Merge from trunk

Changelog.yaml

@@ -19,6 +19,78 @@
 #  new recipes:
 #    - title: 
 
+- version: 0.7.58
+  date: 2011-04-29
+
+  new features:
+    - title: "Support for converting and reading metadata from Plucker format PDB files"
+      type: major
+
+    - title: "The metadata that is displayed in the book details panel on the right is now completely configurable via Preferences->Look & Feel"
+
+    - title: "Add a column that shows the date when the metadata of a book record was last modified in calibre. To see the column, right click on the column headers in calibre and select Show column->Modified. Note that the dates may be incorrect for books added with older versions of calibre."
+
+    - title: "Add command line option to shutdown running calibre"
+
+    - title: "CHM Input: Store extracted files in the input/ sub dir for easy debugging when --debug-pipeline is specified"
+
+    - title: "Add a popup menu to the 'Create saved search button' to allow easy deleting of saved searches"
+  
+  bug fixes:
+    - title: "Fix regression that broke converting to LIT in 0.7.57"
+      tickets: [769334]
+
+    - title: "Conversion pipeline: Remove encoding declarations from input HTML documents to guarantee that there is only a single encoding declaration in the output HTML."
+      tickets: [773337]
+
+    - title: "Correctly parenthesize searches that are used to make search restrictions"
+
+    - title: "Fix ratings in save to disk templates not being divided by 2"
+
+    - title: "TXT to EPUB: Underlined words (following quotes?) fail to become italics"
+      tickets: [772267]
+
+    - title: "Fix template function source code unavailable when not running calibre from source"
+
+    - title: "Fix adding html books from the top of a deep folder hierarchy very slow"
+
+    - title: "Only set language in MOBI metadata is it is not null"
+
+    - title: "Fix 'count-of' searches (e.g., tags:#>3)."
+      tickets: [771175]
+
+    - title: "Fix regression that broke connection to iTunes in some cases"
+      tickets: [771164]
+
+    - title: "Fix buggy regex that made converting PDfs with the string ****************** very slow"
+      tickets: [770534]
+
+    - title: "Fix Ctrl+L shortcut to lookup word not working in ebook viewer"
+      tickets: [769492]
+
+    - title: "Fix regression that broke searching on boolean columns"
+
+  improved recipes:
+    - HBR Blogs
+    - The Marker
+    - Financial Times
+    - Clarin
+    - Honolulu Star Advertiser
+
+  new recipes:
+    - title: Novi Standard
+      author: Darko Miletic
+
+    - title: Autobild.ro and Social Diva
+      author: Silviu Cotoara
+
+    - title: Novinky
+      author: Tomas Latal
+
+    - title: "De Volksrant (subscriber version)"
+      author: Selcal
+
+
 - version: 0.7.57
   date: 2011-04-22
 

recipes/autobild.recipe

@@ -0,0 +1,55 @@
+# -*- coding: utf-8 -*-
+#!/usr/bin/env  python
+
+__license__   = 'GPL v3'
+__copyright__ = u'2011, Silviu Cotoar\u0103'
+'''
+auto-bild.ro
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class AutoBild(BasicNewsRecipe):
+    title                       = u'Auto Bild'
+    __author__                   = u'Silviu Cotoar\u0103'
+    description                   = 'Auto'
+    publisher                   = 'Auto Bild'
+    oldest_article              = 50
+    language                    = 'ro'
+    max_articles_per_feed = 100
+    no_stylesheets          = True
+    use_embedded_content  = False
+    category                  = 'Ziare,Reviste,Auto'
+    encoding                = 'utf-8'
+    cover_url     = 'http://www.auto-bild.ro/images/autobild.gif'
+
+    conversion_options = {
+                             'comments'  : description
+                            ,'tags'           : category
+                            ,'language'    : language
+                            ,'publisher'   : publisher
+                         }
+
+
+    keep_only_tags = [
+                dict(name='div', attrs={'class':'box_2 articol clearfix'})
+                 ]
+
+    remove_tags = [
+             dict(name='div', attrs={'class':['detail']})
+           , dict(name='a', attrs={'id':['zoom_link']})
+           , dict(name='div', attrs={'class':['icons clearfix']})
+           , dict(name='div', attrs={'class':['pub_articol clearfix']})
+
+                          ]
+
+    remove_tags_after = [
+              dict(name='div', attrs={'class':['pub_articol clearfix']})
+           ]
+
+    feeds          = [
+        (u'Feeds', u'http://www.auto-bild.ro/rss/toate')
+                     ]
+
+    def preprocess_html(self, soup):
+        return self.adeify_images(soup)

recipes/hbr_blogs.recipe

@@ -1,9 +1,6 @@
 from calibre.web.feeds.news import BasicNewsRecipe
 import re
 
-# Needed for BLOGs
-from calibre.web.feeds import Feed
-
 class HBR(BasicNewsRecipe):
 
     title = 'Harvard Business Review Blogs'
@@ -32,6 +29,7 @@ class HBR(BasicNewsRecipe):
         feeds = [('Blog','http://feeds.harvardbusiness.org/harvardbusiness')]
         oldest_article = 30
         max_articles_per_feed = 100
+        use_embedded_content = False
     else:
         timefmt                = ' [%B %Y]'
 
@@ -59,9 +57,9 @@ class HBR(BasicNewsRecipe):
     def get_browser(self):
         br = BasicNewsRecipe.get_browser(self)
         br.open(self.LOGIN_URL)
-        br.select_form(name='signInForm')
-        br['signInForm:username'] = self.username
-        br['signInForm:password'] = self.password
+        br.select_form(name='signin-form')
+        br['signin-form:username'] = self.username
+        br['signin-form:password'] = self.password
         raw = br.submit().read()
         if 'My Account' not in raw:
             raise Exception('Failed to login, are you sure your username and password are correct?')
@@ -161,27 +159,13 @@ class HBR(BasicNewsRecipe):
         return startDate, endDate
 
 #-------------------------------------------------------------------------------------------------
-    def hbr_parse_blogs(self, feeds):
-        # Do the "official" parse_feeds first
-        rssFeeds = Feed()
 
-        # Use the PARSE_FEEDS method to get a Feeds object of the articles
-        rssFeeds = BasicNewsRecipe.parse_feeds(self)
-
-        # Create a new feed of the right configuration and append to existing afeeds
-        self.feed_to_index_append(rssFeeds[:], feeds)
-
-#-------------------------------------------------------------------------------------------------
     def parse_index(self):
         if self.INCLUDE_ARTICLES == True:
             soup = self.hbr_get_toc()
             feeds = self.hbr_parse_toc(soup)
         else:
-            feeds = []
-
-        # blog stuff
-        if self.INCLUDE_BLOGS == True:
-            self.hbr_parse_blogs(feeds)
+            return BasicNewsRecipe.parse_index(self)
 
         return feeds
 #-------------------------------------------------------------------------------------------------

recipes/novinky.recipe

@@ -0,0 +1,42 @@
+__license__   = 'GPL v3'
+__copyright__ = '2011, Tomas Latal<latal.tomas at gmail.com>'
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class NovinkyCZ(BasicNewsRecipe):
+    title                   = 'Novinky'
+    __author__              = 'Tomas Latal'
+    __version__             = '1.0'
+    __date__                = '24 April 2011'
+    description             = 'News from server Novinky.cz'
+    oldest_article          = 1
+    max_articles_per_feed   = 10
+    encoding                = 'utf8'
+    publisher               = 'Novinky'
+    category                = 'news, CZ'
+    language                = 'cs'
+    publication_type        = 'newsportal'
+    no_stylesheets          = True
+    remove_javascript       = True
+    extra_css               = 'p.acmDescription{font-style:italic;} p.acmAuthor{font-size:0.8em; color:#707070}'
+
+    feeds          = [
+                        (u'Dom\xe1c\xed', u'http://www.novinky.cz/rss/domaci/'),
+                        (u'Zahrani\u010d\xed', u'http://www.novinky.cz/rss/zahranicni/'),
+                        (u'Krimi', u'http://www.novinky.cz/rss/krimi/'),
+                        (u'Ekonomika', u'http://www.novinky.cz/rss/ekonomika/'),
+                        (u'Finance', u'http://www.novinky.cz/rss/finance/'),
+                        (u'Kultura', u'http://www.novinky.cz/rss/kultura/'),
+                        (u'Koktejl', u'http://www.novinky.cz/rss/koktejl/'),
+                        (u'Internet a PC', u'http://www.novinky.cz/rss/internet-a-pc/'),
+                        (u'Auto-moto', u'http://www.novinky.cz/rss/auto/'),
+                    ]
+
+    remove_tags_before = dict(id='articleContent')
+
+    remove_tags_after = [dict(id='movedArticleAuthors')]
+
+    remove_tags = [
+                      dict(name='div', attrs={'id':['articleColumnInfo','pictureInnerBox']}),
+                      dict(name='p', attrs={'id':['articleDate']})
+                  ]

recipes/novistandard.recipe

@@ -0,0 +1,100 @@
+
+__license__   = 'GPL v3'
+__copyright__ = '2011, Darko Miletic <darko.miletic at gmail.com>'
+'''
+www.standard.rs
+'''
+
+import re
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class NoviStandard(BasicNewsRecipe):
+    title                  = 'Novi Standard'
+    __author__             = 'Darko Miletic'
+    description            = 'NoviStandard - energija je neunistiva!'
+    publisher              = 'Novi Standard'
+    category               = 'news, politics, Serbia'
+    no_stylesheets         = True
+    delay                  = 1
+    oldest_article         = 15
+    encoding               = 'utf-8'
+    publication_type       = 'magazine'
+    needs_subscription     = 'optional'
+    remove_empty_feeds     = True
+    INDEX                  = 'http://www.standard.rs/'
+    use_embedded_content   = False
+    language               = 'sr'
+    publication_type       = 'magazine'
+    masthead_url           = 'http://www.standard.rs/templates/ja_opal/images/red/logo.png'
+    extra_css              = """
+                                 @font-face {font-family: "serif1";src:url(res:///opt/sony/ebook/FONT/tt0011m_.ttf)}
+                                 @font-face {font-family: "sans1";src:url(res:///opt/sony/ebook/FONT/tt0003m_.ttf)}
+                                 body{font-family: Arial,"Segoe UI","Trebuchet MS",Helvetica,sans1,sans-serif}
+                                 .dropcap{font-family: Georgia,Times,serif1,serif; display:inline}
+                                 .dropcap:first-letter{display: inline; font-size: xx-large; font-weight: bold}
+                                 .contentheading{color: gray; font-size: x-large}
+                                 .article-meta, .createdby{color: red}
+                                 img{margin-top:0.5em; margin-bottom: 0.7em; display: block}
+                             """
+
+    conversion_options = {
+                          'comment'   : description
+                        , 'tags'      : category
+                        , 'publisher' : publisher
+                        , 'language'  : language
+                        }
+
+    preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')]
+
+    def get_browser(self):
+        br = BasicNewsRecipe.get_browser()
+        br.open(self.INDEX)
+        if self.username is not None and self.password is not None:
+            br.select_form(name='login')
+            br['username'] = self.username
+            br['passwd'  ] = self.password
+            br.submit()
+        return br
+
+    keep_only_tags    =[dict(attrs={'class':['contentheading','article-meta','article-content']})]
+    remove_tags_after =dict(attrs={'class':'extravote-container'})
+    remove_tags       = [
+                           dict(name=['object','link','iframe','meta','base'])
+                          ,dict(attrs={'class':'extravote-container'})
+                        ]
+    remove_attributes =['border','background','height','width','align','valign','lang']
+    feeds             = [
+                            (u'Naslovna', u'http://www.standard.rs/index.php?format=feed&type=rss')
+                           ,(u'Politika', u'http://www.standard.rs/vesti/36-politika.html?format=feed&type=rss')
+                           ,(u'Cvijanovic preporucuje', u'http://www.standard.rs/-cvijanovi-vam-preporuuje.html?format=feed&type=rss')
+                           ,(u'Kolumne', u'http://www.standard.rs/vesti/49-kolumne.html?format=feed&type=rss')
+                           ,(u'Kultura', u'http://www.standard.rs/vesti/40-kultura.html?format=feed&type=rss')
+                           ,(u'Lifestyle', u'http://www.standard.rs/vesti/39-lifestyle.html?format=feed&type=rss')
+                           ,(u'Svet', u'http://www.standard.rs/vesti/41-svet.html?format=feed&type=rss')
+                           ,(u'Ekonomija', u'http://www.standard.rs/vesti/37-ekonomija.html?format=feed&type=rss')
+                           ,(u'Sport', u'http://www.standard.rs/vesti/38-sport.html?format=feed&type=rss')
+                        ]
+
+
+    def preprocess_html(self, soup):
+        for item in soup.findAll(style=True):
+            del item['style']
+        for item in soup.findAll('div'):
+            if len(item.contents) == 0:
+               item.extract()
+        for item in soup.findAll('a'):
+            limg = item.find('img')
+            if item.string is not None:
+               str = item.string
+               item.replaceWith(str)
+            else:
+               if limg:
+                  item.name = 'div'
+                  item.attrs = []
+               else:
+                   str = self.tag_to_string(item)
+                   item.replaceWith(str)
+        for item in soup.findAll('img'):
+            if not item.has_key('alt'):
+               item['alt'] = 'image'
+        return soup

src/calibre/constants.py

@@ -4,7 +4,7 @@ __license__   = 'GPL v3'
 __copyright__ = '2008, Kovid Goyal kovid@kovidgoyal.net'
 __docformat__ = 'restructuredtext en'
 __appname__   = u'calibre'
-numeric_version = (0, 7, 57)
+numeric_version = (0, 7, 58)
 __version__   = u'.'.join(map(unicode, numeric_version))
 __author__    = u"Kovid Goyal <kovid@kovidgoyal.net>"
 

src/calibre/customize/builtins.py

@@ -1109,6 +1109,11 @@ class StoreAmazonKindleStore(StoreBase):
     description = _('Kindle books from Amazon')
     actual_plugin = 'calibre.gui2.store.amazon_plugin:AmazonKindleStore'
 
+class StoreAmazonUKKindleStore(StoreBase):
+    name = 'Amazon UK Kindle'
+    description = _('Kindle books from Amazon.uk')
+    actual_plugin = 'calibre.gui2.store.amazon_uk_plugin:AmazonUKKindleStore'
+
 class StoreBaenWebScriptionStore(StoreBase):
     name = 'Baen WebScription'
     description = _('Ebooks for readers.')
@@ -1174,10 +1179,27 @@ class StoreSmashwordsStore(StoreBase):
     description = _('Your ebook. Your way.')
     actual_plugin = 'calibre.gui2.store.smashwords_plugin:SmashwordsStore'
 
-plugins += [StoreAmazonKindleStore, StoreBaenWebScriptionStore, StoreBNStore,
+class StoreWaterstonesUKStore(StoreBase):
+    name = 'Waterstones UK'
+    description = _('Feel every word')
+    actual_plugin = 'calibre.gui2.store.waterstones_uk_plugin:WaterstonesUKStore'
+
+class StoreFoylesUKStore(StoreBase):
+    name = 'Foyles UK'
+    description = _('Foyles of London, online')
+    actual_plugin = 'calibre.gui2.store.foyles_uk_plugin:FoylesUKStore'
+
+class AmazonDEKindleStore(StoreBase):
+    name = 'Amazon DE Kindle'
+    description = _('Kindle eBooks')
+    actual_plugin = 'calibre.gui2.store.amazon_de_plugin:AmazonDEKindleStore'
+
+plugins += [StoreAmazonKindleStore, AmazonDEKindleStore, StoreAmazonUKKindleStore,
+    StoreBaenWebScriptionStore, StoreBNStore,
     StoreBeWriteStore, StoreDieselEbooksStore, StoreEbookscomStore,
-    StoreEHarlequinStoretore,
-    StoreFeedbooksStore, StoreGutenbergStore, StoreKoboStore, StoreManyBooksStore,
-    StoreMobileReadStore, StoreOpenLibraryStore, StoreSmashwordsStore]
+    StoreEHarlequinStoretore, StoreFeedbooksStore,
+    StoreFoylesUKStore, StoreGutenbergStore, StoreKoboStore, StoreManyBooksStore,
+    StoreMobileReadStore, StoreOpenLibraryStore, StoreSmashwordsStore,
+    StoreWaterstonesUKStore]
 
 # }}}

src/calibre/ebooks/metadata/sources/isbndb.py

@@ -81,7 +81,7 @@ class ISBNDB(Source):
             author_tokens = self.get_author_tokens(authors,
                     only_first_author=True)
             tokens += author_tokens
-            tokens = [quote(t) for t in tokens]
+            tokens = [quote(t.encode('utf-8') if isinstance(t, unicode) else t) for t in tokens]
             q = '+'.join(tokens)
             q = 'index1=combined&value1='+q
 

src/calibre/ebooks/oeb/base.py

@@ -16,7 +16,7 @@ from urllib import unquote as urlunquote
 from lxml import etree, html
 from calibre.constants import filesystem_encoding, __version__
 from calibre.translations.dynamic import translate
-from calibre.ebooks.chardet import xml_to_unicode
+from calibre.ebooks.chardet import xml_to_unicode, strip_encoding_declarations
 from calibre.ebooks.oeb.entitydefs import ENTITYDEFS
 from calibre.ebooks.conversion.preprocess import CSSPreProcessor
 from calibre import isbytestring, as_unicode, get_types_map
@@ -853,6 +853,7 @@ class Manifest(object):
             self.oeb.log.debug('Parsing', self.href, '...')
             # Convert to Unicode and normalize line endings
             data = self.oeb.decode(data)
+            data = strip_encoding_declarations(data)
             data = self.oeb.html_preprocessor(data)
             # There could be null bytes in data if it had � entities in it
             data = data.replace('\0', '')

src/calibre/gui2/store/amazon_de_plugin.py

@@ -0,0 +1,34 @@
+# -*- coding: utf-8 -*-
+
+from __future__ import (unicode_literals, division, absolute_import, print_function)
+
+__license__ = 'GPL 3'
+__copyright__ = '2011, John Schember <john@nachtimwald.com>'
+__docformat__ = 'restructuredtext en'
+
+from PyQt4.Qt import QUrl
+
+from calibre.gui2 import open_url
+from calibre.gui2.store.amazon_plugin import AmazonKindleStore
+
+class AmazonDEKindleStore(AmazonKindleStore):
+    '''
+    For comments on the implementation, please see amazon_plugin.py
+    '''
+
+    search_url = 'http://www.amazon.de/s/url=search-alias%3Ddigital-text&field-keywords='
+    details_url = 'http://amazon.de/dp/'
+    drm_search_text = u'Gleichzeitige Verwendung von Geräten'
+    drm_free_text = u'Keine Einschränkung'
+
+    def open(self, parent=None, detail_item=None, external=False):
+        aff_id = {'tag': 'charhale0a-21'}
+        store_link = ('http://www.amazon.de/gp/redirect.html?ie=UTF8&site-redirect=de'
+                     '&tag=%(tag)s&linkCode=ur2&camp=1638&creative=19454'
+                     '&location=http://www.amazon.de/ebooks-kindle/b?node=530886031') % aff_id
+        if detail_item:
+            aff_id['asin'] = detail_item
+            store_link = ('http://www.amazon.de/gp/redirect.html?ie=UTF8'
+                          '&location=http://www.amazon.de/dp/%(asin)s&site-redirect=de'
+                          '&tag=%(tag)s&linkCode=ur2&camp=1638&creative=6742') % aff_id
+        open_url(QUrl(store_link))

src/calibre/gui2/store/amazon_plugin.py

@@ -22,6 +22,11 @@ from calibre.gui2.store.search_result import SearchResult
 
 class AmazonKindleStore(StorePlugin):
 
+    search_url = 'http://www.amazon.com/s/url=search-alias%3Ddigital-text&field-keywords='
+    details_url = 'http://amazon.com/dp/'
+    drm_search_text = u'Simultaneous Device Usage'
+    drm_free_text = u'Unlimited'
+
     def open(self, parent=None, detail_item=None, external=False):
         '''
         Amazon comes with a number of difficulties.
@@ -117,7 +122,7 @@ class AmazonKindleStore(StorePlugin):
         open_url(QUrl(store_link))
 
     def search(self, query, max_results=10, timeout=60):
-        url = 'http://www.amazon.com/s/url=search-alias%3Ddigital-text&field-keywords=' + urllib2.quote(query)
+        url =  self.search_url + urllib2.quote(query)
         br = browser()
 
         counter = max_results
@@ -180,18 +185,19 @@ class AmazonKindleStore(StorePlugin):
                 yield s
 
     def get_details(self, search_result, timeout):
-        url = 'http://amazon.com/dp/'
+        url = self.details_url
 
         br = browser()
         with closing(br.open(url + search_result.detail_item, timeout=timeout)) as nf:
             idata = html.fromstring(nf.read())
-            if idata.xpath('boolean(//div[@class="content"]//li/b[contains(text(), "Simultaneous Device Usage")])'):
-                if idata.xpath('boolean(//div[@class="content"]//li[contains(., "Unlimited") and contains(b, "Simultaneous Device Usage")])'):
+            if idata.xpath('boolean(//div[@class="content"]//li/b[contains(text(), "' +
+                           self.drm_search_text + '")])'):
+                if idata.xpath('boolean(//div[@class="content"]//li[contains(., "' +
+                               self.drm_free_text + '") and contains(b, "' +
+                               self.drm_search_text + '")])'):
                     search_result.drm = SearchResult.DRM_UNLOCKED
                 else:
                     search_result.drm = SearchResult.DRM_UNKNOWN
             else:
                 search_result.drm = SearchResult.DRM_LOCKED
         return True
-
-

src/calibre/gui2/store/amazon_uk_plugin.py

@@ -0,0 +1,30 @@
+# -*- coding: utf-8 -*-
+
+from __future__ import (unicode_literals, division, absolute_import, print_function)
+
+__license__ = 'GPL 3'
+__copyright__ = '2011, John Schember <john@nachtimwald.com>'
+__docformat__ = 'restructuredtext en'
+
+
+from PyQt4.Qt import QUrl
+
+from calibre.gui2 import open_url
+from calibre.gui2.store.amazon_plugin import AmazonKindleStore
+
+class AmazonUKKindleStore(AmazonKindleStore):
+    '''
+    For comments on the implementation, please see amazon_plugin.py
+    '''
+
+    search_url = 'http://www.amazon.co.uk/s/url=search-alias%3Ddigital-text&field-keywords='
+    details_url = 'http://amazon.co.uk/dp/'
+
+    def open(self, parent=None, detail_item=None, external=False):
+        aff_id = {'tag': 'calcharles-21'}
+        store_link = 'http://www.amazon.co.uk/gp/redirect.html?ie=UTF8&location=http://www.amazon.co.uk/Kindle-eBooks/b?ie=UTF8&node=341689031&ref_=sa_menu_kbo2&tag=%(tag)s&linkCode=ur2&camp=1634&creative=19450' % aff_id
+
+        if detail_item:
+            aff_id['asin'] = detail_item
+            store_link = 'http://www.amazon.co.uk/gp/redirect.html?ie=UTF8&location=http://www.amazon.co.uk/dp/%(asin)s&tag=%(tag)s&linkCode=ur2&camp=1634&creative=6738' % aff_id
+        open_url(QUrl(store_link))

src/calibre/gui2/store/foyles_uk_plugin.py

@@ -0,0 +1,78 @@
+# -*- coding: utf-8 -*-
+
+from __future__ import (unicode_literals, division, absolute_import, print_function)
+
+__license__ = 'GPL 3'
+__copyright__ = '2011, John Schember <john@nachtimwald.com>'
+__docformat__ = 'restructuredtext en'
+
+import urllib2
+from contextlib import closing
+
+from lxml import html
+
+from PyQt4.Qt import QUrl
+
+from calibre import browser, url_slash_cleaner
+from calibre.gui2 import open_url
+from calibre.gui2.store import StorePlugin
+from calibre.gui2.store.basic_config import BasicStoreConfig
+from calibre.gui2.store.search_result import SearchResult
+from calibre.gui2.store.web_store_dialog import WebStoreDialog
+
+class FoylesUKStore(BasicStoreConfig, StorePlugin):
+
+    def open(self, parent=None, detail_item=None, external=False):
+        url = 'http://www.awin1.com/cread.php?awinmid=1414&awinaffid=120917&clickref=&p='
+        url_redirect = 'http://www.foyles.co.uk'
+
+        if external or self.config.get('open_external', False):
+            if detail_item:
+                url = url + url_redirect + detail_item
+            open_url(QUrl(url_slash_cleaner(url)))
+        else:
+            detail_url = None
+            if detail_item:
+                detail_url = url + url_redirect + detail_item
+            d = WebStoreDialog(self.gui, url, parent, detail_url)
+            d.setWindowTitle(self.name)
+            d.set_tags(self.config.get('tags', ''))
+            d.exec_()
+
+    def search(self, query, max_results=10, timeout=60):
+        url = 'http://www.foyles.co.uk/Public/Shop/Search.aspx?fFacetId=1015&searchBy=1&quick=true&term=' + urllib2.quote(query)
+
+        br = browser()
+
+        counter = max_results
+        with closing(br.open(url, timeout=timeout)) as f:
+            doc = html.fromstring(f.read())
+            for data in doc.xpath('//table[contains(@id, "MainContent")]/tr/td/div[contains(@class, "Item")]'):
+                if counter <= 0:
+                    break
+                id = ''.join(data.xpath('.//a[@class="Title"]/@href')).strip()
+                if not id:
+                    continue
+
+                cover_url = ''.join(data.xpath('.//a[@class="Jacket"]/img/@src'))
+                if cover_url:
+                    cover_url = 'http://www.foyles.co.uk' + cover_url
+                #print(cover_url)
+
+                title = ''.join(data.xpath('.//a[@class="Title"]/text()'))
+                author = ', '.join(data.xpath('.//span[@class="Author"]/text()'))
+                price = ''.join(data.xpath('./ul/li[@class="Strong"]/text()'))
+                price = price[price.rfind(' '):]
+
+                counter -= 1
+
+                s = SearchResult()
+                s.cover_url = cover_url
+                s.title = title.strip()
+                s.author = author.strip()
+                s.price = price
+                s.detail_item = id
+                s.drm = SearchResult.DRM_LOCKED
+                s.formats = 'EPUB'
+
+                yield s

src/calibre/gui2/store/waterstones_uk_plugin.py

@@ -0,0 +1,84 @@
+# -*- coding: utf-8 -*-
+
+from __future__ import (unicode_literals, division, absolute_import, print_function)
+
+__license__ = 'GPL 3'
+__copyright__ = '2011, John Schember <john@nachtimwald.com>'
+__docformat__ = 'restructuredtext en'
+
+import urllib2
+from contextlib import closing
+
+from lxml import html
+
+from PyQt4.Qt import QUrl
+
+from calibre import browser
+from calibre.gui2 import open_url
+from calibre.gui2.store import StorePlugin
+from calibre.gui2.store.basic_config import BasicStoreConfig
+from calibre.gui2.store.search_result import SearchResult
+from calibre.gui2.store.web_store_dialog import WebStoreDialog
+
+class WaterstonesUKStore(BasicStoreConfig, StorePlugin):
+
+    def open(self, parent=None, detail_item=None, external=False):
+        url = 'http://clkuk.tradedoubler.com/click?p=51196&a=1951604&g=19333484'
+        url_details = 'http://clkuk.tradedoubler.com/click?p(51196)a(1951604)g(16460516)url({0})'
+
+        if external or self.config.get('open_external', False):
+            if detail_item:
+                url = url_details.format(detail_item)
+            open_url(QUrl(url))
+        else:
+            detail_url = None
+            if detail_item:
+                detail_url = url_details.format(detail_item)
+            d = WebStoreDialog(self.gui, url, parent, detail_url)
+            d.setWindowTitle(self.name)
+            d.set_tags(self.config.get('tags', ''))
+            d.exec_()
+
+    def search(self, query, max_results=10, timeout=60):
+        url = 'http://www.waterstones.com/waterstonesweb/advancedSearch.do?buttonClicked=1&format=3757&bookkeywords=' + urllib2.quote(query)
+
+        br = browser()
+
+        counter = max_results
+        with closing(br.open(url, timeout=timeout)) as f:
+            doc = html.fromstring(f.read())
+            for data in doc.xpath('//div[contains(@class, "results-pane")]'):
+                if counter <= 0:
+                    break
+
+                id = ''.join(data.xpath('./div/div/h2/a/@href')).strip()
+                if not id:
+                    continue
+                cover_url = ''.join(data.xpath('.//div[@class="image"]/a/img/@src'))
+                title = ''.join(data.xpath('./div/div/h2/a/text()'))
+                author = ', '.join(data.xpath('.//p[@class="byAuthor"]/a/text()'))
+                price = ''.join(data.xpath('.//p[@class="price"]/span[@class="priceStandard"]/text()'))
+                drm = data.xpath('boolean(.//td[@headers="productFormat" and contains(., "DRM")])')
+                pdf = data.xpath('boolean(.//td[@headers="productFormat" and contains(., "PDF")])')
+                epub = data.xpath('boolean(.//td[@headers="productFormat" and contains(., "EPUB")])')
+
+                counter -= 1
+
+                s = SearchResult()
+                s.cover_url = cover_url
+                s.title = title.strip()
+                s.author = author.strip()
+                s.price = price
+                if drm:
+                    s.drm = SearchResult.DRM_LOCKED
+                else:
+                    s.drm = SearchResult.DRM_UNKNOWN
+                s.detail_item = id
+                formats = []
+                if epub:
+                    formats.append('EPUB')
+                if pdf:
+                    formats.append('PDF')
+                s.formats = ', '.join(formats)
+
+                yield s