0.8.41

Changelog.yaml

@@ -19,6 +19,68 @@
 #   new recipes:
 #     - title: 
 
+- version: 0.8.41
+  date: 2012-02-24
+
+  new features:
+    - title: "Driver for Sony Experia Play 4G"
+      tickets: [938831]
+
+    - title: "News download system: Allow use of __future__ in recipes, and do not change line numbers of code in the recipe when compiling it"
+
+    - title: "Use the My Documents folder as the default location for the Calibre Library folder on first start in windows"
+      tickets: [934840] 
+
+    - title: "Add a tweak to Preferences->Tweaks to control the order in which categories appear in the Tag Browser"
+
+    - title: "Tag Browser: Add an entry to the right click menu to quickly delete tags"
+      tickets: [934509] 
+
+    - title: "Amazon metadata download: Try to scrape series information from the amazon details page. Note that currently very few books have series info available. Often the page for hardcover will have series, but the Kindle edition will not. In such cases calibre may or may not find the series, depending on which page it ends up using."
+
+    - title: "Content server: Add favicon to OPDS feeds."
+      tickets: [934731]
+ 
+  bug fixes:
+    - title: "RTF Input: Fix some WMF images embedded in RTF files being distorted on conversion."
+      tickets: [934167]
+
+    - title: "Fix long standing bug preventing calibre from working on east asian windows installs when the user name in windows has non-ascii characters"
+      tickets: [937389]
+
+    - title: "Get Books: Fix Baen Webscription and O'Reilly stores. Fix price detection for Google Books"
+
+    - title: "MOBI Output: When the same anchor is present more than once in the input document, use the first occurrence rather than the last one."
+      tickets: [934031]
+
+    - title: "Use the 'default cover font' tweak when generating default masthead images as well"
+      tickets: [939256] 
+
+    - title: "Fix content server does not correctly display custom field of type 'rating'"
+      tickets: [938303] 
+
+    - title: "Fix welcome wizard does not save send-from email info unless send-to field is filled"
+      tickets: [937087] 
+
+    - title: "When reading metadata from odt files, use initial-creator in preference to creator for setting the author field"
+      tickets: [934564] 
+
+    - title: "Fix conversion erroring out when the input document has very long and thin images"
+      tickets: [935234]
+
+  improved recipes:
+    - The Sun
+    - Various Polish news sources
+    - Mediapart
+
+  new recipes:
+    - title: La pausa caffe 
+      author: faber1971
+
+    - title: Various Polish news sources 
+      author: fenuks
+
+
 - version: 0.8.40
   date: 2012-02-17
 

recipes/archeowiesci.recipe

@@ -7,6 +7,7 @@ class Archeowiesci(BasicNewsRecipe):
     language       = 'pl'
     cover_url='http://archeowiesci.pl/wp-content/uploads/2011/05/Archeowiesci2-115x115.jpg'
     oldest_article = 7
+    needs_subscription='optional'
     max_articles_per_feed = 100
     auto_cleanup = True
     remove_tags=[dict(name='span', attrs={'class':['post-ratings', 'post-ratings-loading']})]
@@ -16,6 +17,16 @@ class Archeowiesci(BasicNewsRecipe):
       feeds = BasicNewsRecipe.parse_feeds(self)
       for feed in feeds:
         for article in feed.articles[:]:
-          if 'subskrypcja' in article.title:
+          if self.username is None and 'subskrypcja' in article.title:
             feed.articles.remove(article)
       return feeds
+
+    def get_browser(self):
+        br = BasicNewsRecipe.get_browser()
+        if self.username is not None and self.password is not None:
+            br.open('http://archeowiesci.pl/wp-login.php')
+            br.select_form(name='loginform')
+            br['log']   = self.username
+            br['pwd'] = self.password
+            br.submit()
+        return br

recipes/astronomia_pl.recipe

@@ -1,15 +1,18 @@
 from calibre.web.feeds.news import BasicNewsRecipe
-
+import re
 class Astronomia_pl(BasicNewsRecipe):
     title          = u'Astronomia.pl'
     __author__        = 'fenuks'
     description   = 'Astronomia - polish astronomy site'
+    masthead_url      = 'http://www.astronomia.pl/grafika/logo.gif'
     cover_url      = 'http://www.astronomia.pl/grafika/logo.gif'
     category       = 'astronomy, science'
     language       = 'pl'
     oldest_article = 8
     max_articles_per_feed = 100
-    #no_stylesheets=True
+    extra_css='#h2 {font-size: 18px;}'
+    no_stylesheets=True
+    preprocess_regexps = [(re.compile(ur'<b>Przeczytaj także:.*?</BODY>', re.DOTALL), lambda match: '</BODY>') ]
     remove_tags_before=dict(name='div', attrs={'id':'a1'})
     keep_only_tags=[dict(name='div', attrs={'id':['a1', 'h2']})]
     feeds          = [(u'Wiadomości z astronomii i astronautyki', u'http://www.astronomia.pl/rss/')]

recipes/benchmark_pl.recipe

@@ -4,16 +4,17 @@ class Benchmark_pl(BasicNewsRecipe):
     title          = u'Benchmark.pl'
     __author__        = 'fenuks'
     description   = u'benchmark.pl -IT site'
+    masthead_url = 'http://www.benchmark.pl/i/logo-footer.png'
     cover_url      = 'http://www.ieaddons.pl/benchmark/logo_benchmark_new.gif'
     category       = 'IT'
     language       = 'pl'
     oldest_article = 8
     max_articles_per_feed = 100
     no_stylesheets=True
-    preprocess_regexps = [(re.compile(ur'\bWięcej o .*</body>', re.DOTALL|re.IGNORECASE), lambda match: '</body>')]
+    preprocess_regexps = [(re.compile(ur'<h3><span style="font-size: small;">&nbsp;Zobacz poprzednie <a href="http://www.benchmark.pl/news/zestawienie/grupa_id/135">Opinie dnia:</a></span>.*</body>', re.DOTALL|re.IGNORECASE), lambda match: '</body>'), (re.compile(ur'Więcej o .*?</ul>', re.DOTALL|re.IGNORECASE), lambda match: '')]
     keep_only_tags=[dict(name='div', attrs={'class':['m_zwykly', 'gallery']})]
     remove_tags_after=dict(name='div', attrs={'class':'body'})
-    remove_tags=[dict(name='div', attrs={'class':['kategoria', 'socialize', 'thumb', 'panelOcenaObserwowane', 'categoryNextToSocializeGallery']})]
+    remove_tags=[dict(name='div', attrs={'class':['kategoria', 'socialize', 'thumb', 'panelOcenaObserwowane', 'categoryNextToSocializeGallery']}), dict(name='table', attrs={'background':'http://www.benchmark.pl/uploads/backend_img/a/fotki_newsy/opinie_dnia/bg.png'}), dict(name='table', attrs={'width':'210', 'cellspacing':'1', 'cellpadding':'4', 'border':'0', 'align':'right'})]
     INDEX= 'http://www.benchmark.pl'
     feeds          = [(u'Aktualności', u'http://www.benchmark.pl/rss/aktualnosci-pliki.xml'), 
                           (u'Testy i recenzje', u'http://www.benchmark.pl/rss/testy-recenzje-minirecenzje.xml')]

recipes/biolog_pl.recipe

@@ -10,10 +10,11 @@ class Biolog_pl(BasicNewsRecipe):
     description   = u'Przyrodnicze aktualności ze świata nauki (codziennie aktualizowane), kurs biologii, testy i sprawdziany, forum dyskusyjne.'
     category       = 'biology'
     language       = 'pl'
+    masthead_url= 'http://www.biolog.pl/naukowy,portal,biolog.png'
     cover_url='http://www.biolog.pl/naukowy,portal,biolog.png'
     no_stylesheets = True
     #keeps_only_tags=[dict(id='main')]
     remove_tags_before=dict(id='main')
     remove_tags_after=dict(name='a', attrs={'name':'komentarze'})
-    remove_tags=[dict(name='img', attrs={'alt':'Komentarze'})]
+    remove_tags=[dict(name='img', attrs={'alt':'Komentarze'}), dict(name='span', attrs={'class':'menu_odsylacze'})]
     feeds          = [(u'Wszystkie', u'http://www.biolog.pl/backend.php'), (u'Medycyna', u'http://www.biolog.pl/medycyna-rss.php'), (u'Ekologia', u'http://www.biolog.pl/rss-ekologia.php'), (u'Genetyka i biotechnologia', u'http://www.biolog.pl/rss-biotechnologia.php'), (u'Botanika', u'http://www.biolog.pl/rss-botanika.php'), (u'Le\u015bnictwo', u'http://www.biolog.pl/rss-lesnictwo.php'), (u'Zoologia', u'http://www.biolog.pl/rss-zoologia.php')]

recipes/cd_action.recipe

@@ -1,16 +1,20 @@
 from calibre.web.feeds.news import BasicNewsRecipe
 
-
 class CD_Action(BasicNewsRecipe):
     title          = u'CD-Action'
     __author__        = 'fenuks'
-    description   = 'cdaction.pl - polish magazine about games site'
+    description   = 'cdaction.pl - polish games magazine site'
     category       = 'games'
     language       = 'pl'
     oldest_article = 8
     max_articles_per_feed = 100
     no_stylesheets= True
-    cover_url =u'http://s.cdaction.pl/obrazki/logo-CD-Action_172k9.JPG'
     keep_only_tags= dict(id='news_content')
     remove_tags_after= dict(name='div', attrs={'class':'tresc'})
     feeds          = [(u'Newsy', u'http://www.cdaction.pl/rss_newsy.xml')]
+
+
+    def get_cover_url(self):
+        soup = self.index_to_soup('http://www.cdaction.pl/magazyn/')
+        self.cover_url='http://www.cdaction.pl'+ soup.find(id='wspolnik').div.a['href']
+        return getattr(self, 'cover_url', self.cover_url)

recipes/cgm_pl.recipe

@@ -5,6 +5,7 @@ class CGM(BasicNewsRecipe):
     oldest_article = 7
     __author__        = 'fenuks'
     description   = u'Codzienna Gazeta Muzyczna'
+    masthead_url='http://www.cgm.pl/img/header/logo.gif'
     cover_url      = 'http://www.krafcy.com/foto/tinymce/Image/cgm%281%29.jpg'
     category       = 'music'
     language       = 'pl'
@@ -23,21 +24,19 @@ class CGM(BasicNewsRecipe):
 
 
     def preprocess_html(self, soup):
+        gallery=soup.find('div', attrs={'class':'galleryFlash'})
+        if gallery:
+            img=gallery.div
+            gallery.img.extract()
+            if img:
+                img=img['style']
+                img='http://www.cgm.pl'+img[img.find('url(')+4:img.find(')')]
+                gallery.contents[1].name='img'
+                gallery.contents[1]['src']=img
         for item in soup.findAll(style=True):
             del item['style']
         ad=soup.findAll('a')
         for r in ad:
-            if 'http://www.hustla.pl' in r['href'] or 'http://www.ebilet.pl' in r['href']:                
+            if 'www.hustla.pl' in r['href'] or 'www.ebilet.pl' in r['href']:                
                  r.extract()
-        gallery=soup.find('div', attrs={'class':'galleryFlash'})
-        if gallery:
-            img=gallery.find('embed')
-            if img:
-                img=img['src'][35:]
-                img='http://www.cgm.pl/_vault/_gallery/_photo/'+img
-                param=gallery.findAll(name='param')
-                for i in param:
-                    i.extract()
-                gallery.contents[1].name='img'
-                gallery.contents[1]['src']=img
         return soup

recipes/chr_mon.recipe

@@ -33,6 +33,32 @@ class ChristianScienceMonitor(BasicNewsRecipe):
 
     remove_javascript     = True
     no_stylesheets = True
+    requires_version = (0, 8, 39)
+
+    def preprocess_raw_html(self, raw, url):
+        try:
+            from html5lib import parse
+            root = parse(raw, namespaceHTMLElements=False,
+                    treebuilder='lxml').getroot()
+            from lxml import etree
+            for tag in root.xpath(
+                    '//script|//style|//noscript|//meta|//link|//object'):
+                tag.getparent().remove(tag)
+            for elem in list(root.iterdescendants(tag=etree.Comment)):
+                elem.getparent().remove(elem)
+            ans = etree.tostring(root, encoding=unicode)
+            ans = re.sub('.*<html', '<html', ans, flags=re.DOTALL)
+            return ans
+        except:
+            import traceback
+            traceback.print_exc()
+            raise
+
+    def index_to_soup(self, url):
+        raw = BasicNewsRecipe.index_to_soup(self, url,
+                raw=True).decode('utf-8')
+        raw = self.preprocess_raw_html(raw, url)
+        return BasicNewsRecipe.index_to_soup(self, raw)
 
     def append_page(self, soup, appendtag, position):
         nav = soup.find('div',attrs={'class':'navigation'})
@@ -78,14 +104,6 @@ class ChristianScienceMonitor(BasicNewsRecipe):
             print_soup = soup
         return print_soup
 
-    preprocess_regexps = [ (re.compile(i[0], re.IGNORECASE | re.DOTALL), i[1]) for i in
-        [
-            (r'<!--.*?-->', lambda match : ''),
-        (r'<body.*?<div id="story"', lambda match : '<body><div id="story"'),
-        (r'<div class="pubdate">.*?</div>', lambda m: ''),
-        (r'Full HTML version of this story which may include photos, graphics, and related links.*</body>',
-              lambda match : '</body>'),
-        ]]
     extra_css      = '''
                         h1{ color:#000000;font-family: Georgia,Times,"Times New Roman",serif; font-size: large}
                         .sub{ color:#000000;font-family: Georgia,Times,"Times New Roman",serif; font-size: small;}

recipes/ciekawostki_historyczne.recipe

@@ -0,0 +1,48 @@
+from calibre.web.feeds.news import BasicNewsRecipe
+import re
+class Ciekawostki_Historyczne(BasicNewsRecipe):
+    title          = u'Ciekawostki Historyczne'
+    oldest_article = 7
+    __author__        = 'fenuks'
+    description   = u'Serwis popularnonaukowy - odkrycia, kontrowersje, historia, ciekawostki, badania, ciekawostki z przeszłości.'
+    category       = 'history'
+    language       = 'pl'
+    masthead_url= 'http://ciekawostkihistoryczne.pl/wp-content/themes/Wordpress_Magazine/images/logo-ciekawostki-historyczne-male.jpg'
+    cover_url='http://ciekawostkihistoryczne.pl/wp-content/themes/Wordpress_Magazine/images/logo-ciekawostki-historyczne-male.jpg'
+    max_articles_per_feed = 100
+    preprocess_regexps = [(re.compile(ur'Ten artykuł ma kilka stron.*?</fb:like>', re.DOTALL), lambda match: ''), (re.compile(ur'<h2>Zobacz też:</h2>.*?</ol>', re.DOTALL), lambda match: '')]
+    no_stylesheets=True
+    remove_empty_feeds=True
+    keep_only_tags=[dict(name='div', attrs={'class':'post'})]
+    remove_tags=[dict(id='singlepostinfo')]
+    feeds          = [(u'Staro\u017cytno\u015b\u0107', u'http://ciekawostkihistoryczne.pl/tag/starozytnosc/feed/'), (u'\u015aredniowiecze', u'http://ciekawostkihistoryczne.pl/tag/sredniowiecze/feed/'), (u'Nowo\u017cytno\u015b\u0107', u'http://ciekawostkihistoryczne.pl/tag/nowozytnosc/feed/'), (u'XIX wiek', u'http://ciekawostkihistoryczne.pl/tag/xix-wiek/feed/'), (u'1914-1939', u'http://ciekawostkihistoryczne.pl/tag/1914-1939/feed/'), (u'1939-1945', u'http://ciekawostkihistoryczne.pl/tag/1939-1945/feed/'), (u'Powojnie (od 1945)', u'http://ciekawostkihistoryczne.pl/tag/powojnie/feed/'), (u'Recenzje', u'http://ciekawostkihistoryczne.pl/category/recenzje/feed/')]
+
+    def append_page(self, soup, appendtag):
+        tag=soup.find(name='h7')
+        if tag:
+            if tag.br:
+                pass
+            elif tag.nextSibling.name=='p':
+                tag=tag.nextSibling
+                nexturl = tag.findAll('a')
+                for nextpage in nexturl:
+                    tag.extract()
+                    nextpage= nextpage['href']
+                    soup2 = self.index_to_soup(nextpage)
+                    pagetext = soup2.find(name='div', attrs={'class':'post'})
+                    for r in pagetext.findAll('div', attrs={'id':'singlepostinfo'}):
+                        r.extract()
+                    for r in pagetext.findAll('div', attrs={'class':'wp-caption alignright'}):
+                        r.extract()
+                    for r in pagetext.findAll('h1'):
+                        r.extract()
+                    pagetext.find('h6').nextSibling.extract()
+                    pagetext.find('h7').nextSibling.extract()
+                    pos = len(appendtag.contents)
+                    appendtag.insert(pos, pagetext)
+
+    def preprocess_html(self, soup):
+        self.append_page(soup, soup.body)
+        return soup
+   
+        

recipes/computerworld_pl.recipe

@@ -7,10 +7,11 @@ class Computerworld_pl(BasicNewsRecipe):
     description   = u'Serwis o IT w przemyśle, finansach, handlu, administracji oraz rynku IT i telekomunikacyjnym - wiadomości, opinie, analizy, porady prawne'
     category       = 'IT'
     language       = 'pl'
+    masthead_url= 'http://g1.computerworld.pl/cw/beta_gfx/cw2.gif'
     no_stylesheets=True
     oldest_article = 7
     max_articles_per_feed = 100
-    keep_only_tags=[dict(name='div', attrs={'id':'s'})]
+    keep_only_tags=[dict(attrs={'class':['tyt_news', 'prawo', 'autor', 'tresc']})]
     remove_tags_after=dict(name='div', attrs={'class':'rMobi'})
     remove_tags=[dict(name='div', attrs={'class':['nnav', 'rMobi']}), dict(name='table', attrs={'class':'ramka_slx'})]
     feeds          = [(u'Wiadomo\u015bci', u'http://rssout.idg.pl/cw/news_iso.xml')]

recipes/dobreprogamy.recipe

@@ -7,6 +7,7 @@ class Dobreprogramy_pl(BasicNewsRecipe):
     __licence__ ='GPL v3'
     category       = 'IT'
     language       = 'pl'
+    masthead_url='http://static.dpcdn.pl/css/Black/Images/header_logo_napis_fullVersion.png'
     cover_url = 'http://userlogos.org/files/logos/Karmody/dobreprogramy_01.png'
     description = u'Aktualności i blogi z dobreprogramy.pl'
     encoding = 'utf-8'
@@ -16,7 +17,8 @@ class Dobreprogramy_pl(BasicNewsRecipe):
     oldest_article = 8
     max_articles_per_feed = 100
     preprocess_regexps = [(re.compile(ur'<div id="\S+360pmp4">Twoja przeglądarka nie obsługuje Flasha i HTML5 lub wyłączono obsługę JavaScript...</div>'), lambda match: '') ]
-    remove_tags = [dict(name='div', attrs={'class':['komentarze', 'block', 'portalInfo', 'menuBar', 'topBar']})]
+    keep_only_tags=[dict(attrs={'class':['news', 'entry single']})]
-    keep_only_tags = [dict(name='div', attrs={'class':['mainBar', 'newsContent', 'postTitle title', 'postInfo', 'contentText', 'content']})]
+    remove_tags = [dict(name='div', attrs={'class':['newsOptions', 'noPrint', 'komentarze', 'tags  font-heading-master']})]
+    #remove_tags = [dict(name='div', attrs={'class':['komentarze', 'block', 'portalInfo', 'menuBar', 'topBar']})]
     feeds = [(u'Aktualności', 'http://feeds.feedburner.com/dobreprogramy/Aktualnosci'),
                  ('Blogi', 'http://feeds.feedburner.com/dobreprogramy/BlogCzytelnikow')]

recipes/dziennik_pl.recipe

@@ -8,15 +8,17 @@ class Dziennik_pl(BasicNewsRecipe):
     description   = u'Wiadomości z kraju i ze świata. Wiadomości gospodarcze. Znajdziesz u nas informacje, wydarzenia, komentarze, opinie.'
     category       = 'newspaper'
     language       = 'pl'
-    cover_url='http://6.s.dziennik.pl/images/og_dziennik.jpg'
+    masthead_url= 'http://5.s.dziennik.pl/images/logos.png'
+    cover_url= 'http://5.s.dziennik.pl/images/logos.png'
     no_stylesheets = True
     oldest_article = 7
     max_articles_per_feed = 100
     remove_javascript=True
     remove_empty_feeds=True
-    preprocess_regexps     = [(re.compile("Komentarze:"), lambda m: '')]
+    extra_css= 'ul {list-style: none; padding: 0; margin: 0;} li {float: left;margin: 0 0.15em;}'
+    preprocess_regexps     = [(re.compile("Komentarze:"), lambda m: ''), (re.compile('<p><strong><a href=".*?">&gt;&gt;&gt; CZYTAJ TAKŻE: ".*?"</a></strong></p>'), lambda m: '')]
     keep_only_tags=[dict(id='article')]
-    remove_tags=[dict(name='div', attrs={'class':['art_box_dodatki', 'new_facebook_icons2', 'leftArt', 'article_print', 'quiz-widget']}), dict(name='a', attrs={'class':'komentarz'})]
+    remove_tags=[dict(name='div', attrs={'class':['art_box_dodatki', 'new_facebook_icons2', 'leftArt', 'article_print', 'quiz-widget', 'belka-spol', 'belka-spol belka-spol-bottom', 'art_data_tags', 'cl_right', 'boxRounded gal_inside']}), dict(name='a', attrs={'class':['komentarz', 'article_icon_addcommnent']})]
     feeds          = [(u'Wszystko', u'http://rss.dziennik.pl/Dziennik-PL/'),
 		(u'Wiadomości', u'http://rss.dziennik.pl/Dziennik-Wiadomosci'),
 		(u'Gospodarka', u'http://rss.dziennik.pl/Dziennik-Gospodarka'),
@@ -30,6 +32,12 @@ class Dziennik_pl(BasicNewsRecipe):
 		(u'Podróże', u'http://rss.dziennik.pl/Dziennik-Podroze/'),
 		(u'Nieruchomości', u'http://rss.dziennik.pl/Dziennik-Nieruchomosci')]
 
+    def skip_ad_pages(self, soup):
+          tag=soup.find(name='a', attrs={'title':'CZYTAJ DALEJ'})
+          if tag:
+            new_soup=self.index_to_soup(tag['href'], raw=True)
+            return new_soup
+
     def append_page(self, soup, appendtag):
         tag=soup.find('a', attrs={'class':'page_next'})
         if tag:
@@ -56,3 +64,4 @@ class Dziennik_pl(BasicNewsRecipe):
     def preprocess_html(self, soup):
          self.append_page(soup, soup.body)
          return soup
+

recipes/film_web.recipe

@@ -10,7 +10,8 @@ class Filmweb_pl(BasicNewsRecipe):
     oldest_article = 8
     max_articles_per_feed = 100
     no_stylesheets= True
-    extra_css      = '.hdrBig {font-size:22px;}'
+    remove_empty_feeds=True
+    extra_css      = '.hdrBig {font-size:22px;} ul {list-style-type:none; padding: 0; margin: 0;}'
     remove_tags= [dict(name='div', attrs={'class':['recommendOthers']}), dict(name='ul', attrs={'class':'fontSizeSet'})]
     keep_only_tags= [dict(name='h1', attrs={'class':'hdrBig'}), dict(name='div', attrs={'class':['newsInfo', 'reviewContent fontSizeCont description']})]
     feeds          = [(u'Wszystkie newsy', u'http://www.filmweb.pl/feed/news/latest'),

recipes/gameplay_pl.recipe

@@ -0,0 +1,21 @@
+from calibre.web.feeds.news import BasicNewsRecipe
+class Gameplay_pl(BasicNewsRecipe):
+    title          = u'Gameplay.pl'
+    oldest_article = 7
+    __author__        = 'fenuks'
+    description   = u'gameplay.pl - serwis o naszych zainteresowaniach, grach, filmach, książkach, muzyce, fotografii i konsolach.'
+    category       = 'games, movies, books, music'
+    language       = 'pl'
+    masthead_url= 'http://gameplay.pl/img/gpy_top_logo.png'
+    cover_url= 'http://gameplay.pl/img/gpy_top_logo.png'
+    max_articles_per_feed = 100
+    no_stylesheets= True
+    keep_only_tags=[dict(name='div', attrs={'class':['news_endpage_tit', 'news']})]
+    remove_tags=[dict(name='div', attrs={'class':['galeria', 'noedit center im']})]
+    feeds          = [(u'Wiadomo\u015bci', u'http://gameplay.pl/rss/')]
+
+    def image_url_processor(self, baseurl, url):
+        if 'http' not in url:
+            return 'http://gameplay.pl'+ url[2:]
+        else:
+		    return url

recipes/gazeta_wyborcza.recipe

@@ -4,10 +4,11 @@ from calibre.web.feeds.news import BasicNewsRecipe
 class Gazeta_Wyborcza(BasicNewsRecipe):
     title          = u'Gazeta Wyborcza'
     __author__        = 'fenuks'
-    cover_url      = 'http://bi.gazeta.pl/im/5/10285/z10285445AA.jpg'
     language       = 'pl'
     description ='news from gazeta.pl'
     category='newspaper'
+    publication_type = 'newspaper'
+    masthead_url='http://bi.gazeta.pl/im/5/10285/z10285445AA.jpg'
     INDEX='http://wyborcza.pl'
     remove_empty_feeds= True
     oldest_article = 3
@@ -81,3 +82,10 @@ class Gazeta_Wyborcza(BasicNewsRecipe):
             return url
         else:
              return url.replace('http://wyborcza.biz/biznes/1', 'http://wyborcza.biz/biznes/2029020')
+
+    def get_cover_url(self):
+        soup = self.index_to_soup('http://wyborcza.pl/0,76762,3751429.html')
+        cover=soup.find(id='GWmini2')  
+        soup = self.index_to_soup('http://wyborcza.pl/'+ cover.contents[3].a['href'])
+        self.cover_url='http://wyborcza.pl' + soup.img['src']
+        return getattr(self, 'cover_url', self.cover_url)

recipes/gry_online_pl.recipe

@@ -8,29 +8,31 @@ class Gry_online_pl(BasicNewsRecipe):
     language       = 'pl'
     oldest_article = 13
     INDEX= 'http://www.gry-online.pl/'
-    cover_url='http://www.gry-online.pl/img/1st_10/1st-gol-logo.png'
+    masthead_url='http://www.gry-online.pl/im/gry-online-logo.png'
+    cover_url='http://www.gry-online.pl/im/gry-online-logo.png'
     max_articles_per_feed = 100
     no_stylesheets= True
-    extra_css              = 'p.wn1{font-size:22px;}'
+    keep_only_tags=[dict(name='div', attrs={'class':'gc660'})]
-    remove_tags_after= [dict(name='div', attrs={'class':['tresc-newsa']})]
+    remove_tags=[dict({'class':['nav-social', 'add-info', 'smlb', 'lista lista3 lista-gry', 'S013po', 'zm_gfx_cnt_bottom', 'ocen-txt', 'wiecej-txt', 'wiecej-txt2']})]
-    keep_only_tags = [dict(name='div', attrs={'class':['txthead']}), dict(name='p', attrs={'class':['wtx1', 'wn1', 'wob']}), dict(name='a', attrs={'class':['num_str_nex']})]
-    #remove_tags= [dict(name='div', attrs={'class':['news_plat']})]
     feeds          = [(u'Newsy', 'http://www.gry-online.pl/rss/news.xml'), ('Teksty', u'http://www.gry-online.pl/rss/teksty.xml')]
 
 
     def append_page(self, soup, appendtag):
-        nexturl = soup.find('a', attrs={'class':'num_str_nex'})
+        tag = appendtag.find('div', attrs={'class':'n5p'})
-        if appendtag.find('a', attrs={'class':'num_str_nex'}) is not None:
+        if tag:
-            appendtag.find('a', attrs={'class':'num_str_nex'}).replaceWith('\n')
+            nexturls=tag.findAll('a')
-        if nexturl is not None:
+            for nexturl in nexturls[1:]:
-            if 'strona' in nexturl.div.string:
+                try:
-                nexturl= self.INDEX + nexturl['href']
+                    soup2 = self.index_to_soup('http://www.gry-online.pl/S020.asp'+ nexturl['href'])
-                soup2 = self.index_to_soup(nexturl)
+                except:
-                pagetext = soup2.findAll(name='p', attrs={'class':['wtx1', 'wn1', 'wob']})
+                    soup2 = self.index_to_soup('http://www.gry-online.pl/S022.asp'+ nexturl['href'])
-                for tag in pagetext:
+                pagetext = soup2.find(attrs={'class':'gc660'})
-                    pos = len(appendtag.contents)
+                for r in pagetext.findAll(name='header'):
-                    appendtag.insert(pos, tag)
+                    r.extract()
-                self.append_page(soup2, appendtag)
+                pos = len(appendtag.contents)
+                appendtag.insert(pos, pagetext)
+            for r in appendtag.findAll(attrs={'class':['n5p', 'add-info', 'twitter-share-button']}):
+                r.extract()
 
 
     def preprocess_html(self, soup):

recipes/in4_pl.recipe

@@ -0,0 +1,44 @@
+from calibre.web.feeds.news import BasicNewsRecipe
+import re
+class in4(BasicNewsRecipe):
+    title          = u'IN4.pl'
+    oldest_article = 7
+    max_articles_per_feed = 100
+    __author__        = 'fenuks'
+    description   = u'Serwis Informacyjny - Aktualnosci, recenzje'
+    category       = 'IT'
+    language       = 'pl'
+    #cover_url= 'http://www.in4.pl/recenzje/337/in4pl.jpg'
+    no_stylesheets = True
+    remove_empty_feeds = True
+    preprocess_regexps = [(re.compile(ur'<a title="translate into.*?</a>', re.DOTALL), lambda match: '') ]
+    keep_only_tags=[dict(name='div', attrs={'class':'left_alone'})]
+    remove_tags_after=dict(name='img', attrs={'title':'komentarze'})
+    remove_tags=[dict(name='img', attrs={'title':'komentarze'})]
+    feeds          = [(u'Wiadomo\u015bci', u'http://www.in4.pl/rss.php'), (u'Recenzje', u'http://www.in4.pl/rss_recenzje.php'), (u'Mini recenzje', u'http://www.in4.pl/rss_mini.php')]
+
+    def append_page(self, soup, appendtag):
+        a=soup.findAll('a')
+        nexturl=None
+        for i in a:
+            if i.string and 'następna str' in i.string:
+                nexturl='http://www.in4.pl/' + i['href']
+                i.extract()
+        while nexturl:
+                    soup2 = self.index_to_soup(nexturl)
+                    pagetext = soup2.find(id='news')
+                    pos = len(appendtag.contents)
+                    appendtag.insert(pos, pagetext)
+                    nexturl=None
+                    tag=soup2.findAll('a')
+                    for z in tag:
+                        if z.string and u'następna str' in z.string:
+                            nexturl='http://www.in4.pl/' + z['href']
+                            break
+                    
+
+    def preprocess_html(self, soup):
+        self.append_page(soup, soup.body)
+        return soup
+   
+        

recipes/informacje_usa.recipe

@@ -0,0 +1,18 @@
+from calibre.web.feeds.news import BasicNewsRecipe
+import re
+class Informacje_USA(BasicNewsRecipe):
+    title          = u'Informacje USA'
+    oldest_article = 7
+    max_articles_per_feed = 100
+    __author__        = 'fenuks'
+    description   = u'portal wiadomości amerykańskich'
+    category       = 'news'
+    language       = 'pl'
+    masthead_url= 'http://www.informacjeusa.com/wp-content/add_images/top_logo_5_2010.jpg'
+    cover_url='http://www.informacjeusa.com/wp-content/add_images/top_logo_5_2010.jpg'
+    no_stylesheets = True
+    preprocess_regexps = [(re.compile(ur'<p>Zobacz:.*?</p>', re.DOTALL), lambda match: ''), (re.compile(ur'<p><a href=".*?Zobacz także:.*?</a></p>', re.DOTALL), lambda match: ''), (re.compile(ur'<p><p>Zobacz też:.*?</a></p>', re.DOTALL), lambda match: '')]
+    keep_only_tags=[dict(name='div', attrs={'class':'box box-single'})]
+    remove_tags_after= dict(attrs={'class':'tags'})
+    remove_tags= [dict(attrs={'class':['postmetadata', 'tags', 'banner']}), dict(name='a', attrs={'title':['Drukuj', u'Wyślij']})]
+    feeds          = [(u'Informacje', u'http://www.informacjeusa.com/feed/')]

recipes/kresy_pl.recipe

@@ -0,0 +1,14 @@
+from calibre.web.feeds.news import BasicNewsRecipe
+class Kresy(BasicNewsRecipe):
+    title          = u'Kresy'
+    __author__        = 'fenuks'
+    description   = u'portal społeczności kresowej'
+    language       = 'pl'
+    masthead_url= 'http://www.kresy.pl/public/img/logo.png'
+    cover_url= 'http://www.kresy.pl/public/img/logo.png'
+    oldest_article = 7
+    max_articles_per_feed = 100
+    no_stylesheets = True
+    keep_only_tags= [dict(id='artykul')]
+    remove_tags= [dict(attrs={'class':['twitter-share-button', 'likefbborder', 'tagi']})]
+    feeds          = [(u'Wszystkie', u'http://www.kresy.pl/rss')]

recipes/la_pausa_caffe.recipe

@@ -0,0 +1,17 @@
+__version__     = 'v1.0'
+__date__        = '13, February 2011'
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class AdvancedUserRecipe1329125921(BasicNewsRecipe):
+    title          = u'La pausa caff\xe8'
+    __author__      = 'faber1971'
+    description    = 'An Italian satirical blog'
+    language = 'it'
+
+    oldest_article = 7
+    max_articles_per_feed = 100
+    auto_cleanup = True
+    no_stylesheets = True
+    feeds          = [(u'La pausa caff\xe8', u'http://feeds.feedburner.com/LapausaCaffe')]
+

recipes/marketing_magazine.recipe

@@ -1,4 +1,5 @@
 __license__   = 'GPL v3'
+
 from calibre.web.feeds.news import BasicNewsRecipe
 
 class AdvancedUserRecipe1327062445(BasicNewsRecipe):
@@ -7,10 +8,13 @@ class AdvancedUserRecipe1327062445(BasicNewsRecipe):
     max_articles_per_feed = 100
     auto_cleanup = True
     remove_javascript = True
+    no_stylesheets = True
+    remove_tags = [
+                     dict(name='ul', attrs={'id':'ads0'})
+                  ]
     masthead_url            = 'http://www.simrendeogun.com/wp-content/uploads/2011/06/New-Marketing-Magazine-Logo.jpg'
-    feeds          = [(u'My Marketing', u'http://feed43.com/0537744466058428.xml'), (u'My Marketing_', u'http://feed43.com/8126723074604845.xml'), (u'Venturini', u'http://robertoventurini.blogspot.com/feeds/posts/default?alt=rss'), (u'Ninja Marketing', u'http://feeds.feedburner.com/NinjaMarketing'), (u'Comunitàzione', u'http://www.comunitazione.it/feed/novita.asp'), (u'Brandforum news', u'http://www.brandforum.it/rss/news'), (u'Brandforum papers', u'http://www.brandforum.it/rss/papers'), (u'Disambiguando', u'http://giovannacosenza.wordpress.com/feed/')]
     __author__    = 'faber1971'
-    description   = 'Collection of Italian marketing websites - v1.00 (28, January 2012)'
+    description   = 'Collection of Italian marketing websites - v1.03 (20, February 2012)'
     language = 'it'
 
-
+    feeds          = [(u'My Marketing', u'http://feed43.com/0537744466058428.xml'), (u'My Marketing_', u'http://feed43.com/8126723074604845.xml'), (u'Venturini', u'http://robertoventurini.blogspot.com/feeds/posts/default?alt=rss'), (u'Ninja Marketing', u'http://feeds.feedburner.com/NinjaMarketing'), (u'Comunitàzione', u'http://www.comunitazione.it/feed/novita.asp'), (u'Brandforum news', u'http://www.brandforum.it/rss/news'), (u'Brandforum papers', u'http://www.brandforum.it/rss/papers'), (u'MarketingArena', u'http://feeds.feedburner.com/marketingarena'), (u'minimarketing', u'http://feeds.feedburner.com/minimarketingit'), (u'Disambiguando', u'http://giovannacosenza.wordpress.com/feed/')]

recipes/mediapart.recipe

@@ -1,16 +1,17 @@
 __license__   = 'GPL v3'
-__copyright__ = '2009, Mathieu Godlewski <mathieu at godlewski.fr>; 2010, Louis Gesbert <meta at antislash dot info>'
+__copyright__ = '2009, Mathieu Godlewski <mathieu at godlewski.fr>; 2010, 2011, Louis Gesbert <meta at antislash dot info>'
 '''
 Mediapart
 '''
 
-from calibre.ebooks.BeautifulSoup import Tag
+import re
+from calibre.ebooks.BeautifulSoup import BeautifulSoup
 from calibre.web.feeds.news import BasicNewsRecipe
 
 class Mediapart(BasicNewsRecipe):
     title          = 'Mediapart'
-    __author__ = 'Mathieu Godlewski'
+    __author__ = 'Mathieu Godlewski, Louis Gesbert'
-    description = 'Global news in french from online newspapers'
+    description = 'Global news in french from news site Mediapart'
     oldest_article = 7
     language = 'fr'
     needs_subscription = True
@@ -18,52 +19,30 @@ class Mediapart(BasicNewsRecipe):
     max_articles_per_feed = 50
     no_stylesheets = True
 
-    cover_url = 'http://www.mediapart.fr/sites/all/themes/mediapart/mediapart/images/annonce.jpg'
+    cover_url = 'http://static.mediapart.fr/files/pave_mediapart.jpg'
 
     feeds =  [
         ('Les articles', 'http://www.mediapart.fr/articles/feed'),
     ]
 
-# -- print-version has poor quality on this website, better do the conversion ourselves
+# -- print-version
-#
-#     preprocess_regexps = [ (re.compile(i[0], re.IGNORECASE|re.DOTALL), i[1]) for i in
-#         [
-#             (r'<div class="print-title">([^>]+)</div>', lambda match : '<h2>'+match.group(1)+'</h2>'),
-#             (r'<span class=\'auteur_staff\'>[^>]+<a title=\'[^\']*\'[^>]*>([^<]*)</a>[^<]*</span>',
-#              lambda match : '<i>'+match.group(1)+'</i>'),
-#             (r'\'', lambda match: '&rsquo;'),
-#         ]
-#      ]
-#
-#     remove_tags    = [ dict(name='div', attrs={'class':'print-source_url'}),
-#                        dict(name='div', attrs={'class':'print-links'}),
-#                        dict(name='img', attrs={'src':'entete_article.png'}),
-#                        dict(name='br') ]
-#
-#     def print_version(self, url):
-#         raw = self.browser.open(url).read()
-#         soup = BeautifulSoup(raw.decode('utf8', 'replace'))
-#         div = soup.find('div', {'id':re.compile('node-\d+')})
-#         if div is None:
-#             return None
-#         article_id = string.replace(div['id'], 'node-', '')
-#         if article_id is None:
-#             return None
-#         return 'http://www.mediapart.fr/print/'+article_id
 
-# -- Non-print version [dict(name='div', attrs={'class':'advert'})]
+    preprocess_regexps = [ (re.compile(i[0], re.IGNORECASE|re.DOTALL), i[1]) for i in
-
+        [
-    keep_only_tags = [
+            (r'<div class="print-title">([^>]+)</div>', lambda match : '<h2>'+match.group(1)+'</h2>'),
-        dict(name='h1', attrs={'class':'title'}),
+            (r'\'', lambda match: '&rsquo;')
-        dict(name='div', attrs={'class':'page_papier_detail'}),
         ]
+    ]
 
-    def preprocess_html(self,soup):
+    remove_tags    = [ dict(name='div', attrs={'class':'print-source_url'}) ]
-        for title in soup.findAll('div', {'class':'titre'}):
+
-            tag = Tag(soup, 'h3')
+    def print_version(self, url):
-            title.replaceWith(tag)
+        raw = self.browser.open(url).read()
-            tag.insert(0,title)
+        soup = BeautifulSoup(raw.decode('utf8', 'replace'))
-        return soup
+        link = soup.find('a', {'title':'Imprimer'})
+        if link is None:
+            return None
+        return link['href']
 
 # -- Handle login
 
@@ -76,4 +55,3 @@ class Mediapart(BasicNewsRecipe):
             br['pass'] = self.password
             br.submit()
         return br
-

recipes/naczytniki.recipe

@@ -1,8 +1,9 @@
 from calibre.web.feeds.news import BasicNewsRecipe
-
+import re
 class naczytniki(BasicNewsRecipe):
     title          = u'naczytniki.pl'
     __author__        = 'fenuks'
+    masthead_url= 'http://naczytniki.pl/wp-content/uploads/2010/08/logo_nc28.png'
     cover_url      = 'http://naczytniki.pl/wp-content/uploads/2010/08/logo_nc28.png'
     language       = 'pl'
     description ='everything about e-readers'
@@ -10,6 +11,7 @@ class naczytniki(BasicNewsRecipe):
     no_stylesheets=True
     oldest_article = 7
     max_articles_per_feed = 100
+    preprocess_regexps = [(re.compile(ur'<p><br><b>Zobacz także:</b></p>.*?</body>', re.DOTALL), lambda match: '</body>') ]
     remove_tags_after= dict(name='div', attrs={'class':'sociable'})
     keep_only_tags=[dict(name='div', attrs={'class':'post'})]
     remove_tags=[dict(name='span', attrs={'class':'comments'}), dict(name='div', attrs={'class':'sociable'})]

recipes/nowa_fantastyka.recipe

@@ -1,21 +1,33 @@
 # -*- coding: utf-8 -*-
 from calibre.web.feeds.news import BasicNewsRecipe
+import re
+
 class Nowa_Fantastyka(BasicNewsRecipe):
     title          = u'Nowa Fantastyka'
     oldest_article = 7
     __author__        = 'fenuks'
+    __modified_by__   = 'zaslav'
     language       = 'pl'
     encoding='latin2'
     description ='site for fantasy readers'
     category='fantasy'
+    masthead_url='http://farm5.static.flickr.com/4133/4956658792_7ba7fbf562.jpg'
+    #extra_css='.tytul {font-size: 20px;}' #not working
     max_articles_per_feed = 100
     INDEX='http://www.fantastyka.pl/'
     no_stylesheets=True
     needs_subscription = 'optional'
-    remove_tags_before=dict(attrs={'class':'belka1-tlo-md'})
+    remove_tags_before=dict(attrs={'class':'naglowek2'})
     #remove_tags_after=dict(name='span', attrs={'class':'naglowek-oceny'})
-    remove_tags_after=dict(name='td', attrs={'class':'belka1-bot'})
+    remove_tags_after=dict(name='form', attrs={'name':'form1'})
-    remove_tags=[dict(attrs={'class':'avatar2'}), dict(name='span', attrs={'class':'alert-oceny'}), dict(name='img', attrs={'src':['obrazki/sledz1.png', 'obrazki/print.gif', 'obrazki/mlnf.gif']}), dict(name='b', text='Dodaj komentarz'),dict(name='a', attrs={'href':'http://www.fantastyka.pl/10,1727.html'})]
+    remove_tags=[dict(attrs={'class':['avatar2', 'belka-margin', 'naglowek2']}), dict(name='span', attrs={'class':'alert-oceny'}), dict(name='img', attrs={'src':['obrazki/sledz1.png', 'obrazki/print.gif', 'obrazki/mlnf.gif']}), dict(name='b', text='Dodaj komentarz'),dict(name='a', attrs={'href':'http://www.fantastyka.pl/10,1727.html'}), dict(name='form')]
+    preprocess_regexps = [
+    (re.compile(r'\<table .*?\>'), lambda match: ''),
+    (re.compile(r'\<td.*?\>'), lambda match: ''),
+    (re.compile(r'\<center\>'), lambda match: '')]
+
+
+
 
     def find_articles(self, url):
         articles = []
@@ -41,10 +53,10 @@ class Nowa_Fantastyka(BasicNewsRecipe):
 
          return feeds
 
+
     def get_cover_url(self):
-        soup = self.index_to_soup('http://www.fantastyka.pl/1.html')
+        soup = self.index_to_soup('http://www.e-kiosk.pl/nowa_fantastyka')
-        cover=soup.find(name='img', attrs={'class':'okladka'})
+        self.cover_url='http://www.e-kiosk.pl' + soup.find(name='a', attrs={'class':'img'})['href']
-        self.cover_url=self.INDEX+ cover['src']
         return getattr(self, 'cover_url', self.cover_url)
 
     def get_browser(self):
@@ -56,3 +68,18 @@ class Nowa_Fantastyka(BasicNewsRecipe):
             br['pass'] = self.password
             br.submit()
         return br
+
+    def preprocess_html(self, soup):        
+        for item in soup.findAll(style=True):
+            del item['style']
+        for item in soup.findAll(font=True):
+            del item['font']
+        for item in soup.findAll(align=True):
+            del item['align']
+        for item in soup.findAll(name='tr'):
+            item.name='div'
+        title=soup.find(attrs={'class':'tytul'})
+        if title:
+            title['style']='font-size: 20px; font-weight: bold;'
+        self.log.warn(soup)
+        return soup

recipes/oclab_pl.recipe

@@ -0,0 +1,31 @@
+from calibre.web.feeds.news import BasicNewsRecipe
+class OCLab(BasicNewsRecipe):
+    title          = u'OCLab.pl'
+    oldest_article = 7
+    max_articles_per_feed = 100
+    __author__        = 'fenuks'
+    description   = u'Portal OCLab.pl jest miejscem przyjaznym pasjonatom sprzętu komputerowego, w szczególności overclockerom, które będzie służyć im za aktualną bazę wiedzy o podkręcaniu komputera, źródło aktualnych informacji z rynku oraz opinii na temat sprzętu komputerowego.'
+    category       = 'IT'
+    language       = 'pl'
+    cover_url= 'http://www.idealforum.ru/attachment.php?attachmentid=7963&d=1316008118'
+    no_stylesheets = True
+    keep_only_tags=[dict(id='main')]
+    remove_tags_after= dict(attrs={'class':'single-postmetadata'})
+    remove_tags=[dict(attrs={'class':['single-postmetadata', 'pagebar']})]
+    feeds          = [(u'Wpisy', u'http://oclab.pl/feed/')]
+
+
+    def append_page(self, soup, appendtag):
+        tag=soup.find(attrs={'class':'contentjumpddl'})
+        if tag:
+            nexturl=tag.findAll('option')
+            for nextpage in nexturl[1:-1]:
+               soup2 = self.index_to_soup(nextpage['value'])
+               pagetext = soup2.find(attrs={'class':'single-entry'})
+               pos = len(appendtag.contents)
+               appendtag.insert(pos, pagetext)
+            for r in appendtag.findAll(attrs={'class':'post-nav-bottom-list'}):
+                r.extract()
+    def preprocess_html(self, soup):
+        self.append_page(soup, soup.body)
+        return soup

recipes/overclock_pl.recipe

@@ -0,0 +1,37 @@
+import re
+from calibre.web.feeds.news import BasicNewsRecipe
+class Overclock_pl(BasicNewsRecipe):
+    title          = u'Overclock.pl'
+    oldest_article = 7
+    max_articles_per_feed = 100
+    __author__        = 'fenuks'
+    description   = u'Vortal poświęcony tematyce hardware, kładący największy nacisk na podkręcanie / overclocking (włącznie z extreme) i chłodzenie / cooling (air cooling, water cooling, freon cooling, dry ice, liquid nitrogen).'
+    category       = 'IT'
+    language       = 'pl'
+    masthead_url='http://www.overclock.pl/gfx/logo_m.png'
+    cover_url='http://www.overclock.pl/gfx/logo_m.png'
+    no_stylesheets = True
+    remove_empty_feeds = True
+    preprocess_regexps = [(re.compile(ur'<b>Komentarze do aktualności:.*?</a>', re.DOTALL), lambda match: ''), (re.compile(ur'<h3>Nawigacja</h3>', re.DOTALL), lambda match: '') ]
+    keep_only_tags=[dict(name='div', attrs={'class':'news'}), dict(id='articleContent')]
+    remove_tags=[dict(name='span', attrs={'class':'info'}), dict(attrs={'class':'shareit'})]
+    feeds          = [(u'Aktualno\u015bci', u'http://www.overclock.pl/rss.news.xml'), (u'Testy i recenzje', u'http://www.overclock.pl/rss.articles.xml')]
+
+
+    def append_page(self, soup, appendtag):
+        tag=soup.find(id='navigation')
+        if tag:
+            nexturl=tag.findAll('option')
+            tag.extract()
+            for nextpage in nexturl[2:]:
+               soup2 = self.index_to_soup(nextpage['value'])
+               pagetext = soup2.find(id='content')
+               pos = len(appendtag.contents)
+               appendtag.insert(pos, pagetext)
+            rem=appendtag.find(attrs={'alt':'Pierwsza'})
+            if rem:
+                rem.parent.extract()
+
+    def preprocess_html(self, soup):
+        self.append_page(soup, soup.body)
+        return soup

recipes/palmtop_pl.recipe

@@ -0,0 +1,14 @@
+from calibre.web.feeds.news import BasicNewsRecipe
+class palmtop_pl(BasicNewsRecipe):
+    title          = u'Palmtop.pl'
+    __author__        = 'fenuks'
+    description   = 'wortal technologii mobilnych'
+    category       = 'mobile'
+    language       = 'pl'
+    cover_url='http://cdn.g-point.biz/wp-content/themes/palmtop-new/images/header_palmtop_logo.png'
+    masthead_url='http://cdn.g-point.biz/wp-content/themes/palmtop-new/images/header_palmtop_logo.png'
+    oldest_article = 7
+    max_articles_per_feed = 100
+    no_stylesheets = True
+
+    feeds          = [(u'Newsy', u'http://palmtop.pl/feed/atom/')]

recipes/pc_arena.recipe

@@ -0,0 +1,31 @@
+from calibre.web.feeds.news import BasicNewsRecipe
+class PC_Arena(BasicNewsRecipe):
+    title          = u'PCArena'
+    oldest_article = 18300
+    max_articles_per_feed = 100
+    __author__        = 'fenuks'
+    description   = u'Najnowsze informacje z branży IT - testy, recenzje, aktualności, rankingi, wywiady. Twoje źródło informacji o sprzęcie komputerowym.'
+    category       = 'IT'
+    language       = 'pl'
+    masthead_url='http://pcarena.pl/public/design/frontend/images/logo.gif'
+    cover_url= 'http://pcarena.pl/public/design/frontend/images/logo.gif'
+    no_stylesheets = True
+    keep_only_tags=[dict(attrs={'class':['artHeader', 'art']})]
+    remove_tags=[dict(attrs={'class':'pages'})]
+    feeds          = [(u'Newsy', u'http://pcarena.pl/misc/rss/news'), (u'Artyku\u0142y', u'http://pcarena.pl/misc/rss/articles')]
+
+    def append_page(self, soup, appendtag):
+        tag=soup.find(name='div', attrs={'class':'pagNum'})
+        if tag:
+            nexturl=tag.findAll('a')
+            tag.extract()
+            for nextpage in nexturl[1:]:
+               nextpage= 'http://pcarena.pl' + nextpage['href']
+               soup2 = self.index_to_soup(nextpage)
+               pagetext = soup2.find(attrs={'class':'artBody'})
+               pos = len(appendtag.contents)
+               appendtag.insert(pos, pagetext)
+
+    def preprocess_html(self, soup):
+        self.append_page(soup, soup.body)
+        return soup

recipes/pc_centre_pl.recipe

@@ -0,0 +1,41 @@
+from calibre.web.feeds.news import BasicNewsRecipe
+class PC_Centre(BasicNewsRecipe):
+    title          = u'PC Centre'
+    oldest_article = 7
+    max_articles_per_feed = 100
+    __author__        = 'fenuks'
+    description   = u'Portal komputerowy, a w nim: testy sprzętu komputerowego, recenzje gier i oprogramowania. a także opisy produktów związanych z komputerami.'
+    category       = 'IT'
+    language       = 'pl'
+    masthead_url= 'http://pccentre.pl/views/images/logo.gif'
+    cover_url= 'http://pccentre.pl/views/images/logo.gif'
+    no_stylesheets = True
+    keep_only_tags= [dict(id='content')]
+    remove_tags=[dict(attrs={'class':['ikony r', 'list_of_content', 'dot accordion']}), dict(id='comments')]
+    feeds          = [(u'Publikacje', u'http://pccentre.pl/backend.php?mode=a'), (u'Aktualno\u015bci', u'http://pccentre.pl/backend.php'), (u'Sprz\u0119t komputerowy', u'http://pccentre.pl/backend.php?mode=n&section=2'), (u'Oprogramowanie', u'http://pccentre.pl/backend.php?mode=n&section=3'), (u'Gry komputerowe i konsole', u'http://pccentre.pl/backend.php?mode=n&section=4'), (u'Internet', u'http://pccentre.pl/backend.php?mode=n&section=7'), (u'Bezpiecze\u0144stwo', u'http://pccentre.pl/backend.php?mode=n&section=5'), (u'Multimedia', u'http://pccentre.pl/backend.php?mode=n&section=6'), (u'Biznes', u'http://pccentre.pl/backend.php?mode=n&section=9')]
+
+
+    def append_page(self, soup, appendtag):
+        tag=soup.find(name='div', attrs={'class':'pages'})
+        if tag:
+            nexturl=tag.findAll('a')
+            tag.extract()
+            for nextpage in nexturl[:-1]:
+               nextpage= 'http://pccentre.pl' + nextpage['href']
+               soup2 = self.index_to_soup(nextpage)
+               pagetext = soup2.find(id='content')
+               rem=pagetext.findAll(attrs={'class':['subtitle', 'content_info', 'list_of_content', 'pages', 'social2', 'pcc_acc', 'pcc_acc_na']})
+               for r in rem:
+                   r.extract()
+               rem=pagetext.findAll(id='comments')
+               for r in rem:
+                   r.extract()
+               rem=pagetext.findAll('h1')
+               for r in rem:
+                   r.extract()
+               pos = len(appendtag.contents)
+               appendtag.insert(pos, pagetext)
+
+    def preprocess_html(self, soup):
+        self.append_page(soup, soup.body)
+        return soup

recipes/pc_foster.recipe

@@ -0,0 +1,35 @@
+from calibre.web.feeds.news import BasicNewsRecipe
+class PC_Foster(BasicNewsRecipe):
+    title          = u'PC Foster'
+    oldest_article = 7
+    max_articles_per_feed = 100
+    __author__        = 'fenuks'
+    description   = u'Vortal technologiczny: testy, recenzje sprzętu komputerowego i telefonów, nowinki hardware, programy i gry dla Windows. Podkręcanie, modding i Overclocking.'
+    category       = 'IT'
+    language       = 'pl'
+    masthead_url='http://pcfoster.pl/public/images/logo.png'
+    cover_url= 'http://pcfoster.pl/public/images/logo.png'
+    no_stylesheets= True
+    remove_empty_feeds= True
+    keep_only_tags= [dict(id=['news_details', 'review_details']), dict(attrs={'class':'pager more_top'})]
+    remove_tags=[dict(name='p', attrs={'class':'right'})]
+    feeds          = [(u'G\u0142\xf3wny', u'http://pcfoster.pl/public/rss/main.xml')]
+
+
+    def append_page(self, soup, appendtag):
+        nexturl= appendtag.find(attrs={'alt':u'Następna strona'})
+        if nexturl:
+            appendtag.find(attrs={'class':'pager more_top'}).extract()
+            while nexturl:
+                nexturl='http://pcfoster.pl' + nexturl.parent['href']
+                soup2 = self.index_to_soup(nexturl)
+                nexturl=soup2.find(attrs={'alt':u'Następna strona'})
+                pagetext = soup2.find(attrs={'class':'content'})
+                pos = len(appendtag.contents)
+                appendtag.insert(pos, pagetext)
+            for r in appendtag.findAll(attrs={'class':'review_content double'}):
+                r.extract()
+
+    def preprocess_html(self, soup):
+        self.append_page(soup, soup.body)
+        return soup

recipes/polska_times.recipe

@@ -0,0 +1,81 @@
+from calibre.web.feeds.news import BasicNewsRecipe
+import re
+class Polska_times(BasicNewsRecipe):
+    title          = u'Polska Times'
+    __author__        = 'fenuks'
+    description   = u'Internetowe wydanie dziennika ogólnopolskiego Polska The Times. Najświeższe informacje: wydarzenia w kraju i na świecie, reportaże, poradniki, opinie.'
+    category       = 'newspaper'
+    language       = 'pl'
+    masthead_url = 'http://s.polskatimes.pl/g/logo_naglowek/polska.gif?17'
+    oldest_article = 7
+    max_articles_per_feed = 100
+    remove_emty_feeds= True
+    no_stylesheets = True
+    preprocess_regexps = [(re.compile(ur'<b>Czytaj także:.*?</b>', re.DOTALL), lambda match: ''), (re.compile(ur',<b>Czytaj też:.*?</b>', re.DOTALL), lambda match: ''), (re.compile(ur'<b>Zobacz także:.*?</b>', re.DOTALL), lambda match: ''), (re.compile(ur'<center><h4><a.*?</a></h4></center>', re.DOTALL), lambda match: ''), (re.compile(ur'<b>CZYTAJ TEŻ:.*?</b>', re.DOTALL), lambda match: ''), (re.compile(ur'<b>CZYTAJ WIĘCEJ:.*?</b>', re.DOTALL), lambda match: ''), (re.compile(ur'<b>CZYTAJ TAKŻE:.*?</b>', re.DOTALL), lambda match: ''), (re.compile(ur'<b>\* CZYTAJ KONIECZNIE:.*', re.DOTALL), lambda match: '</body>'), (re.compile(ur'<b>Nasze serwisy:</b>.*', re.DOTALL), lambda match: '</body>') ]
+    keep_only_tags= [dict(id=['tytul-artykulu', 'kontent'])]
+    remove_tags_after= dict(id='material-tagi')
+    remove_tags=[dict(attrs={'id':'reklama_srodtekst_0'}), dict(attrs={'id':'material-tagi'}), dict(name='div', attrs={'class':'zakladki'}), dict(attrs={'title':u'CZYTAJ TAKŻE'}), dict(attrs={'id':'podobne'}), dict(name='a', attrs={'href':'http://www.dzienniklodzki.pl/newsletter'})]
+    feeds          = [(u'Fakty', u'http://polskatimes.feedsportal.com/c/32980/f/533648/index.rss'), (u'Opinie', u'http://www.polskatimes.pl/rss/opinie.xml'), (u'Sport', u'http://polskatimes.feedsportal.com/c/32980/f/533649/index.rss'), (u'Pieni\u0105dze', u'http://polskatimes.feedsportal.com/c/32980/f/533657/index.rss'), (u'Twoje finanse', u'http://www.polskatimes.pl/rss/twojefinanse.xml'), (u'Kultura', u'http://polskatimes.feedsportal.com/c/32980/f/533650/index.rss'), (u'Dodatki', u'http://www.polskatimes.pl/rss/dodatki.xml')]
+
+    def skip_ad_pages(self, soup):
+        if 'Advertisement' in soup.title:
+            nexturl=soup.find('a')['href']
+            return self.index_to_soup(nexturl, raw=True)
+
+    def append_page(self, soup, appendtag):
+        nexturl=soup.find(id='nastepna_strona')
+        while nexturl:
+            soup2= self.index_to_soup(nexturl['href'])
+            nexturl=soup2.find(id='nastepna_strona')
+            pagetext = soup2.find(id='tresc')
+            for dictionary in self.remove_tags:
+                 v=pagetext.findAll(attrs=dictionary['attrs'])
+                 for delete in v:
+                     delete.extract()
+            for b in pagetext.findAll(name='b'):
+                if b.string:
+                    if u'CZYTAJ TEŻ' in b.string or u'Czytaj także' in b.string or u'Czytaj też' in b.string or u'Zobacz także' in b.string:
+                        b.extract()
+            for center in pagetext.findAll(name='center'):
+                if center.h4:
+                    if center.h4.a:
+                        center.extract()
+            pos = len(appendtag.contents)
+            appendtag.insert(pos, pagetext)
+        for paginator in appendtag.findAll(attrs={'class':'stronicowanie'}):
+            paginator.extract()
+
+    def image_article(self, soup, appendtag):
+        nexturl=soup.find('a', attrs={'class':'nastepna'})
+        urls=[]
+        while nexturl:
+            if nexturl not in urls:
+                urls.append(nexturl)
+            else:
+                break
+            soup2= self.index_to_soup('http://www.polskatimes.pl/artykul/' + nexturl['href'])
+            nexturl=soup2.find('a', attrs={'class':'nastepna'})
+            if nexturl in urls:
+                break;
+            pagetext = soup2.find(id='galeria-material')
+            pos = len(appendtag.contents)
+            appendtag.insert(pos, '<br />')
+            pos = len(appendtag.contents)
+            appendtag.insert(pos, pagetext)
+        for rem in appendtag.findAll(attrs={'class':['galeriaNawigator', 'miniaturyPojemnik']}):
+            rem.extract()
+        for paginator in appendtag.findAll(attrs={'class':'stronicowanie'}):
+            paginator.extract()
+
+    def preprocess_html(self, soup):
+        if soup.find('a', attrs={'class':'nastepna'}):
+            self.image_article(soup, soup.body)
+        elif soup.find(id='nastepna_strona'):
+            self.append_page(soup, soup.body)
+        return soup
+
+
+    def get_cover_url(self):
+        soup = self.index_to_soup('http://www.prasa24.pl/gazeta/metropolia-warszawska/')
+        self.cover_url=soup.find(id='pojemnik').img['src']
+        return getattr(self, 'cover_url', self.cover_url)

recipes/pure_pc.recipe

@@ -0,0 +1,33 @@
+from calibre.web.feeds.news import BasicNewsRecipe
+class PurePC(BasicNewsRecipe):
+    title          = u'PurePC'
+    oldest_article = 7
+    max_articles_per_feed = 100
+    __author__        = 'fenuks'
+    description   = u'Artykuły, aktualności, sprzęt, forum, chłodzenie, modding, urządzenia mobilne - wszystko w jednym miejscu.'
+    category       = 'IT'
+    language       = 'pl'
+    masthead_url= 'http://www.purepc.pl/themes/new/images/purepc.jpg'
+    cover_url= 'http://www.purepc.pl/themes/new/images/purepc.jpg'
+    no_stylesheets = True
+    keep_only_tags= [dict(id='content')]
+    remove_tags_after= dict(attrs={'class':'fivestar-widget'})
+    remove_tags= [dict(id='navigator'), dict(attrs={'class':['box-tools', 'fivestar-widget', 'PageMenuList']})]
+    feeds          = [(u'Wiadomo\u015bci', u'http://www.purepc.pl/node/feed')]
+
+
+    def append_page(self, soup, appendtag):
+        nexturl= appendtag.find(attrs={'class':'pager-next'})
+        if nexturl:
+            while nexturl:
+                soup2 = self.index_to_soup('http://www.purepc.pl'+ nexturl.a['href'])
+                nexturl=soup2.find(attrs={'class':'pager-next'})
+                pagetext = soup2.find(attrs={'class':'article'})
+                pos = len(appendtag.contents)
+                appendtag.insert(pos, pagetext)
+            for r in appendtag.findAll(attrs={'class':['PageMenuList', 'pager', 'fivestar-widget']}):
+                r.extract()
+
+    def preprocess_html(self, soup):
+        self.append_page(soup, soup.body)
+        return soup

recipes/tablety_pl.recipe

@@ -1,14 +1,16 @@
 from calibre.web.feeds.news import BasicNewsRecipe
-
+import re
 class Tablety_pl(BasicNewsRecipe):
     title          = u'Tablety.pl'
     __author__        = 'fenuks'
     description   = u'tablety.pl - latest tablet news'
+    masthead_url= 'http://www.tablety.pl/wp-content/themes/kolektyw/img/logo.png'
     cover_url      = 'http://www.tablety.pl/wp-content/themes/kolektyw/img/logo.png'
     category       = 'IT'
     language       = 'pl'
     oldest_article = 8
     max_articles_per_feed = 100
+    preprocess_regexps = [(re.compile(ur'<p><strong>Przeczytaj także.*?</a></strong></p>', re.DOTALL), lambda match: ''), (re.compile(ur'<p><strong>Przeczytaj koniecznie.*?</a></strong></p>', re.DOTALL), lambda match: '')]
     remove_tags_before=dict(name="h1", attrs={'class':'entry-title'})
     remove_tags_after=dict(name="div", attrs={'class':'snap_nopreview sharing robots-nocontent'})
     remove_tags=[dict(name='div', attrs={'class':'snap_nopreview sharing robots-nocontent'})]

recipes/tanuki.recipe

@@ -0,0 +1,37 @@
+from calibre.web.feeds.news import BasicNewsRecipe
+import re
+class tanuki(BasicNewsRecipe):
+    title          = u'Tanuki'
+    oldest_article = 7
+    __author__        = 'fenuks'
+    category       = 'anime, manga'
+    language       = 'pl'
+    max_articles_per_feed = 100
+    encoding='utf-8'
+    extra_css= 'ul {list-style: none; padding: 0; margin: 0;} .kadr{float: left;} .dwazdania {float: right;}'
+    preprocess_regexps = [(re.compile(ur'<h3><a class="screen".*?</h3>', re.DOTALL), lambda match: ''), (re.compile(ur'<div><a href="/strony/((manga)|(anime))/[0-9]+?/oceny(\-redakcji){0,1}">Zobacz jak ocenili</a></div>', re.DOTALL), lambda match: '')]
+    remove_empty_feeds= True
+    no_stylesheets = True
+    keep_only_tags=[dict(attrs={'class':['animename', 'storyname', 'nextarrow','sideinfov', 'sidelinfov', 'sideinfo', 'sidelinfo']}), dict(name='table', attrs={'summary':'Technikalia'}), dict(attrs={'class':['chaptername','copycat']}), dict(id='rightcolumn'), dict(attrs={'class':['headn_tt', 'subtable']})]
+    remove_tags=[dict(name='div', attrs={'class':'screen'}), dict(id='randomtoplist'), dict(attrs={'class':'note'})]
+    feeds          = [(u'Anime', u'http://anime.tanuki.pl/rss_anime.xml'), (u'Manga', u'http://manga.tanuki.pl/rss_manga.xml'), (u'Tomiki', u'http://manga.tanuki.pl/rss_mangabooks.xml'), (u'Artyku\u0142y', u'http://czytelnia.tanuki.pl/rss_czytelnia_artykuly.xml'), (u'Opowiadania', u'http://czytelnia.tanuki.pl/rss_czytelnia.xml')]
+
+
+    def append_page(self, soup, appendtag):
+        nexturl= appendtag.find(attrs={'class':'nextarrow'})
+        if nexturl:
+            while nexturl:
+                soup2 = self.index_to_soup('http://czytelnia.tanuki.pl'+ nexturl['href'])
+                nexturl=soup2.find(attrs={'class':'nextarrow'})
+                pagetext = soup2.find(attrs={'class':['chaptername', 'copycat']})
+                pos = len(appendtag.contents)
+                appendtag.insert(pos, pagetext)
+                pagetext = soup2.find(attrs={'class':'copycat'})
+                pos = len(appendtag.contents)
+                appendtag.insert(pos, pagetext)
+            for r in appendtag.findAll(attrs={'class':'nextarrow'}):
+                r.extract()
+
+    def preprocess_html(self, soup):
+        self.append_page(soup, soup.body)
+        return soup

recipes/the_sun.recipe

@@ -1,49 +1,57 @@
 import re
-from calibre.web.feeds.news import BasicNewsRecipe
+from calibre.web.feeds.recipes import BasicNewsRecipe
-from calibre.ebooks.BeautifulSoup import Tag
 
-class AdvancedUserRecipe1268409464(BasicNewsRecipe):
+class AdvancedUserRecipe1325006965(BasicNewsRecipe):
-    title = u'The Sun'
+
-    __author__ = 'Chaz Ralph'
+    title          = u'The Sun UK'
-    description = 'News from The Sun'
+    cover_url = 'http://www.thesun.co.uk/img/global/new-masthead-logo.png'
+
+    description = 'A Recipe for The Sun tabloid UK - uses feed43'
+    __author__ = 'Dave Asbury'
+    # last updated 20/2/12
+    language = 'en_GB'
     oldest_article = 1
-    max_articles_per_feed = 100
+    max_articles_per_feed = 15
-    language = 'en'
+    remove_empty_feeds = True
     no_stylesheets = True
-    extra_css = '.headline {font-size: x-large;} \n .fact { padding-top: 10pt }'
+
-    encoding= 'iso-8859-1'
+    masthead_url = 'http://www.thesun.co.uk/sol/img/global/Sun-logo.gif'
-    remove_javascript = True
+    encoding = 'cp1251'
+
+    encoding = 'cp1252'
+    remove_empty_feeds = True
+    remove_javascript     = True
+    no_stylesheets = 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;}
+                     '''
+
+    preprocess_regexps = [
+        (re.compile(r'<div class="foot-copyright".*?</div>', re.IGNORECASE | re.DOTALL), lambda match: '')]
 
     keep_only_tags = [
-            dict(id='column-print')
+                               dict(name='h1'),dict(name='h2',attrs={'class' : 'medium centered'}),
+               dict(name='div',attrs={'class' : 'text-center'}),
+               dict(name='div',attrs={'id' : 'bodyText'})
+               # dict(name='p')
+               ]
+
+    remove_tags=[
+           #dict(name='head'),
+           dict(attrs={'class' : ['mystery-meat-link','ltbx-container','ltbx-var ltbx-hbxpn','ltbx-var ltbx-nav-loop','ltbx-var ltbx-url']}),
+                           dict(name='div',attrs={'class' : 'cf'}),
+           dict(attrs={'title' : 'download flash'}),
+                           dict(attrs={'style' : 'padding: 5px'})
+
+           ]
+
+    feeds          = [
+        (u'News','http://feed43.com/2517447382644748.xml'),
+        (u'Sport', u'http://feed43.com/4283846255668687.xml'),
+        (u'Bizarre', u'http://feed43.com/0233840304242011.xml'),
+        (u'Film',u'http://feed43.com/1307545221226200.xml'),
+        (u'Music',u'http://feed43.com/1701513435064132.xml'),
+        (u'Sun Woman',u'http://feed43.com/0022626854226453.xml'),
     ]
 
-    remove_tags = [
-        dict(name='div', attrs={'class':[
-            'clear text-center small padding-left-right-5 text-999 padding-top-5 padding-bottom-10 grey-solid-line',
-            'clear width-625 bg-fff padding-top-10'
-            ]}),
-        dict(name='video'),
-    ]
-
-    def preprocess_html(self, soup):
-        h1 = soup.find('h1')
-        if h1 is not None:
-            text = self.tag_to_string(h1)
-            nh = Tag(soup, 'h1')
-            nh.insert(0, text)
-            h1.replaceWith(nh)
-
-        return soup
-
-
-    feeds = [(u'News', u'http://www.thesun.co.uk/sol/homepage/feeds/rss/article312900.ece')
-,(u'Sport', u'http://www.thesun.co.uk/sol/homepage/feeds/rss/article247732.ece')
-,(u'Football', u'http://www.thesun.co.uk/sol/homepage/feeds/rss/article247739.ece')
-,(u'Gizmo', u'http://www.thesun.co.uk/sol/homepage/feeds/rss/article247829.ece')
-,(u'Bizarre', u'http://www.thesun.co.uk/sol/homepage/feeds/rss/article247767.ece')]
-
-    def print_version(self, url):
-        return re.sub(r'\?OTC-RSS&ATTR=[-a-zA-Z]+', '?print=yes', url)
-
-

recipes/times_of_malta.recipe

@@ -0,0 +1,11 @@
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class BasicUserRecipe1317069944(BasicNewsRecipe):
+    title          = u'Times of Malta'
+    __author__ = 'To Do'
+    language = 'en'
+    oldest_article = 7
+    max_articles_per_feed = 100
+    auto_cleanup = True
+
+    feeds          = [(u'Times of Malta', u'http://www.timesofmalta.com/rss')]

recipes/tvn24.recipe

@@ -0,0 +1,24 @@
+from calibre.web.feeds.news import BasicNewsRecipe
+class tvn24(BasicNewsRecipe):
+    title          = u'TVN24'
+    oldest_article = 7
+    max_articles_per_feed = 100
+    __author__        = 'fenuks'
+    description   = u'Sport, Biznes, Gospodarka, Informacje, Wiadomości Zawsze aktualne wiadomości z Polski i ze świata'
+    category       = 'news'
+    language       = 'pl'
+    masthead_url= 'http://www.tvn24.pl/_d/topmenu/logo2.gif'
+    cover_url= 'http://www.tvn24.pl/_d/topmenu/logo2.gif'
+    extra_css= 'ul {list-style: none; padding: 0; margin: 0;} li {float: left;margin: 0 0.15em;}'
+    remove_empty_feeds = True
+    remove_javascript = True
+    no_stylesheets = True
+    keep_only_tags=[dict(id='tvn24_wiadomosci_detal'), dict(name='h1', attrs={'class':'standardHeader1'}), dict(attrs={'class':['date60m rd5', 'imageBackground fl rd7', 'contentFromCMS']})]
+    remove_tags_after= dict(name='div', attrs={'class':'socialBoxesBottom'})
+    remove_tags=[dict(attrs={'class':['tagi_detal', 'socialBoxesBottom', 'twitterBox', 'commentsInfo', 'textSize', 'obj_ukrytydruk obj_ramka1_r', 'related newsNews align-right', 'box', 'newsUserList', 'watchMaterial text']})]
+    feeds          = [(u'Najnowsze', u'http://www.tvn24.pl/najnowsze.xml'), (u'Polska', u'www.tvn24.pl/polska.xml'), (u'\u015awiat', u'http://www.tvn24.pl/swiat.xml'), (u'Sport', u'http://www.tvn24.pl/sport.xml'), (u'Biznes', u'http://www.tvn24.pl/biznes.xml'), (u'Meteo', u'http://www.tvn24.pl/meteo.xml'), (u'Micha\u0142ki', u'http://www.tvn24.pl/michalki.xml'), (u'Kultura', u'http://www.tvn24.pl/kultura.xml')]
+
+    def preprocess_html(self, soup):
+        for item in soup.findAll(style=True):
+            del item['style']
+        return soup

recipes/ubuntu_pl.recipe

@@ -4,10 +4,12 @@ class Ubuntu_pl(BasicNewsRecipe):
     title          = u'UBUNTU.pl'
     __author__        = 'fenuks'
     description   = 'UBUNTU.pl - polish ubuntu community site'
+    masthead_url= 'http://ubuntu.pl/img/logo.jpg'
     cover_url      = 'http://ubuntu.pl/img/logo.jpg'
     category       = 'linux, IT'
     language       = 'pl'
     no_stylesheets = True
+    remove_empty_feeds = True
     oldest_article = 8
     max_articles_per_feed = 100
     extra_css      = '#main {text-align:left;}'

recipes/webhosting_pl.recipe

@@ -0,0 +1,39 @@
+from calibre.web.feeds.news import BasicNewsRecipe
+class webhosting_pl(BasicNewsRecipe):
+    title          = u'Webhosting.pl'
+    __author__        = 'fenuks'
+    description   = 'Webhosting.pl to pierwszy na polskim rynku serwis poruszający w szerokim aspekcie tematy związane z hostingiem, globalną Siecią i usługami internetowymi. Głównym celem przedsięwzięcia jest dostarczanie przydatnej i bogatej merytorycznie wiedzy osobom, które chcą tworzyć i efektywnie wykorzystywać współczesny Internet.'
+    category       = 'web'
+    language       = 'pl'
+    cover_url='http://webhosting.pl/images/logo.png'
+    masthead_url='http://webhosting.pl/images/logo.png'
+    oldest_article = 7
+    max_articles_per_feed = 100
+    no_stylesheets = True
+    remove_empty_feeds = True
+    #keep_only_tags= [dict(name='div', attrs={'class':'content_article'}), dict(attrs={'class':'paging'})]
+    #remove_tags=[dict(attrs={'class':['tags', 'wykop', 'facebook_button_count', 'article_bottom']})]
+    feeds          = [(u'Newsy', u'http://webhosting.pl/feed/rss/an'), 
+		(u'Artyku\u0142y', u'http://webhosting.pl/feed/rss/aa'), 
+		(u'Software', u'http://webhosting.pl/feed/rss/n/12'), 
+		(u'Internet', u'http://webhosting.pl/feed/rss/n/9'), 
+		(u'Biznes', u'http://webhosting.pl/feed/rss/n/13'), 
+		(u'Bezpiecze\u0144stwo', u'http://webhosting.pl/feed/rss/n/10'), 
+		(u'Blogi', u'http://webhosting.pl/feed/rss/ab'),  
+		(u'Programowanie', u'http://webhosting.pl/feed/rss/n/8'), 
+		(u'Kursy', u'http://webhosting.pl/feed/rss/n/11'), 
+		(u'Tips&Tricks', u'http://webhosting.pl/feed/rss/n/15'), 
+		(u'Imprezy', u'http://webhosting.pl/feed/rss/n/22'), 
+		(u'Wywiady', u'http://webhosting.pl/feed/rss/n/24'), 
+		(u'Porady', u'http://webhosting.pl/feed/rss/n/3027'), 
+		(u'Znalezione w sieci', u'http://webhosting.pl/feed/rss/n/6804'), 
+		(u'Dev area', u'http://webhosting.pl/feed/rss/n/24504'), 
+		(u"Webmaster's blog", u'http://webhosting.pl/feed/rss/n/29195'), 
+		(u'Domeny', u'http://webhosting.pl/feed/rss/n/11513'), 
+		(u'Praktyka', u'http://webhosting.pl/feed/rss/n/2'), 
+		(u'Serwery', u'http://webhosting.pl/feed/rss/n/11514'), 
+		(u'Inne', u'http://webhosting.pl/feed/rss/n/24811'), 
+		(u'Marketing', u'http://webhosting.pl/feed/rss/n/11535')]
+
+    def print_version(self, url):
+        return url.replace('webhosting.pl', 'webhosting.pl/print')

recipes/worldcrunch.recipe

@@ -3,7 +3,7 @@ from calibre.web.feeds.news import BasicNewsRecipe
 class Worldcrunch(BasicNewsRecipe):
     title          = u'Worldcrunch'
     __author__     = 'Krittika Goyal'
-    oldest_article = 1 #days
+    oldest_article = 2 #days
     max_articles_per_feed = 25
     use_embedded_content = False
 

resources/default_tweaks.py

@@ -128,6 +128,17 @@ categories_collapsed_name_template = r'{first.sort:shorten(4,,0)} - {last.sort:s
 categories_collapsed_rating_template = r'{first.avg_rating:4.2f:ifempty(0)} - {last.avg_rating:4.2f:ifempty(0)}'
 categories_collapsed_popularity_template = r'{first.count:d} - {last.count:d}'
 
+#: Control order of categories in the tag browser
+# Change the following dict to change the order that categories are displayed in
+# the tag browser. Items are named using their lookup name, and will be sorted
+# using the number supplied. The lookup name '*' stands for all names that
+# otherwise do not appear. Two names with the same value will be sorted
+# according to the default order; the one used when the dict is empty.
+# Example: tag_browser_category_order = {'series':1, 'tags':2, '*':3}
+# resulting in the order series, tags, then everything else in default order.
+tag_browser_category_order = {'*':1}
+
+
 #: Specify columns to sort the booklist by on startup
 # Provide a set of columns to be sorted on when calibre starts
 #  The argument is None if saved sort history is to be used
@@ -374,10 +385,11 @@ maximum_resort_levels = 5
 # the fields that are being displayed.
 sort_dates_using_visible_fields = False
 
-#: Specify which font to use when generating a default cover
+#: Specify which font to use when generating a default cover or masthead
 # Absolute path to .ttf font files to use as the fonts for the title, author
-# and footer when generating a default cover. Useful if the default font (Liberation
+# and footer when generating a default cover or masthead image. Useful if the
-# Serif) does not contain glyphs for the language of the books in your library.
+# default font (Liberation Serif) does not contain glyphs for the language of
+# the books in your library.
 generate_cover_title_font = None
 generate_cover_foot_font = None
 

setup/iso_639/en_GB.po

@@ -8,14 +8,14 @@ msgstr ""
 "Project-Id-Version: calibre\n"
 "Report-Msgid-Bugs-To: FULL NAME <EMAIL@ADDRESS>\n"
 "POT-Creation-Date: 2011-11-25 14:01+0000\n"
-"PO-Revision-Date: 2012-02-15 11:31+0000\n"
+"PO-Revision-Date: 2012-02-22 10:57+0000\n"
 "Last-Translator: Vibhav Pant <vibhavp@gmail.com>\n"
 "Language-Team: English (United Kingdom) <en_GB@li.org>\n"
 "MIME-Version: 1.0\n"
 "Content-Type: text/plain; charset=UTF-8\n"
 "Content-Transfer-Encoding: 8bit\n"
-"X-Launchpad-Export-Date: 2012-02-16 05:03+0000\n"
+"X-Launchpad-Export-Date: 2012-02-23 04:37+0000\n"
-"X-Generator: Launchpad (build 14781)\n"
+"X-Generator: Launchpad (build 14855)\n"
 
 #. name for aaa
 msgid "Ghotuo"
@@ -7883,523 +7883,523 @@ msgstr "Gants"
 
 #. name for gap
 msgid "Gal"
-msgstr ""
+msgstr "Gal"
 
 #. name for gaq
 msgid "Gata'"
-msgstr ""
+msgstr "Gata'"
 
 #. name for gar
 msgid "Galeya"
-msgstr ""
+msgstr "Galeya"
 
 #. name for gas
 msgid "Garasia; Adiwasi"
-msgstr ""
+msgstr "Garasia; Adiwasi"
 
 #. name for gat
 msgid "Kenati"
-msgstr ""
+msgstr "Kenati"
 
 #. name for gau
 msgid "Gadaba; Mudhili"
-msgstr ""
+msgstr "Gadaba; Mudhili"
 
 #. name for gaw
 msgid "Nobonob"
-msgstr ""
+msgstr "Nobonob"
 
 #. name for gax
 msgid "Oromo; Borana-Arsi-Guji"
-msgstr ""
+msgstr "Oromo; Borana-Arsi-Guji"
 
 #. name for gay
 msgid "Gayo"
-msgstr ""
+msgstr "Gayo"
 
 #. name for gaz
 msgid "Oromo; West Central"
-msgstr ""
+msgstr "Oromo; West Central"
 
 #. name for gba
 msgid "Gbaya (Central African Republic)"
-msgstr ""
+msgstr "Gbaya (Central African Republic)"
 
 #. name for gbb
 msgid "Kaytetye"
-msgstr ""
+msgstr "Kaytetye"
 
 #. name for gbc
 msgid "Garawa"
-msgstr ""
+msgstr "Garawa"
 
 #. name for gbd
 msgid "Karadjeri"
-msgstr ""
+msgstr "Karadjeri"
 
 #. name for gbe
 msgid "Niksek"
-msgstr ""
+msgstr "Niksek"
 
 #. name for gbf
 msgid "Gaikundi"
-msgstr ""
+msgstr "Gaikundi"
 
 #. name for gbg
 msgid "Gbanziri"
-msgstr ""
+msgstr "Gbanziri"
 
 #. name for gbh
 msgid "Gbe; Defi"
-msgstr ""
+msgstr "Gbe; Defi"
 
 #. name for gbi
 msgid "Galela"
-msgstr ""
+msgstr "Galela"
 
 #. name for gbj
 msgid "Gadaba; Bodo"
-msgstr ""
+msgstr "Gadaba; Bodo"
 
 #. name for gbk
 msgid "Gaddi"
-msgstr ""
+msgstr "Gaddi"
 
 #. name for gbl
 msgid "Gamit"
-msgstr ""
+msgstr "Gamit"
 
 #. name for gbm
 msgid "Garhwali"
-msgstr ""
+msgstr "Garhwali"
 
 #. name for gbn
 msgid "Mo'da"
-msgstr ""
+msgstr "Mo'da"
 
 #. name for gbo
 msgid "Grebo; Northern"
-msgstr ""
+msgstr "Grebo; Northern"
 
 #. name for gbp
 msgid "Gbaya-Bossangoa"
-msgstr ""
+msgstr "Gbaya-Bossangoa"
 
 #. name for gbq
 msgid "Gbaya-Bozoum"
-msgstr ""
+msgstr "Gbaya-Bozoum"
 
 #. name for gbr
 msgid "Gbagyi"
-msgstr ""
+msgstr "Gbagyi"
 
 #. name for gbs
 msgid "Gbe; Gbesi"
-msgstr ""
+msgstr "Gbe; Gbesi"
 
 #. name for gbu
 msgid "Gagadu"
-msgstr ""
+msgstr "Gagadu"
 
 #. name for gbv
 msgid "Gbanu"
-msgstr ""
+msgstr "Gbanu"
 
 #. name for gbx
 msgid "Gbe; Eastern Xwla"
-msgstr ""
+msgstr "Gbe; Eastern Xwla"
 
 #. name for gby
 msgid "Gbari"
-msgstr ""
+msgstr "Gbari"
 
 #. name for gbz
 msgid "Dari; Zoroastrian"
-msgstr ""
+msgstr "Dari; Zoroastrian"
 
 #. name for gcc
 msgid "Mali"
-msgstr ""
+msgstr "Mali"
 
 #. name for gcd
 msgid "Ganggalida"
-msgstr ""
+msgstr "Ganggalida"
 
 #. name for gce
 msgid "Galice"
-msgstr ""
+msgstr "Galice"
 
 #. name for gcf
 msgid "Creole French; Guadeloupean"
-msgstr ""
+msgstr "Creole French; Guadeloupean"
 
 #. name for gcl
 msgid "Creole English; Grenadian"
-msgstr ""
+msgstr "Creole English; Grenadian"
 
 #. name for gcn
 msgid "Gaina"
-msgstr ""
+msgstr "Gaina"
 
 #. name for gcr
 msgid "Creole French; Guianese"
-msgstr ""
+msgstr "Creole French; Guianese"
 
 #. name for gct
 msgid "German; Colonia Tovar"
-msgstr ""
+msgstr "German; Colonia Tovar"
 
 #. name for gda
 msgid "Lohar; Gade"
-msgstr ""
+msgstr "Lohar; Gade"
 
 #. name for gdb
 msgid "Gadaba; Pottangi Ollar"
-msgstr ""
+msgstr "Gadaba; Pottangi Ollar"
 
 #. name for gdc
 msgid "Gugu Badhun"
-msgstr ""
+msgstr "Gugu Badhun"
 
 #. name for gdd
 msgid "Gedaged"
-msgstr ""
+msgstr "Gedaged"
 
 #. name for gde
 msgid "Gude"
-msgstr ""
+msgstr "Gude"
 
 #. name for gdf
 msgid "Guduf-Gava"
-msgstr ""
+msgstr "Guduf-Gava"
 
 #. name for gdg
 msgid "Ga'dang"
-msgstr ""
+msgstr "Ga'dang"
 
 #. name for gdh
 msgid "Gadjerawang"
-msgstr ""
+msgstr "Gadjerawang"
 
 #. name for gdi
 msgid "Gundi"
-msgstr ""
+msgstr "Gundi"
 
 #. name for gdj
 msgid "Gurdjar"
-msgstr ""
+msgstr "Gurdjar"
 
 #. name for gdk
 msgid "Gadang"
-msgstr ""
+msgstr "Gadang"
 
 #. name for gdl
 msgid "Dirasha"
-msgstr ""
+msgstr "Dirasha"
 
 #. name for gdm
 msgid "Laal"
-msgstr ""
+msgstr "Laal"
 
 #. name for gdn
 msgid "Umanakaina"
-msgstr ""
+msgstr "Umanakaina"
 
 #. name for gdo
 msgid "Ghodoberi"
-msgstr ""
+msgstr "Ghodoberi"
 
 #. name for gdq
 msgid "Mehri"
-msgstr ""
+msgstr "Mehri"
 
 #. name for gdr
 msgid "Wipi"
-msgstr ""
+msgstr "Wipi"
 
 #. name for gdu
 msgid "Gudu"
-msgstr ""
+msgstr "Gudu"
 
 #. name for gdx
 msgid "Godwari"
-msgstr ""
+msgstr "Godwari"
 
 #. name for gea
 msgid "Geruma"
-msgstr ""
+msgstr "Geruma"
 
 #. name for geb
 msgid "Kire"
-msgstr ""
+msgstr "Kire"
 
 #. name for gec
 msgid "Grebo; Gboloo"
-msgstr ""
+msgstr "Grebo; Gboloo"
 
 #. name for ged
 msgid "Gade"
-msgstr ""
+msgstr "Gade"
 
 #. name for geg
 msgid "Gengle"
-msgstr ""
+msgstr "Gengle"
 
 #. name for geh
 msgid "German; Hutterite"
-msgstr ""
+msgstr "German; Hutterite"
 
 #. name for gei
 msgid "Gebe"
-msgstr ""
+msgstr "Gebe"
 
 #. name for gej
 msgid "Gen"
-msgstr ""
+msgstr "Gen"
 
 #. name for gek
 msgid "Yiwom"
-msgstr ""
+msgstr "Yiwom"
 
 #. name for gel
 msgid "ut-Ma'in"
-msgstr ""
+msgstr "ut-Ma'in"
 
 #. name for geq
 msgid "Geme"
-msgstr ""
+msgstr "Geme"
 
 #. name for ges
 msgid "Geser-Gorom"
-msgstr ""
+msgstr "Geser-Gorom"
 
 #. name for gew
 msgid "Gera"
-msgstr ""
+msgstr "Gera"
 
 #. name for gex
 msgid "Garre"
-msgstr ""
+msgstr "Garre"
 
 #. name for gey
 msgid "Enya"
-msgstr ""
+msgstr "Enya"
 
 #. name for gez
 msgid "Geez"
-msgstr ""
+msgstr "Geez"
 
 #. name for gfk
 msgid "Patpatar"
-msgstr ""
+msgstr "Patpatar"
 
 #. name for gft
 msgid "Gafat"
-msgstr ""
+msgstr "Gafat"
 
 #. name for gga
 msgid "Gao"
-msgstr ""
+msgstr "Gao"
 
 #. name for ggb
 msgid "Gbii"
-msgstr ""
+msgstr "Gbii"
 
 #. name for ggd
 msgid "Gugadj"
-msgstr ""
+msgstr "Gugadj"
 
 #. name for gge
 msgid "Guragone"
-msgstr ""
+msgstr "Guragone"
 
 #. name for ggg
 msgid "Gurgula"
-msgstr ""
+msgstr "Gurgula"
 
 #. name for ggk
 msgid "Kungarakany"
-msgstr ""
+msgstr "Kungarakany"
 
 #. name for ggl
 msgid "Ganglau"
-msgstr ""
+msgstr "Ganglau"
 
 #. name for ggn
 msgid "Gurung; Eastern"
-msgstr ""
+msgstr "Gurung; Eastern"
 
 #. name for ggo
 msgid "Gondi; Southern"
-msgstr ""
+msgstr "Gondi; Southern"
 
 #. name for ggr
 msgid "Aghu Tharnggalu"
-msgstr ""
+msgstr "Aghu Tharnggalu"
 
 #. name for ggt
 msgid "Gitua"
-msgstr ""
+msgstr "Gitua"
 
 #. name for ggu
 msgid "Gagu"
-msgstr ""
+msgstr "Gagu"
 
 #. name for ggw
 msgid "Gogodala"
-msgstr ""
+msgstr "Gogodala"
 
 #. name for gha
 msgid "Ghadamès"
-msgstr ""
+msgstr "Ghadamès"
 
 #. name for ghc
 msgid "Gaelic; Hiberno-Scottish"
-msgstr ""
+msgstr "Gaelic; Hiberno-Scottish"
 
 #. name for ghe
 msgid "Ghale; Southern"
-msgstr ""
+msgstr "Ghale; Southern"
 
 #. name for ghh
 msgid "Ghale; Northern"
-msgstr ""
+msgstr "Ghale; Northern"
 
 #. name for ghk
 msgid "Karen; Geko"
-msgstr ""
+msgstr "Karen; Geko"
 
 #. name for ghl
 msgid "Ghulfan"
-msgstr ""
+msgstr "Ghulfan"
 
 #. name for ghn
 msgid "Ghanongga"
-msgstr ""
+msgstr "Ghanongga"
 
 #. name for gho
 msgid "Ghomara"
-msgstr ""
+msgstr "Ghomara"
 
 #. name for ghr
 msgid "Ghera"
-msgstr ""
+msgstr "Ghera"
 
 #. name for ghs
 msgid "Guhu-Samane"
-msgstr ""
+msgstr "Guhu-Samane"
 
 #. name for ght
 msgid "Ghale; Kutang"
-msgstr ""
+msgstr "Ghale; Kutang"
 
 #. name for gia
 msgid "Kitja"
-msgstr ""
+msgstr "Kitja"
 
 #. name for gib
 msgid "Gibanawa"
-msgstr ""
+msgstr "Gibanawa"
 
 #. name for gic
 msgid "Gail"
-msgstr ""
+msgstr "Gail"
 
 #. name for gid
 msgid "Gidar"
-msgstr ""
+msgstr "Gidar"
 
 #. name for gig
 msgid "Goaria"
-msgstr ""
+msgstr "Goaria"
 
 #. name for gil
 msgid "Gilbertese"
-msgstr ""
+msgstr "Gilbertese"
 
 #. name for gim
 msgid "Gimi (Eastern Highlands)"
-msgstr ""
+msgstr "Gimi (Eastern Highlands)"
 
 #. name for gin
 msgid "Hinukh"
-msgstr ""
+msgstr "Hinukh"
 
 #. name for gio
 msgid "Gelao"
-msgstr ""
+msgstr "Gelao"
 
 #. name for gip
 msgid "Gimi (West New Britain)"
-msgstr ""
+msgstr "Gimi (West New Britain)"
 
 #. name for giq
 msgid "Gelao; Green"
-msgstr ""
+msgstr "Gelao; Green"
 
 #. name for gir
 msgid "Gelao; Red"
-msgstr ""
+msgstr "Gelao; Red"
 
 #. name for gis
 msgid "Giziga; North"
-msgstr ""
+msgstr "Giziga; North"
 
 #. name for git
 msgid "Gitxsan"
-msgstr ""
+msgstr "Gitxsan"
 
 #. name for giw
 msgid "Gelao; White"
-msgstr ""
+msgstr "Gelao; White"
 
 #. name for gix
 msgid "Gilima"
-msgstr ""
+msgstr "Gilima"
 
 #. name for giy
 msgid "Giyug"
-msgstr ""
+msgstr "Giyug"
 
 #. name for giz
 msgid "Giziga; South"
-msgstr ""
+msgstr "Giziga; South"
 
 #. name for gji
 msgid "Geji"
-msgstr ""
+msgstr "Geji"
 
 #. name for gjk
 msgid "Koli; Kachi"
-msgstr ""
+msgstr "Koli; Kachi"
 
 #. name for gjn
 msgid "Gonja"
-msgstr ""
+msgstr "Gonja"
 
 #. name for gju
 msgid "Gujari"
-msgstr ""
+msgstr "Gujari"
 
 #. name for gka
 msgid "Guya"
-msgstr ""
+msgstr "Guya"
 
 #. name for gke
 msgid "Ndai"
-msgstr ""
+msgstr "Ndai"
 
 #. name for gkn
 msgid "Gokana"
-msgstr ""
+msgstr "Gokana"
 
 #. name for gkp
 msgid "Kpelle; Guinea"
-msgstr ""
+msgstr "Kpelle; Guinea"
 
 #. name for gla
 msgid "Gaelic; Scottish"
-msgstr ""
+msgstr "Gaelic; Scottish"
 
 #. name for glc
 msgid "Bon Gula"

src/calibre/__init__.py

@@ -419,7 +419,7 @@ class CurrentDir(object):
         self.cwd = None
 
     def __enter__(self, *args):
-        self.cwd = os.getcwd()
+        self.cwd = os.getcwdu()
         os.chdir(self.path)
         return self.cwd
 

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, 8, 40)
+numeric_version = (0, 8, 41)
 __version__   = u'.'.join(map(unicode, numeric_version))
 __author__    = u"Kovid Goyal <kovid@kovidgoyal.net>"
 
@@ -190,3 +190,16 @@ def get_windows_username():
             return buf.value
 
     return get_unicode_windows_env_var(u'USERNAME')
+
+def get_windows_temp_path():
+    import ctypes
+    n = ctypes.windll.kernel32.GetTempPathW(0, None)
+    if n == 0:
+        return None
+    buf = ctypes.create_unicode_buffer(u'\0'*n)
+    ctypes.windll.kernel32.GetTempPathW(n, buf)
+    ans = buf.value
+    if ans[-1] == u'\\':
+        ans = ans[:-1]
+    return ans if ans else None
+

src/calibre/customize/builtins.py

@@ -284,7 +284,7 @@ class OPFMetadataReader(MetadataReaderPlugin):
 
     def get_metadata(self, stream, ftype):
         from calibre.ebooks.metadata.opf2 import OPF
-        return OPF(stream, os.getcwd()).to_book_metadata()
+        return OPF(stream, os.getcwdu()).to_book_metadata()
 
 class PDBMetadataReader(MetadataReaderPlugin):
 
@@ -1217,7 +1217,7 @@ class StoreArchiveOrgStore(StoreBase):
     formats = ['DAISY', 'DJVU', 'EPUB', 'MOBI', 'PDF', 'TXT']
 
 class StoreBaenWebScriptionStore(StoreBase):
-    name = 'Baen WebScription'
+    name = 'Baen Ebooks'
     description = u'Sci-Fi & Fantasy brought to you by Jim Baen.'
     actual_plugin = 'calibre.gui2.store.stores.baen_webscription_plugin:BaenWebScriptionStore'
 

src/calibre/customize/conversion.py

@@ -192,9 +192,13 @@ class InputFormatPlugin(Plugin):
 
     def __call__(self, stream, options, file_ext, log,
                  accelerators, output_dir):
-        log('InputFormatPlugin: %s running'%self.name)
+        try:
-        if hasattr(stream, 'name'):
+            log('InputFormatPlugin: %s running'%self.name)
-            log('on', stream.name)
+            if hasattr(stream, 'name'):
+                log('on', stream.name)
+        except:
+            # In case stdout is broken
+            pass
 
         with CurrentDir(output_dir):
             for x in os.listdir('.'):

src/calibre/debug.py

@@ -137,7 +137,7 @@ def add_simple_plugin(path_to_plugin):
     tdir = tempfile.mkdtemp()
     open(os.path.join(tdir, 'custom_plugin.py'),
             'wb').write(open(path_to_plugin, 'rb').read())
-    odir = os.getcwd()
+    odir = os.getcwdu()
     os.chdir(tdir)
     zf = zipfile.ZipFile('plugin.zip', 'w')
     zf.write('custom_plugin.py')

src/calibre/devices/android/driver.py

@@ -68,6 +68,7 @@ class ANDROID(USBMS):
             # Sony Ericsson
             0xfce : {
                 0xd12e : [0x0100],
+                0xe15d : [0x226],
                 0xe14f : [0x0226],
                 0x614f : [0x0226, 0x100],
                 0x6156 : [0x0226, 0x100],
@@ -184,14 +185,14 @@ class ANDROID(USBMS):
             'ALPANDIGITAL', 'ANDROID_MID', 'VTAB1008', 'EMX51_BBG_ANDROI',
             'UMS', '.K080', 'P990', 'LTE', 'MB853', 'GT-S5660_CARD', 'A107',
             'GT-I9003_CARD', 'XT912', 'FILE-CD_GADGET', 'RK29_SDK', 'MB855',
-            'XT910', 'BOOK_A10', 'USB_2.0_DRIVER']
+            'XT910', 'BOOK_A10', 'USB_2.0_DRIVER', 'I9100T']
     WINDOWS_CARD_A_MEM = ['ANDROID_PHONE', 'GT-I9000_CARD', 'SGH-I897',
             'FILE-STOR_GADGET', 'SGH-T959', 'SAMSUNG_ANDROID', 'GT-P1000_CARD',
             'A70S', 'A101IT', '7', 'INCREDIBLE', 'A7EB', 'SGH-T849_CARD',
             '__UMS_COMPOSITE', 'SGH-I997_CARD', 'MB870', 'ALPANDIGITAL',
             'ANDROID_MID', 'P990_SD_CARD', '.K080', 'LTE_CARD', 'MB853',
             'A1-07___C0541A4F', 'XT912', 'MB855', 'XT910', 'BOOK_A10_CARD',
-            'USB_2.0_DRIVER']
+            'USB_2.0_DRIVER', 'I9100T']
 
     OSX_MAIN_MEM = 'Android Device Main Memory'
 

src/calibre/devices/apple/driver.py

@@ -103,17 +103,6 @@ class AppleOpenFeedback(OpenFeedback):
 
 
 
-if isosx:
-    try:
-        import appscript
-        appscript
-    except:
-        # appscript fails to load on 10.4
-        appscript = None
-
-if iswindows:
-    import pythoncom, win32com.client
-
 class DriverBase(DeviceConfig, DevicePlugin):
     # Needed for config_widget to work
     FORMATS = ['epub', 'pdf']
@@ -467,6 +456,7 @@ class ITUNES(DriverBase):
                     self._purge_orphans(library_books, cached_books)
 
                 elif iswindows:
+                    import pythoncom, win32com.client
                     try:
                         pythoncom.CoInitialize()
                         self.iTunes = win32com.client.Dispatch("iTunes.Application")
@@ -533,6 +523,11 @@ class ITUNES(DriverBase):
         instantiate iTunes if necessary
         This gets called ~1x/second while device fingerprint is sensed
         '''
+        try:
+            import appscript
+            appscript
+        except:
+            appscript = None
         if appscript is None:
             return False
 
@@ -600,6 +595,7 @@ class ITUNES(DriverBase):
 
         '''
         if self.iTunes:
+            import pythoncom
             # We've previously run, so the user probably ejected the device
             try:
                 pythoncom.CoInitialize()
@@ -709,6 +705,7 @@ class ITUNES(DriverBase):
                     if self.manual_sync_mode:
                         self._remove_from_device(self.cached_books[path])
                 elif iswindows:
+                    import pythoncom, win32com.client
                     try:
                         pythoncom.CoInitialize()
                         self.iTunes = win32com.client.Dispatch("iTunes.Application")
@@ -754,6 +751,8 @@ class ITUNES(DriverBase):
             self.iTunes.eject(self.sources['iPod'])
         elif iswindows:
             if 'iPod' in self.sources:
+                import pythoncom, win32com.client
+
                 try:
                     pythoncom.CoInitialize()
                     self.iTunes = win32com.client.Dispatch("iTunes.Application")
@@ -788,6 +787,7 @@ class ITUNES(DriverBase):
 
         elif iswindows:
             if 'iPod' in self.sources:
+                import pythoncom, win32com.client
 
                 while True:
                     try:
@@ -1098,6 +1098,8 @@ class ITUNES(DriverBase):
                         _('%(num)d of %(tot)d') % dict(num=i+1, tot=file_count))
 
         elif iswindows:
+            import pythoncom, win32com.client
+
             try:
                 pythoncom.CoInitialize()
                 self.iTunes = win32com.client.Dispatch("iTunes.Application")
@@ -1163,6 +1165,7 @@ class ITUNES(DriverBase):
         '''
         logger().info(" ITUNES._add_device_book()")
         if isosx:
+            import appscript
             if 'iPod' in self.sources:
                 connected_device = self.sources['iPod']
                 device = self.iTunes.sources[connected_device]
@@ -1257,6 +1260,7 @@ class ITUNES(DriverBase):
         if DEBUG:
             logger().info(" ITUNES._add_library_book()")
         if isosx:
+            import appscript
             added = self.iTunes.add(appscript.mactypes.File(file))
 
         elif iswindows:
@@ -1541,6 +1545,7 @@ class ITUNES(DriverBase):
         if wait:
             time.sleep(wait)
         if isosx:
+            import appscript
             connected_device = self.sources['iPod']
             dev_books = None
             device = self.iTunes.sources[connected_device]
@@ -2077,6 +2082,7 @@ class ITUNES(DriverBase):
 
         device_books = []
         if isosx:
+            import appscript
             if 'iPod' in self.sources:
                 connected_device = self.sources['iPod']
                 device = self.iTunes.sources[connected_device]
@@ -2104,6 +2110,8 @@ class ITUNES(DriverBase):
                     logger().info()
 
         elif iswindows:
+            import pythoncom
+
             if 'iPod' in self.sources:
                 try:
                     pythoncom.CoInitialize()
@@ -2171,6 +2179,7 @@ class ITUNES(DriverBase):
         lib = None
 
         if isosx:
+            import appscript
             for source in self.iTunes.sources():
                 if source.kind() == appscript.k.library:
                     lib = source
@@ -2341,6 +2350,7 @@ class ITUNES(DriverBase):
             logger().info(" ITUNES:_launch_iTunes():\n  Instantiating iTunes")
 
         if isosx:
+            import appscript
             '''
             Launch iTunes if not already running
             '''
@@ -2382,6 +2392,8 @@ class ITUNES(DriverBase):
                 logger().info("  calibre_library_path: %s" % self.calibre_library_path)
 
         if iswindows:
+            import win32com.client
+
             '''
             Launch iTunes if not already running
             Assumes pythoncom wrapper
@@ -2752,6 +2764,8 @@ class ITUNES(DriverBase):
                     time.sleep(2)
                 print
         elif iswindows:
+            import pythoncom, win32com.client
+
             try:
                 pythoncom.CoInitialize()
                 self.iTunes = win32com.client.Dispatch("iTunes.Application")
@@ -3088,6 +3102,12 @@ class ITUNES_ASYNC(ITUNES):
         if DEBUG:
             logger().info("ITUNES_ASYNC:__init__()")
 
+        try:
+            import appscript
+            appscript
+        except:
+            appscript = None
+
         if isosx and appscript is None:
             self.connected = False
             raise UserFeedback('OSX 10.5 or later required', details=None, level=UserFeedback.WARN)
@@ -3099,6 +3119,8 @@ class ITUNES_ASYNC(ITUNES):
             self._launch_iTunes()
 
         if iswindows:
+            import pythoncom
+
             try:
                 pythoncom.CoInitialize()
                 self._launch_iTunes()
@@ -3180,6 +3202,8 @@ class ITUNES_ASYNC(ITUNES):
                                 _('%(num)d of %(tot)d') % dict(num=i+1, tot=book_count))
 
             elif iswindows:
+                import pythoncom, win32com.client
+
                 try:
                     pythoncom.CoInitialize()
                     self.iTunes = win32com.client.Dispatch("iTunes.Application")

src/calibre/ebooks/__init__.py

@@ -215,7 +215,11 @@ def unit_convert(value, base, font, dpi):
 def generate_masthead(title, output_path=None, width=600, height=60):
     from calibre.ebooks.conversion.config import load_defaults
     from calibre.utils.fonts import fontconfig
-    font_path = default_font = P('fonts/liberation/LiberationSerif-Bold.ttf')
+    from calibre.utils.config import tweaks
+    fp = tweaks['generate_cover_title_font']
+    if not fp:
+        fp = P('fonts/liberation/LiberationSerif-Bold.ttf')
+    font_path = default_font = fp
     recs = load_defaults('mobi_output')
     masthead_font_family = recs.get('masthead_font', 'Default')
 

src/calibre/ebooks/conversion/plugins/azw4_input.py

@@ -22,6 +22,6 @@ class AZW4Input(InputFormatPlugin):
 
         header = PdbHeaderReader(stream)
         reader = Reader(header, stream, log, options)
-        opf = reader.extract_content(os.getcwd())
+        opf = reader.extract_content(os.getcwdu())
 
         return opf

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

@@ -173,7 +173,7 @@ class ComicInput(InputFormatPlugin):
         comics = []
         for i, x in enumerate(comics_):
             title, fname = x
-            cdir = 'comic_%d'%(i+1) if len(comics_) > 1 else '.'
+            cdir = u'comic_%d'%(i+1) if len(comics_) > 1 else u'.'
             cdir = os.path.abspath(cdir)
             if not os.path.exists(cdir):
                 os.makedirs(cdir)
@@ -187,7 +187,7 @@ class ComicInput(InputFormatPlugin):
 
         mi  = MetaInformation(os.path.basename(stream.name).rpartition('.')[0],
             [_('Unknown')])
-        opf = OPFCreator(os.path.abspath('.'), mi)
+        opf = OPFCreator(os.getcwdu(), mi)
         entries = []
 
         def href(x):
@@ -225,9 +225,9 @@ class ComicInput(InputFormatPlugin):
                                 _('Page')+' %d'%(i+1), play_order=po)
                         po += 1
         opf.set_toc(toc)
-        m, n = open('metadata.opf', 'wb'), open('toc.ncx', 'wb')
+        m, n = open(u'metadata.opf', 'wb'), open('toc.ncx', 'wb')
-        opf.render(m, n, 'toc.ncx')
+        opf.render(m, n, u'toc.ncx')
-        return os.path.abspath('metadata.opf')
+        return os.path.abspath(u'metadata.opf')
 
     def create_wrappers(self, pages):
         from calibre.ebooks.oeb.base import XHTML_NS
@@ -252,7 +252,7 @@ class ComicInput(InputFormatPlugin):
         dir = os.path.dirname(pages[0])
         for i, page in enumerate(pages):
             wrapper = WRAPPER%(XHTML_NS, i+1, os.path.basename(page), i+1)
-            page = os.path.join(dir, 'page_%d.xhtml'%(i+1))
+            page = os.path.join(dir, u'page_%d.xhtml'%(i+1))
             open(page, 'wb').write(wrapper)
             wrappers.append(page)
         return wrappers

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

@@ -138,7 +138,7 @@ class EPUBInput(InputFormatPlugin):
         from calibre.ebooks import DRMError
         from calibre.ebooks.metadata.opf2 import OPF
         zf = ZipFile(stream)
-        zf.extractall(os.getcwd())
+        zf.extractall(os.getcwdu())
         encfile = os.path.abspath(os.path.join('META-INF', 'encryption.xml'))
         opf = self.find_opf()
         if opf is None:
@@ -150,7 +150,7 @@ class EPUBInput(InputFormatPlugin):
         path = getattr(stream, 'name', 'stream')
 
         if opf is None:
-            raise ValueError('%s is not a valid EPUB file'%path)
+            raise ValueError('%s is not a valid EPUB file (could not find opf)'%path)
 
         opf = os.path.relpath(opf, os.getcwdu())
         parts = os.path.split(opf)
@@ -197,4 +197,4 @@ class EPUBInput(InputFormatPlugin):
         with open('content.opf', 'wb') as nopf:
             nopf.write(opf.render())
 
-        return os.path.abspath('content.opf')
+        return os.path.abspath(u'content.opf')

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

@@ -196,7 +196,7 @@ class EPUBOutput(OutputFormatPlugin):
             uuid = str(uuid4())
             oeb.metadata.add('identifier', uuid, scheme='uuid', id=uuid)
 
-        with TemporaryDirectory('_epub_output') as tdir:
+        with TemporaryDirectory(u'_epub_output') as tdir:
             from calibre.customize.ui import plugin_for_output_format
             metadata_xml = None
             extra_entries = []
@@ -204,7 +204,7 @@ class EPUBOutput(OutputFormatPlugin):
                 if self.opts.output_profile.epub_periodical_format == 'sony':
                     from calibre.ebooks.epub.periodical import sony_metadata
                     metadata_xml, atom_xml = sony_metadata(oeb)
-                    extra_entries = [('atom.xml', 'application/atom+xml', atom_xml)]
+                    extra_entries = [(u'atom.xml', 'application/atom+xml', atom_xml)]
             oeb_output = plugin_for_output_format('oeb')
             oeb_output.convert(oeb, tdir, input_plugin, opts, log)
             opf = [x for x in os.listdir(tdir) if x.endswith('.opf')][0]

src/calibre/ebooks/conversion/plugins/fb2_input.py

@@ -33,8 +33,6 @@ class FB2Input(InputFormatPlugin):
         ),
     ])
 
-
-
     def convert(self, stream, options, file_ext, log,
                 accelerators):
         from lxml import etree
@@ -92,8 +90,8 @@ class FB2Input(InputFormatPlugin):
             src = img.get('src')
             img.set('src', self.binary_map.get(src, src))
         index = transform.tostring(result)
-        open('index.xhtml', 'wb').write(index)
+        open(u'index.xhtml', 'wb').write(index)
-        open('inline-styles.css', 'wb').write(css)
+        open(u'inline-styles.css', 'wb').write(css)
         stream.seek(0)
         mi = get_metadata(stream, 'fb2')
         if not mi.title:
@@ -102,9 +100,9 @@ class FB2Input(InputFormatPlugin):
             mi.authors = [_('Unknown')]
         cpath = None
         if mi.cover_data and mi.cover_data[1]:
-            with open('fb2_cover_calibre_mi.jpg', 'wb') as f:
+            with open(u'fb2_cover_calibre_mi.jpg', 'wb') as f:
                 f.write(mi.cover_data[1])
-            cpath = os.path.abspath('fb2_cover_calibre_mi.jpg')
+            cpath = os.path.abspath(u'fb2_cover_calibre_mi.jpg')
         else:
             for img in doc.xpath('//f:coverpage/f:image', namespaces=NAMESPACES):
                 href = img.get('{%s}href'%XLINK_NS, img.get('href', None))
@@ -115,14 +113,14 @@ class FB2Input(InputFormatPlugin):
                     break
 
         opf = OPFCreator(os.getcwdu(), mi)
-        entries = [(f, guess_type(f)[0]) for f in os.listdir('.')]
+        entries = [(f, guess_type(f)[0]) for f in os.listdir(u'.')]
         opf.create_manifest(entries)
-        opf.create_spine(['index.xhtml'])
+        opf.create_spine([u'index.xhtml'])
         if cpath:
             opf.guide.set_cover(cpath)
-        with open('metadata.opf', 'wb') as f:
+        with open(u'metadata.opf', 'wb') as f:
             opf.render(f)
-        return os.path.join(os.getcwd(), 'metadata.opf')
+        return os.path.join(os.getcwdu(), u'metadata.opf')
 
     def extract_embedded_content(self, doc):
         self.binary_map = {}

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

@@ -57,7 +57,7 @@ class HTMLInput(InputFormatPlugin):
     def convert(self, stream, opts, file_ext, log,
                 accelerators):
         self._is_case_sensitive = None
-        basedir = os.getcwd()
+        basedir = os.getcwdu()
         self.opts = opts
 
         fname = None

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

@@ -37,18 +37,18 @@ class HTMLZInput(InputFormatPlugin):
         index = u''
         multiple_html = False
         # Get a list of all top level files in the archive.
-        for x in os.listdir('.'):
+        for x in os.listdir(u'.'):
             if os.path.isfile(x):
                 top_levels.append(x)
         # Try to find an index. file.
         for x in top_levels:
-            if x.lower() in ('index.html', 'index.xhtml', 'index.htm'):
+            if x.lower() in (u'index.html', u'index.xhtml', u'index.htm'):
                 index = x
                 break
         # Look for multiple HTML files in the archive. We look at the
         # top level files only as only they matter in HTMLZ.
         for x in top_levels:
-            if os.path.splitext(x)[1].lower() in ('.html', '.xhtml', '.htm'):
+            if os.path.splitext(x)[1].lower() in (u'.html', u'.xhtml', u'.htm'):
                 # Set index to the first HTML file found if it's not
                 # called index.
                 if not index:
@@ -85,11 +85,11 @@ class HTMLZInput(InputFormatPlugin):
             setattr(options, opt.option.name, opt.recommended_value)
         options.input_encoding = 'utf-8'
         base = os.getcwdu()
-        fname = os.path.join(base, 'index.html')
+        fname = os.path.join(base, u'index.html')
         c = 0
         while os.path.exists(fname):
             c += 1
-            fname = 'index%d.html'%c
+            fname = u'index%d.html'%c
         htmlfile = open(fname, 'wb')
         with htmlfile:
             htmlfile.write(html.encode('utf-8'))
@@ -111,16 +111,16 @@ class HTMLZInput(InputFormatPlugin):
         cover_path = None
         opf = None
         for x in top_levels:
-            if os.path.splitext(x)[1].lower() in ('.opf'):
+            if os.path.splitext(x)[1].lower() == u'.opf':
                 opf = x
                 break
         if opf:
-            opf = OPF(opf, basedir=os.getcwd())
+            opf = OPF(opf, basedir=os.getcwdu())
             cover_path = opf.raster_cover
         # Set the cover.
         if cover_path:
             cdata = None
-            with open(os.path.join(os.getcwd(), cover_path), 'rb') as cf:
+            with open(os.path.join(os.getcwdu(), cover_path), 'rb') as cf:
                 cdata = cf.read()
             cover_name = os.path.basename(cover_path)
             id, href = oeb.manifest.generate('cover', cover_name)

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

@@ -55,30 +55,30 @@ class HTMLZOutput(OutputFormatPlugin):
         else:
             from calibre.ebooks.htmlz.oeb2html import OEB2HTMLClassCSSizer as OEB2HTMLizer
 
-        with TemporaryDirectory('_htmlz_output') as tdir:
+        with TemporaryDirectory(u'_htmlz_output') as tdir:
             htmlizer = OEB2HTMLizer(log)
             html = htmlizer.oeb2html(oeb_book, opts)
 
-            with open(os.path.join(tdir, 'index.html'), 'wb') as tf:
+            with open(os.path.join(tdir, u'index.html'), 'wb') as tf:
                 tf.write(html)
 
             # CSS
             if opts.htmlz_css_type == 'class' and opts.htmlz_class_style == 'external':
-                with open(os.path.join(tdir, 'style.css'), 'wb') as tf:
+                with open(os.path.join(tdir, u'style.css'), 'wb') as tf:
                     tf.write(htmlizer.get_css(oeb_book))
 
             # Images
             images = htmlizer.images
             if images:
-                if not os.path.exists(os.path.join(tdir, 'images')):
+                if not os.path.exists(os.path.join(tdir, u'images')):
-                    os.makedirs(os.path.join(tdir, 'images'))
+                    os.makedirs(os.path.join(tdir, u'images'))
                 for item in oeb_book.manifest:
                     if item.media_type in OEB_IMAGES and item.href in images:
                         if item.media_type == SVG_MIME:
                             data = unicode(etree.tostring(item.data, encoding=unicode))
                         else:
                             data = item.data
-                        fname = os.path.join(tdir, 'images', images[item.href])
+                        fname = os.path.join(tdir, u'images', images[item.href])
                         with open(fname, 'wb') as img:
                             img.write(data)
 
@@ -91,7 +91,7 @@ class HTMLZOutput(OutputFormatPlugin):
                     cover_data = oeb_book.guide[term].item.data
                 if cover_data:
                     from calibre.utils.magick.draw import save_cover_data_to
-                    cover_path = os.path.join(tdir, 'cover.jpg')
+                    cover_path = os.path.join(tdir, u'cover.jpg')
                     with open(cover_path, 'w') as cf:
                         cf.write('')
                     save_cover_data_to(cover_data, cover_path)
@@ -100,11 +100,11 @@ class HTMLZOutput(OutputFormatPlugin):
                 traceback.print_exc()
 
             # Metadata
-            with open(os.path.join(tdir, 'metadata.opf'), 'wb') as mdataf:
+            with open(os.path.join(tdir, u'metadata.opf'), 'wb') as mdataf:
                 opf = OPF(StringIO(etree.tostring(oeb_book.metadata.to_opf1())))
                 mi = opf.to_book_metadata()
                 if cover_path:
-                    mi.cover = 'cover.jpg'
+                    mi.cover = u'cover.jpg'
                 mdataf.write(metadata_to_opf(mi))
 
             htmlz = ZipFile(output_path, 'w')

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

@@ -28,7 +28,7 @@ class LRFInput(InputFormatPlugin):
         d.parse()
         xml = d.to_xml(write_files=True)
         if options.verbose > 2:
-            open('lrs.xml', 'wb').write(xml.encode('utf-8'))
+            open(u'lrs.xml', 'wb').write(xml.encode('utf-8'))
         parser = etree.XMLParser(no_network=True, huge_tree=True)
         try:
             doc = etree.fromstring(xml, parser=parser)
@@ -84,4 +84,4 @@ class LRFInput(InputFormatPlugin):
         with open('content.opf', 'wb') as f:
             f.write(result)
         styles.write()
-        return os.path.abspath('content.opf')
+        return os.path.abspath(u'content.opf')

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

@@ -182,7 +182,7 @@ class LRFOutput(OutputFormatPlugin):
         self.flatten_toc()
 
         from calibre.ptempfile import TemporaryDirectory
-        with TemporaryDirectory('_lrf_output') as tdir:
+        with TemporaryDirectory(u'_lrf_output') as tdir:
             from calibre.customize.ui import plugin_for_output_format
             oeb_output = plugin_for_output_format('oeb')
             oeb_output.convert(oeb, tdir, input_plugin, opts, log)

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

@@ -20,17 +20,17 @@ class MOBIInput(InputFormatPlugin):
         try:
             mr = MobiReader(stream, log, options.input_encoding,
                         options.debug_pipeline)
-            mr.extract_content('.', parse_cache)
+            mr.extract_content(u'.', parse_cache)
         except:
             mr = MobiReader(stream, log, options.input_encoding,
                         options.debug_pipeline, try_extra_data_fix=True)
-            mr.extract_content('.', parse_cache)
+            mr.extract_content(u'.', parse_cache)
 
         raw = parse_cache.pop('calibre_raw_mobi_markup', False)
         if raw:
             if isinstance(raw, unicode):
                 raw = raw.encode('utf-8')
-            open('debug-raw.html', 'wb').write(raw)
+            open(u'debug-raw.html', 'wb').write(raw)
         for f, root in parse_cache.items():
             with open(f, 'wb') as q:
                 q.write(html.tostring(root, encoding='utf-8', method='xml',

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

@@ -29,6 +29,6 @@ class PDBInput(InputFormatPlugin):
         log.debug('Detected ebook format as: %s with identity: %s' % (IDENTITY_TO_NAME[header.ident], header.ident))
 
         reader = Reader(header, stream, log, options)
-        opf = reader.extract_content(os.getcwd())
+        opf = reader.extract_content(os.getcwdu())
 
         return opf

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

@@ -35,9 +35,9 @@ class PDFInput(InputFormatPlugin):
         if pdfreflow_err:
             raise RuntimeError('Failed to load pdfreflow: ' + pdfreflow_err)
         pdfreflow.reflow(stream.read(), 1, -1)
-        xml = clean_ascii_chars(open('index.xml', 'rb').read())
+        xml = clean_ascii_chars(open(u'index.xml', 'rb').read())
         PDFDocument(xml, self.opts, self.log)
-        return os.path.join(os.getcwd(), 'metadata.opf')
+        return os.path.join(os.getcwdu(), u'metadata.opf')
 
 
     def convert(self, stream, options, file_ext, log,
@@ -50,25 +50,25 @@ class PDFInput(InputFormatPlugin):
         self.opts, self.log = options, log
         if options.new_pdf_engine:
             return self.convert_new(stream, accelerators)
-        pdftohtml(os.getcwd(), stream.name, options.no_images)
+        pdftohtml(os.getcwdu(), stream.name, options.no_images)
 
         from calibre.ebooks.metadata.meta import get_metadata
         log.debug('Retrieving document metadata...')
         mi = get_metadata(stream, 'pdf')
-        opf = OPFCreator(os.getcwd(), mi)
+        opf = OPFCreator(os.getcwdu(), mi)
 
-        manifest = [('index.html', None)]
+        manifest = [(u'index.html', None)]
 
-        images = os.listdir(os.getcwd())
+        images = os.listdir(os.getcwdu())
         images.remove('index.html')
         for i in images:
             manifest.append((i, None))
         log.debug('Generating manifest...')
         opf.create_manifest(manifest)
 
-        opf.create_spine(['index.html'])
+        opf.create_spine([u'index.html'])
         log.debug('Rendering manifest...')
-        with open('metadata.opf', 'wb') as opffile:
+        with open(u'metadata.opf', 'wb') as opffile:
             opf.render(opffile)
 
-        return os.path.join(os.getcwd(), 'metadata.opf')
+        return os.path.join(os.getcwdu(), u'metadata.opf')

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

@@ -69,12 +69,12 @@ class PMLInput(InputFormatPlugin):
                 imgs = glob.glob(os.path.join(tdir, os.path.splitext(os.path.basename(stream.name))[0] + '_img', '*.png'))
         # No images in Dropbook location try generic images directory
         if not imgs:
-            imgs = glob.glob(os.path.join(os.path.join(tdir, 'images'), '*.png'))
+            imgs = glob.glob(os.path.join(os.path.join(tdir, u'images'), u'*.png'))
         if imgs:
-            os.makedirs(os.path.join(os.getcwd(), 'images'))
+            os.makedirs(os.path.join(os.getcwdu(), u'images'))
         for img in imgs:
             pimg_name = os.path.basename(img)
-            pimg_path = os.path.join(os.getcwd(), 'images', pimg_name)
+            pimg_path = os.path.join(os.getcwdu(), 'images', pimg_name)
 
             images.append('images/' + pimg_name)
 
@@ -94,14 +94,14 @@ class PMLInput(InputFormatPlugin):
 
         if file_ext == 'pmlz':
             log.debug('De-compressing content to temporary directory...')
-            with TemporaryDirectory('_unpmlz') as tdir:
+            with TemporaryDirectory(u'_unpmlz') as tdir:
                 zf = ZipFile(stream)
                 zf.extractall(tdir)
 
-                pmls = glob.glob(os.path.join(tdir, '*.pml'))
+                pmls = glob.glob(os.path.join(tdir, u'*.pml'))
                 for pml in pmls:
                     html_name = os.path.splitext(os.path.basename(pml))[0]+'.html'
-                    html_path = os.path.join(os.getcwd(), html_name)
+                    html_path = os.path.join(os.getcwdu(), html_name)
 
                     pages.append(html_name)
                     log.debug('Processing PML item %s...' % pml)
@@ -109,8 +109,8 @@ class PMLInput(InputFormatPlugin):
                     toc += ttoc
                 images = self.get_images(stream, tdir, True)
         else:
-            toc = self.process_pml(stream, 'index.html')
+            toc = self.process_pml(stream, u'index.html')
-            pages.append('index.html')
+            pages.append(u'index.html')
 
             if hasattr(stream, 'name'):
                 images = self.get_images(stream, os.path.abspath(os.path.dirname(stream.name)))
@@ -126,14 +126,14 @@ class PMLInput(InputFormatPlugin):
         log.debug('Reading metadata from input file...')
         mi = get_metadata(stream, 'pml')
         if 'images/cover.png' in images:
-            mi.cover = 'images/cover.png'
+            mi.cover = u'images/cover.png'
-        opf = OPFCreator(os.getcwd(), mi)
+        opf = OPFCreator(os.getcwdu(), mi)
         log.debug('Generating manifest...')
         opf.create_manifest(manifest_items)
         opf.create_spine(pages)
         opf.set_toc(toc)
-        with open('metadata.opf', 'wb') as opffile:
+        with open(u'metadata.opf', 'wb') as opffile:
-            with open('toc.ncx', 'wb') as tocfile:
+            with open(u'toc.ncx', 'wb') as tocfile:
-                opf.render(opffile, tocfile, 'toc.ncx')
+                opf.render(opffile, tocfile, u'toc.ncx')
 
-        return os.path.join(os.getcwd(), 'metadata.opf')
+        return os.path.join(os.getcwdu(), u'metadata.opf')

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

@@ -20,6 +20,6 @@ class RBInput(InputFormatPlugin):
         from calibre.ebooks.rb.reader import Reader
 
         reader = Reader(stream, log, options.input_encoding)
-        opf = reader.extract_content(os.getcwd())
+        opf = reader.extract_content(os.getcwdu())
 
         return opf

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

@@ -58,7 +58,7 @@ class RecipeInput(InputFormatPlugin):
             zf = ZipFile(recipe_or_file, 'r')
             zf.extractall()
             zf.close()
-            self.recipe_source = open('download.recipe', 'rb').read()
+            self.recipe_source = open(u'download.recipe', 'rb').read()
             recipe = compile_recipe(self.recipe_source)
             recipe.needs_subscription = False
             self.recipe_object = recipe(opts, log, self.report_progress)
@@ -108,11 +108,11 @@ class RecipeInput(InputFormatPlugin):
         for key, val in self.recipe_object.conversion_options.items():
             setattr(opts, key, val)
 
-        for f in os.listdir('.'):
+        for f in os.listdir(u'.'):
             if f.endswith('.opf'):
                 return os.path.abspath(f)
 
-        for f in walk('.'):
+        for f in walk(u'.'):
             if f.endswith('.opf'):
                 return os.path.abspath(f)
 

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

@@ -47,12 +47,12 @@ class RTFInput(InputFormatPlugin):
 
     def generate_xml(self, stream):
         from calibre.ebooks.rtf2xml.ParseRtf import ParseRtf
-        ofile = 'dataxml.xml'
+        ofile = u'dataxml.xml'
         run_lev, debug_dir, indent_out = 1, None, 0
         if getattr(self.opts, 'debug_pipeline', None) is not None:
             try:
-                os.mkdir('rtfdebug')
+                os.mkdir(u'rtfdebug')
-                debug_dir = 'rtfdebug'
+                debug_dir = u'rtfdebug'
                 run_lev = 4
                 indent_out = 1
                 self.log('Running RTFParser in debug mode')
@@ -124,7 +124,7 @@ class RTFInput(InputFormatPlugin):
             if fmt is None:
                 fmt = 'wmf'
             count += 1
-            name = '%04d.%s' % (count, fmt)
+            name = u'%04d.%s' % (count, fmt)
             with open(name, 'wb') as f:
                 f.write(data)
             imap[count] = name
@@ -201,7 +201,7 @@ class RTFInput(InputFormatPlugin):
         for cls, val in border_styles.iteritems():
             css += '\n\n.%s {\n%s\n}'%(cls, val)
 
-        with open('styles.css', 'ab') as f:
+        with open(u'styles.css', 'ab') as f:
             f.write(css)
 
     def convert_borders(self, doc):
@@ -271,7 +271,7 @@ class RTFInput(InputFormatPlugin):
         extensions = { ('calibre', 'inline-class') : inline_class }
         transform = etree.XSLT(styledoc, extensions=extensions)
         result = transform(doc)
-        html = 'index.xhtml'
+        html = u'index.xhtml'
         with open(html, 'wb') as f:
             res = transform.tostring(result)
             # res = res[:100].replace('xmlns:html', 'xmlns') + res[100:]
@@ -289,10 +289,10 @@ class RTFInput(InputFormatPlugin):
             mi.title = _('Unknown')
         if not mi.authors:
             mi.authors = [_('Unknown')]
-        opf = OPFCreator(os.getcwd(), mi)
+        opf = OPFCreator(os.getcwdu(), mi)
-        opf.create_manifest([('index.xhtml', None)])
+        opf.create_manifest([(u'index.xhtml', None)])
-        opf.create_spine(['index.xhtml'])
+        opf.create_spine([u'index.xhtml'])
-        opf.render(open('metadata.opf', 'wb'))
+        opf.render(open(u'metadata.opf', 'wb'))
-        return os.path.abspath('metadata.opf')
+        return os.path.abspath(u'metadata.opf')
 
 

src/calibre/ebooks/conversion/plumber.py

@@ -208,6 +208,7 @@ OptionRecommendation(name='level1_toc',
             'should be added to the Table of Contents at level one. If '
             'this is specified, it takes precedence over other forms '
             'of auto-detection.'
+            ' See the XPath Tutorial in the calibre User Manual for examples.'
                 )
         ),
 
@@ -216,6 +217,7 @@ OptionRecommendation(name='level2_toc',
             help=_('XPath expression that specifies all tags that should be '
             'added to the Table of Contents at level two. Each entry is added '
             'under the previous level one entry.'
+            ' See the XPath Tutorial in the calibre User Manual for examples.'
                 )
         ),
 
@@ -224,6 +226,7 @@ OptionRecommendation(name='level3_toc',
             help=_('XPath expression that specifies all tags that should be '
                 'added to the Table of Contents at level three. Each entry '
                 'is added under the previous level two entry.'
+            ' See the XPath Tutorial in the calibre User Manual for examples.'
                 )
         ),
 

src/calibre/ebooks/lit/writer.py

@@ -664,7 +664,8 @@ class LitWriter(object):
         quickref = []
         name = directory[0].name
         for entry in directory:
-            next = ''.join([decint(len(entry.name)), entry.name,
+            en = entry.name.encode('utf-8') if entry.name else entry.name
+            next = ''.join([decint(len(en)), en,
                 decint(entry.section), decint(entry.offset),
                 decint(entry.size)])
             usedlen = dchunk.tell() + len(next) + (len(quickref) * 2) + 52
@@ -673,7 +674,7 @@ class LitWriter(object):
                 dchunk = StringIO()
                 dcount = 0
                 quickref = []
-                name = entry.name
+                name = en
             if (dcount % qrn) == 0:
                 quickref.append(dchunk.tell())
             dchunk.write(next)

src/calibre/ebooks/lrf/html/convert_from.py

@@ -374,13 +374,12 @@ class HTMLConverter(object):
             else:
                 self.css[selector] = self.override_css[selector]
 
-        upath = path.encode(sys.getfilesystemencoding()) if isinstance(path, unicode) else path
+        self.file_name = os.path.basename(path)
-        self.file_name = os.path.basename(upath.decode(sys.getfilesystemencoding()))
+        self.log.info(_('Processing %s')%( path if self.verbose else self.file_name))
-        self.log.info(_('Processing %s')%( repr(upath) if self.verbose else repr(self.file_name)))
 
-        if not os.path.exists(upath):
+        if not os.path.exists(path):
-            upath = upath.replace('&', '%26') #convertlit replaces & with %26 in file names
+            path = path.replace('&', '%26') #convertlit replaces & with %26 in file names
-        f = open(upath, 'rb')
+        f = open(path, 'rb')
         raw = f.read()
         if self.pdftohtml: # Bug in pdftohtml that causes it to output invalid UTF-8 files
             raw = raw.decode('utf-8', 'ignore')
@@ -1938,7 +1937,7 @@ def process_file(path, options, logger):
     if not oname:
         suffix = '.lrs' if options.lrs else '.lrf'
         name = os.path.splitext(os.path.basename(path))[0] + suffix
-        oname = os.path.join(os.getcwd(), name)
+        oname = os.path.join(os.getcwdu(), name)
     oname = os.path.abspath(os.path.expanduser(oname))
     conv.writeto(oname, lrs=options.lrs)
     conv.cleanup()

src/calibre/ebooks/metadata/__init__.py

@@ -187,7 +187,7 @@ class Resource(object):
 
     '''
 
-    def __init__(self, href_or_path, basedir=os.getcwd(), is_path=True):
+    def __init__(self, href_or_path, basedir=os.getcwdu(), is_path=True):
         self._href = None
         self._basedir = basedir
         self.path = None
@@ -230,7 +230,7 @@ class Resource(object):
             if self._basedir:
                 basedir = self._basedir
             else:
-                basedir = os.getcwd()
+                basedir = os.getcwdu()
         if self.path is None:
             return self._href
         f = self.fragment.encode('utf-8') if isinstance(self.fragment, unicode) else self.fragment

src/calibre/ebooks/metadata/lit.py

@@ -14,7 +14,7 @@ def get_metadata(stream):
     litfile = LitContainer(stream, Log())
     src = litfile.get_metadata().encode('utf-8')
     litfile = litfile._litfile
-    opf = OPF(cStringIO.StringIO(src), os.getcwd())
+    opf = OPF(cStringIO.StringIO(src), os.getcwdu())
     mi = opf.to_book_metadata()
     covers = []
     for item in opf.iterguide():

src/calibre/ebooks/metadata/meta.py

@@ -199,7 +199,7 @@ def metadata_from_filename(name, pat=None):
 def opf_metadata(opfpath):
     if hasattr(opfpath, 'read'):
         f = opfpath
-        opfpath = getattr(f, 'name', os.getcwd())
+        opfpath = getattr(f, 'name', os.getcwdu())
     else:
         f = open(opfpath, 'rb')
     try:

src/calibre/ebooks/metadata/odt.py

@@ -153,7 +153,9 @@ def get_metadata(stream):
     mi = MetaInformation(None, [])
     if data.has_key('title'):
         mi.title = data['title']
-    if data.has_key('creator'):
+    if data.get('initial-creator', '').strip():
+        mi.authors = string_to_authors(data['initial-creator'])
+    elif data.has_key('creator'):
         mi.authors = string_to_authors(data['creator'])
     if data.has_key('description'):
         mi.comments = data['description']

src/calibre/ebooks/metadata/opf2.py

@@ -36,7 +36,7 @@ class Resource(object): # {{{
     :method:`href`
     '''
 
-    def __init__(self, href_or_path, basedir=os.getcwd(), is_path=True):
+    def __init__(self, href_or_path, basedir=os.getcwdu(), is_path=True):
         self.orig = href_or_path
         self._href = None
         self._basedir = basedir
@@ -81,7 +81,7 @@ class Resource(object): # {{{
             if self._basedir:
                 basedir = self._basedir
             else:
-                basedir = os.getcwd()
+                basedir = os.getcwdu()
         if self.path is None:
             return self._href
         f = self.fragment.encode('utf-8') if isinstance(self.fragment, unicode) else self.fragment
@@ -1487,7 +1487,7 @@ class OPFTest(unittest.TestCase):
 </package>
 '''
         )
-        self.opf = OPF(self.stream, os.getcwd())
+        self.opf = OPF(self.stream, os.getcwdu())
 
     def testReading(self, opf=None):
         if opf is None:
@@ -1518,11 +1518,11 @@ class OPFTest(unittest.TestCase):
         self.opf.render()
 
     def testCreator(self):
-        opf = OPFCreator(os.getcwd(), self.opf)
+        opf = OPFCreator(os.getcwdu(), self.opf)
         buf = cStringIO.StringIO()
         opf.render(buf)
         raw = buf.getvalue()
-        self.testReading(opf=OPF(cStringIO.StringIO(raw), os.getcwd()))
+        self.testReading(opf=OPF(cStringIO.StringIO(raw), os.getcwdu()))
 
     def testSmartUpdate(self):
         self.opf.smart_update(MetaInformation(self.opf))
@@ -1547,7 +1547,7 @@ def test_user_metadata():
         }
     mi.set_all_user_metadata(um)
     raw = metadata_to_opf(mi)
-    opfc = OPFCreator(os.getcwd(), other=mi)
+    opfc = OPFCreator(os.getcwdu(), other=mi)
     out = StringIO()
     opfc.render(out)
     raw2 = out.getvalue()

src/calibre/ebooks/metadata/toc.py

@@ -29,9 +29,9 @@ C = ElementMaker(namespace=CALIBRE_NS, nsmap=NSMAP)
 
 class TOC(list):
 
-    def __init__(self, href=None, fragment=None, text=None, parent=None, play_order=0,
+    def __init__(self, href=None, fragment=None, text=None, parent=None,
-                 base_path=os.getcwd(), type='unknown', author=None,
+            play_order=0, base_path=os.getcwdu(), type='unknown', author=None,
-                 description=None, toc_thumbnail=None):
+            description=None, toc_thumbnail=None):
         self.href = href
         self.fragment = fragment
         if not self.fragment:

src/calibre/ebooks/metadata/zip.py

@@ -44,7 +44,7 @@ def zip_opf_metadata(opfpath, zf):
     from calibre.ebooks.metadata.opf2 import OPF
     if hasattr(opfpath, 'read'):
         f = opfpath
-        opfpath = getattr(f, 'name', os.getcwd())
+        opfpath = getattr(f, 'name', os.getcwdu())
     else:
         f = open(opfpath, 'rb')
     opf = OPF(f, os.path.dirname(opfpath))

src/calibre/ebooks/mobi/reader.py

@@ -785,11 +785,11 @@ class MobiReader(object):
             mi = MetaInformation(self.book_header.title, [_('Unknown')])
         opf = OPFCreator(os.path.dirname(htmlfile), mi)
         if hasattr(self.book_header.exth, 'cover_offset'):
-            opf.cover = 'images/%05d.jpg' % (self.book_header.exth.cover_offset + 1)
+            opf.cover = u'images/%05d.jpg' % (self.book_header.exth.cover_offset + 1)
         elif mi.cover is not None:
             opf.cover = mi.cover
         else:
-            opf.cover = 'images/%05d.jpg' % 1
+            opf.cover = u'images/%05d.jpg' % 1
             if not os.path.exists(os.path.join(os.path.dirname(htmlfile),
                 * opf.cover.split('/'))):
                 opf.cover = None
@@ -799,7 +799,7 @@ class MobiReader(object):
         if cover is not None:
             cover = cover.replace('/', os.sep)
             if os.path.exists(cover):
-                ncover = 'images'+os.sep+'calibre_cover.jpg'
+                ncover = u'images'+os.sep+u'calibre_cover.jpg'
                 if os.path.exists(ncover):
                     os.remove(ncover)
                 shutil.copyfile(cover, ncover)
@@ -807,7 +807,7 @@ class MobiReader(object):
                 opf.cover = ncover.replace(os.sep, '/')
 
         manifest = [(htmlfile, 'application/xhtml+xml'),
-            (os.path.abspath('styles.css'), 'text/css')]
+            (os.path.abspath(u'styles.css'), 'text/css')]
         bp = os.path.dirname(htmlfile)
         added = set([])
         for i in getattr(self, 'image_names', []):

src/calibre/ebooks/mobi/writer2/serializer.py

@@ -306,7 +306,9 @@ class Serializer(object):
         if id_:
             href = '#'.join((item.href, id_))
             offset = self.anchor_offset or buf.tell()
-            self.id_offsets[urlnormalize(href)] = offset
+            key = urlnormalize(href)
+            # Only set this id_offset if it wasn't previously seen
+            self.id_offsets[key] = self.id_offsets.get(key, offset)
         if self.anchor_offset is not None and \
             tag == 'a' and not elem.attrib and \
             not len(elem) and not elem.text:

src/calibre/ebooks/oeb/base.py

@@ -774,6 +774,8 @@ class Manifest(object):
 
         def __init__(self, oeb, id, href, media_type,
                      fallback=None, loader=str, data=None):
+            if href:
+                href = unicode(href)
             self.oeb = oeb
             self.id = id
             self.href = self.path = urlnormalize(href)
@@ -1106,7 +1108,7 @@ class Manifest(object):
             while href.lower() in lhrefs:
                 href = base + str(index) + ext
                 index += 1
-        return id, href
+        return id, unicode(href)
 
     def __iter__(self):
         for item in self.items:
@@ -1320,6 +1322,8 @@ class Guide(object):
 
     def add(self, type, title, href):
         """Add a new reference to the `Guide`."""
+        if href:
+            href = unicode(href)
         ref = self.Reference(self.oeb, type, title, href)
         self.refs[type] = ref
         return ref

src/calibre/ebooks/oeb/transforms/cover.py

@@ -104,7 +104,7 @@ class CoverManager(object):
             img_data = calibre_cover(title, authors_to_string(authors),
                     series_string=series_string)
             id, href = self.oeb.manifest.generate('cover',
-                    'cover_image.jpg')
+                    u'cover_image.jpg')
             item = self.oeb.manifest.add(id, href, guess_type('t.jpg')[0],
                         data=img_data)
             m.clear('cover')
@@ -154,7 +154,7 @@ class CoverManager(object):
                 templ = self.non_svg_template if self.no_svg_cover \
                         else self.svg_template
                 tp = templ%unquote(href)
-                id, href = m.generate('titlepage', 'titlepage.xhtml')
+                id, href = m.generate('titlepage', u'titlepage.xhtml')
                 item = m.add(id, href, guess_type('t.xhtml')[0],
                         data=etree.fromstring(tp))
         else:

src/calibre/ebooks/oeb/transforms/rescale.py

@@ -48,6 +48,8 @@ class RescaleImages(object):
                 scaled, new_width, new_height = fit_image(width, height,
                         page_width, page_height)
                 if scaled:
+                    new_width = max(1, new_width)
+                    new_height = max(1, new_height)
                     self.log('Rescaling image from %dx%d to %dx%d'%(
                         width, height, new_width, new_height), item.href)
                     try:

src/calibre/ebooks/oeb/transforms/split.py

@@ -188,7 +188,7 @@ class FlowSplitter(object):
         self.csp_counter    = 0
 
         base, ext = os.path.splitext(self.base)
-        self.base = base.replace('%', '%%')+'_split_%.3d'+ext
+        self.base = base.replace('%', '%%')+u'_split_%.3d'+ext
 
         self.trees = [self.item.data.getroottree()]
         self.splitting_on_page_breaks = True

src/calibre/ebooks/pdf/pdftohtml.py

@@ -5,15 +5,13 @@ __copyright__ = '2008, Kovid Goyal <kovid at kovidgoyal.net>, ' \
                 '2009, John Schember <john@nachtimwald.com>'
 __docformat__ = 'restructuredtext en'
 
-import errno
+import errno, os, sys, subprocess, shutil
-import os
-import sys
-import subprocess
 from functools import partial
 
 from calibre.ebooks import ConversionError, DRMError
 from calibre.ptempfile import PersistentTemporaryFile
-from calibre.constants import isosx, iswindows, islinux, isbsd
+from calibre.constants import (isosx, iswindows, islinux, isbsd,
+            filesystem_encoding)
 from calibre import CurrentDir
 
 PDFTOHTML = 'pdftohtml'
@@ -30,31 +28,45 @@ def pdftohtml(output_dir, pdf_path, no_images):
     '''
     Convert the pdf into html using the pdftohtml app.
     This will write the html as index.html into output_dir.
-    It will also wirte all extracted images to the output_dir
+    It will also write all extracted images to the output_dir
     '''
 
-    if isinstance(pdf_path, unicode):
+    pdfsrc = os.path.join(output_dir, u'src.pdf')
-        pdf_path = pdf_path.encode(sys.getfilesystemencoding())
+    index = os.path.join(output_dir, u'index.html')
-    if not os.access(pdf_path, os.R_OK):
+
-        raise ConversionError('Cannot read from ' + pdf_path)
+    with open(pdf_path, 'rb') as src, open(pdfsrc, 'wb') as dest:
+        shutil.copyfileobj(src, dest)
 
     with CurrentDir(output_dir):
-        index = os.path.join(os.getcwd(), 'index.html')
+        # This is necessary as pdftohtml doesn't always (linux) respect
-        # This is neccessary as pdftohtml doesn't always (linux) respect absolute paths
+        # absolute paths. Also, it allows us to safely pass only bytestring
-        pdf_path = os.path.abspath(pdf_path)
+        # arguments to subprocess on widows
-        cmd = [PDFTOHTML, '-enc', 'UTF-8', '-noframes', '-p', '-nomerge', '-nodrm', '-q', pdf_path, os.path.basename(index)]
-        if isbsd:
-            cmd.remove('-nodrm')
-        if no_images:
-            cmd.append('-i')
 
-        logf = PersistentTemporaryFile('pdftohtml_log')
+        # subprocess in python 2 cannot handle unicode arguments on windows
+        # that cannot be encoded with mbcs. