __author__  = 'bubak'
+    title = u'Piratská strana'
+    publisher = u''
+    description = ''
+    oldest_article = 3
+    max_articles_per_feed = 20
+    use_embedded_content = False
+    remove_empty_feeds = True
+
+    feeds = [
+            (u'Články', u'http://www.pirati.cz/rss.xml')
+            ]
+
+
+    #encoding = 'iso-8859-2'
+    language = 'cs'
+    cover_url = 'http://www.pirati.cz/sites/all/themes/addari-cps/images/headbg.jpg'
+    remove_javascript = True
+    no_stylesheets = True
+    extra_css             = """
+                            """
+
+    remove_attributes = []
+    keep_only_tags = [dict(name='div', attrs={'id':'postarea'})]
+    remove_tags = [dict(name='div', attrs={'class':['breadcrumb', 'submitted', 'links-readmore']}),
+        dict(name='div', attrs={'id':['comments']})]
+    remove_tags_before  = dict(name='font', attrs={'size':'+3'})
+    remove_tags_after  = [dict(name='iframe')]
+
+    conversion_options = {'linearize_tables' : True}
+
+
+
+
+

recipes/piratske_noviny.recipe

@@ -0,0 +1,34 @@
+# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai
+from __future__ import unicode_literals
+from calibre.web.feeds.recipes import BasicNewsRecipe
+
+class nfpkRecipe(BasicNewsRecipe):
+    __author__  = 'bubak'
+    title = u'Piratské noviny'
+    publisher = u''
+    description = 'nfpk.cz'
+    oldest_article = 2
+    max_articles_per_feed = 20
+    use_embedded_content = False
+    remove_empty_feeds = True
+
+    feeds = [
+            (u'Aktuality', u'http://www.piratskenoviny.cz/run/rss.php')
+            ]
+
+
+    #encoding = 'iso-8859-2'
+    language = 'cs'
+    cover_url = 'http://www.piratskenoviny.cz/imgs/piratske-noviny.gif'
+    remove_javascript = True
+    no_stylesheets = True
+    extra_css             = """
+                            """
+
+    remove_attributes = []
+    remove_tags_before  = dict(name='font', attrs={'size':'+3'})
+    remove_tags_after  = [dict(name='iframe')]
+    conversion_options = {'linearize_tables' : True}
+
+
+

recipes/portfolio_hu.recipe

@@ -4,7 +4,7 @@ class AdvancedUserRecipe1348063712(BasicNewsRecipe):
     title          = u'Portfolio.hu - English Edition'
     __author__ = 'laca'
     oldest_article = 7
-    language = 'en_HUN'
+    language = 'en_HU'
     masthead_url          = 'http://www.portfolio.hu/img/sit/angolfejlec2010.jpg'
     use_embedded_content  = False
     auto_cleanup = True

recipes/pravo.recipe

@@ -0,0 +1,64 @@
+# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai
+from __future__ import unicode_literals
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class pravo(BasicNewsRecipe):
+    __author__  = 'bubak'
+    title      = 'Právo'
+    language = 'cs'
+
+    remove_tags_before = dict(name='div', attrs={'class':'rubrika-ostat'})
+    remove_tags_after = dict(name='td', attrs={'class':'rubrika'})
+    remove_tags        = [dict(name='td', attrs={'width':'273'})
+                 ,dict(name='td', attrs={'class':'rubrika'})
+                 ,dict(name='div', attrs={'class':'rubrika-ostat'})
+    ]
+    extra_css = '.nadpis {font-weight: bold; font-size: 130%;} .medium {text-align: justify;}'
+    cover_url = 'http://pravo.novinky.cz/images/horni_6_logo.gif'
+    cover_margins = (0, 100, '#ffffff')
+    conversion_options = {'linearize_tables' : True}
+
+    no_stylesheets = True
+
+    # our variables
+    seen_titles = set([])
+    # only yesterday's articles are online
+    parent_url = 'http://pravo.novinky.cz/minule/'
+    feeds = [
+            ('Hlavní stránka', 'http://pravo.novinky.cz/minule/index.php'),
+            ('Zpravodajství', 'http://pravo.novinky.cz/minule/zpravodajstvi.php'),
+            ('Komentáře', 'http://pravo.novinky.cz/minule/komentare.php'),
+            ('Praha a střední Čechy', 'http://pravo.novinky.cz/minule/praha_stredni_cechy.php')
+        ]
+
+
+    def parse_index(self):
+        articles = []
+
+        for feed in self.feeds:
+            articles.append(self.parse_page(feed))
+        return articles
+
+    def parse_page(self, (feed_title, url)):
+        articles = []
+
+        soup = self.index_to_soup(url)
+        titles = soup.findAll('a', attrs={'class':'nadpis'})
+        if titles is None:
+            raise ValueError('Could not find any articles on page ' + url)
+
+        articles = []
+        for article in titles:
+            title = article.string
+            if title in self.seen_titles:
+                continue
+            self.seen_titles.add(title)
+            url = article['href']
+            if not url.startswith('http'):
+                url = self.parent_url + url
+            self.log('\tFound article:', title, 'at', url)
+            articles.append({'title':title.string, 'url':url, 'description':'',
+                            'date':''})
+            return (feed_title, articles)
+

recipes/respekt.recipe

@@ -0,0 +1,37 @@
+# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai
+from __future__ import unicode_literals
+from calibre.web.feeds.recipes import BasicNewsRecipe
+import re
+
+class respektRecipe(BasicNewsRecipe):
+    __author__  = 'bubak'
+    title = u'Respekt'
+    publisher = u'Respekt'
+    description = 'Respekt'
+    oldest_article = 1
+    max_articles_per_feed = 20
+
+    feeds = [
+            (u'Všechny články', u'http://respekt.ihned.cz/index.php?p=R00000_rss')
+            ,(u'Blogy', u'http://blog.respekt.ihned.cz/?p=Rb00VR_rss')
+            #,(u'Respekt DJ', u'http://respekt.ihned.cz/index.php?p=R00RDJ_rss')
+            ]
+
+
+    encoding = 'cp1250'
+    language = 'cs'
+    cover_url = 'http://respekt.ihned.cz/img/R/respekt_logo.png'
+    remove_javascript = True
+    no_stylesheets = True
+
+    remove_tags = [dict(name='div',   attrs={'class':['d-tools', 'actions']})]
+    remove_tags_before  = dict(name='div',attrs={'id':['detail']})
+    remove_tags_after  = dict(name='div',attrs={'class':'d-tools'})
+    preprocess_regexps = [(re.compile(r'<div class="paid-zone".*', re.DOTALL|re.IGNORECASE), lambda match: 'Za zbytek článku je nutno platit. </body>'),
+			(re.compile(r'.*<div class="mm-ow">', re.DOTALL|re.IGNORECASE), lambda match: '<body>'),
+			(re.compile(r'<div class="col3">.*', re.DOTALL|re.IGNORECASE), lambda match: '</body>')]
+
+    keep_only_tags = []
+
+
+

recipes/spektrum.recipe

@@ -16,7 +16,7 @@ class AdvancedUserRecipe1303841067(BasicNewsRecipe):
     no_stylesheets        = True
     remove_javascript     = True
     remove_empty_feeds    = True
-    language              = 'de_DE'
+    language              = 'de'
 
     #conversion_options    = {'base_font_size': 20}
 

recipes/telepolis_pl.recipe

@@ -0,0 +1,67 @@
+#!/usr/bin/env  python
+
+__license__ = 'GPL v3'
+
+from calibre.web.feeds.news import BasicNewsRecipe
+import re
+
+
+class telepolis(BasicNewsRecipe):
+    title = u'Telepolis.pl'
+    __author__ = 'Artur Stachecki <artur.stachecki@gmail.com>'
+    language = 'pl'
+    description = u'Twój telekomunikacyjny serwis informacyjny.\
+                  Codzienne informacje, testy i artykuły,\
+                  promocje, baza telefonów oraz centrum rozrywki'
+    oldest_article = 7
+    masthead_url = 'http://telepolis.pl/i/telepolis-logo2.gif'
+    max_articles_per_feed = 100
+    simultaneous_downloads = 5
+    remove_javascript = True
+    no_stylesheets = True
+    use_embedded_content = False
+
+    remove_tags = []
+    remove_tags.append(dict(attrs={'alt': 'TELEPOLIS.pl'}))
+
+    preprocess_regexps = [(re.compile(r'<: .*? :>'),
+                           lambda match: ''),
+                          (re.compile(r'<b>Zobacz:</b>.*?</a>', re.DOTALL),
+                           lambda match: ''),
+                          (re.compile(r'<-ankieta.*?>'),
+                           lambda match: ''),
+                          (re.compile(r'\(Q\!\)'),
+                           lambda match: ''),
+                          (re.compile(r'\(plik.*?\)'),
+                           lambda match: ''),
+                          (re.compile(r'<br.*?><br.*?>', re.DOTALL),
+                           lambda match: '')
+                          ]
+
+    extra_css = '''.tb { font-weight: bold; font-size: 20px;}'''
+
+    feeds = [
+        (u'Wiadomości', u'http://www.telepolis.pl/rss/news.php'),
+        (u'Artykuły', u'http://www.telepolis.pl/rss/artykuly.php')
+    ]
+
+    def print_version(self, url):
+        if 'news.php' in url:
+            print_url = url.replace('news.php', 'news_print.php')
+        else:
+            print_url = url.replace('artykuly.php', 'art_print.php')
+        return print_url
+
+    def preprocess_html(self, soup):
+        for image in soup.findAll('img'):
+            if 'm.jpg' in image['src']:
+                image_big = image['src']
+                image_big = image_big.replace('m.jpg', '.jpg')
+                image['src'] = image_big
+        logo = soup.find('tr')
+        logo.extract()
+        for tag in soup.findAll('tr'):
+            for strings in ['Wiadomość wydrukowana', 'copyright']:
+                if strings in self.tag_to_string(tag):
+                    tag.extract()
+        return self.adeify_images(soup)

recipes/tyden.cz.recipe

@@ -0,0 +1,44 @@
+# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai
+from __future__ import unicode_literals
+from calibre.web.feeds.recipes import BasicNewsRecipe
+
+class tydenRecipe(BasicNewsRecipe):
+    __author__  = 'bubak'
+    title = u'Tyden.cz'
+    publisher = u''
+    description = ''
+    oldest_article = 1
+    max_articles_per_feed = 20
+
+    feeds = [
+            (u'Domácí', u'http://www.tyden.cz/rss/rss.php?rubrika_id=6'),
+            (u'Politika', u'http://www.tyden.cz/rss/rss.php?rubrika_id=173'),
+            (u'Kauzy', u'http://www.tyden.cz/rss/rss.php?rubrika_id=340')
+            ]
+
+
+    #encoding = 'iso-8859-2'
+    language = 'cs'
+    cover_url = 'http://www.tyden.cz/img/tyden-logo.png'
+    remove_javascript = True
+    no_stylesheets = True
+    remove_attributes = []
+    remove_tags_before  = dict(name='p', attrs={'id':['breadcrumbs']})
+    remove_tags_after  = dict(name='p', attrs={'class':['author']})
+
+    visited_urls = {}
+    def get_article_url(self, article):
+        url = BasicNewsRecipe.get_article_url(self, article)
+        if url in self.visited_urls:
+            self.log.debug('Ignoring duplicate: ' + url)
+            return None
+        else:
+            self.visited_urls[url] = True
+            self.log.debug('Accepting: ' + url)
+            return url
+
+
+
+
+
+

recipes/xpatloop.recipe

@@ -4,7 +4,7 @@ class AdvancedUserRecipe1347997197(BasicNewsRecipe):
     title          = u'XpatLoop.com'
     __author__     = 'laca'
     oldest_article = 7
-    language = 'en_HUN'
+    language = 'en_HU'
     auto_cleanup = True
     masthead_url          = 'http://www.xpatloop.com/images/cms/xs_logo.gif'
     use_embedded_content  = False

recipes/zeitde.recipe

@@ -16,7 +16,7 @@ class ZeitDe(BasicNewsRecipe):
     category              = 'news, Germany'
     timefmt               = ' [%a, %d %b %Y]'
     publication_type      = 'newspaper'
-    language              = 'de_DE'
+    language              = 'de'
     encoding              = 'UTF-8'
 
     oldest_article        = 7

src/calibre/customize/__init__.py

@@ -308,6 +308,10 @@ class FileTypePlugin(Plugin): # {{{
     #: to the database
     on_import      = False
 
+    #: If True, this plugin is run after books are added
+    #: to the database
+    on_postimport  = False
+
     #: If True, this plugin is run just before a conversion
     on_preprocess  = False
 
@@ -337,6 +341,16 @@ class FileTypePlugin(Plugin): # {{{
         # Default implementation does nothing
         return path_to_ebook
 
+    def postimport(self, book_id, book_format, db):
+        '''
+        Called post import, i.e., after the book file has been added to the database.
+
+        :param book_id: Database id of the added book.
+        :param book_format: The file type of the book that was added.
+		:param db: Library database.
+        '''
+        pass # Default implementation does nothing
+
 # }}}
 
 class MetadataReaderPlugin(Plugin): # {{{
@@ -447,8 +461,8 @@ class CatalogPlugin(Plugin): # {{{
         # Return a list of requested fields, with opts.sort_by first
         all_std_fields = set(
                           ['author_sort','authors','comments','cover','formats',
-                           'id','isbn','ondevice','pubdate','publisher','rating',
-                           'series_index','series','size','tags','timestamp',
+                           'id','isbn','library_name','ondevice','pubdate','publisher',
+                           'rating','series_index','series','size','tags','timestamp',
                            'title_sort','title','uuid','languages','identifiers'])
         all_custom_fields = set(db.custom_field_keys())
         for field in list(all_custom_fields):
@@ -460,6 +474,16 @@ class CatalogPlugin(Plugin): # {{{
         if opts.fields != 'all':
             # Make a list from opts.fields
             requested_fields = set(opts.fields.split(','))
+
+            # Validate requested_fields
+            if requested_fields - all_fields:
+                from calibre.library import current_library_name
+                invalid_fields = sorted(list(requested_fields - all_fields))
+                print("invalid --fields specified: %s" % ', '.join(invalid_fields))
+                print("available fields in '%s': %s" %
+                      (current_library_name(), ', '.join(sorted(list(all_fields)))))
+                raise ValueError("unable to generate catalog with specified fields")
+
             fields = list(all_fields & requested_fields)
         else:
             fields = list(all_fields)

src/calibre/customize/ui.py

@@ -104,14 +104,17 @@ def is_disabled(plugin):
 # File type plugins {{{
 
 _on_import           = {}
+_on_postimport       = {}
 _on_preprocess       = {}
 _on_postprocess      = {}
 
 def reread_filetype_plugins():
     global _on_import
+    global _on_postimport
     global _on_preprocess
     global _on_postprocess
     _on_import           = {}
+    _on_postimport       = {}
     _on_preprocess       = {}
     _on_postprocess      = {}
 
@@ -122,6 +125,10 @@ def reread_filetype_plugins():
                     if not _on_import.has_key(ft):
                         _on_import[ft] = []
                     _on_import[ft].append(plugin)
+                if plugin.on_postimport:
+                    if not _on_postimport.has_key(ft):
+                        _on_postimport[ft] = []
+                    _on_postimport[ft].append(plugin)
                 if plugin.on_preprocess:
                     if not _on_preprocess.has_key(ft):
                         _on_preprocess[ft] = []
@@ -163,6 +170,22 @@ run_plugins_on_preprocess  = functools.partial(_run_filetype_plugins,
                                                occasion='preprocess')
 run_plugins_on_postprocess = functools.partial(_run_filetype_plugins,
                                                occasion='postprocess')
+
+def run_plugins_on_postimport(db, book_id, fmt):
+    customization = config['plugin_customization']
+    fmt = fmt.lower()
+    for plugin in _on_postimport.get(fmt, []):
+        if is_disabled(plugin):
+            continue
+        plugin.site_customization = customization.get(plugin.name, '')
+        with plugin:
+            try:
+                plugin.postimport(book_id, fmt, db)
+            except:
+                print ('Running file type plugin %s failed with traceback:'%
+                       plugin.name)
+                traceback.print_exc()
+
 # }}}
 
 # Plugin customization {{{

src/calibre/devices/teclast/driver.py

@@ -19,9 +19,9 @@ class TECLAST_K3(USBMS):
     PRODUCT_ID  = [0x3203]
     BCD         = [0x0000, 0x0100]
 
-    VENDOR_NAME      = ['TECLAST', 'IMAGIN', 'RK28XX', 'PER3274B']
+    VENDOR_NAME      = ['TECLAST', 'IMAGIN', 'RK28XX', 'PER3274B', 'BEBOOK']
     WINDOWS_MAIN_MEM = WINDOWS_CARD_A_MEM = ['DIGITAL_PLAYER', 'TL-K5',
-            'EREADER', 'USB-MSC', 'PER3274B']
+            'EREADER', 'USB-MSC', 'PER3274B', 'BEBOOK']
 
     MAIN_MEMORY_VOLUME_LABEL  = 'K3 Main Memory'
     STORAGE_CARD_VOLUME_LABEL = 'K3 Storage Card'

src/calibre/ebooks/__init__.py

@@ -263,8 +263,11 @@ def generate_masthead(title, output_path=None, width=600, height=60):
     masthead_font_family = recs.get('masthead_font', 'Default')
 
     if masthead_font_family != 'Default':
-        from calibre.utils.fonts.scanner import font_scanner
+        from calibre.utils.fonts.scanner import font_scanner, NoFonts
+        try:
             faces = font_scanner.fonts_for_family(masthead_font_family)
+        except NoFonts:
+            faces = []
         if faces:
             font_path = faces[0]['path']
 

src/calibre/ebooks/conversion/plumber.py

@@ -1103,10 +1103,14 @@ OptionRecommendation(name='search_replace',
             from calibre.ebooks.oeb.transforms.unsmarten import UnsmartenPunctuation
             UnsmartenPunctuation()(self.oeb, self.opts)
 
