sync with Kovid's branch

Changelog.yaml

@@ -20,6 +20,58 @@
 #   new recipes:
 #     - title: 
 
+- version: 0.9.26
+  date: 2013-04-05
+
+  new features:
+    - title: "PDF Output: Allow using templates to create arbitrary headers and footers. Look under PDF Output in the conversion dialog for this feature."
+
+    - title: "ToC Editor: Allow generating the ToC directly from individual files inside the ebook. Useful for EPUBs that have individual chapters in single files."
+      tickets: [1163520]
+
+    - title: "ToC Editor: Add buttons to indent/unindent the current entry"
+
+    - title: "ToC Editor: Right-click menu to perform various useful actions on entries in the ToC"
+
+    - title: "Column icons: Allow use of wide images as column icons"
+
+    - title: "Add USB ids for the Palm Pre2 and Samsung Galaxy phone to the device drivers"
+      tickets: [1162293,1163115]
+ 
+  bug fixes:
+    - title: "PDF Output: Fix generating page numbers causing links to not work."
+      tickets: [1162573]
+
+    - title: "Wrong filename output in error message when 'Guide reference not found'"
+      tickets: [1163659]
+
+    - title: "Get Books: Update Amazon, Barnes & Noble, Waterstones and Gutenberg store plugins for website change"
+
+    - title: "PDF Output: Fix 1 pixel wide left and top margins on the cover page for some PDF conversions due to incorrect rounding."
+      tickets: [1162054]
+
+    - title: "ToC Editor: Fix drag and drop of multiple items resulting in the dropped items being in random order sometimes."
+      tickets: [1161999]
+
+  improved recipes:
+    - Financial Times UK
+    - Sing Tao Daily
+    - Apple Daily
+    - A List Apart
+    - Business Week
+    - Harpers printed edition
+    - Harvard Business Review
+
+  new recipes:
+    - title: AM730
+      author: Eddie Lau
+
+    - title: Arret sur images 
+      author: Francois D
+
+    - title: Diario de Noticias
+      author: Jose Pinto
+
 - version: 0.9.25
   date: 2013-03-29
 

recipes/am730.recipe

@@ -0,0 +1,290 @@
+# vim:fileencoding=UTF-8
+from __future__ import unicode_literals
+__license__   = 'GPL v3'
+__copyright__ = '2013, Eddie Lau'
+__Date__ = ''
+__HiResImg__ = True
+
+'''
+Change Log:
+2013/03/30 -- first version
+'''
+
+from calibre import (__appname__, force_unicode, strftime)
+from calibre.utils.date import now as nowf
+import os, datetime, re
+from calibre.web.feeds.recipes import BasicNewsRecipe
+from contextlib import nested
+from calibre.ebooks.BeautifulSoup import BeautifulSoup, Tag
+from calibre.ebooks.metadata.opf2 import OPFCreator
+from calibre.ebooks.metadata.toc import TOC
+from calibre.ebooks.metadata import MetaInformation
+from calibre.utils.localization import canonicalize_lang
+
+class AppleDaily(BasicNewsRecipe):
+    title          = u'AM730'
+    __author__     = 'Eddie Lau'
+    publisher      = 'AM730'
+    oldest_article = 1
+    max_articles_per_feed = 100
+    auto_cleanup = False
+    language = 'zh'
+    encoding = 'utf-8'
+    auto_cleanup = False
+    remove_javascript = True
+    use_embedded_content   = False
+    no_stylesheets = True
+    description = 'http://www.am730.com.hk'
+    category    = 'Chinese, News, Hong Kong'
+    masthead_url = 'http://www.am730.com.hk/images/logo.jpg'
+
+    extra_css = 'img {display: block; margin-left: auto; margin-right: auto; margin-top: 10px; margin-bottom: 10px; max-height:90%;} div[id=articleHeader] {font-size:200%; text-align:left; font-weight:bold;} photocaption {font-size:50%; margin-left:auto; margin-right:auto;}'
+    keep_only_tags = [dict(name='div', attrs={'id':'articleHeader'}),
+                      dict(name='div', attrs={'class':'thecontent wordsnap'}),
+                      dict(name='a', attrs={'class':'lightboximg'})]
+    remove_tags = [dict(name='img', attrs={'src':'/images/am730_article_logo.jpg'}),
+                   dict(name='img', attrs={'src':'/images/am_endmark.gif'})]
+
+    def get_dtlocal(self):
+        dt_utc = datetime.datetime.utcnow()
+        # convert UTC to local hk time - at HKT 6am, all news are available
+        return dt_utc + datetime.timedelta(8.0/24) - datetime.timedelta(6.0/24)
+
+    def get_fetchdate(self):
+        if __Date__ <> '':
+            return __Date__
+        else:
+            return self.get_dtlocal().strftime("%Y%m%d")
+
+    def get_fetchformatteddate(self):
+        if __Date__ <> '':
+            return __Date__[0:4]+'-'+__Date__[4:6]+'-'+__Date__[6:8]
+        else:
+            return self.get_dtlocal().strftime("%Y-%m-%d")
+
+    def get_fetchyear(self):
+        if __Date__ <> '':
+            return __Date__[0:4]
+        else:
+            return self.get_dtlocal().strftime("%Y")
+
+    def get_fetchmonth(self):
+        if __Date__ <> '':
+            return __Date__[4:6]
+        else:
+            return self.get_dtlocal().strftime("%m")
+
+    def get_fetchday(self):
+        if __Date__ <> '':
+            return __Date__[6:8]
+        else:
+            return self.get_dtlocal().strftime("%d")
+
+    # Note: does not work with custom date given by __Date__
+    def get_weekday(self):
+        return self.get_dtlocal().weekday()
+
+    def populate_article_metadata(self, article, soup, first):
+        if first and hasattr(self, 'add_toc_thumbnail'):
+            picdiv = soup.find('img')
+            if picdiv is not None:
+                self.add_toc_thumbnail(article,picdiv['src'])
+
+    def parse_index(self):
+        feeds = []
+        soup = self.index_to_soup('http://www.am730.com.hk/')
+        ul = soup.find(attrs={'class':'nav-section'})
+        sectionList = []
+        for li in ul.findAll('li'):
+            a = 'http://www.am730.com.hk/' + li.find('a', href=True).get('href', False)
+            title = li.find('a').get('title', False).strip()
+            sectionList.append((title, a))
+        for title, url in sectionList:
+            articles = self.parse_section(url)
+            if articles:
+                feeds.append((title, articles))
+        return feeds
+
+    def parse_section(self, url):
+        soup = self.index_to_soup(url)
+        items = soup.findAll(attrs={'style':'padding-bottom: 15px;'})
+        current_articles = []
+        for item in items:
+            a = item.find(attrs={'class':'t6 f14'}).find('a', href=True)
+            articlelink = 'http://www.am730.com.hk/' + a.get('href', True)
+            title = self.tag_to_string(a)
+            description = self.tag_to_string(item.find(attrs={'class':'t3 f14'}))
+            current_articles.append({'title': title, 'url': articlelink, 'description': description})
+        return current_articles
+
+    def preprocess_html(self, soup):
+        multia = soup.findAll('a')
+        for a in multia:
+            if not (a == None):
+                image = a.find('img')
+                if not (image == None):
+                    if __HiResImg__:
+                        image['src'] = image.get('src').replace('/thumbs/', '/')
+                    caption = image.get('alt')
+                    tag = Tag(soup, "photo", [])
+                    tag2 = Tag(soup, "photocaption", [])
+                    tag.insert(0, image)
+                    if not caption == None:
+                        tag2.insert(0, caption)
+                        tag.insert(1, tag2)
+                    a.replaceWith(tag)
+        return soup
+
+    def create_opf(self, feeds, dir=None):
+        if dir is None:
+            dir = self.output_dir
+        title = self.short_title()
+        if self.output_profile.periodical_date_in_title:
+            title += strftime(self.timefmt)
+        mi = MetaInformation(title, [__appname__])
+        mi.publisher = __appname__
+        mi.author_sort = __appname__
+        if self.publication_type:
+            mi.publication_type = 'periodical:'+self.publication_type+':'+self.short_title()
+        mi.timestamp = nowf()
+        article_titles, aseen = [], set()
+        for f in feeds:
+            for a in f:
+                if a.title and a.title not in aseen:
+                    aseen.add(a.title)
+                    article_titles.append(force_unicode(a.title, 'utf-8'))
+
+        mi.comments = self.description
+        if not isinstance(mi.comments, unicode):
+            mi.comments = mi.comments.decode('utf-8', 'replace')
+        mi.comments += ('\n\n' + _('Articles in this issue: ') + '\n' +
+                '\n\n'.join(article_titles))
+
+        language = canonicalize_lang(self.language)
+        if language is not None:
+            mi.language = language
+        # This one affects the pub date shown in kindle title
+        #mi.pubdate = nowf()
+        # now appears to need the time field to be > 12.00noon as well
+        mi.pubdate = datetime.datetime(int(self.get_fetchyear()), int(self.get_fetchmonth()), int(self.get_fetchday()), 12, 30, 0)
+        opf_path = os.path.join(dir, 'index.opf')
+        ncx_path = os.path.join(dir, 'index.ncx')
+
+        opf = OPFCreator(dir, mi)
+        # Add mastheadImage entry to <guide> section
+        mp = getattr(self, 'masthead_path', None)
+        if mp is not None and os.access(mp, os.R_OK):
+            from calibre.ebooks.metadata.opf2 import Guide
+            ref = Guide.Reference(os.path.basename(self.masthead_path), os.getcwdu())
+            ref.type = 'masthead'
+            ref.title = 'Masthead Image'
+            opf.guide.append(ref)
+
+        manifest = [os.path.join(dir, 'feed_%d'%i) for i in range(len(feeds))]
+        manifest.append(os.path.join(dir, 'index.html'))
+        manifest.append(os.path.join(dir, 'index.ncx'))
+
+        # Get cover
+        cpath = getattr(self, 'cover_path', None)
+        if cpath is None:
+            pf = open(os.path.join(dir, 'cover.jpg'), 'wb')
+            if self.default_cover(pf):
+                cpath =  pf.name
+        if cpath is not None and os.access(cpath, os.R_OK):
+            opf.cover = cpath
+            manifest.append(cpath)
+
+        # Get masthead
+        mpath = getattr(self, 'masthead_path', None)
+        if mpath is not None and os.access(mpath, os.R_OK):
+            manifest.append(mpath)
+
+        opf.create_manifest_from_files_in(manifest)
+        for mani in opf.manifest:
+            if mani.path.endswith('.ncx'):
+                mani.id = 'ncx'
+            if mani.path.endswith('mastheadImage.jpg'):
+                mani.id = 'masthead-image'
+
+        entries = ['index.html']
+        toc = TOC(base_path=dir)
+        self.play_order_counter = 0
+        self.play_order_map = {}
+
+
+        def feed_index(num, parent):
+            f = feeds[num]
+            for j, a in enumerate(f):
+                if getattr(a, 'downloaded', False):
+                    adir = 'feed_%d/article_%d/'%(num, j)
+                    auth = a.author
+                    if not auth:
+                        auth = None
+                    desc = a.text_summary
+                    if not desc:
+                        desc = None
+                    else:
+                        desc = self.description_limiter(desc)
+                    tt = a.toc_thumbnail if a.toc_thumbnail else None
+                    entries.append('%sindex.html'%adir)
+                    po = self.play_order_map.get(entries[-1], None)
+                    if po is None:
+                        self.play_order_counter += 1
+                        po = self.play_order_counter
+                    parent.add_item('%sindex.html'%adir, None,
+                            a.title if a.title else _('Untitled Article'),
+                            play_order=po, author=auth,
+                            description=desc, toc_thumbnail=tt)
+                    last = os.path.join(self.output_dir, ('%sindex.html'%adir).replace('/', os.sep))
+                    for sp in a.sub_pages:
+                        prefix = os.path.commonprefix([opf_path, sp])
+                        relp = sp[len(prefix):]
+                        entries.append(relp.replace(os.sep, '/'))
+                        last = sp
+
+                    if os.path.exists(last):
+                        with open(last, 'rb') as fi:
+                            src = fi.read().decode('utf-8')
+                        soup = BeautifulSoup(src)
+                        body = soup.find('body')
+                        if body is not None:
+                            prefix = '/'.join('..'for i in range(2*len(re.findall(r'link\d+', last))))
+                            templ = self.navbar.generate(True, num, j, len(f),
+                                            not self.has_single_feed,
+                                            a.orig_url, __appname__, prefix=prefix,
+                                            center=self.center_navbar)
+                            elem = BeautifulSoup(templ.render(doctype='xhtml').decode('utf-8')).find('div')
+                            body.insert(len(body.contents), elem)
+                            with open(last, 'wb') as fi:
+                                fi.write(unicode(soup).encode('utf-8'))
+        if len(feeds) == 0:
+            raise Exception('All feeds are empty, aborting.')
+
+        if len(feeds) > 1:
+            for i, f in enumerate(feeds):
+                entries.append('feed_%d/index.html'%i)
+                po = self.play_order_map.get(entries[-1], None)
+                if po is None:
+                    self.play_order_counter += 1
+                    po = self.play_order_counter
+                auth = getattr(f, 'author', None)
+                if not auth:
+                    auth = None
+                desc = getattr(f, 'description', None)
+                if not desc:
+                    desc = None
+                feed_index(i, toc.add_item('feed_%d/index.html'%i, None,
+                    f.title, play_order=po, description=desc, author=auth))
+
+        else:
+            entries.append('feed_%d/index.html'%0)
+            feed_index(0, toc)
+
+        for i, p in enumerate(entries):
+            entries[i] = os.path.join(dir, p.replace('/', os.sep))
+        opf.create_spine(entries)
+        opf.set_toc(toc)
+
+        with nested(open(opf_path, 'wb'), open(ncx_path, 'wb')) as (opf_file, ncx_file):
+            opf.render(opf_file, ncx_file)
+

recipes/apple_daily.recipe

@@ -1,161 +1,275 @@
-# -*- coding: utf-8 -*-
+# vim:fileencoding=UTF-8
-import re
+from __future__ import unicode_literals
+__license__   = 'GPL v3'
+__copyright__ = '2013, Eddie Lau'
+__Date__ = ''
+
+from calibre import (__appname__, force_unicode, strftime)
+from calibre.utils.date import now as nowf
+import os, datetime, re
 from calibre.web.feeds.recipes import BasicNewsRecipe
+from contextlib import nested
+from calibre.ebooks.BeautifulSoup import BeautifulSoup
+from calibre.ebooks.metadata.opf2 import OPFCreator
+from calibre.ebooks.metadata.toc import TOC
+from calibre.ebooks.metadata import MetaInformation
+from calibre.utils.localization import canonicalize_lang
 
 class AppleDaily(BasicNewsRecipe):
-
+    title          = u'蘋果日報 (香港)'
-    title       = u'蘋果日報'
+    __author__     = 'Eddie Lau'
-    __author__  = u'蘋果日報'
+    publisher      = '蘋果日報'
-    __publisher__  = u'蘋果日報'
+    oldest_article = 1
-    description = u'蘋果日報'
+    max_articles_per_feed = 100
-    masthead_url = 'http://hk.apple.nextmedia.com/template/common/header/2009/images/atnextheader_logo_appledaily.gif'
+    auto_cleanup = False
-    language = 'zh_TW'
+    language = 'zh'
-    encoding = 'UTF-8'
+    encoding = 'utf-8'
-    timefmt = ' [%a, %d %b, %Y]'
+    auto_cleanup = False
-    needs_subscription = False
     remove_javascript = True
-    remove_tags_before = dict(name=['ul', 'h1'])
+    use_embedded_content   = False
-    remove_tags_after  = dict(name='form')
-    remove_tags = [dict(attrs={'class':['articleTools', 'post-tools', 'side_tool', 'nextArticleLink clearfix']}),
-                dict(id=['footer', 'toolsRight', 'articleInline', 'navigation', 'archive', 'side_search', 'blog_sidebar', 'side_tool', 'side_index']),
-                dict(name=['script', 'noscript', 'style', 'form'])]
     no_stylesheets = True
-    extra_css = '''
+    description = 'http://hkm.appledaily.com/'
-    	@font-face {font-family: "uming", serif, sans-serif;  src: url(res:///usr/share/fonts/truetype/arphic/uming.ttc); }\n
+    category    = 'Chinese, News, Hong Kong'
-	    body {margin-right: 8pt; font-family: 'uming', serif;}
+    masthead_url = 'http://upload.wikimedia.org/wikipedia/zh/c/cf/AppleDailyLogo1.png'
-        h1 {font-family: 'uming', serif, sans-serif}
-            '''
-    #extra_css = 'h1 {font: sans-serif large;}\n.byline {font:monospace;}'
 
-    preprocess_regexps = [
+    extra_css = 'img {display: block; margin-left: auto; margin-right: auto; margin-top: 10px; margin-bottom: 10px; max-height:90%;} h1 {font-size:200%; text-align:left; font-weight:bold;} p[class=video-caption] {font-size:50%; margin-left:auto; margin-right:auto;}'
-       (re.compile(r'img.php?server=(?P<server>[^&]+)&path=(?P<path>[^&]+).*', re.DOTALL|re.IGNORECASE),
+    keep_only_tags = [dict(name='div', attrs={'id':'content-article'})]
-        lambda match: 'http://' + match.group('server') + '/' + match.group('path')),
+    remove_tags = [dict(name='div', attrs={'class':'prev-next-btn'}),
-    ]
+                   dict(name='p', attrs={'class':'next'})]
+
+    def get_dtlocal(self):
+        dt_utc = datetime.datetime.utcnow()
+        # convert UTC to local hk time - at HKT 6am, all news are available
+        return dt_utc + datetime.timedelta(8.0/24) - datetime.timedelta(6.0/24)
+
+    def get_fetchdate(self):
+        if __Date__ <> '':
+            return __Date__
+        else:
+            return self.get_dtlocal().strftime("%Y%m%d")
+
+    def get_fetchformatteddate(self):
+        if __Date__ <> '':
+            return __Date__[0:4]+'-'+__Date__[4:6]+'-'+__Date__[6:8]
+        else:
+            return self.get_dtlocal().strftime("%Y-%m-%d")
+
+    def get_fetchyear(self):
+        if __Date__ <> '':
+            return __Date__[0:4]
+        else:
+            return self.get_dtlocal().strftime("%Y")
+
+    def get_fetchmonth(self):
+        if __Date__ <> '':
+            return __Date__[4:6]
+        else:
+            return self.get_dtlocal().strftime("%m")
+
+    def get_fetchday(self):
+        if __Date__ <> '':
+            return __Date__[6:8]
+        else:
+            return self.get_dtlocal().strftime("%d")
+
+    # Note: does not work with custom date given by __Date__
+    def get_weekday(self):
+        return self.get_dtlocal().weekday()
 
     def get_cover_url(self):
-        return 'http://hk.apple.nextmedia.com/template/common/header/2009/images/atnextheader_logo_appledaily.gif'
+        soup = self.index_to_soup('http://hkm.appledaily.com/')
-
+        cover = soup.find(attrs={'class':'top-news'}).get('src', False)
-
+        br = BasicNewsRecipe.get_browser(self)
-    #def get_browser(self):
+        try:
-        #br = BasicNewsRecipe.get_browser(self)
+            br.open(cover)
-        #if self.username is not None and self.password is not None:
+        except:
-        #    br.open('http://www.nytimes.com/auth/login')
+            cover = None
-        #    br.select_form(name='login')
+        return cover
-        #    br['USERID']   = self.username
-        #    br['PASSWORD'] = self.password
-        #    br.submit()
-        #return br
-
-    def preprocess_html(self, soup):
-        #process all the images
-        for tag in soup.findAll(lambda tag: tag.name.lower()=='img' and tag.has_key('src')):
-            iurl = tag['src']
-            #print 'checking image: ' + iurl
-
-            #img\.php?server\=(?P<server>[^&]+)&path=(?P<path>[^&]+)
-            p = re.compile(r'img\.php\?server=(?P<server>[^&]+)&path=(?P<path>[^&]+)', re.DOTALL|re.IGNORECASE)
-
-            m = p.search(iurl)
-
-            if m is not None:
-                iurl = 'http://' + m.group('server') + '/' + m.group('path')
-                #print 'working! new url: ' + iurl
-                tag['src'] = iurl
-            #else:
-                #print 'not good'
-
-        for tag in soup.findAll(lambda tag: tag.name.lower()=='a' and tag.has_key('href')):
-            iurl = tag['href']
-            #print 'checking image: ' + iurl
-
-            #img\.php?server\=(?P<server>[^&]+)&path=(?P<path>[^&]+)
-            p = re.compile(r'img\.php\?server=(?P<server>[^&]+)&path=(?P<path>[^&]+)', re.DOTALL|re.IGNORECASE)
-
-            m = p.search(iurl)
-
-            if m is not None:
-                iurl = 'http://' + m.group('server') + '/' + m.group('path')
-                #print 'working! new url: ' + iurl
-                tag['href'] = iurl
-            #else:
-                #print 'not good'
-
-        return soup
 
+    def populate_article_metadata(self, article, soup, first):
+        if first and hasattr(self, 'add_toc_thumbnail'):
+            picdiv = soup.find('img')
+            if picdiv is not None:
+                self.add_toc_thumbnail(article,picdiv['src'])
 
     def parse_index(self):
-        base = 'http://news.hotpot.hk/fruit'
+        feeds = []
-        soup = self.index_to_soup('http://news.hotpot.hk/fruit/index.php')
+        soup = self.index_to_soup('http://hkm.appledaily.com/')
+        ul = soup.find(attrs={'class':'menu'})
+        sectionList = []
+        for li in ul.findAll('li'):
+            a = 'http://hkm.appledaily.com/' + li.find('a', href=True).get('href', False)
+            title = li.find('a', text=True).strip()
+            if not title == u'動新聞':
+                sectionList.append((title, a))
+        for title, url in sectionList:
+            articles = self.parse_section(url)
+            if articles:
+                feeds.append((title, articles))
+        return feeds
 
-        #def feed_title(div):
+    def parse_section(self, url):
-        #    return ''.join(div.findAll(text=True, recursive=False)).strip()
+        soup = self.index_to_soup(url)
+        ul = soup.find(attrs={'class':'list'})
+        current_articles = []
+        for li in ul.findAll('li'):
+            a = li.find('a', href=True)
+            title = li.find('p', text=True).strip()
+            if a is not None:
+                current_articles.append({'title': title, 'url':'http://hkm.appledaily.com/' + a.get('href', False)})
+            pass
+        return current_articles
 
-        articles = {}
+    def create_opf(self, feeds, dir=None):
-        key = None
+        if dir is None:
-        ans = []
+            dir = self.output_dir
-        for div in soup.findAll('li'):
+        title = self.short_title()
-            key = div.find(text=True, recursive=True);
+        if self.output_profile.periodical_date_in_title:
-            #if key == u'豪情':
+            title += strftime(self.timefmt)
-           #    continue;
+        mi = MetaInformation(title, [__appname__])
+        mi.publisher = __appname__
+        mi.author_sort = __appname__
+        if self.publication_type:
+            mi.publication_type = 'periodical:'+self.publication_type+':'+self.short_title()
+        mi.timestamp = nowf()
+        article_titles, aseen = [], set()
+        for f in feeds:
+            for a in f:
+                if a.title and a.title not in aseen:
+                    aseen.add(a.title)
+                    article_titles.append(force_unicode(a.title, 'utf-8'))
 
-            print 'section=' + key
+        mi.comments = self.description
+        if not isinstance(mi.comments, unicode):
+            mi.comments = mi.comments.decode('utf-8', 'replace')
+        mi.comments += ('\n\n' + _('Articles in this issue: ') + '\n' +
+                '\n\n'.join(article_titles))
 
-            articles[key] = []
+        language = canonicalize_lang(self.language)
+        if language is not None:
+            mi.language = language
+        # This one affects the pub date shown in kindle title
+        #mi.pubdate = nowf()
+        # now appears to need the time field to be > 12.00noon as well
+        mi.pubdate = datetime.datetime(int(self.get_fetchyear()), int(self.get_fetchmonth()), int(self.get_fetchday()), 12, 30, 0)
+        opf_path = os.path.join(dir, 'index.opf')
+        ncx_path = os.path.join(dir, 'index.ncx')
 
-            ans.append(key)
+        opf = OPFCreator(dir, mi)
+        # Add mastheadImage entry to <guide> section
+        mp = getattr(self, 'masthead_path', None)
+        if mp is not None and os.access(mp, os.R_OK):
+            from calibre.ebooks.metadata.opf2 import Guide
+            ref = Guide.Reference(os.path.basename(self.masthead_path), os.getcwdu())
+            ref.type = 'masthead'
+            ref.title = 'Masthead Image'
+            opf.guide.append(ref)
 
-            a = div.find('a', href=True)
+        manifest = [os.path.join(dir, 'feed_%d'%i) for i in range(len(feeds))]
+        manifest.append(os.path.join(dir, 'index.html'))
+        manifest.append(os.path.join(dir, 'index.ncx'))
 
-            if not a:
+        # Get cover
-                continue
+        cpath = getattr(self, 'cover_path', None)
+        if cpath is None:
+            pf = open(os.path.join(dir, 'cover.jpg'), 'wb')
+            if self.default_cover(pf):
+                cpath =  pf.name
+        if cpath is not None and os.access(cpath, os.R_OK):
+            opf.cover = cpath
+            manifest.append(cpath)
 
-            url = base + '/' + a['href']
+        # Get masthead
-            print 'url=' + url
+        mpath = getattr(self, 'masthead_path', None)
+        if mpath is not None and os.access(mpath, os.R_OK):
+            manifest.append(mpath)
 
-            if not articles.has_key(key):
+        opf.create_manifest_from_files_in(manifest)
-                articles[key] = []
+        for mani in opf.manifest:
-            else:
+            if mani.path.endswith('.ncx'):
-                # sub page
+                mani.id = 'ncx'
-                subSoup = self.index_to_soup(url)
+            if mani.path.endswith('mastheadImage.jpg'):
+                mani.id = 'masthead-image'
 
-                for subDiv in subSoup.findAll('li'):
+        entries = ['index.html']
-                    subA = subDiv.find('a', href=True)
+        toc = TOC(base_path=dir)
-                    subTitle = subDiv.find(text=True, recursive=True)
+        self.play_order_counter = 0
-                    subUrl = base + '/' + subA['href']
+        self.play_order_map = {}
-
-                    print 'subUrl' + subUrl
-
-                    articles[key].append(
-                        dict(title=subTitle,
-                         url=subUrl,
-                         date='',
-                         description='',
-                         content=''))
 
 
-#             elif div['class'] in ['story', 'story headline']:
+        def feed_index(num, parent):
-#                 a = div.find('a', href=True)
+            f = feeds[num]
-#                 if not a:
+            for j, a in enumerate(f):
-#                     continue
+                if getattr(a, 'downloaded', False):
-#                 url = re.sub(r'\?.*', '', a['href'])
+                    adir = 'feed_%d/article_%d/'%(num, j)
-#                 url += '?pagewanted=all'
+                    auth = a.author
-#                 title = self.tag_to_string(a, use_alt=True).strip()
+                    if not auth:
-#                 description = ''
+                        auth = None
-#                 pubdate = strftime('%a, %d %b')
+                    desc = a.text_summary
-#                 summary = div.find(True, attrs={'class':'summary'})
+                    if not desc:
-#                 if summary:
+                        desc = None
-#                     description = self.tag_to_string(summary, use_alt=False)
+                    else:
-#
+                        desc = self.description_limiter(desc)
-#                 feed = key if key is not None else 'Uncategorized'
+                    tt = a.toc_thumbnail if a.toc_thumbnail else None
-#                 if not articles.has_key(feed):
+                    entries.append('%sindex.html'%adir)
-#                     articles[feed] = []
+                    po = self.play_order_map.get(entries[-1], None)
-#                 if not 'podcasts' in url:
+                    if po is None:
-#                     articles[feed].append(
+                        self.play_order_counter += 1
-#                               dict(title=title, url=url, date=pubdate,
+                        po = self.play_order_counter
-#                                    description=description,
+                    parent.add_item('%sindex.html'%adir, None,
-#                                    content=''))
+                            a.title if a.title else _('Untitled Article'),
-#        ans = self.sort_index_by(ans, {'The Front Page':-1, 'Dining In, Dining Out':1, 'Obituaries':2})
+                            play_order=po, author=auth,
-        ans = [(unicode(key), articles[key]) for key in ans if articles.has_key(key)]
+                            description=desc, toc_thumbnail=tt)
-        return ans
+                    last = os.path.join(self.output_dir, ('%sindex.html'%adir).replace('/', os.sep))
+                    for sp in a.sub_pages:
+                        prefix = os.path.commonprefix([opf_path, sp])
+                        relp = sp[len(prefix):]
+                        entries.append(relp.replace(os.sep, '/'))
+                        last = sp
 
+                    if os.path.exists(last):
+                        with open(last, 'rb') as fi:
+                            src = fi.read().decode('utf-8')
+                        soup = BeautifulSoup(src)
+                        body = soup.find('body')
+                        if body is not None:
+                            prefix = '/'.join('..'for i in range(2*len(re.findall(r'link\d+', last))))
+                            templ = self.navbar.generate(True, num, j, len(f),
+                                            not self.has_single_feed,
+                                            a.orig_url, __appname__, prefix=prefix,
+                                            center=self.center_navbar)
+                            elem = BeautifulSoup(templ.render(doctype='xhtml').decode('utf-8')).find('div')
+                            body.insert(len(body.contents), elem)
+                            with open(last, 'wb') as fi:
+                                fi.write(unicode(soup).encode('utf-8'))
+        if len(feeds) == 0:
+            raise Exception('All feeds are empty, aborting.')
+
+        if len(feeds) > 1:
+            for i, f in enumerate(feeds):
+                entries.append('feed_%d/index.html'%i)
+                po = self.play_order_map.get(entries[-1], None)
+                if po is None:
+                    self.play_order_counter += 1
+                    po = self.play_order_counter
+                auth = getattr(f, 'author', None)
+                if not auth:
+                    auth = None
+                desc = getattr(f, 'description', None)
+                if not desc:
+                    desc = None
+                feed_index(i, toc.add_item('feed_%d/index.html'%i, None,
+                    f.title, play_order=po, description=desc, author=auth))
+
+        else:
+            entries.append('feed_%d/index.html'%0)
+            feed_index(0, toc)
+
+        for i, p in enumerate(entries):
+            entries[i] = os.path.join(dir, p.replace('/', os.sep))
+        opf.create_spine(entries)
+        opf.set_toc(toc)
+
+        with nested(open(opf_path, 'wb'), open(ncx_path, 'wb')) as (opf_file, ncx_file):
+            opf.render(opf_file, ncx_file)
 

recipes/birmingham_post.recipe

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

recipes/bwmagazine2.recipe

@@ -1,3 +1,4 @@
+import re
 from calibre.web.feeds.recipes import BasicNewsRecipe
 from collections import OrderedDict
 
@@ -39,7 +40,7 @@ class BusinessWeekMagazine(BasicNewsRecipe):
             title=self.tag_to_string(div.a).strip()
             url=div.a['href']
             soup0 = self.index_to_soup(url)
-            urlprint=soup0.find('li', attrs={'class':'print tracked'}).a['href']
+            urlprint=soup0.find('a', attrs={'href':re.compile('.*printer.*')})['href']
             articles.append({'title':title, 'url':urlprint, 'description':'', 'date':''})
 
 
@@ -56,7 +57,7 @@ class BusinessWeekMagazine(BasicNewsRecipe):
             title=self.tag_to_string(div.a).strip()
             url=div.a['href']
             soup0 = self.index_to_soup(url)
-            urlprint=soup0.find('li', attrs={'class':'print tracked'}).a['href']
+            urlprint=soup0.find('a', attrs={'href':re.compile('.*printer.*')})['href']
             articles.append({'title':title, 'url':urlprint, 'description':desc, 'date':''})
 
             if articles:

recipes/countryfile.recipe

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

recipes/daily_mirror.recipe

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

recipes/diario_de_noticias.recipe

@@ -0,0 +1,23 @@
+# vim:fileencoding=UTF-8
+
+from __future__ import unicode_literals
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class AdvancedUserRecipe1365070687(BasicNewsRecipe):
+  title ='Diário de Notícias'
+  oldest_article = 7
+  language = 'pt'
+  __author__ = 'Jose Pinto'
+  max_articles_per_feed = 100
+  keep_only_tags = [dict(name='div', attrs={'id':'cln-esqmid'}) ]
+  remove_tags    = [ dict(name='table', attrs={'class':'TabFerramentasInf'}) ]
+
+  feeds = [(u'Portugal', u'http://feeds.dn.pt/DN-Portugal'),
+    (u'Globo', u'http://feeds.dn.pt/DN-Globo'),
+    (u'Economia', u'http://feeds.dn.pt/DN-Economia'),
+    (u'Ci\xeancia', u'http://feeds.dn.pt/DN-Ciencia'),
+    (u'Artes', u'http://feeds.dn.pt/DN-Artes'),
+    (u'TV & Media', u'http://feeds.dn.pt/DN-Media'),
+    (u'Opini\xe3o', u'http://feeds.dn.pt/DN-Opiniao'),
+    (u'Pessoas', u'http://feeds.dn.pt/DN-Pessoas')
+    ]

recipes/economia.recipe

@@ -0,0 +1,17 @@
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class AdvancedUserRecipe1314326622(BasicNewsRecipe):
+    title          = u'Economia'
+    __author__     = 'Manish Bhattarai'
+    description = 'Economia - Intelligence & Insight for ICAEW Members'
+    language = 'en_GB'
+    oldest_article = 7
+    max_articles_per_feed = 25
+    masthead_url = 'http://economia.icaew.com/~/media/Images/Design%20Images/Economia_Red_website.ashx'
+    cover_url = 'http://economia.icaew.com/~/media/Images/Design%20Images/Economia_Red_website.ashx'
+    no_stylesheets = True
+    remove_empty_feeds = True
+    remove_tags_before = dict(id='content')
+    remove_tags_after  = dict(id='stars-wrapper')
+    remove_tags = [dict(attrs={'class':['floatR', 'sharethis', 'rating clearfix']})]
+    feeds          = [(u'News', u'http://feedity.com/icaew-com/VlNTVFRa.rss'),(u'Business', u'http://feedity.com/icaew-com/VlNTVFtS.rss'),(u'People', u'http://feedity.com/icaew-com/VlNTVFtX.rss'),(u'Opinion', u'http://feedity.com/icaew-com/VlNTVFtW.rss'),(u'Finance', u'http://feedity.com/icaew-com/VlNTVFtV.rss')]

recipes/financial_times_uk.recipe

@@ -8,6 +8,7 @@ import datetime
 from calibre.ptempfile import PersistentTemporaryFile
 from calibre import strftime
 from calibre.web.feeds.news import BasicNewsRecipe
+from collections import OrderedDict
 
 class FinancialTimes(BasicNewsRecipe):
     title                 = 'Financial Times (UK)'
@@ -93,7 +94,7 @@ class FinancialTimes(BasicNewsRecipe):
             try:
                 urlverified = self.browser.open_novisit(url).geturl() # resolve redirect.
             except:
-                continue 
+                continue
             title = self.tag_to_string(item)
             date = strftime(self.timefmt)
             articles.append({
@@ -105,29 +106,30 @@ class FinancialTimes(BasicNewsRecipe):
         return articles
 
     def parse_index(self):
-        feeds = []
+        feeds = OrderedDict()
         soup = self.index_to_soup(self.INDEX)
-        dates= self.tag_to_string(soup.find('div', attrs={'class':'btm-links'}).find('div'))
+        #dates= self.tag_to_string(soup.find('div', attrs={'class':'btm-links'}).find('div'))
-        self.timefmt = ' [%s]'%dates
+        #self.timefmt = ' [%s]'%dates
-        wide = soup.find('div',attrs={'class':'wide'})
+        section_title = 'Untitled'
-        if not wide:
+
-           return feeds
+        for column in soup.findAll('div', attrs = {'class':'feedBoxes clearfix'}):
-        allsections = wide.findAll(attrs={'class':lambda x: x and 'footwell' in x.split()})
+            for section in column. findAll('div', attrs = {'class':'feedBox'}):
-        if not allsections:
+                sectiontitle=self.tag_to_string(section.find('h4'))
-           return feeds
+                if '...' not in sectiontitle: section_title=sectiontitle
-        count = 0
+                for article in section.ul.findAll('li'):
-        for item in allsections:
+                    articles = []
-            count = count + 1
+                    title=self.tag_to_string(article.a)
-            if self.test and count > 2:
+                    url=article.a['href']
-               return feeds
+                    articles.append({'title':title, 'url':url, 'description':'', 'date':''})
-            fitem = item.h3
+
-            if not fitem:
+                    if articles:
-               fitem = item.h4
+                        if section_title not in feeds:
-            ftitle = self.tag_to_string(fitem)   
+                            feeds[section_title] = []
-            self.report_progress(0, _('Fetching feed')+' %s...'%(ftitle))
+                        feeds[section_title] += articles
-            feedarts = self.get_artlinks(item.ul)
+
-            feeds.append((ftitle,feedarts))
+
-        return feeds
+        ans = [(key, val) for key, val in feeds.iteritems()]
+        return ans
 
     def preprocess_html(self, soup):
         items = ['promo-box','promo-title',
@@ -174,9 +176,6 @@ class FinancialTimes(BasicNewsRecipe):
             count += 1
         tfile = PersistentTemporaryFile('_fa.html')
         tfile.write(html)
-        tfile.close()        
+        tfile.close()
         self.temp_files.append(tfile)
         return tfile.name
-
-    def cleanup(self):
-        self.browser.open('https://registration.ft.com/registration/login/logout?location=')

recipes/forbes_pl.recipe

@@ -5,7 +5,6 @@ __license__ = 'GPL v3'
 from calibre.web.feeds.news import BasicNewsRecipe
 import datetime
 import re
-from calibre.ebooks.BeautifulSoup import Comment
 
 class forbes_pl(BasicNewsRecipe):
     title = u'Forbes.pl'
@@ -26,9 +25,9 @@ class forbes_pl(BasicNewsRecipe):
     pages_count = 4
     keep_only_tags = [dict(attrs={'class':['Block-Node Content-Article ', 'Block-Node Content-Article piano-closed']})]
     remove_tags = [dict(attrs={'class':['Keywords Styled', 'twitter-share-button', 'Block-List-Related Block-List']})]
-    
+
     feeds = [(u'Wszystkie', 'http://www.forbes.pl/rss')]
-    
+
     '''def preprocess_html(self, soup):
         self.append_page(soup, soup.body)
         return soup
@@ -51,4 +50,4 @@ class forbes_pl(BasicNewsRecipe):
             appendtag.insert(pos, pagetext)
         if cleanup:
             for r in appendtag.findAll(attrs={'class':'paginator'}):
-                r.extract()'''
+                r.extract()'''

recipes/galaxys_edge.recipe

@@ -0,0 +1,108 @@
+from __future__ import with_statement
+__license__ = 'GPL 3'
+__copyright__ = '2009, Kovid Goyal <kovid@kovidgoyal.net>'
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class GalaxyEdge(BasicNewsRecipe):
+    title                 = u'The Galaxy\'s Edge'
+    language = 'en'
+
+    oldest_article        = 7
+    __author__            = 'Krittika Goyal'
+    no_stylesheets = True
+
+    auto_cleanup = True
+
+    #keep_only_tags = [dict(id='content')]
+    #remove_tags = [dict(attrs={'class':['article-links', 'breadcr']}),
+            #dict(id=['email-section', 'right-column', 'printfooter', 'topover',
+                     #'slidebox', 'th_footer'])]
+
+    extra_css = '.photo-caption { font-size: smaller }'
+
+    def parse_index(self):
+        soup = self.index_to_soup('http://www.galaxysedge.com/')
+        main = soup.find('table', attrs={'width':'911'})
+        toc = main.find('td', attrs={'width':'225'})
+
+
+
+        current_section = None
+        current_articles = []
+        feeds = []
+        c = 0
+        for x in toc.findAll(['p']):
+            c = c+1
+            if c == 5:
+                if current_articles and current_section:
+                    feeds.append((current_section, current_articles))
+                edwo = x.find('a')
+                current_section = self.tag_to_string(edwo)
+                current_articles = []
+                self.log('\tFound section:', current_section)
+                title = self.tag_to_string(edwo)
+                url = edwo.get('href', True)
+                url = 'http://www.galaxysedge.com/'+url
+                print(title)
+                print(c)
+                if not url or not title:
+                    continue
+                self.log('\t\tFound article:', title)
+                self.log('\t\t\t', url)
+                current_articles.append({'title': title, 'url':url,
+                    'description':'', 'date':''})
+            elif c>5:
+                current_section = self.tag_to_string(x.find('b'))
+                current_articles = []
+                self.log('\tFound section:', current_section)
+                for y in x.findAll('a'):
+                    title = self.tag_to_string(y)
+                    url = y.get('href', True)
+                    url = 'http://www.galaxysedge.com/'+url
+                    print(title)
+                    if not url or not title:
+                        continue
+                    self.log('\t\tFound article:', title)
+                    self.log('\t\t\t', url)
+                    current_articles.append({'title': title, 'url':url,
+                        'description':'', 'date':''})
+            if current_articles and current_section:
+                 feeds.append((current_section, current_articles))
+
+        return feeds
+
+
+
+
+    #def preprocess_raw_html(self, raw, url):
+        #return raw.replace('<body><p>', '<p>').replace('</p></body>', '</p>')
+
+    #def postprocess_html(self, soup, first_fetch):
+        #for t in soup.findAll(['table', 'tr', 'td','center']):
+            #t.name = 'div'
+        #return soup
+
+    #def parse_index(self):
+        #today = time.strftime('%Y-%m-%d')
+        #soup = self.index_to_soup(
+                #'http://www.thehindu.com/todays-paper/tp-index/?date=' + today)
+        #div = soup.find(id='left-column')
+        #feeds = []
+        #current_section = None
+        #current_articles = []
+        #for x in div.findAll(['h3', 'div']):
+            #if current_section and x.get('class', '') == 'tpaper':
+                #a = x.find('a', href=True)
+                #if a is not None:
+                    #current_articles.append({'url':a['href']+'?css=print',
+                        #'title':self.tag_to_string(a), 'date': '',
+                        #'description':''})
+            #if x.name == 'h3':
+                #if current_section and current_articles:
+                    #feeds.append((current_section, current_articles))
+                #current_section = self.tag_to_string(x)
+                #current_articles = []
+        #return feeds
+
+

recipes/hbr.recipe

@@ -1,6 +1,4 @@
 from calibre.web.feeds.news import BasicNewsRecipe
-import re
-from datetime import date, timedelta
 
 class HBR(BasicNewsRecipe):
 
@@ -11,23 +9,18 @@ class HBR(BasicNewsRecipe):
     timefmt                = ' [%B %Y]'
     language = 'en'
     no_stylesheets = True
-    # recipe_disabled = ('hbr.org has started requiring the use of javascript'
-    #         ' to log into their website. This is unsupported in calibre, so'
-    #         ' this recipe has been disabled. If you would like to see '
-    #         ' HBR supported in calibre, contact hbr.org and ask them'
-    #         ' to provide a javascript free login method.')
 
     LOGIN_URL = 'https://hbr.org/login?request_url=/'
     LOGOUT_URL = 'https://hbr.org/logout?request_url=/'
 
-    INDEX = 'http://hbr.org/archive-toc/BR'
+    INDEX = 'http://hbr.org'
 
     keep_only_tags = [dict(name='div', id='pageContainer')]
     remove_tags = [dict(id=['mastheadContainer', 'magazineHeadline',
         'articleToolbarTopRD', 'pageRightSubColumn', 'pageRightColumn',
         'todayOnHBRListWidget', 'mostWidget', 'keepUpWithHBR',
         'mailingListTout', 'partnerCenter', 'pageFooter',
-        'superNavHeadContainer', 'hbrDisqus',
+        'superNavHeadContainer', 'hbrDisqus', 'article-toolbox',
         'articleToolbarTop', 'articleToolbarBottom', 'articleToolbarRD']),
         dict(name='iframe')]
     extra_css = '''
@@ -57,22 +50,6 @@ class HBR(BasicNewsRecipe):
         if url.endswith('/ar/1'):
             return url[:-1]+'pr'
 
-    def hbr_get_toc(self):
-        # return self.index_to_soup(open('/t/toc.html').read())
-
-        today = date.today()
-        future = today + timedelta(days=30)
-        past = today - timedelta(days=30)
-        for x in [x.strftime('%y%m') for x in (future, today, past)]:
-            url = self.INDEX + x
-            soup = self.index_to_soup(url)
-            if (not soup.find(text='Issue Not Found') and not soup.find(
-                text="We're Sorry.  There was an error processing your request")
-                and 'Exception: java.io.FileNotFoundException' not in
-                unicode(soup)):
-                return soup
-        raise Exception('Could not find current issue')
-
     def hbr_parse_toc(self, soup):
         feeds = []
         current_section = None
@@ -105,23 +82,19 @@ class HBR(BasicNewsRecipe):
 
                 articles.append({'title':title, 'url':url, 'description':desc,
                     'date':''})
+
+        if current_section is not None and articles:
+            feeds.append((current_section, articles))
         return feeds
 
     def parse_index(self):
-        soup = self.hbr_get_toc()
+        soup0 = self.index_to_soup('http://hbr.org/magazine')
-        # open('/t/hbr.html', 'wb').write(unicode(soup).encode('utf-8'))
+        datencover = soup0.find('ul', attrs={'id':'magazineArchiveCarousel'}).findAll('li')[-1]
+        #find date & cover
+        self.cover_url=datencover.img['src']
+        dates=self.tag_to_string(datencover.img['alt'])
+        self.timefmt = u' [%s]'%dates
+        soup = self.index_to_soup(self.INDEX + soup0.find('div', attrs = {'class':'magazine_page'}).a['href'])
         feeds = self.hbr_parse_toc(soup)
         return feeds
 
-    def get_cover_url(self):
-        cover_url = None
-        index = 'http://hbr.org/current'
-        soup = self.index_to_soup(index)
-        link_item = soup.find('img', alt=re.compile("Current Issue"), src=True)
-
-        if link_item:
-           cover_url = 'http://hbr.org' + link_item['src']
-
-        return cover_url
-
-

recipes/list_apart.recipe

@@ -1,33 +1,23 @@
-# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai
+# vim:fileencoding=UTF-8
+from __future__ import unicode_literals
 from calibre.web.feeds.news import BasicNewsRecipe
 
 class AListApart (BasicNewsRecipe):
-   __author__ = u'Marc Busqué <marc@lamarciana.com>'
+   __author__ = 'Marc Busqué <marc@lamarciana.com>'
    __url__ = 'http://www.lamarciana.com'
-   __version__ = '1.0'
+   __version__ = '2.0'
    __license__   = 'GPL v3'
-   __copyright__ = u'2012, Marc Busqué <marc@lamarciana.com>'
+   __copyright__ = '2012, Marc Busqué <marc@lamarciana.com>'
    title = u'A List Apart'
-   description = u'A List Apart Magazine (ISSN: 1534-0295) explores the design, development, and meaning of web content, with a special focus on web standards and best practices.'
+   description = u'A List Apart Magazine (ISSN: 1534-0295) explores the design, development, and meaning of web content, with a special focus on web standards and best practices. This recipe retrieve articles and columns.'
    language = 'en'
    tags = 'web development, software'
    oldest_article = 120
    remove_empty_feeds = True
-   no_stylesheets = True
    encoding = 'utf8'
    cover_url = u'http://alistapart.com/pix/alalogo.gif'
-   keep_only_tags = [
+   extra_css = u'img {max-width: 100%; display: block; margin: auto;}'
-         dict(name='div', attrs={'id': 'content'})
-         ]
-   remove_tags = [
-         dict(name='ul', attrs={'id': 'metastuff'}),
-         dict(name='div', attrs={'class': 'discuss'}),
-         dict(name='div', attrs={'class': 'discuss'}),
-         dict(name='div', attrs={'id': 'learnmore'}),
-         ]
-   remove_attributes = ['border', 'cellspacing', 'align', 'cellpadding', 'colspan', 'valign', 'vspace', 'hspace', 'alt', 'width', 'height']
-   extra_css = u'img {max-width: 100%; display: block; margin: auto;} #authorbio img {float: left; margin-right: 2%;}'
 
    feeds = [
-         (u'A List Apart', u'http://www.alistapart.com/site/rss'),
+         (u'A List Apart', u'http://feeds.feedburner.com/alistapart/abridged'),
          ]

recipes/metro_uk.recipe

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

recipes/new_yorker.recipe

@@ -1,64 +1,44 @@
+#!/usr/bin/env  python
+# -*- coding: utf-8 -*-
 __license__   = 'GPL v3'
-__copyright__ = '2008-2013, Darko Miletic <darko.miletic at gmail.com>'
-'''
-newyorker.com
-'''
 
+'''
+www.canada.com
+'''
+import re
 from calibre.web.feeds.news import BasicNewsRecipe
 
+from calibre.ebooks.BeautifulSoup import BeautifulStoneSoup
+
 class NewYorker(BasicNewsRecipe):
-    title                 = 'The New Yorker'
-    __author__            = 'Darko Miletic'
-    description           = 'The best of US journalism'
-    oldest_article        = 15
-    language              = 'en'
-    max_articles_per_feed = 100
-    no_stylesheets        = True
-    use_embedded_content  = False
-    publisher             = 'Conde Nast Publications'
-    category              = 'news, politics, USA'
-    encoding              = 'cp1252'
-    publication_type      = 'magazine'
-    masthead_url          = 'http://www.newyorker.com/css/i/hed/logo.gif'
-    extra_css             = """
-                                body {font-family: "Times New Roman",Times,serif}
-                                .articleauthor{color: #9F9F9F;
-                                               font-family: Arial, sans-serif;
-                                               font-size: small;
-                                               text-transform: uppercase}
-                                .rubric,.dd,h6#credit{color: #CD0021;
-                                        font-family: Arial, sans-serif;
-                                        font-size: small;
-                                        text-transform: uppercase}
-                                .descender:first-letter{display: inline; font-size: xx-large; font-weight: bold}
-                                .dd,h6#credit{color: gray}
-                                .c{display: block}
-                                .caption,h2#articleintro{font-style: italic}
-                                .caption{font-size: small}
-                            """
 
-    conversion_options = {
-                          'comment'   : description
-                        , 'tags'      : category
-                        , 'publisher' : publisher
-                        , 'language'  : language
-                        }
 
-    keep_only_tags = [dict(name='div', attrs={'id':'pagebody'})]
+    title = u'New Yorker Magazine'
-    remove_tags    = [
+    newyorker_prefix = 'http://m.newyorker.com'
-                         dict(name=['meta','iframe','base','link','embed','object'])
+    description = u'Content from the New Yorker website'
-                        ,dict(attrs={'class':['utils','socialUtils','articleRailLinks','icons','social-utils-top','entry-keywords','entry-categories','utilsPrintEmail'] })
+    fp_tag = 'CAN_TC'
-                        ,dict(attrs={'id':['show-header','show-footer'] })
-                     ]
-    remove_tags_after = dict(attrs={'class':'entry-content'}) 
-    remove_attributes = ['lang']
-    feeds             = [(u'The New Yorker', u'http://www.newyorker.com/services/mrss/feeds/everything.xml')]
 
-    def print_version(self, url):
+    masthead_url = 'http://www.newyorker.com/images/elements/print/newyorker_printlogo.gif'
-        return url + '?printable=true&currentPage=all'
 
-    def image_url_processor(self, baseurl, url):
+    compress_news_images = True
-        return url.strip()
+    compress_news_images_auto_size = 8
+    scale_news_images_to_device = False
+    scale_news_images = (768, 1024)
+
+    url_list = []
+    language = 'en'
+    __author__ = 'Nick Redding'
+    no_stylesheets = True
+    timefmt =  ' [%b %d]'
+    encoding = 'utf-8'
+    extra_css = '''
+                .byline { font-size:xx-small; font-weight: bold;}
+                h3 { margin-bottom: 6px; }
+                .caption { font-size: xx-small; font-style: italic; font-weight: normal; }
+                '''
+    keep_only_tags = [dict(name='div', attrs={'id':re.compile('pagebody')})]
+
+    remove_tags = [{'class':'socialUtils'},{'class':'entry-keywords'}]
 
     def get_cover_url(self):
         cover_url = "http://www.newyorker.com/images/covers/1925/1925_02_21_p233.jpg"
@@ -68,13 +48,233 @@ class NewYorker(BasicNewsRecipe):
            cover_url = 'http://www.newyorker.com' + cover_item.div.img['src'].strip()
         return cover_url
 
-    def preprocess_html(self, soup):
+    def fixChars(self,string):
-        for item in soup.findAll(style=True):
+        # Replace lsquo (\x91)
-            del item['style']
+        fixed = re.sub("\x91","‘",string)
-        auth = soup.find(attrs={'id':'articleauthor'})
+        # Replace rsquo (\x92)
-        if auth:
+        fixed = re.sub("\x92","’",fixed)
-           alink = auth.find('a')
+        # Replace ldquo (\x93)
-           if alink and alink.string is not None:
+        fixed = re.sub("\x93","“",fixed)
-              txt = alink.string
+        # Replace rdquo (\x94)
-              alink.replaceWith(txt)
+        fixed = re.sub("\x94","”",fixed)
+        # Replace ndash (\x96)
+        fixed = re.sub("\x96","–",fixed)
+        # Replace mdash (\x97)
+        fixed = re.sub("\x97","—",fixed)
+        fixed = re.sub("&#x2019;","’",fixed)
+        return fixed
+
+    def massageNCXText(self, description):
+        # Kindle TOC descriptions won't render certain characters
+        if description:
+            massaged = unicode(BeautifulStoneSoup(description, convertEntities=BeautifulStoneSoup.HTML_ENTITIES))
+            # Replace '&' with '&'
+            massaged = re.sub("&","&", massaged)
+            return self.fixChars(massaged)
+        else:
+            return description
+
+    def populate_article_metadata(self, article, soup, first):
+        if first:
+            picdiv = soup.find('body').find('img')
+            if picdiv is not None:
+                self.add_toc_thumbnail(article,re.sub(r'links\\link\d+\\','',picdiv['src']))
+        xtitle = article.text_summary.strip()
+        if len(xtitle) == 0:
+            desc = soup.find('meta',attrs={'property':'og:description'})
+            if desc is not None:
+                article.summary = article.text_summary = desc['content']
+        shortparagraph = ""
+##        try:
+        if len(article.text_summary.strip()) == 0:
+            articlebodies = soup.findAll('div',attrs={'class':'entry-content'})
+            if articlebodies:
+                for articlebody in articlebodies:
+                    if articlebody:
+                        paras = articlebody.findAll('p')
+                        for p in paras:
+                            refparagraph = self.massageNCXText(self.tag_to_string(p,use_alt=False)).strip()
+                            #account for blank paragraphs and short paragraphs by appending them to longer ones
+                            if len(refparagraph) > 0:
+                                if len(refparagraph) > 70: #approximately one line of text
+                                    newpara = shortparagraph + refparagraph
+                                    article.summary = article.text_summary = newpara.strip()
+                                    return
+                                else:
+                                    shortparagraph = refparagraph + " "
+                                    if shortparagraph.strip().find(" ") == -1 and not shortparagraph.strip().endswith(":"):
+                                        shortparagraph = shortparagraph + "- "
+        else:
+            article.summary = article.text_summary = self.massageNCXText(article.text_summary)
+##        except:
+##            self.log("Error creating article descriptions")
+##            return
+
+
+    def strip_anchors(self,soup):
+        paras = soup.findAll(True)
+        for para in paras:
+            aTags = para.findAll('a')
+            for a in aTags:
+                if a.img is None:
+                    a.replaceWith(a.renderContents().decode('cp1252','replace'))
         return soup
+
+    def preprocess_html(self,soup):
+        dateline = soup.find('div','published')
+        byline = soup.find('div','byline')
+        title = soup.find('h1','entry-title')
+        if title is None:
+            return self.strip_anchors(soup)
+        if byline is None:
+            title.append(dateline)
+            return self.strip_anchors(soup)
+        byline.append(dateline)
+        return self.strip_anchors(soup)
+
+    def load_global_nav(self,soup):
+        seclist = []
+        ul = soup.find('ul',attrs={'id':re.compile('global-nav-menu')})
+        if ul is not None:
+            for li in ul.findAll('li'):
+                if li.a is not None:
+                    securl = li.a['href']
+                    if securl != '/' and securl != '/magazine' and securl.startswith('/'):
+                        seclist.append((self.tag_to_string(li.a),self.newyorker_prefix+securl))
+        return seclist
+
+    def exclude_url(self,url):
+        if url in self.url_list:
+            return True
+        if not url.endswith('html'):
+            return True
+        if 'goings-on-about-town-app' in url:
+            return True
+        if 'something-to-be-thankful-for' in url:
+            return True
+        if '/shouts/' in url:
+            return True
+        if 'out-loud' in url:
+            return True
+        if '/rss/' in url:
+            return True
+        if '/video-' in url:
+            return True
+        self.url_list.append(url)
+        return False
+
+
+    def load_index_page(self,soup):
+        article_list = []
+        for div in soup.findAll('div',attrs={'class':re.compile('^rotator')}):
+            h2 = div.h2
+            if h2 is not None:
+                a = h2.a
+                if a is not None:
+                    url = a['href']
+                    if not self.exclude_url(url):
+                        if url.startswith('/'):
+                            url = self.newyorker_prefix+url
+                        byline = h2.span
+                        if byline is not None:
+                            author = self.tag_to_string(byline)
+                            if author.startswith('by '):
+                                author.replace('by ','')
+                            byline.extract()
+                        else:
+                            author = ''
+                        if h2.br is not None:
+                            h2.br.replaceWith(' ')
+                        title = self.tag_to_string(h2)
+                        desc = div.find(attrs={'class':['rotator-ad-body','feature-blurb-text']})
+                        if desc is not None:
+                            description = self.tag_to_string(desc)
+                        else:
+                            description = ''
+                        article_list.append(dict(title=title,url=url,date='',description=description,author=author,content=''))
+                        ul = div.find('ul','feature-blurb-links')
+                        if ul is not None:
+                            for li in ul.findAll('li'):
+                                a = li.a
+                                if a is not None:
+                                    url = a['href']
+                                    if not self.exclude_url(url):
+                                        if url.startswith('/'):
+                                            url = self.newyorker_prefix+url
+                                        if a.br is not None:
+                                            a.br.replaceWith(' ')
+                                        title = '>>'+self.tag_to_string(a)
+                                        article_list.append(dict(title=title,url=url,date='',description='',author='',content=''))
+        for h3 in soup.findAll('h3','header'):
+            a = h3.a
+            if a is not None:
+                url = a['href']
+                if not self.exclude_url(url):
+                    if url.startswith('/'):
+                        url = self.newyorker_prefix+url
+                    byline = h3.span
+                    if byline is not None:
+                        author = self.tag_to_string(byline)
+                        if author.startswith('by '):
+                            author = author.replace('by ','')
+                        byline.extract()
+                    else:
+                        author = ''
+                    if h3.br is not None:
+                        h3.br.replaceWith(' ')
+                    title = self.tag_to_string(h3).strip()
+                    article_list.append(dict(title=title,url=url,date='',description='',author=author,content=''))
+        return article_list
+
+    def load_global_section(self,securl):
+        article_list = []
+        try:
+            soup = self.index_to_soup(securl)
+        except:
+            return article_list
+        if '/blogs/' not in securl:
+            return self.load_index_page(soup)
+        for div in soup.findAll('div',attrs={'id':re.compile('^entry')}):
+            h3 = div.h3
+            if h3 is not None:
+                a = h3.a
+                if a is not None:
+                    url = a['href']
+                    if not self.exclude_url(url):
+                        if url.startswith('/'):
+                            url = self.newyorker_prefix+url
+                        if h3.br is not None:
+                            h3.br.replaceWith(' ')
+                        title = self.tag_to_string(h3)
+                        article_list.append(dict(title=title,url=url,date='',description='',author='',content=''))
+        return article_list
+
+    def filter_ans(self, ans) :
+        total_article_count = 0
+        idx = 0
+        idx_max = len(ans)-1
+        while idx <= idx_max:
+            if True: #self.verbose
+                self.log("Section %s: %d articles" % (ans[idx][0], len(ans[idx][1])) )
+            for article in ans[idx][1]:
+                total_article_count += 1
+                if True: #self.verbose
+                    self.log("\t%-40.40s... \t%-60.60s..." % (article['title'].encode('cp1252','replace'),
+                              article['url'].replace('http://m.newyorker.com','').encode('cp1252','replace')))
+            idx = idx+1
+        self.log( "Queued %d articles" % total_article_count )
+        return ans
+
+
+    def parse_index(self):
+        ans = []
+        try:
+            soup = self.index_to_soup(self.newyorker_prefix)
+        except:
+            return ans
+        seclist = self.load_global_nav(soup)
+        ans.append(('Front Page',self.load_index_page(soup)))
+        for (sectitle,securl) in seclist:
+            ans.append((sectitle,self.load_global_section(securl)))
+        return self.filter_ans(ans)
+

recipes/nme.recipe

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

recipes/singtaohk.recipe

@@ -1,30 +1,30 @@
+# vim:fileencoding=UTF-8
+from __future__ import unicode_literals
 __license__   = 'GPL v3'
-__copyright__ = '2011, Eddie Lau'
+__copyright__ = '2011-2013, Eddie Lau'
 
 # data source: normal, mobile
 __Source__ = 'mobile'
 # please replace the following "True" with "False". (Default: True)
 __MakePeriodical__ = True
 # Turn below to True if your device supports display of CJK titles (Default: False)
-__UseChineseTitle__ = False
+__UseChineseTitle__ = True
 # Set it to False if you want to skip images (Default: True)
 __KeepImages__ = True
 # Set it to True if you want to include a summary in Kindle's article view (Default: False)
-__IncludeSummary__ = False
+__IncludeSummary__ = True
 # Set it to True if you want thumbnail images in Kindle's article view (Default: True)
 __IncludeThumbnails__ = True
 
 
 '''
 Change Log:
+2013/03/31 -- fix cover retrieval code and heading size, and remove   in summary
 2011/12/29 -- first version done
-TODO:
-* use alternative source at http://m.singtao.com/index.php
 '''
 
 from calibre.utils.date import now as nowf
 import os, datetime, re
-from datetime import date
 from calibre.web.feeds.recipes import BasicNewsRecipe
 from contextlib import nested
 from calibre.ebooks.BeautifulSoup import BeautifulSoup
@@ -41,7 +41,7 @@ class STHKRecipe(BasicNewsRecipe):
         title   = 'Sing Tao Daily - Hong Kong'
     description = 'Hong Kong Chinese Newspaper (http://singtao.com)'
     category    = 'Chinese, News, Hong Kong'
-    extra_css = 'img {display: block; margin-left: auto; margin-right: auto; margin-top: 10px; margin-bottom: 10px; max-height:90%;} td[class=caption] {font-size:50%;} td[class=bodyhead]{font-weight:bold; font-size:150%;} td[class=stmobheadline]{font-weight:bold; font-size:150%;}'
+    extra_css = 'img {display: block; margin-left: auto; margin-right: auto; margin-top: 10px; margin-bottom: 10px; max-height:90%;} td[class=caption] {font-size:50%;} td[class=bodyhead]{font-weight:bold; font-size:150%;} td[class=stmobheadline]{font-weight:bold; font-size:200%;}'
     masthead_url = 'http://upload.wikimedia.org/wikipedia/en/d/dd/Singtao-usa.png'
     if __Source__ == 'normal':
         keep_only_tags = [dict(name='td', attrs={'class':['bodyhead','bodytext']})]
@@ -96,17 +96,13 @@ class STHKRecipe(BasicNewsRecipe):
         return self.get_dtlocal().strftime("%d")
 
     def get_cover_url(self):
-        #cover = 'http://singtao.com/media/a/a(2660).jpg'  # for 2011/12/29
+        soup = self.index_to_soup('http://m.singtao.com/')
-        base = 2660
+        cover = soup.find(attrs={'class':'special'}).get('src', False)
-        todaydate = date(int(self.get_fetchyear()), int(self.get_fetchmonth()), int(self.get_fetchday()))
-        diff = todaydate - date(2011, 12, 29)
-        base = base + int(diff.total_seconds()/(3600*24))
-        cover = 'http://singtao.com/media/a/a(' + str(base) +').jpg'
         br = BasicNewsRecipe.get_browser(self)
         try:
             br.open(cover)
         except:
-            cover = 'http://singtao.com/images/stlogo.gif'
+            cover = None
         return cover
 
     def parse_index(self):
@@ -289,11 +285,11 @@ class STHKRecipe(BasicNewsRecipe):
                             # the text may or may not be enclosed in <p></p> tag
                             paras = articlebody.findAll('p')
                             if not paras:
-                            	paras = articlebody
+                                paras = articlebody
                             textFound = False
                             for p in paras:
                                 if not textFound:
-                                    summary_candidate = self.tag_to_string(p).strip()
+                                    summary_candidate = self.tag_to_string(p).strip().replace('&nbsp;', '')
                                     if len(summary_candidate) > 0:
                                         summary_candidate = summary_candidate.replace(u'(\u661f\u5cf6\u65e5\u5831\u5831\u9053)', '', 1)
                                         article.summary = article.text_summary = summary_candidate
@@ -489,3 +485,4 @@ class STHKRecipe(BasicNewsRecipe):
 
 
 
+

recipes/sportowefakty.recipe

@@ -2,6 +2,7 @@
 
 __license__ = 'GPL v3'
 
+import re
 from calibre.web.feeds.news import BasicNewsRecipe
 from calibre.utils.magick import Image
 

recipes/the_sun.recipe

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

recipes/theonion.recipe

@@ -36,47 +36,21 @@ class TheOnion(BasicNewsRecipe):
                         , 'publisher': publisher
                         , 'language' : language
                         }
-
+    keep_only_tags = [dict(name='article', attrs={'class':'full-article'})]
-    keep_only_tags = [
-                         dict(name='h2', attrs={'class':['section_title','title']})
-                        ,dict(attrs={'class':['main_image','meta','article_photo_lead','article_body']})
-                        ,dict(attrs={'id':['entries']})
-                     ]
-    remove_attributes=['lang','rel']
-    remove_tags_after = dict(attrs={'class':['article_body','feature_content']})
     remove_tags = [
-                     dict(name=['object','link','iframe','base','meta'])
+        dict(name=['nav', 'aside', 'section', 'meta']),
-                    ,dict(name='div', attrs={'class':['toolbar_side','graphical_feature','toolbar_bottom']})
+        {'attrs':{'class':lambda x: x and ('share-tools' in x or 'ad-zone' in x)}},
-                    ,dict(name='div', attrs={'id':['recent_slider','sidebar','pagination','related_media']})
+    ]
-                  ]
-
 
     feeds = [
               (u'Daily'  , u'http://feeds.theonion.com/theonion/daily' )
              ,(u'Sports' , u'http://feeds.theonion.com/theonion/sports' )
             ]
 
-    def get_article_url(self, article):
+    def preprocess_html(self, soup, *args):
-        artl = BasicNewsRecipe.get_article_url(self, article)
+        for img in soup.findAll('img', attrs={'data-src':True}):
-        if artl.startswith('http://www.theonion.com/audio/'):
+            if img['data-src']:
-           artl = None
+                img['src'] = img['data-src']
-        return artl
-
-    def preprocess_html(self, soup):
-        for item in soup.findAll(style=True):
-            del item['style']
-        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 = []
-                  if not limg.has_key('alt'):
-                     limg['alt'] = 'image'
-               else:
-                   str = self.tag_to_string(item)
-                   item.replaceWith(str)
         return soup
+
+

recipes/universe_today.recipe

@@ -0,0 +1,17 @@
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class UniverseToday(BasicNewsRecipe):
+    title                 = u'Universe Today'
+    language = 'en'
+    description           = u'Space and astronomy news.'
+    __author__ = 'seird'
+    publisher             = u'universetoday.com'
+    category              = 'science, astronomy, news, rss'
+    oldest_article = 7
+    max_articles_per_feed = 40
+    auto_cleanup = True
+    no_stylesheets = True
+    use_embedded_content = False
+    remove_empty_feeds = True
+
+    feeds          = [(u'Universe Today', u'http://feeds.feedburner.com/universetoday/pYdq')]

recipes/vic_times.recipe

@@ -6,17 +6,62 @@ __license__   = 'GPL v3'
 www.canada.com
 '''
 import re
-from calibre.web.feeds.recipes import BasicNewsRecipe
+from calibre.web.feeds.news import BasicNewsRecipe
+
 from calibre.ebooks.BeautifulSoup import Tag, BeautifulStoneSoup
 
 
 class TimesColonist(BasicNewsRecipe):
 
+    # Customization -- remove sections you don't want.
+    # If your e-reader is an e-ink Kindle and your output profile is
+    # set properly this recipe will not include images because the
+    # resulting file is too large. If you have one of these and want
+    # images you can set kindle_omit_images = False
+    # and remove sections (typically the e-ink Kindles will
+    # work with about a dozen of these, but your mileage may vary).
+
+    kindle_omit_images = True
+
+    section_list = [
+        ('','Web Front Page'),
+        ('news/','News Headlines'),
+        ('news/b-c/','BC News'),
+        ('news/national/','National News'),
+        ('news/world/','World News'),
+        ('opinion/','Opinion'),
+        ('opinion/letters/','Letters'),
+        ('business/','Business'),
+        ('business/money/','Money'),
+        ('business/technology/','Technology'),
+        ('business/working/','Working'),
+        ('sports/','Sports'),
+        ('sports/hockey/','Hockey'),
+        ('sports/football/','Football'),
+        ('sports/basketball/','Basketball'),
+        ('sports/golf/','Golf'),
+        ('entertainment/','entertainment'),
+        ('entertainment/go/','Go!'),
+        ('entertainment/music/','Music'),
+        ('entertainment/books/','Books'),
+        ('entertainment/Movies/','Movies'),
+        ('entertainment/television/','Television'),
+        ('life/','Life'),
+        ('life/health/','Health'),
+        ('life/travel/','Travel'),
+        ('life/driving/','Driving'),
+        ('life/homes/','Homes'),
+        ('life/food-drink/','Food & Drink')
+    ]
+
     title = u'Victoria Times Colonist'
     url_prefix = 'http://www.timescolonist.com'
     description = u'News from Victoria, BC'
     fp_tag = 'CAN_TC'
 
+    masthead_url = 'http://www.timescolonist.com/gmg/img/global/logoTimesColonist.png'
+
+
     url_list = []
     language = 'en_CA'
     __author__ = 'Nick Redding'
@@ -29,15 +74,21 @@ class TimesColonist(BasicNewsRecipe):
                 .caption { font-size: xx-small; font-style: italic; font-weight: normal; }
                 '''
     keep_only_tags = [dict(name='div', attrs={'class':re.compile('main.content')})]
-    remove_tags = [{'class':'comments'},
-                   {'id':'photocredit'},
-                   dict(name='div', attrs={'class':re.compile('top.controls')}),
-                   dict(name='div', attrs={'class':re.compile('social')}),
-                   dict(name='div', attrs={'class':re.compile('tools')}),
-                   dict(name='div', attrs={'class':re.compile('bottom.tools')}),
-                   dict(name='div', attrs={'class':re.compile('window')}),
-                   dict(name='div', attrs={'class':re.compile('related.news.element')})]
 
+    def __init__(self, options, log, progress_reporter):
+        self.remove_tags = [{'class':'comments'},
+                       {'id':'photocredit'},
+                       dict(name='div', attrs={'class':re.compile('top.controls')}),
+                       dict(name='div', attrs={'class':re.compile('^comments')}),
+                       dict(name='div', attrs={'class':re.compile('social')}),
+                       dict(name='div', attrs={'class':re.compile('tools')}),
+                       dict(name='div', attrs={'class':re.compile('bottom.tools')}),
+                       dict(name='div', attrs={'class':re.compile('window')}),
+                       dict(name='div', attrs={'class':re.compile('related.news.element')})]
+        print("PROFILE NAME = "+options.output_profile.short_name)
+        if self.kindle_omit_images and options.output_profile.short_name in ['kindle', 'kindle_dx', 'kindle_pw']:
+            self.remove_tags.append(dict(name='div', attrs={'class':re.compile('image-container')}))
+        BasicNewsRecipe.__init__(self, options, log, progress_reporter)
 
     def get_cover_url(self):
         from datetime import timedelta, date
@@ -122,7 +173,6 @@ class TimesColonist(BasicNewsRecipe):
     def preprocess_html(self,soup):
         byline = soup.find('p',attrs={'class':re.compile('ancillary')})
         if byline is not None:
-            byline.find('a')
             authstr = self.tag_to_string(byline,False)
             authstr = re.sub('/ *Times Colonist','/',authstr, flags=re.IGNORECASE)
             authstr = re.sub('BY */','',authstr, flags=re.IGNORECASE)
@@ -149,9 +199,10 @@ class TimesColonist(BasicNewsRecipe):
         atag = htag.a
         if atag is not None:
             url = atag['href']
-            #print("Checking "+url)
+            url = url.strip()
-            if atag['href'].startswith('/'):
+            # print("Checking >>"+url+'<<\n\r')
-                url = self.url_prefix+atag['href']
+            if url.startswith('/'):
+                url = self.url_prefix+url
             if url in self.url_list:
                 return
             self.url_list.append(url)
@@ -171,10 +222,10 @@ class TimesColonist(BasicNewsRecipe):
             if dtag is not None:
                 description = self.tag_to_string(dtag,False)
             article_list.append(dict(title=title,url=url,date='',description=description,author='',content=''))
-            #print(sectitle+title+": description = "+description+" URL="+url)
+            print(sectitle+title+": description = "+description+" URL="+url+'\n\r')
 
     def add_section_index(self,ans,securl,sectitle):
-        print("Add section url="+self.url_prefix+'/'+securl)
+        print("Add section url="+self.url_prefix+'/'+securl+'\n\r')
         try:
             soup = self.index_to_soup(self.url_prefix+'/'+securl)
         except:
@@ -193,33 +244,7 @@ class TimesColonist(BasicNewsRecipe):
 
     def parse_index(self):
         ans = []
-        ans = self.add_section_index(ans,'','Web Front Page')
+        for (url,title) in self.section_list:
-        ans = self.add_section_index(ans,'news/','News Headlines')
+            ans = self.add_section_index(ans,url,title)
-        ans = self.add_section_index(ans,'news/b-c/','BC News')
-        ans = self.add_section_index(ans,'news/national/','Natioanl News')
-        ans = self.add_section_index(ans,'news/world/','World News')
-        ans = self.add_section_index(ans,'opinion/','Opinion')
-        ans = self.add_section_index(ans,'opinion/letters/','Letters')
-        ans = self.add_section_index(ans,'business/','Business')
-        ans = self.add_section_index(ans,'business/money/','Money')
-        ans = self.add_section_index(ans,'business/technology/','Technology')
-        ans = self.add_section_index(ans,'business/working/','Working')
-        ans = self.add_section_index(ans,'sports/','Sports')
-        ans = self.add_section_index(ans,'sports/hockey/','Hockey')
-        ans = self.add_section_index(ans,'sports/football/','Football')
-        ans = self.add_section_index(ans,'sports/basketball/','Basketball')
-        ans = self.add_section_index(ans,'sports/golf/','Golf')
-        ans = self.add_section_index(ans,'entertainment/','entertainment')
-        ans = self.add_section_index(ans,'entertainment/go/','Go!')
-        ans = self.add_section_index(ans,'entertainment/music/','Music')
-        ans = self.add_section_index(ans,'entertainment/books/','Books')
-        ans = self.add_section_index(ans,'entertainment/Movies/','movies')
-        ans = self.add_section_index(ans,'entertainment/television/','Television')
-        ans = self.add_section_index(ans,'life/','Life')
-        ans = self.add_section_index(ans,'life/health/','Health')
-        ans = self.add_section_index(ans,'life/travel/','Travel')
-        ans = self.add_section_index(ans,'life/driving/','Driving')
-        ans = self.add_section_index(ans,'life/homes/','Homes')
-        ans = self.add_section_index(ans,'life/food-drink/','Food & Drink')
         return ans
 

recipes/wysokie_obcasy.recipe

@@ -1,6 +1,5 @@
 #!/usr/bin/env python
 __license__ = 'GPL v3'
-import re
 
 from calibre.web.feeds.news import BasicNewsRecipe
 
@@ -51,8 +50,8 @@ class WysokieObcasyRecipe(BasicNewsRecipe):
         printVerString=articleURL1 + ',' + articleURL2
         s=  baseURL + subPath + printVerString + '.html'
         return s
-        
+
     def get_cover_url(self):
         soup = self.index_to_soup('http://www.wysokieobcasy.pl/wysokie-obcasy/0,0.html')
         self.cover_url = soup.find(attrs={'class':'holder_cr'}).find('img')['src']
-        return getattr(self, 'cover_url', self.cover_url)
+        return getattr(self, 'cover_url', self.cover_url)

resources/templates/rtf.xsl

@@ -357,7 +357,7 @@
        <xsl:apply-templates/>
    </xsl:template>
 
-       <xsl:template match="rtf:table">
+    <xsl:template match="rtf:table">
         <xsl:element name="table">
             <xsl:attribute name="id">
                 <xsl:value-of select="generate-id(.)"/>
@@ -390,7 +390,6 @@
 
 
     <xsl:output method = "xml"/>
-
     <xsl:key name="style-types" match="rtf:paragraph-definition" use="@style-number"/>
 
 
@@ -415,13 +414,11 @@
     </xsl:template>
 
     <xsl:template match="rtf:page-break">
-        <xsl:element name="br">
+        <br style = "page-break-after:always"/>
-            <xsl:attribute name="style">page-break-after:always</xsl:attribute>
-        </xsl:element>
     </xsl:template>
     
     <xsl:template match="rtf:hardline-break">
-        <xsl:element name="br"/>
+        <br/>
     </xsl:template>
 
     <xsl:template match="rtf:rtf-definition|rtf:font-table|rtf:color-table|rtf:style-table|rtf:page-definition|rtf:list-table|rtf:override-table|rtf:override-list|rtf:list-text"/>
@@ -445,7 +442,7 @@
     </xsl:template>
 
     <xsl:template match = "rtf:field-block">
-      <xsl:apply-templates/>
+        <xsl:apply-templates/>
     </xsl:template>
 
     <xsl:template match = "rtf:field[@type='hyperlink']">
@@ -472,9 +469,7 @@
     </xsl:template>
 
     <xsl:template match="rtf:pict">
-        <xsl:element name="img">
+        <img src = "{@num}"/>
-            <xsl:attribute name="src"><xsl:value-of select="@num" /></xsl:attribute>
-        </xsl:element>
     </xsl:template>
 
     <xsl:template match="*">

setup/installer/linux/freeze2.py

@@ -47,6 +47,10 @@ binary_includes = [
                 '/usr/lib/libgthread-2.0.so.0',
                 '/usr/lib/libpng14.so.14',
                 '/usr/lib/libexslt.so.0',
+                # Ensure that libimobiledevice is compiled against openssl, not gnutls
+                '/usr/lib/libimobiledevice.so.3',
+                '/usr/lib/libusbmuxd.so.2',
+                '/usr/lib/libplist.so.1',
                 MAGICK_PREFIX+'/lib/libMagickWand.so.5',
                 MAGICK_PREFIX+'/lib/libMagickCore.so.5',
                 '/usr/lib/libgcrypt.so.11',

setup/installer/osx/app/main.py

@@ -399,7 +399,8 @@ class Py2App(object):
     @flush
     def add_fontconfig(self):
         info('\nAdding fontconfig')
-        for x in ('fontconfig.1', 'freetype.6', 'expat.1'):
+        for x in ('fontconfig.1', 'freetype.6', 'expat.1',
+                  'plist.1', 'usbmuxd.2', 'imobiledevice.3'):
             src = os.path.join(SW, 'lib', 'lib'+x+'.dylib')
             self.install_dylib(src)
         dst = os.path.join(self.resources_dir, 'fonts')

setup/iso_639/ca.po

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

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, 9, 25)
+numeric_version = (0, 9, 26)
 __version__   = u'.'.join(map(unicode, numeric_version))
 __author__    = u"Kovid Goyal <kovid@kovidgoyal.net>"
 

src/calibre/customize/builtins.py

@@ -757,9 +757,10 @@ from calibre.ebooks.metadata.sources.isbndb import ISBNDB
 from calibre.ebooks.metadata.sources.overdrive import OverDrive
 from calibre.ebooks.metadata.sources.douban import Douban
 from calibre.ebooks.metadata.sources.ozon import Ozon
-# from calibre.ebooks.metadata.sources.google_images import GoogleImages
+from calibre.ebooks.metadata.sources.google_images import GoogleImages
+from calibre.ebooks.metadata.sources.big_book_search import BigBookSearch
 
-plugins += [GoogleBooks, Amazon, Edelweiss, OpenLibrary, ISBNDB, OverDrive, Douban, Ozon]
+plugins += [GoogleBooks, GoogleImages, Amazon, Edelweiss, OpenLibrary, ISBNDB, OverDrive, Douban, Ozon, BigBookSearch]
 
 # }}}
 

src/calibre/customize/ui.py

@@ -91,7 +91,7 @@ def restore_plugin_state_to_default(plugin_or_name):
     config['enabled_plugins'] = ep
 
 default_disabled_plugins = set([
-    'Overdrive', 'Douban Books', 'OZON.ru', 'Edelweiss', 'Google Images',
+    'Overdrive', 'Douban Books', 'OZON.ru', 'Edelweiss', 'Google Images', 'Big Book Search',
 ])
 
 def is_disabled(plugin):

src/calibre/ebooks/conversion/plugins/txt_input.py

@@ -97,6 +97,12 @@ class TXTInput(InputFormatPlugin):
         if not ienc:
             ienc = 'utf-8'
             log.debug('No input encoding specified and could not auto detect using %s' % ienc)
+        # Remove BOM from start of txt as its presence can confuse markdown
+        import codecs
+        for bom in (codecs.BOM_UTF16_LE, codecs.BOM_UTF16_BE, codecs.BOM_UTF8, codecs.BOM_UTF32_LE, codecs.BOM_UTF32_BE):
+            if txt.startswith(bom):
+                txt = txt[len(bom):]
+                break
         txt = txt.decode(ienc, 'replace')
 
         # Replace entities

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

@@ -132,7 +132,7 @@ class Worker(Thread): # Get details {{{
                  text()="Détails sur le produit" or \
                  text()="Detalles del producto" or \
                  text()="Detalhes do produto" or \
-                 text()="登録情報"]/../div[@class="content"]
+                 starts-with(text(), "登録情報")]/../div[@class="content"]
             '''
         # Editor: is for Spanish
         self.publisher_xpath = '''
@@ -235,6 +235,12 @@ class Worker(Thread): # Get details {{{
             msg = 'Failed to parse amazon details page: %r'%self.url
             self.log.exception(msg)
             return
+        if self.domain == 'jp':
+            for a in root.xpath('//a[@href]'):
+                if 'black-curtain-redirect.html' in a.get('href'):
+                    self.url = 'http://amazon.co.jp'+a.get('href')
+                    self.log('Black curtain redirect found, following')
+                    return self.get_details()
 
         errmsg = root.xpath('//*[@id="errorMessage"]')
         if errmsg:
@@ -252,8 +258,8 @@ class Worker(Thread): # Get details {{{
             self.log.exception('Error parsing asin for url: %r'%self.url)
             asin = None
         if self.testing:
-            import tempfile
+            import tempfile, uuid
-            with tempfile.NamedTemporaryFile(prefix=asin + '_',
+            with tempfile.NamedTemporaryFile(prefix=(asin or str(uuid.uuid4()))+ '_',
                     suffix='.html', delete=False) as f:
                 f.write(raw)
             print ('Downloaded html for', asin, 'saved in', f.name)
@@ -499,7 +505,7 @@ class Worker(Thread): # Get details {{{
     def parse_language(self, pd):
         for x in reversed(pd.xpath(self.language_xpath)):
             if x.tail:
-                raw = x.tail.strip()
+                raw = x.tail.strip().partition(',')[0].strip()
                 ans = self.lang_map.get(raw, None)
                 if ans:
                     return ans
@@ -1004,6 +1010,11 @@ if __name__ == '__main__': # tests {{{
     ] # }}}
 
     jp_tests = [ # {{{
+            ( # Adult filtering test
+             {'identifiers':{'isbn':'4799500066'}},
+             [title_test(u'Ｂｉｔｃｈ Ｔｒａｐ'),]
+            ),
+
             ( # isbn -> title, authors
                 {'identifiers':{'isbn': '9784101302720' }},
                 [title_test(u'精霊の守り人',

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

@@ -31,7 +31,7 @@ msprefs.defaults['find_first_edition_date'] = False
 # Google covers are often poor quality (scans/errors) but they have high
 # resolution, so they trump covers from better sources. So make sure they
 # are only used if no other covers are found.
-msprefs.defaults['cover_priorities'] = {'Google':2, 'Google Images':2}
+msprefs.defaults['cover_priorities'] = {'Google':2, 'Google Images':2, 'Big Book Search':2}
 
 def create_log(ostream=None):
     from calibre.utils.logging import ThreadSafeLog, FileStream
@@ -429,6 +429,40 @@ class Source(Plugin):
             mi.tags = list(map(fixcase, mi.tags))
         mi.isbn = check_isbn(mi.isbn)
 
+    def download_multiple_covers(self, title, authors, urls, get_best_cover, timeout, result_queue, abort, log, prefs_name='max_covers'):
+        if not urls:
+            log('No images found for, title: %r and authors: %r'%(title, authors))
+            return
+        from threading import Thread
+        import time
+        if prefs_name:
+            urls = urls[:self.prefs[prefs_name]]
+        if get_best_cover:
+            urls = urls[:1]
+        log('Downloading %d covers'%len(urls))
+        workers = [Thread(target=self.download_image, args=(u, timeout, log, result_queue)) for u in urls]
+        for w in workers:
+            w.daemon = True
+            w.start()
+        alive = True
+        start_time = time.time()
+        while alive and not abort.is_set() and time.time() - start_time < timeout:
+            alive = False
+            for w in workers:
+                if w.is_alive():
+                    alive = True
+                    break
+            abort.wait(0.1)
+
+    def download_image(self, url, timeout, log, result_queue):
+        try:
+            ans = self.browser.open_novisit(url, timeout=timeout).read()
+            result_queue.put((self, ans))
+            log('Downloaded cover from: %s'%url)
+        except Exception:
+            self.log.exception('Failed to download cover from: %r'%url)
+
+
     # }}}
 
     # Metadata API {{{

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

@@ -0,0 +1,58 @@
+#!/usr/bin/env python
+# vim:fileencoding=UTF-8
+from __future__ import (unicode_literals, division, absolute_import,
+                        print_function)
+
+__license__   = 'GPL v3'
+__copyright__ = '2013, Kovid Goyal <kovid@kovidgoyal.net>'
+__docformat__ = 'restructuredtext en'
+
+from calibre.ebooks.metadata.sources.base import Source, Option
+
+def get_urls(br, tokens):
+    from urllib import quote_plus
+    from mechanize import Request
+    from lxml import html
+    escaped = [quote_plus(x.encode('utf-8')) for x in tokens if x and x.strip()]
+    q = b'+'.join(escaped)
+    url = 'http://bigbooksearch.com/books/'+q
+    br.open(url).read()
+    req = Request('http://bigbooksearch.com/query.php?SearchIndex=books&Keywords=%s&ItemPage=1'%q)
+    req.add_header('X-Requested-With', 'XMLHttpRequest')
+    req.add_header('Referer', url)
+    raw = br.open(req).read()
+    root = html.fromstring(raw.decode('utf-8'))
+    urls = [i.get('src') for i in root.xpath('//img[@src]')]
+    return urls
+
+class BigBookSearch(Source):
+
+    name = 'Big Book Search'
+    description = _('Downloads multiple book covers from Amazon. Useful to find alternate covers.')
+    capabilities = frozenset(['cover'])
+    config_help_message = _('Configure the Big Book Search plugin')
+    can_get_multiple_covers = True
+    options = (Option('max_covers', 'number', 5, _('Maximum number of covers to get'),
+                      _('The maximum number of covers to process from the search result')),
+    )
+    supports_gzip_transfer_encoding = True
+
+    def download_cover(self, log, result_queue, abort,
+            title=None, authors=None, identifiers={}, timeout=30, get_best_cover=False):
+        if not title:
+            return
+        br = self.browser
+        tokens = tuple(self.get_title_tokens(title)) + tuple(self.get_author_tokens(authors))
+        urls = get_urls(br, tokens)
+        self.download_multiple_covers(title, authors, urls, get_best_cover, timeout, result_queue, abort, log)
+
+def test():
+    from calibre import browser
+    import pprint
+    br = browser()
+    urls = get_urls(br, ['consider', 'phlebas', 'banks'])
+    pprint.pprint(urls)
+
+if __name__ == '__main__':
+    test()
+

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

@@ -18,12 +18,13 @@ from calibre.utils.magick.draw import Image, save_cover_data_to
 
 class Worker(Thread):
 
-    def __init__(self, plugin, abort, title, authors, identifiers, timeout, rq):
+    def __init__(self, plugin, abort, title, authors, identifiers, timeout, rq, get_best_cover=False):
         Thread.__init__(self)
         self.daemon = True
 
         self.plugin = plugin
         self.abort = abort
+        self.get_best_cover = get_best_cover
         self.buf = BytesIO()
         self.log = create_log(self.buf)
         self.title, self.authors, self.identifiers = (title, authors,
@@ -37,7 +38,7 @@ class Worker(Thread):
             try:
                 if self.plugin.can_get_multiple_covers:
                     self.plugin.download_cover(self.log, self.rq, self.abort,
-                        title=self.title, authors=self.authors, get_best_cover=True,
+                        title=self.title, authors=self.authors, get_best_cover=self.get_best_cover,
                         identifiers=self.identifiers, timeout=self.timeout)
                 else:
                     self.plugin.download_cover(self.log, self.rq, self.abort,
@@ -72,7 +73,7 @@ def process_result(log, result):
     return (plugin, width, height, fmt, data)
 
 def run_download(log, results, abort,
-        title=None, authors=None, identifiers={}, timeout=30):
+        title=None, authors=None, identifiers={}, timeout=30, get_best_cover=False):
     '''
     Run the cover download, putting results into the queue :param:`results`.
 
@@ -89,7 +90,7 @@ def run_download(log, results, abort,
     plugins = [p for p in metadata_plugins(['cover']) if p.is_configured()]
 
     rq = Queue()
-    workers = [Worker(p, abort, title, authors, identifiers, timeout, rq) for p
+    workers = [Worker(p, abort, title, authors, identifiers, timeout, rq, get_best_cover=get_best_cover) for p
             in plugins]
     for w in workers:
         w.start()
@@ -163,7 +164,7 @@ def download_cover(log,
     abort = Event()
 
     run_download(log, rq, abort, title=title, authors=authors,
-            identifiers=identifiers, timeout=timeout)
+            identifiers=identifiers, timeout=timeout, get_best_cover=True)
 
     results = []
 

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

@@ -106,6 +106,8 @@ class Worker(Thread): # {{{
             parts = pub.partition(':')[0::2]
             pub = parts[1] or parts[0]
             try:
+                if ', Ship Date:' in pub:
+                    pub = pub.partition(', Ship Date:')[0]
                 q = parse_only_date(pub, assume_utc=True)
                 if q.year != UNDEFINED_DATE:
                     mi.pubdate = q

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

@@ -39,39 +39,11 @@ class GoogleImages(Source):
             title=None, authors=None, identifiers={}, timeout=30, get_best_cover=False):
         if not title:
             return
-        from threading import Thread
-        import time
         timeout = max(60, timeout) # Needs at least a minute
         title = ' '.join(self.get_title_tokens(title))
         author = ' '.join(self.get_author_tokens(authors))
         urls = self.get_image_urls(title, author, log, abort, timeout)
-        if not urls:
+        self.download_multiple_covers(title, authors, urls, get_best_cover, timeout, result_queue, abort, log)
-            log('No images found in Google for, title: %r and authors: %r'%(title, author))
-            return
-        urls = urls[:self.prefs['max_covers']]
-        if get_best_cover:
-            urls = urls[:1]
-        workers = [Thread(target=self.download_image, args=(url, timeout, log, result_queue)) for url in urls]
-        for w in workers:
-            w.daemon = True
-            w.start()
-        alive = True
-        start_time = time.time()
-        while alive and not abort.is_set() and time.time() - start_time < timeout:
-            alive = False
-            for w in workers:
-                if w.is_alive():
-                    alive = True
-                    break
-            abort.wait(0.1)
-
-    def download_image(self, url, timeout, log, result_queue):
-        try:
-            ans = self.browser.open_novisit(url, timeout=timeout).read()
-            result_queue.put((self, ans))
-            log('Downloaded cover from: %s'%url)
-        except Exception:
-            self.log.exception('Failed to download cover from: %r'%url)
 
     def get_image_urls(self, title, author, log, abort, timeout):
         from calibre.utils.ipc.simple_worker import fork_job, WorkerError

src/calibre/ebooks/oeb/polish/toc.py

@@ -262,6 +262,35 @@ def from_links(container):
             toc.remove(child)
     return toc
 
+def find_text(node):
+    LIMIT = 200
+    pat = re.compile(r'\s+')
+    for child in node:
+        if isinstance(child, etree._Element):
+            text = xml2text(child).strip()
+            text = pat.sub(' ', text)
+            if len(text) < 1:
+                continue
+            if len(text) > LIMIT:
+                # Look for less text in a child of this node, recursively
+                ntext = find_text(child)
+                return ntext or (text[:LIMIT] + '...')
+            else:
+                return text
+
+def from_files(container):
+    toc = TOC()
+    for spinepath in container.spine_items:
+        name = container.abspath_to_name(spinepath)
+        root = container.parsed(name)
+        body = XPath('//h:body')(root)
+        if not body:
+            continue
+        text = find_text(body[0])
+        if text:
+            toc.add(text, name)
+    return toc
+
 def add_id(container, name, loc):
     root = container.parsed(name)
     body = root.xpath('//*[local-name()="body"]')[0]

src/calibre/ebooks/oeb/reader.py

@@ -333,8 +333,8 @@ class OEBReader(object):
         guide = self.oeb.guide
         manifest = self.oeb.manifest
         for elem in xpath(opf, '/o2:package/o2:guide/o2:reference'):
-            href = elem.get('href')
+            ref_href = elem.get('href')
-            path = urlnormalize(urldefrag(href)[0])
+            path = urlnormalize(urldefrag(ref_href)[0])
             if path not in manifest.hrefs:
                 corrected_href = None
                 for href in manifest.hrefs:
@@ -342,12 +342,12 @@ class OEBReader(object):
                         corrected_href = href
                         break
                 if corrected_href is None:
-                    self.logger.warn(u'Guide reference %r not found' % href)
+                    self.logger.warn(u'Guide reference %r not found' % ref_href)
                     continue
-                href = corrected_href
+                ref_href = corrected_href
             typ = elem.get('type')
             if typ not in guide:
-                guide.add(typ, elem.get('title'), href)
+                guide.add(typ, elem.get('title'), ref_href)
 
     def _find_ncx(self, opf):
         result = xpath(opf, '/o2:package/o2:spine/@toc')

src/calibre/ebooks/rtf2xml/border_parse.py

@@ -180,5 +180,6 @@ class BorderParse:
         elif 'single' in border_style_list:
             new_border_dict[att] = 'single'
         else:
-            new_border_dict[att] = border_style_list[0]
+            if border_style_list:
+                new_border_dict[att] = border_style_list[0]
         return new_border_dict

src/calibre/gui2/actions/store.py

@@ -88,9 +88,7 @@ class StoreAction(InterfaceAction):
         if row == None:
             error_dialog(self.gui, _('Cannot search'), _('No book selected'), show=True)
             return
-
+        self.search({ 'author': self._get_author(row) })
-        query = 'author:"%s"' % self._get_author(row)
-        self.search(query)
 
     def _get_title(self, row):
         title = ''
@@ -107,18 +105,14 @@ class StoreAction(InterfaceAction):
         if row == None:
             error_dialog(self.gui, _('Cannot search'), _('No book selected'), show=True)
             return
-
+        self.search({ 'title': self._get_title(row) })
-        query = 'title:"%s"' % self._get_title(row)
-        self.search(query)
 
     def search_author_title(self):
         row = self._get_selected_row()
         if row == None:
             error_dialog(self.gui, _('Cannot search'), _('No book selected'), show=True)
             return
-
+        self.search({ 'author': self._get_author(row), 'title': self._get_title(row) })
-        query = 'author:"%s" title:"%s"' % (self._get_author(row), self._get_title(row))
-        self.search(query)
 
     def choose(self):
         from calibre.gui2.store.config.chooser.chooser_dialog import StoreChooserDialog

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

@@ -62,16 +62,20 @@ class SearchDialog(QDialog, Ui_Dialog):
         self.setup_store_checks()
 
         # Set the search query
+        if isinstance(query, (str, unicode)):
+            self.search_edit.setText(query)
+        elif isinstance(query, dict):
+            if 'author' in query:
+                self.search_author.setText(query['author'])
+            if 'title' in query:
+                self.search_title.setText(query['title'])
         # 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)
 
@@ -408,7 +412,7 @@ class SearchDialog(QDialog, Ui_Dialog):
         self.save_state()
 
     def exec_(self):
-        if unicode(self.search_edit.text()).strip():
+        if unicode(self.search_edit.text()).strip() or unicode(self.search_title.text()).strip() or unicode(self.search_author.text()).strip():
             self.do_search()
         return QDialog.exec_(self)
 

src/calibre/gui2/store/stores/nexto_plugin.py

@@ -1,7 +1,7 @@
 # -*- coding: utf-8 -*-
 
 from __future__ import (unicode_literals, division, absolute_import, print_function)
-store_version = 2 # Needed for dynamic plugin loading
+store_version = 3 # Needed for dynamic plugin loading
 
 __license__ = 'GPL 3'
 __copyright__ = '2011-2013, Tomasz Długosz <tomek3d@gmail.com>'
@@ -67,7 +67,7 @@ class NextoStore(BasicStoreConfig, StorePlugin):
 
                     cover_url = ''.join(data.xpath('.//img[@class="cover"]/@src'))
                     cover_url = re.sub(r'%2F', '/', cover_url)
-                    cover_url = re.sub(r'\widthMax=120&heightMax=200', 'widthMax=64&heightMax=64', cover_url)
+                    cover_url = re.sub(r'widthMax=120&heightMax=200', 'widthMax=64&heightMax=64', cover_url)
                     title = ''.join(data.xpath('.//a[@class="title"]/text()'))
                     title = re.sub(r' - ebook$', '', title)
                     formats = ', '.join(data.xpath('.//ul[@class="formats_available"]/li//b/text()'))
@@ -82,7 +82,7 @@ class NextoStore(BasicStoreConfig, StorePlugin):
                     counter -= 1
 
                     s = SearchResult()
-                    s.cover_url = 'http://www.nexto.pl' + cover_url
+                    s.cover_url = cover_url if cover_url[:4] == 'http' else 'http://www.nexto.pl' + cover_url
                     s.title = title.strip()
                     s.author = author.strip()
                     s.price = price

src/calibre/gui2/store/stores/virtualo_plugin.py

@@ -1,7 +1,7 @@
 # -*- coding: utf-8 -*-
 
 from __future__ import (unicode_literals, division, absolute_import, print_function)
-store_version = 2 # Needed for dynamic plugin loading
+store_version = 3 # Needed for dynamic plugin loading
 
 __license__ = 'GPL 3'
 __copyright__ = '2011-2013, Tomasz Długosz <tomek3d@gmail.com>'
@@ -41,7 +41,7 @@ class VirtualoStore(BasicStoreConfig, StorePlugin):
         url = 'http://virtualo.pl/?q=' + urllib.quote(query) + '&f=format_id:4,6,3'
 
         br = browser()
-        no_drm_pattern = re.compile("Znak wodny")
+        no_drm_pattern = re.compile(r'Znak wodny|Brak')
 
         counter = max_results
         with closing(br.open(url, timeout=timeout)) as f:
@@ -58,8 +58,8 @@ class VirtualoStore(BasicStoreConfig, StorePlugin):
                 cover_url = ''.join(data.xpath('.//div[@class="list_middle_left"]//a//img/@src'))
                 title = ''.join(data.xpath('.//div[@class="list_title list_text_left"]/a/text()'))
                 author = ', '.join(data.xpath('.//div[@class="list_authors list_text_left"]/a/text()'))
-                formats = [ form.split('_')[-1].replace('.png', '') for form in data.xpath('.//div[@style="width:55%;float:left;text-align:left;height:18px;"]//a/img/@src')]
+                formats = [ form.split('_')[-1].replace('.png', '') for form in data.xpath('.//div[@style="width:55%;float:left;text-align:left;height:18px;"]//a/span/img/@src')]
-                nodrm = no_drm_pattern.search(''.join(data.xpath('.//div[@style="width:45%;float:right;text-align:right;height:18px;"]/div/div/text()')))
+                nodrm = no_drm_pattern.search(''.join(data.xpath('.//div[@style="width:45%;float:right;text-align:right;height:18px;"]//span[@class="prompt_preview"]/text()')))
 
                 counter -= 1
 
@@ -70,6 +70,6 @@ class VirtualoStore(BasicStoreConfig, StorePlugin):
                 s.price = price + ' zł'
                 s.detail_item = 'http://virtualo.pl' + id.strip().split('http://')[0]
                 s.formats = ', '.join(formats).upper()
-                s.drm = SearchResult.DRM_UNLOCKED if nodrm else SearchResult.DRM_UNKNOWN
+                s.drm = SearchResult.DRM_UNLOCKED if nodrm else SearchResult.DRM_LOCKED
 
                 yield s

src/calibre/gui2/store/stores/waterstones_uk_plugin.py

@@ -1,7 +1,7 @@
 # -*- coding: utf-8 -*-
 
 from __future__ import (unicode_literals, division, absolute_import, print_function)
-store_version = 1 # Needed for dynamic plugin loading
+store_version = 2 # Needed for dynamic plugin loading
 
 __license__ = 'GPL 3'
 __copyright__ = '2011, John Schember <john@nachtimwald.com>'
@@ -24,8 +24,8 @@ 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 = 'http://www.awin1.com/awclick.php?mid=3787&id=120917'
-        url_details = 'http://clkuk.tradedoubler.com/click?p(51196)a(1951604)g(16460516)url({0})'
+        url_details = 'http://www.awin1.com/cread.php?awinmid=3787&awinaffid=120917&clickref=&p={0}'
 
         if external or self.config.get('open_external', False):
             if detail_item:

src/calibre/gui2/toc/main.py

@@ -18,7 +18,7 @@ from PyQt4.Qt import (QPushButton, QFrame, QVariant, QMenu, QInputDialog,
 
 from calibre.ebooks.oeb.polish.container import get_container, AZW3Container
 from calibre.ebooks.oeb.polish.toc import (
-    get_toc, add_id, TOC, commit_toc, from_xpaths, from_links)
+    get_toc, add_id, TOC, commit_toc, from_xpaths, from_links, from_files)
 from calibre.gui2 import Application, error_dialog, gprefs
 from calibre.gui2.progress_indicator import ProgressIndicator
 from calibre.gui2.toc.location import ItemEdit
@@ -126,6 +126,7 @@ class ItemView(QFrame): # {{{
     go_to_root = pyqtSignal()
     create_from_xpath = pyqtSignal(object)
     create_from_links = pyqtSignal()
+    create_from_files = pyqtSignal()
     flatten_toc = pyqtSignal()
 
     def __init__(self, parent):
@@ -183,6 +184,15 @@ class ItemView(QFrame): # {{{
         )))
         l.addWidget(b)
 
+        self.cfb = b = QPushButton(_('Generate ToC from &files'))
+        b.clicked.connect(self.create_from_files)
+        b.setToolTip(textwrap.fill(_(
+            'Generate a Table of Contents from individual files in the book.'
+            ' Each entry in the ToC will point to the start of the file, the'
+            ' text of the entry will be the "first line" of text from the file.'
+        )))
+        l.addWidget(b)
+
         self.xpb = b = QPushButton(_('Generate ToC from &XPath'))
         b.clicked.connect(self.create_from_user_xpath)
         b.setToolTip(textwrap.fill(_(
@@ -549,11 +559,11 @@ class TOCView(QWidget): # {{{
         b.setToolTip(_('Remove all selected entries'))
         b.clicked.connect(self.del_items)
 
-        self.left_button = b = QToolButton(self)
+        self.right_button = b = QToolButton(self)
         b.setIcon(QIcon(I('forward.png')))
         b.setIconSize(QSize(ICON_SIZE, ICON_SIZE))
         l.addWidget(b, 4, 3)
-        b.setToolTip(_('Unindent the current entry [Ctrl+Left]'))
+        b.setToolTip(_('Indent the current entry [Ctrl+Right]'))
         b.clicked.connect(self.tocw.move_right)
 
         self.down_button = b = QToolButton(self)
@@ -577,6 +587,7 @@ class TOCView(QWidget): # {{{
         i.add_new_item.connect(self.add_new_item)
         i.create_from_xpath.connect(self.create_from_xpath)
         i.create_from_links.connect(self.create_from_links)
+        i.create_from_files.connect(self.create_from_files)
         i.flatten_item.connect(self.flatten_item)
         i.flatten_toc.connect(self.flatten_toc)
         i.go_to_root.connect(self.go_to_root)
@@ -778,6 +789,14 @@ class TOCView(QWidget): # {{{
                 _('No links were found that could be added to the Table of Contents.'), show=True)
         self.insert_toc_fragment(toc)
 
+    def create_from_files(self):
+        toc = from_files(self.ebook)
+        if len(toc) == 0:
+            return error_dialog(self, _('No items found'),
+                _('No files were found that could be added to the Table of Contents.'), show=True)
+        self.insert_toc_fragment(toc)
+
+
 # }}}
 
 class TOCEditor(QDialog): # {{{

src/calibre/library/cli.py

@@ -54,7 +54,7 @@ def get_parser(usage):
 def get_db(dbpath, options):
     global do_notify
     if options.library_path is not None:
-        dbpath = options.library_path
+        dbpath = os.path.expanduser(options.library_path)
     if dbpath is None:
         raise ValueError('No saved library path, either run the GUI or use the'
                 ' --with-library option')