+        mobi_file_type = getattr(self.opts, 'mobi_file_type', 'old')
+        needs_old_markup = (self.output_plugin.file_type == 'lit' or
+                    (self.output_plugin.file_type == 'mobi' and mobi_file_type
+                     == 'old'))
         flattener = CSSFlattener(fbase=fbase, fkey=fkey,
                 lineh=line_height,
-                untable=self.output_plugin.file_type in ('mobi','lit'),
-                unfloat=self.output_plugin.file_type in ('mobi', 'lit'),
+                untable=needs_old_markup,
+                unfloat=needs_old_markup,
                 page_break_on_body=self.output_plugin.file_type in ('mobi',
                     'lit'),
                 specializer=partial(self.output_plugin.specialize_css_for_output,

src/calibre/ebooks/mobi/mobiml.py

@@ -322,6 +322,10 @@ class MobiMLizer(object):
         istates.append(istate)
         left = 0
         display = style['display']
+        if display == 'table-cell':
+            display = 'inline'
+        elif display.startswith('table'):
+            display = 'block'
         isblock = (not display.startswith('inline') and style['display'] !=
                 'none')
         isblock = isblock and style['float'] == 'none'

src/calibre/gui2/__init__.py

@@ -93,6 +93,7 @@ gprefs.defaults['tag_browser_dont_collapse'] = []
 gprefs.defaults['edit_metadata_single_layout'] = 'default'
 gprefs.defaults['default_author_link'] = 'http://en.wikipedia.org/w/index.php?search={author}'
 gprefs.defaults['preserve_date_on_ctl'] = True
+gprefs.defaults['manual_add_auto_convert'] = False
 gprefs.defaults['cb_fullscreen'] = False
 gprefs.defaults['worker_max_time'] = 0
 gprefs.defaults['show_files_after_save'] = True

src/calibre/gui2/actions/choose_library.py

@@ -320,15 +320,23 @@ class ChooseLibraryAction(InterfaceAction):
                     _('Path to library too long. Must be less than'
                     ' %d characters.')%LibraryDatabase2.WINDOWS_LIBRARY_PATH_LIMIT,
                     show=True)
+        if not os.path.exists(loc):
+            error_dialog(self.gui, _('Not found'),
+                    _('Cannot rename as no library was found at %s. '
+                      'Try switching to this library first, then switch back '
+                      'and retry the renaming.')%loc, show=True)
+            return
         try:
             os.rename(loc, newloc)
         except:
             import traceback
+            det_msg = 'Location: %r New Location: %r\n%s'%(loc, newloc,
+                                                        traceback.format_exc())
             error_dialog(self.gui, _('Rename failed'),
                     _('Failed to rename the library at %s. '
                 'The most common cause for this is if one of the files'
                 ' in the library is open in another program.') % loc,
-                    det_msg=traceback.format_exc(), show=True)
+                    det_msg=det_msg, show=True)
             return
         self.stats.rename(location, newloc)
         self.build_menus()

src/calibre/gui2/actions/view.py

@@ -267,8 +267,8 @@ class ViewAction(InterfaceAction):
 
     def _view_books(self, rows):
         if not rows or len(rows) == 0:
-            self._launch_viewer()
-            return
+            return error_dialog(self.gui, _('Cannot view'),
+                             _('No books selected'), show=True)
 
         if not self._view_check(len(rows)):
             return

src/calibre/gui2/add.py

@@ -42,6 +42,7 @@ class DuplicatesAdder(QObject): # {{{
         # here we add all the formats for dupe book record created above
         self.db_adder.add_formats(id, formats)
         self.db_adder.number_of_books_added += 1
+        self.db_adder.auto_convert_books.add(id)
         self.count += 1
         self.added.emit(self.count)
         single_shot(self.add_one)
@@ -107,8 +108,16 @@ class DBAdder(QObject): # {{{
         self.input_queue = Queue()
         self.output_queue = Queue()
         self.merged_books = set([])
+        self.auto_convert_books = set()
 
     def end(self):
+        if (gprefs['manual_add_auto_convert'] and
+                self.auto_convert_books):
+            from calibre.gui2.ui import get_gui
+            gui = get_gui()
+            gui.iactions['Convert Books'].auto_convert_auto_add(
+                self.auto_convert_books)
+
         self.input_queue.put((None, None, None))
 
     def start(self):
@@ -152,7 +161,6 @@ class DBAdder(QObject): # {{{
                 fmts[-1] = fmt
         return fmts
 
-
     def add(self, id, opf, cover, name):
         formats = self.ids.pop(id)
         if opf.endswith('.error'):
@@ -219,6 +227,7 @@ class DBAdder(QObject): # {{{
                     self.duplicates.append((mi, cover, orig_formats))
                 else:
                     self.add_formats(id_, formats)
+                    self.auto_convert_books.add(id_)
                     self.number_of_books_added += 1
         else:
             self.names.append(name)

src/calibre/gui2/library/models.py

@@ -1057,6 +1057,7 @@ class DeviceBooksModel(BooksModel): # {{{
 
     booklist_dirtied = pyqtSignal()
     upload_collections = pyqtSignal(object)
+    resize_rows = pyqtSignal()
 
     def __init__(self, parent):
         BooksModel.__init__(self, parent)
@@ -1163,6 +1164,11 @@ class DeviceBooksModel(BooksModel): # {{{
         return flags
 
     def search(self, text, reset=True):
+        # This should not be here, but since the DeviceBooksModel does not
+        # implement count_changed and I am too lazy to fix that, this kludge
+        # will have to do
+        self.resize_rows.emit()
+
         if not text or not text.strip():
             self.map = list(range(len(self.db)))
         else:

src/calibre/gui2/library/views.py

@@ -90,6 +90,7 @@ class BooksView(QTableView): # {{{
 
     def __init__(self, parent, modelcls=BooksModel, use_edit_metadata_dialog=True):
         QTableView.__init__(self, parent)
+        self.row_sizing_done = False
 
         if not tweaks['horizontal_scrolling_per_column']:
             self.setHorizontalScrollMode(self.ScrollPerPixel)
@@ -141,6 +142,8 @@ class BooksView(QTableView): # {{{
         self.display_parent = parent
         self._model = modelcls(self)
         self.setModel(self._model)
+        self._model.count_changed_signal.connect(self.do_row_sizing,
+                                                 type=Qt.QueuedConnection)
         self.setSelectionBehavior(QAbstractItemView.SelectRows)
         self.setSortingEnabled(True)
         self.selectionModel().currentRowChanged.connect(self._model.current_changed)
@@ -521,13 +524,17 @@ class BooksView(QTableView): # {{{
         self.apply_state(old_state, max_sort_levels=max_levels)
         self.column_header.blockSignals(False)
 
-        # Resize all rows to have the correct height
-        if self.model().rowCount(QModelIndex()) > 0:
-            self.resizeRowToContents(0)
-            self.verticalHeader().setDefaultSectionSize(self.rowHeight(0))
+        self.do_row_sizing()
 
         self.was_restored = True
 
+    def do_row_sizing(self):
+        # Resize all rows to have the correct height
+        if not self.row_sizing_done and self.model().rowCount(QModelIndex()) > 0:
+            self.resizeRowToContents(0)
+            self.verticalHeader().setDefaultSectionSize(self.rowHeight(0))
+            self.row_sizing_done = True
+
     def resize_column_to_fit(self, column):
         col = self.column_map.index(column)
         self.column_resized(col, self.columnWidth(col), self.columnWidth(col))
@@ -943,6 +950,8 @@ class DeviceBooksView(BooksView): # {{{
     def __init__(self, parent):
         BooksView.__init__(self, parent, DeviceBooksModel,
                            use_edit_metadata_dialog=False)
+        self._model.resize_rows.connect(self.do_row_sizing,
+                                                 type=Qt.QueuedConnection)
         self.can_add_columns = False
         self.columns_resized = False
         self.resize_on_select = False

src/calibre/gui2/metadata/basic_widgets.py

@@ -867,6 +867,7 @@ class Cover(ImageView): # {{{
 
     def __init__(self, parent):
         ImageView.__init__(self, parent)
+        self.show_size = True
         self.dialog = parent
         self._cdata = None
         self.cover_changed.connect(self.set_pixmap_from_data)

src/calibre/gui2/preferences/adding.py

@@ -28,6 +28,7 @@ class ConfigWidget(ConfigWidgetBase, Ui_Form):
         r('swap_author_names', prefs)
         r('add_formats_to_existing', prefs)
         r('preserve_date_on_ctl', gprefs)
+        r('manual_add_auto_convert', gprefs)
         choices = [
                 (_('Ignore duplicate incoming formats'), 'ignore'),
                 (_('Overwrite existing duplicate formats'), 'overwrite'),

src/calibre/gui2/preferences/adding.ui

@@ -6,7 +6,7 @@
    <rect>
     <x>0</x>
     <y>0</y>
-    <width>753</width>
+    <width>1035</width>
     <height>547</height>
    </rect>
   </property>
@@ -24,6 +24,36 @@
        <string>The Add &amp;Process</string>
       </attribute>
       <layout class="QGridLayout" name="gridLayout_2">
+       <item row="4" column="0" colspan="2">
+        <widget class="QCheckBox" name="opt_add_formats_to_existing">
+         <property name="toolTip">
+          <string>Automerge: If books with similar titles and authors found, merge the incoming formats automatically into
+existing book records. The box to the right controls what happens when an existing record already has
+the incoming format. Note that this option also affects the Copy to library action.
+
+Title match ignores leading indefinite articles (&quot;the&quot;, &quot;a&quot;, &quot;an&quot;), punctuation, case, etc. Author match is exact.</string>
+         </property>
+         <property name="text">
+          <string>&amp;Automerge added books if they already exist in the calibre library:</string>
+         </property>
+        </widget>
+       </item>
+       <item row="4" column="2">
+        <widget class="QComboBox" name="opt_automerge">
+         <property name="toolTip">
+          <string>Automerge: If books with similar titles and authors found, merge the incoming formats automatically into
+existing book records. This box controls what happens when an existing record already has
+the incoming format: 
+
+Ignore duplicate incoming files - means that existing files in your calibre library will not be replaced
+Overwrite existing duplicate files - means that existing files in your calibre library will be replaced
+Create new record for each duplicate file - means that a new book entry will be created for each duplicate file
+
+Title matching ignores leading indefinite articles (&quot;the&quot;, &quot;a&quot;, &quot;an&quot;), punctuation, case, etc.
+Author matching is exact.</string>
+         </property>
+        </widget>
+       </item>
        <item row="0" column="0" colspan="3">
         <widget class="QLabel" name="label_6">
          <property name="text">
@@ -68,44 +98,7 @@
          </item>
         </layout>
        </item>
-       <item row="2" column="0" colspan="3">
-        <widget class="QCheckBox" name="opt_preserve_date_on_ctl">
-         <property name="text">
-          <string>When using the  &quot;&amp;Copy to library&quot; action to copy books between libraries, preserve the date</string>
-         </property>
-        </widget>
-       </item>
-       <item row="3" column="0" colspan="2">
-        <widget class="QCheckBox" name="opt_add_formats_to_existing">
-         <property name="toolTip">
-          <string>Automerge: If books with similar titles and authors found, merge the incoming formats automatically into
-existing book records. The box to the right controls what happens when an existing record already has
-the incoming format. Note that this option also affects the Copy to library action.
-
-Title match ignores leading indefinite articles (&quot;the&quot;, &quot;a&quot;, &quot;an&quot;), punctuation, case, etc. Author match is exact.</string>
-         </property>
-         <property name="text">
-          <string>&amp;Automerge added books if they already exist in the calibre library:</string>
-         </property>
-        </widget>
-       </item>
-       <item row="3" column="2">
-        <widget class="QComboBox" name="opt_automerge">
-         <property name="toolTip">
-          <string>Automerge: If books with similar titles and authors found, merge the incoming formats automatically into
-existing book records. This box controls what happens when an existing record already has
-the incoming format: 
-
-Ignore duplicate incoming files - means that existing files in your calibre library will not be replaced
-Overwrite existing duplicate files - means that existing files in your calibre library will be replaced
-Create new record for each duplicate file - means that a new book entry will be created for each duplicate file
-
-Title matching ignores leading indefinite articles (&quot;the&quot;, &quot;a&quot;, &quot;an&quot;), punctuation, case, etc.
-Author matching is exact.</string>
-         </property>
-        </widget>
-       </item>
-       <item row="4" column="0">
+       <item row="5" column="0">
         <widget class="QLabel" name="label_230">
          <property name="text">
           <string>&amp;Tags to apply when adding a book:</string>
@@ -115,14 +108,14 @@ Author matching is exact.</string>
          </property>
         </widget>
        </item>
-       <item row="4" column="2">
+       <item row="5" column="2">
         <widget class="QLineEdit" name="opt_new_book_tags">
          <property name="toolTip">
           <string>A comma-separated list of tags that will be applied to books added to the library</string>
          </property>
         </widget>
        </item>
-       <item row="5" column="0" colspan="3">
+       <item row="6" column="0" colspan="3">
         <widget class="QGroupBox" name="metadata_box">
          <property name="title">
           <string>&amp;Configure metadata from file name</string>
@@ -144,6 +137,20 @@ Author matching is exact.</string>
          </layout>
         </widget>
        </item>
+       <item row="2" column="0" colspan="3">
+        <widget class="QCheckBox" name="opt_preserve_date_on_ctl">
+         <property name="text">
+          <string>When using the  &quot;&amp;Copy to library&quot; action to copy books between libraries, preserve the date</string>
+         </property>
+        </widget>
+       </item>
+       <item row="3" column="0" colspan="2">
+        <widget class="QCheckBox" name="opt_manual_add_auto_convert">
+         <property name="text">
+          <string>Automatically &amp;convert added books to the current output format</string>
+         </property>
+        </widget>
+       </item>
       </layout>
      </widget>
      <widget class="QWidget" name="tab_4">

src/calibre/gui2/store/search/models.py

@@ -16,8 +16,6 @@ from calibre.gui2 import NONE, FunctionDispatcher
 from calibre.gui2.store.search_result import SearchResult
 from calibre.gui2.store.search.download_thread import DetailsThreadPool, \
     CoverThreadPool
-from calibre.library.caches import _match, CONTAINS_MATCH, EQUALS_MATCH, \
-    REGEXP_MATCH
 from calibre.utils.icu import sort_key
 from calibre.utils.search_query_parser import SearchQueryParser
 
@@ -153,7 +151,7 @@ class Matches(QAbstractItemModel):
         mod_query = query
         # Remove filter identifiers
         # Remove the prefix.
-        for loc in ('all', 'author', 'authors', 'title'):
+        for loc in ('all', 'author', 'author2', 'authors', 'title', 'title2'):
             query = re.sub(r'%s:"(?P<a>[^\s"]+)"' % loc, '\g<a>', query)
             query = query.replace('%s:' % loc, '')
         # Remove the prefix and search text.
@@ -301,11 +299,16 @@ class Matches(QAbstractItemModel):
 
 
 class SearchFilter(SearchQueryParser):
+    CONTAINS_MATCH = 0
+    EQUALS_MATCH   = 1
+    REGEXP_MATCH   = 2
+    IN_MATCH       = 3
 
     USABLE_LOCATIONS = [
         'all',
         'affiliate',
         'author',
+        'author2',
         'authors',
         'cover',
         'download',
@@ -315,6 +318,7 @@ class SearchFilter(SearchQueryParser):
         'formats',
         'price',
         'title',
+        'title2',
         'store',
     ]
 
@@ -331,6 +335,26 @@ class SearchFilter(SearchQueryParser):
     def universal_set(self):
         return self.srs
 
+    def _match(self, query, value, matchkind):
+        for t in value:
+            try:     ### ignore regexp exceptions, required because search-ahead tries before typing is finished
+                t = icu_lower(t)
+                if matchkind == self.EQUALS_MATCH:
+                    if query == t:
+                        return True
+                elif matchkind == self.REGEXP_MATCH:
+                    if re.search(query, t, re.I|re.UNICODE):
+                        return True
+                elif matchkind == self.CONTAINS_MATCH:
+                    if query in t:
+                        return True
+                elif matchkind == self.IN_MATCH:
+                    if t in query:
+                        return True
+            except re.error:
+                pass
+        return False
+
     def get_matches(self, location, query):
         query = query.strip()
         location = location.lower().strip()
@@ -341,17 +365,17 @@ class SearchFilter(SearchQueryParser):
         elif location == 'formats':
             location = 'format'
 
-        matchkind = CONTAINS_MATCH
+        matchkind = self.CONTAINS_MATCH
         if len(query) > 1:
             if query.startswith('\\'):
                 query = query[1:]
             elif query.startswith('='):
-                matchkind = EQUALS_MATCH
+                matchkind = self.EQUALS_MATCH
                 query = query[1:]
             elif query.startswith('~'):
-                matchkind = REGEXP_MATCH
+                matchkind = self.REGEXP_MATCH
                 query = query[1:]
-        if matchkind != REGEXP_MATCH: ### leave case in regexps because it can be significant e.g. \S \W \D
+        if matchkind != self.REGEXP_MATCH: ### leave case in regexps because it can be significant e.g. \S \W \D
             query = query.lower()
 
         if location not in self.USABLE_LOCATIONS:
@@ -372,6 +396,8 @@ class SearchFilter(SearchQueryParser):
         }
         for x in ('author', 'download', 'format'):
             q[x+'s'] = q[x]
+        q['author2'] = q['author']
+        q['title2'] = q['title']
         
         # make the price in query the same format as result
         if location == 'price':
@@ -415,16 +441,19 @@ class SearchFilter(SearchQueryParser):
                     ### Can't separate authors because comma is used for name sep and author sep
                     ### Exact match might not get what you want. For that reason, turn author
                     ### exactmatch searches into contains searches.
-                    if locvalue == 'author' and matchkind == EQUALS_MATCH:
-                        m = CONTAINS_MATCH
+                    if locvalue == 'author' and matchkind == self.EQUALS_MATCH:
+                        m = self.CONTAINS_MATCH
                     else:
                         m = matchkind
 
                     if locvalue == 'format':
                         vals = accessor(sr).split(',')
+                    elif locvalue in ('author2', 'title2'):
+                        m = self.IN_MATCH
+                        vals = re.sub(r'(^|\s)(and|not|or|a|the|is|of|,)(\s|$)', ' ', accessor(sr)).split(' ')
                     else:
                         vals = [accessor(sr)]
-                    if _match(query, vals, m):
+                    if self._match(query, vals, m):
                         matches.add(sr)
                         break
                 except ValueError: # Unicode errors

src/calibre/gui2/store/search/search.py

@@ -13,7 +13,7 @@ from PyQt4.Qt import (Qt, QDialog, QDialogButtonBox, QTimer, QCheckBox, QLabel,
                       QVBoxLayout, QIcon, QWidget, QTabWidget, QGridLayout,
                       QComboBox)
 
-from calibre.gui2 import JSONConfig, info_dialog
+from calibre.gui2 import JSONConfig, info_dialog, error_dialog
 from calibre.gui2.dialogs.choose_format import ChooseFormatDialog
 from calibre.gui2.progress_indicator import ProgressIndicator
 from calibre.gui2.store.config.chooser.chooser_widget import StoreChooserWidget
@@ -31,6 +31,8 @@ class SearchDialog(QDialog, Ui_Dialog):
         self.setupUi(self)
 
         self.config = JSONConfig('store/search')
+        self.search_title.initialize('store_search_search_title')
+        self.search_author.initialize('store_search_search_author')
         self.search_edit.initialize('store_search_search')
 
         # Loads variables that store various settings.
@@ -60,13 +62,24 @@ class SearchDialog(QDialog, Ui_Dialog):
         self.setup_store_checks()
 
         # Set the search query
+        # Title
+        self.search_title.setText(query)
+        self.search_title.setSizeAdjustPolicy(QComboBox.AdjustToMinimumContentsLengthWithIcon)
+        self.search_title.setMinimumContentsLength(25)
+        # Author
+        self.search_author.setText(query)
+        self.search_author.setSizeAdjustPolicy(QComboBox.AdjustToMinimumContentsLengthWithIcon)
+        self.search_author.setMinimumContentsLength(25)
+        # Keyword
         self.search_edit.setText(query)
         self.search_edit.setSizeAdjustPolicy(QComboBox.AdjustToMinimumContentsLengthWithIcon)
         self.search_edit.setMinimumContentsLength(25)
 
         # Create and add the progress indicator
         self.pi = ProgressIndicator(self, 24)
-        self.top_layout.addWidget(self.pi)
+        self.button_layout.takeAt(0)
+        self.button_layout.setAlignment(Qt.AlignCenter)
+        self.button_layout.insertWidget(0, self.pi, 0, Qt.AlignCenter)
 
         self.adv_search_button.setIcon(QIcon(I('search.png')))
         self.configure.setIcon(QIcon(I('config.png')))
@@ -152,8 +165,18 @@ class SearchDialog(QDialog, Ui_Dialog):
         self.results_view.model().clear_results()
 
         # Don't start a search if there is nothing to search for.
-        query = unicode(self.search_edit.text())
+        query = []
+        if self.search_title.text():
+            query.append(u'title2:"~%s"' % unicode(self.search_title.text()).replace('"', ' '))
+        if self.search_author.text():
+            query.append(u'author2:"%s"' % unicode(self.search_author.text()).replace('"', ' '))
+        if self.search_edit.text():
+            query.append(unicode(self.search_edit.text()))
+        query = " ".join(query)
         if not query.strip():
+            error_dialog(self, _('No query'),
+                        _('You must enter a title, author or keyword to'
+                          ' search for.'), show=True)
             return
         # Give the query to the results model so it can do
         # futher filtering.
@@ -188,7 +211,7 @@ class SearchDialog(QDialog, Ui_Dialog):
         query = query.replace('>', '')
         query = query.replace('<', '')
         # Remove the prefix.
-        for loc in ('all', 'author', 'authors', 'title'):
+        for loc in ('all', 'author', 'author2', 'authors', 'title', 'title2'):
             query = re.sub(r'%s:"(?P<a>[^\s"]+)"' % loc, '\g<a>', query)
             query = query.replace('%s:' % loc, '')
         # Remove the prefix and search text.

src/calibre/gui2/store/search/search.ui

@@ -14,30 +14,61 @@
    <string>Get Books</string>
   </property>
   <property name="windowIcon">
-   <iconset>
+   <iconset resource="../../../../../resources/images.qrc">
     <normaloff>:/images/store.png</normaloff>:/images/store.png</iconset>
   </property>
   <property name="sizeGripEnabled">
    <bool>true</bool>
   </property>
-  <layout class="QVBoxLayout" name="verticalLayout_5">
-   <item>
-    <layout class="QHBoxLayout" name="top_layout">
-     <item>
-      <widget class="QLabel" name="label">
-       <property name="text">
-        <string>Query:</string>
+  <layout class="QGridLayout" name="gridLayout">
+   <item row="0" column="2">
+    <widget class="HistoryLineEdit" name="search_title">
+     <property name="placeholderText">
+      <string>Search by title</string>
      </property>
     </widget>
    </item>
-     <item>
+   <item row="1" column="0" colspan="2">
+    <widget class="QLabel" name="label_3">
+     <property name="text">
+      <string>&amp;Author:</string>
+     </property>
+     <property name="alignment">
+      <set>Qt::AlignRight|Qt::AlignTrailing|Qt::AlignVCenter</set>
+     </property>
+     <property name="buddy">
+      <cstring>search_author</cstring>
+     </property>
+    </widget>
+   </item>
+   <item row="1" column="2">
+    <widget class="HistoryLineEdit" name="search_author">
+     <property name="placeholderText">
+      <string>Search by author</string>
+     </property>
+    </widget>
+   </item>
+   <item row="2" column="0">
     <widget class="QToolButton" name="adv_search_button">
      <property name="text">
       <string>...</string>
      </property>
     </widget>
    </item>
-     <item>
+   <item row="2" column="1">
+    <widget class="QLabel" name="label">
+     <property name="text">
+      <string>&amp;Keyword:</string>
+     </property>
+     <property name="alignment">
+      <set>Qt::AlignRight|Qt::AlignTrailing|Qt::AlignVCenter</set>
+     </property>
+     <property name="buddy">
+      <cstring>search_edit</cstring>
+     </property>
+    </widget>
+   </item>
+   <item row="2" column="2">
     <widget class="HistoryLineEdit" name="search_edit">
      <property name="sizePolicy">
       <sizepolicy hsizetype="Expanding" vsizetype="Fixed">
@@ -45,18 +76,12 @@
        <verstretch>0</verstretch>
       </sizepolicy>
      </property>
-      </widget>
-     </item>
-     <item>
-      <widget class="QPushButton" name="search">
-       <property name="text">
-        <string>Search</string>
+     <property name="placeholderText">
+      <string>Search by any keyword</string>
      </property>
     </widget>
    </item>
-    </layout>
-   </item>
-   <item>
+   <item row="3" column="0" colspan="4">
     <widget class="QSplitter" name="store_splitter">
      <property name="orientation">
       <enum>Qt::Horizontal</enum>
@@ -82,8 +107,8 @@
            <rect>
             <x>0</x>
             <y>0</y>
-            <width>193</width>
-            <height>127</height>
+            <width>204</width>
+            <height>141</height>
            </rect>
           </property>
          </widget>
@@ -202,7 +227,7 @@
      </widget>
     </widget>
    </item>
-   <item>
+   <item row="4" column="0" colspan="3">
     <layout class="QHBoxLayout" name="bottom_layout">
      <item>
       <widget class="QLabel" name="label_2">
@@ -234,7 +259,47 @@
      <item>
       <widget class="QPushButton" name="close">
        <property name="text">
-        <string>Close</string>
+        <string>&amp;Close</string>
+       </property>
+      </widget>
+     </item>
+    </layout>
+   </item>
+   <item row="0" column="1">
+    <widget class="QLabel" name="label_4">
+     <property name="text">
+      <string>&amp;Title:</string>
+     </property>
+     <property name="alignment">
+      <set>Qt::AlignRight|Qt::AlignTrailing|Qt::AlignVCenter</set>
+     </property>
+     <property name="buddy">
+      <cstring>search_title</cstring>
+     </property>
+    </widget>
+   </item>
+   <item row="0" column="3" rowspan="3">
+    <layout class="QVBoxLayout" name="button_layout">
+     <item>
+      <widget class="QWidget" name="widget" native="true">
+       <property name="sizePolicy">
+        <sizepolicy hsizetype="Fixed" vsizetype="Fixed">
+         <horstretch>0</horstretch>
+         <verstretch>0</verstretch>
+        </sizepolicy>
+       </property>
+       <property name="baseSize">
+        <size>
+         <width>24</width>
+         <height>24</height>
+        </size>
+       </property>
+      </widget>
+     </item>
+     <item>
+      <widget class="QPushButton" name="search">
+       <property name="text">
+        <string>&amp;Search</string>
        </property>
       </widget>
      </item>
@@ -255,17 +320,19 @@
   </customwidget>
  </customwidgets>
  <tabstops>
+  <tabstop>search_title</tabstop>
+  <tabstop>search_author</tabstop>
+  <tabstop>adv_search_button</tabstop>
   <tabstop>search_edit</tabstop>
   <tabstop>search</tabstop>
-  <tabstop>results_view</tabstop>
   <tabstop>store_list</tabstop>
   <tabstop>select_all_stores</tabstop>
   <tabstop>select_invert_stores</tabstop>
   <tabstop>select_none_stores</tabstop>
+  <tabstop>results_view</tabstop>
   <tabstop>configure</tabstop>
   <tabstop>open_external</tabstop>
   <tabstop>close</tabstop>
-  <tabstop>adv_search_button</tabstop>
  </tabstops>
  <resources>
   <include location="../../../../../resources/images.qrc"/>

src/calibre/gui2/viewer/config.py

@@ -59,6 +59,10 @@ def config(defaults=None):
             help=_('Show reading position in fullscreen mode.'))
     c.add_opt('fullscreen_scrollbar', default=True, action='store_false',
             help=_('Show the scrollbar in fullscreen mode.'))
+    c.add_opt('start_in_fullscreen', default=False, action='store_true',
+              help=_('Start viewer in full screen mode'))
+    c.add_opt('show_fullscreen_help', default=True, action='store_false',
+              help=_('Show full screen usage help'))
     c.add_opt('cols_per_screen', default=1)
     c.add_opt('use_book_margins', default=False, action='store_true')
     c.add_opt('top_margin', default=20)
@@ -206,6 +210,8 @@ class ConfigDialog(QDialog, Ui_Dialog):
         self.opt_fit_images.setChecked(opts.fit_images)
         self.opt_fullscreen_clock.setChecked(opts.fullscreen_clock)
         self.opt_fullscreen_scrollbar.setChecked(opts.fullscreen_scrollbar)
+        self.opt_start_in_fullscreen.setChecked(opts.start_in_fullscreen)
+        self.opt_show_fullscreen_help.setChecked(opts.show_fullscreen_help)
         self.opt_fullscreen_pos.setChecked(opts.fullscreen_pos)
         self.opt_cols_per_screen.setValue(opts.cols_per_screen)
         self.opt_override_book_margins.setChecked(not opts.use_book_margins)
@@ -279,6 +285,7 @@ class ConfigDialog(QDialog, Ui_Dialog):
         c.set('fullscreen_clock', self.opt_fullscreen_clock.isChecked())
         c.set('fullscreen_pos', self.opt_fullscreen_pos.isChecked())
         c.set('fullscreen_scrollbar', self.opt_fullscreen_scrollbar.isChecked())
+        c.set('show_fullscreen_help', self.opt_show_fullscreen_help.isChecked())
         c.set('cols_per_screen', int(self.opt_cols_per_screen.value()))
         c.set('use_book_margins', not
                 self.opt_override_book_margins.isChecked())

src/calibre/gui2/viewer/config.ui

@@ -388,20 +388,34 @@ QToolBox::tab:hover {
              </property>
             </widget>
            </item>
-           <item row="3" column="0" colspan="2">
+           <item row="5" column="0" colspan="2">
             <widget class="QCheckBox" name="opt_fullscreen_pos">
              <property name="text">
               <string>Show reading &amp;position in full screen mode</string>
              </property>
             </widget>
            </item>
-           <item row="2" column="0" colspan="2">
+           <item row="4" column="0" colspan="2">
             <widget class="QCheckBox" name="opt_fullscreen_scrollbar">
              <property name="text">
               <string>Show &amp;scrollbar in full screen mode</string>
              </property>
             </widget>
            </item>
+           <item row="3" column="0" colspan="2">
+            <widget class="QCheckBox" name="opt_start_in_fullscreen">
+             <property name="text">
+              <string>&amp;Start viewer in full screen mode</string>
+             </property>
+            </widget>
+           </item>
+           <item row="2" column="0" colspan="2">
+            <widget class="QCheckBox" name="opt_show_fullscreen_help">
+             <property name="text">
+              <string>Show &amp;help message when starting full screen mode</string>
+             </property>
+            </widget>
+           </item>
           </layout>
          </widget>
          <widget class="QWidget" name="page_6">

src/calibre/gui2/viewer/documentview.py

@@ -16,6 +16,7 @@ from PyQt4.QtWebKit import QWebPage, QWebView, QWebSettings
 
 from calibre.gui2.viewer.flip import SlideFlip
 from calibre.gui2.shortcuts import Shortcuts
+from calibre.gui2 import open_url
 from calibre import prints
 from calibre.customize.ui import all_viewer_plugins
 from calibre.gui2.viewer.keys import SHORTCUTS
@@ -144,6 +145,8 @@ class Document(QWebPage): # {{{
         self.fullscreen_clock = opts.fullscreen_clock
         self.fullscreen_scrollbar = opts.fullscreen_scrollbar
         self.fullscreen_pos = opts.fullscreen_pos
+        self.start_in_fullscreen = opts.start_in_fullscreen
+        self.show_fullscreen_help = opts.show_fullscreen_help
         self.use_book_margins = opts.use_book_margins
         self.cols_per_screen = opts.cols_per_screen
         self.side_margin = opts.side_margin
@@ -481,7 +484,12 @@ class DocumentView(QWebView): # {{{
         d = self.document
         self.unimplemented_actions = list(map(self.pageAction,
             [d.DownloadImageToDisk, d.OpenLinkInNewWindow, d.DownloadLinkToDisk,
-                d.OpenImageInNewWindow, d.OpenLink, d.Reload]))
+                d.OpenImageInNewWindow, d.OpenLink, d.Reload, d.InspectElement]))
+
+        self.search_online_action = QAction(QIcon(I('search.png')), '', self)
+        self.search_online_action.setShortcut(Qt.CTRL+Qt.Key_E)
+        self.search_online_action.triggered.connect(self.search_online)
+        self.addAction(self.search_online_action)
         self.dictionary_action = QAction(QIcon(I('dictionary.png')),
                 _('&Lookup in dictionary'), self)
         self.dictionary_action.setShortcut(Qt.CTRL+Qt.Key_L)
@@ -526,6 +534,10 @@ class DocumentView(QWebView): # {{{
         self.goto_location_action.setMenu(self.goto_location_menu)
         self.grabGesture(Qt.SwipeGesture)
 
+        self.restore_fonts_action = QAction(_('Normal font size'), self)
+        self.restore_fonts_action.setCheckable(True)
+        self.restore_fonts_action.triggered.connect(self.restore_font_size)
+
     def goto_next_section(self, *args):
         if self.manager is not None:
             self.manager.goto_next_section()
@@ -582,6 +594,15 @@ class DocumentView(QWebView): # {{{
         if self.manager is not None:
             self.manager.selection_changed(unicode(self.document.selectedText()))
 
+    def _selectedText(self):
+        t = unicode(self.selectedText()).strip()
+        if not t:
+            return u''
+        if len(t) > 40:
+            t = t[:40] + u'...'
+        t = t.replace(u'&', u'&&')
+        return _("S&earch Google for '%s'")%t
+
     def contextMenuEvent(self, ev):
         mf = self.document.mainFrame()
         r = mf.hitTestContent(ev.pos())
@@ -591,17 +612,48 @@ class DocumentView(QWebView): # {{{
         menu = self.document.createStandardContextMenu()
         for action in self.unimplemented_actions:
             menu.removeAction(action)
-        text = unicode(self.selectedText())
-        if text:
-            menu.insertAction(list(menu.actions())[0], self.dictionary_action)
-            menu.insertAction(list(menu.actions())[0], self.search_action)
+
         if not img.isNull():
             menu.addAction(self.view_image_action)
+
+        text = self._selectedText()
+        if text and img.isNull():
+            self.search_online_action.setText(text)
+            menu.addAction(self.search_online_action)
+            menu.addAction(self.dictionary_action)
+            menu.addAction(self.search_action)
+
+        if not text and img.isNull():
             menu.addSeparator()
+            if self.manager.action_back.isEnabled():
+                menu.addAction(self.manager.action_back)
+            if self.manager.action_forward.isEnabled():
+                menu.addAction(self.manager.action_forward)
             menu.addAction(self.goto_location_action)
-        if self.document.in_fullscreen_mode and self.manager is not None:
+
+            if self.manager is not None:
                 menu.addSeparator()
+                menu.addAction(self.manager.action_table_of_contents)
+
+                menu.addSeparator()
+                menu.addAction(self.manager.action_font_size_larger)
+                self.restore_fonts_action.setChecked(self.multiplier == 1)
+                menu.addAction(self.restore_fonts_action)
+                menu.addAction(self.manager.action_font_size_smaller)
+
+        menu.addSeparator()
+        inspectAction = self.pageAction(self.document.InspectElement)
+        menu.addAction(inspectAction)
+
+        if not text and img.isNull() and self.manager is not None:
+            menu.addSeparator()
+            if self.document.in_fullscreen_mode and self.manager is not None:
                 menu.addAction(self.manager.toggle_toolbar_action)
+            menu.addAction(self.manager.action_full_screen)
+
+            menu.addSeparator()
+            menu.addAction(self.manager.action_quit)
+
         menu.exec_(ev.globalPos())
 
     def lookup(self, *args):
@@ -616,6 +668,12 @@ class DocumentView(QWebView): # {{{
             if t:
                 self.manager.search.set_search_string(t)
 
+    def search_online(self):
+        t = unicode(self.selectedText()).strip()
+        if t:
+            url = 'https://www.google.com/search?q=' + QUrl().toPercentEncoding(t)
+            open_url(QUrl.fromEncoded(url))
+
     def set_manager(self, manager):
         self.manager = manager
         self.scrollbar = manager.horizontal_scrollbar
@@ -993,6 +1051,11 @@ class DocumentView(QWebView): # {{{
                 self.multiplier -= amount
         return self.document.scroll_fraction
 
+    def restore_font_size(self):
+        with self.document.page_position:
+            self.multiplier = 1
+        return self.document.scroll_fraction
+
     def changeEvent(self, event):
         if event.type() == event.EnabledChange:
             self.update()

src/calibre/gui2/viewer/main.py

@@ -21,7 +21,7 @@ from calibre.gui2 import (Application, ORG_NAME, APP_UID, choose_files,
     info_dialog, error_dialog, open_url, available_height)
 from calibre.ebooks.oeb.iterator.book import EbookIterator
 from calibre.ebooks import DRMError
-from calibre.constants import islinux, isbsd, filesystem_encoding
+from calibre.constants import islinux, filesystem_encoding
 from calibre.utils.config import Config, StringConfig, JSONConfig
 from calibre.gui2.search_box import SearchBox2
 from calibre.ebooks.metadata import MetaInformation
@@ -160,7 +160,8 @@ class EbookViewer(MainWindow, Ui_EbookViewer):
     PAGED_MODE_TT = _('Switch to flow mode - where the text is not broken up '
             'into pages')
 
-    def __init__(self, pathtoebook=None, debug_javascript=False, open_at=None):
+    def __init__(self, pathtoebook=None, debug_javascript=False, open_at=None,
+                 start_in_fullscreen=False):
         MainWindow.__init__(self, None)
         self.setupUi(self)
         self.view.initialize_view(debug_javascript)
@@ -178,6 +179,7 @@ class EbookViewer(MainWindow, Ui_EbookViewer):
         self.pending_restore   = False
         self.existing_bookmarks= []
         self.selected_text     = None
+        self.was_maximized     = False
         self.read_settings()
         self.dictionary_box.hide()
         self.close_dictionary_view.clicked.connect(lambda
@@ -207,7 +209,7 @@ class EbookViewer(MainWindow, Ui_EbookViewer):
         self.view.set_manager(self)
         self.pi = ProgressIndicator(self)
         self.toc.setVisible(False)
-        self.action_quit = QAction(self)
+        self.action_quit = QAction(_('&Quit'), self)
         self.addAction(self.action_quit)
         self.view_resized_timer = QTimer(self)
         self.view_resized_timer.timeout.connect(self.viewport_resize_finished)
@@ -299,6 +301,7 @@ class EbookViewer(MainWindow, Ui_EbookViewer):
         ''')
         self.window_mode_changed = None
         self.toggle_toolbar_action = QAction(_('Show/hide controls'), self)
+        self.toggle_toolbar_action.setCheckable(True)
         self.toggle_toolbar_action.triggered.connect(self.toggle_toolbars)
         self.addAction(self.toggle_toolbar_action)
         self.full_screen_label_anim = QPropertyAnimation(
@@ -358,6 +361,8 @@ class EbookViewer(MainWindow, Ui_EbookViewer):
 
         self.restore_state()
         self.action_toggle_paged_mode.toggled[bool].connect(self.toggle_paged_mode)
+        if (start_in_fullscreen or self.view.document.start_in_fullscreen):
+            self.action_full_screen.trigger()
 
     def toggle_paged_mode(self, checked, at_start=False):
         in_paged_mode = not self.action_toggle_paged_mode.isChecked()
@@ -397,7 +402,7 @@ class EbookViewer(MainWindow, Ui_EbookViewer):
                 count += 1
 
     def shutdown(self):
-        if self.isFullScreen():
+        if self.isFullScreen() and not self.view.document.start_in_fullscreen:
             self.action_full_screen.trigger()
             return False
         self.save_state()
@@ -421,6 +426,7 @@ class EbookViewer(MainWindow, Ui_EbookViewer):
     def save_state(self):
         state = bytearray(self.saveState(self.STATE_VERSION))
         vprefs['viewer_toolbar_state'] = state
+        if not self.isFullScreen():
             vprefs.set('viewer_window_geometry', bytearray(self.saveGeometry()))
         if self.current_book_has_toc:
             vprefs.set('viewer_toc_isvisible', bool(self.toc.isVisible()))
@@ -488,6 +494,7 @@ class EbookViewer(MainWindow, Ui_EbookViewer):
         self.window_mode_changed = 'fullscreen'
         self.tool_bar.setVisible(False)
         self.tool_bar2.setVisible(False)
+        self.was_maximized = self.isMaximized()
         if not self.view.document.fullscreen_scrollbar:
             self.vertical_scrollbar.setVisible(False)
             self.frame.layout().setSpacing(0)
@@ -574,6 +581,9 @@ class EbookViewer(MainWindow, Ui_EbookViewer):
             om = self._original_frame_margins
             self.centralwidget.layout().setContentsMargins(om[0])
             self.frame.layout().setContentsMargins(om[1])
+        if self.was_maximized:
+            super(EbookViewer, self).showMaximized()
+        else:
             super(EbookViewer, self).showNormal()
 
     def handle_window_mode_toggle(self):
@@ -581,6 +591,7 @@ class EbookViewer(MainWindow, Ui_EbookViewer):
             fs = self.window_mode_changed == 'fullscreen'
             self.window_mode_changed = None
             if fs:
+                if self.view.document.show_fullscreen_help:
                     self.show_full_screen_label()
             else:
                 self.view.document.switch_to_window_mode()
@@ -681,13 +692,9 @@ class EbookViewer(MainWindow, Ui_EbookViewer):
 
     def font_size_larger(self):
         self.view.magnify_fonts()
-        self.action_font_size_larger.setEnabled(self.view.multiplier < 3)
-        self.action_font_size_smaller.setEnabled(self.view.multiplier > 0.2)
 
     def font_size_smaller(self):
         self.view.shrink_fonts()
-        self.action_font_size_larger.setEnabled(self.view.multiplier < 3)
-        self.action_font_size_smaller.setEnabled(self.view.multiplier > 0.2)
 
     def magnification_changed(self, val):
         tt = _('Make font size %(which)s\nCurrent magnification: %(mag).1f')
@@ -695,6 +702,8 @@ class EbookViewer(MainWindow, Ui_EbookViewer):
                 tt %dict(which=_('larger'), mag=val))
         self.action_font_size_smaller.setToolTip(
                 tt %dict(which=_('smaller'), mag=val))
+        self.action_font_size_larger.setEnabled(self.view.multiplier < 3)
+        self.action_font_size_smaller.setEnabled(self.view.multiplier > 0.2)
 
     def find(self, text, repeat=False, backwards=False):
         if not text:
@@ -1129,12 +1138,10 @@ def main(args=sys.argv):
 
     parser = option_parser()
     opts, args = parser.parse_args(args)
-    pid = os.fork() if False and (islinux or isbsd) else -1
     try:
         open_at = float(opts.open_at)
     except:
         open_at = None
-    if pid <= 0:
     override = 'calibre-ebook-viewer' if islinux else None
     app = Application(args, override_program_name=override)
     app.load_builtin_fonts()
@@ -1142,7 +1149,8 @@ def main(args=sys.argv):
     QApplication.setOrganizationName(ORG_NAME)
     QApplication.setApplicationName(APP_UID)
     main = EbookViewer(args[1] if len(args) > 1 else None,
-                debug_javascript=opts.debug_javascript, open_at=open_at)
+            debug_javascript=opts.debug_javascript, open_at=open_at,
+                       start_in_fullscreen=opts.full_screen)
     # This is needed for paged mode. Without it, the first document that is
     # loaded will have extra blank space at the bottom, as
     # turn_off_internal_scrollbars does not take effect for the first
@@ -1153,8 +1161,6 @@ def main(args=sys.argv):
     main.show()
     if opts.raise_window:
         main.raise_()
-    if opts.full_screen:
-        main.action_full_screen.trigger()
     with main:
         return app.exec_()
     return 0

src/calibre/gui2/widgets.py

@@ -283,6 +283,7 @@ class ImageView(QWidget, ImageDropMixin): # {{{
         self.setMinimumSize(QSize(150, 200))
         ImageDropMixin.__init__(self)
         self.draw_border = True
+        self.show_size = False
 
     def setPixmap(self, pixmap):
         if not isinstance(pixmap, QPixmap):
@@ -305,6 +306,7 @@ class ImageView(QWidget, ImageDropMixin): # {{{
         if pmap.isNull():
             return
         w, h = pmap.width(), pmap.height()
+        ow, oh = w, h
         cw, ch = self.rect().width(), self.rect().height()
         scaled, nw, nh = fit_image(w, h, cw, ch)
         if scaled:
@@ -317,12 +319,22 @@ class ImageView(QWidget, ImageDropMixin): # {{{
         p = QPainter(self)
         p.setRenderHints(QPainter.Antialiasing | QPainter.SmoothPixmapTransform)
         p.drawPixmap(target, pmap)
+        if self.draw_border:
             pen = QPen()
             pen.setWidth(self.BORDER_WIDTH)
             p.setPen(pen)
-        if self.draw_border:
             p.drawRect(target)
-        #p.drawRect(self.rect())
+        if self.show_size:
+            sztgt = target.adjusted(0, 0, 0, -4)
+            f = p.font()
+            f.setBold(True)
+            p.setFont(f)
+            sz = u'\u00a0%d x %d\u00a0'%(ow, oh)
+            flags = Qt.AlignBottom|Qt.AlignRight|Qt.TextSingleLine
+            szrect = p.boundingRect(sztgt, flags, sz)
+            p.fillRect(szrect.adjusted(0, 0, 0, 4), QColor(0, 0, 0, 200))
+            p.setPen(QPen(QColor(255,255,255)))
+            p.drawText(sztgt, flags, sz)
         p.end()
 # }}}
 
@@ -582,6 +594,9 @@ class HistoryLineEdit(QComboBox): # {{{
         self.setInsertPolicy(self.NoInsert)
         self.setMaxCount(10)
 
+    def setPlaceholderText(self, txt):
+        return self.lineEdit().setPlaceholderText(txt)
+
     @property
     def store_name(self):
         return 'lineedit_history_'+self._name

src/calibre/library/catalogs/__init__.py

@@ -9,7 +9,7 @@ __docformat__ = 'restructuredtext en'
 
 
 FIELDS = ['all', 'title', 'title_sort', 'author_sort', 'authors', 'comments',
-          'cover', 'formats','id', 'isbn', 'ondevice', 'pubdate', 'publisher',
+          'cover', 'formats','id', 'isbn', 'library_name','ondevice', 'pubdate', 'publisher',
           'rating', 'series_index', 'series', 'size', 'tags', 'timestamp',
           'uuid', 'languages', 'identifiers']
 

src/calibre/library/catalogs/csv_xml.py

@@ -48,17 +48,21 @@ class CSV_XML(CatalogPlugin):
                 "Applies to: CSV, XML output formats"))]
 
     def run(self, path_to_output, opts, db, notification=DummyReporter()):
+        from calibre.library import current_library_name
         from calibre.utils.date import isoformat
         from calibre.utils.html2text import html2text
-        from lxml import etree
         from calibre.utils.logging import default_log as log
+        from lxml import etree
 
         self.fmt = path_to_output.rpartition('.')[2]
         self.notification = notification
+        current_library = current_library_name()
+        if getattr(opts, 'library_path', None):
+            current_library = os.path.basename(opts.library_path)
 
         if opts.verbose:
             opts_dict = vars(opts)
-            log("%s(): Generating %s" % (self.name,self.fmt.upper()))
+            log("%s('%s'): Generating %s" % (self.name, current_library, self.fmt.upper()))
             if opts.connected_device['is_device_connected']:
                 log(" connected_device: %s" % opts.connected_device['name'])
             if opts_dict['search_text']:
@@ -110,6 +114,8 @@ class CSV_XML(CatalogPlugin):
                 for field in fields:
                     if field.startswith('#'):
                         item = db.get_field(entry['id'],field,index_is_id=True)
+                    elif field == 'library_name':
+                        item = current_library
                     elif field == 'title_sort':
                         item = entry['sort']
                     else:
@@ -215,6 +221,9 @@ class CSV_XML(CatalogPlugin):
                         fmt.append(E.format(f.replace(os.sep, '/')))
                     record.append(fmt)
 
+                if 'library_name' in fields:
+                    record.append(E.library_name(current_library))
+
             with open(path_to_output, 'w') as f:
                 f.write(etree.tostring(root, encoding='utf-8',
                     xml_declaration=True, pretty_print=True))

src/calibre/library/catalogs/epub_mobi.py

@@ -14,6 +14,7 @@ from calibre import strftime
 from calibre.customize import CatalogPlugin
 from calibre.customize.conversion import OptionRecommendation, DummyReporter
 from calibre.ebooks import calibre_cover
+from calibre.library import current_library_name
 from calibre.library.catalogs import AuthorSortMismatchException, EmptyCatalogException
 from calibre.ptempfile import PersistentTemporaryFile
 from calibre.utils.localization import get_lang
@@ -208,8 +209,9 @@ class EPUB_MOBI(CatalogPlugin):
 
         build_log = []
 
-        build_log.append(u"%s(): Generating %s %sin %s environment, locale: '%s'" %
+        build_log.append(u"%s('%s'): Generating %s %sin %s environment, locale: '%s'" %
             (self.name,
+             current_library_name(),
              self.fmt,
              'for %s ' % opts.output_profile if opts.output_profile else '',
              'CLI' if opts.cli_environment else 'GUI',

src/calibre/library/database2.py

@@ -28,7 +28,8 @@ from calibre.ebooks.metadata.book.base import Metadata
 from calibre.constants import preferred_encoding, iswindows, filesystem_encoding
 from calibre.ptempfile import (PersistentTemporaryFile,
         base_dir, SpooledTemporaryFile)
-from calibre.customize.ui import run_plugins_on_import
+from calibre.customize.ui import (run_plugins_on_import,
+                                  run_plugins_on_postimport)
 from calibre import isbytestring
 from calibre.utils.filenames import (ascii_filename, samefile,
         WindowsAtomicFolderMove, hardlink_file)
@@ -1495,8 +1496,10 @@ class LibraryDatabase2(LibraryDatabase, SchemaUpgrade, CustomColumns):
         format = os.path.splitext(npath)[-1].lower().replace('.', '').upper()
         stream = lopen(npath, 'rb')
         format = check_ebook_format(stream, format)
-        return self.add_format(index, format, stream,
+        retval = self.add_format(index, format, stream,
                                index_is_id=index_is_id, path=path, notify=notify)
+        run_plugins_on_postimport(self, id, format)
+        return retval
 
     def add_format(self, index, format, stream, index_is_id=False, path=None,
             notify=True, replace=True, copy_function=None):
@@ -3475,6 +3478,7 @@ class LibraryDatabase2(LibraryDatabase, SchemaUpgrade, CustomColumns):
         formats, metadata = iter(formats), iter(metadata)
         duplicates = []
         ids = []
+        postimport = []
         for path in paths:
             mi = metadata.next()
             self._add_newbook_tag(mi)
@@ -3506,8 +3510,11 @@ class LibraryDatabase2(LibraryDatabase, SchemaUpgrade, CustomColumns):
             format = check_ebook_format(stream, format)
             self.add_format(id, format, stream, index_is_id=True)
             stream.close()
+            postimport.append((id, format))
         self.conn.commit()
         self.data.refresh_ids(self, ids) # Needed to update format list and size
+        for book_id, fmt in postimport:
+            run_plugins_on_postimport(self, book_id, fmt)
         if duplicates:
             paths    = list(duplicate[0] for duplicate in duplicates)
             formats  = list(duplicate[1] for duplicate in duplicates)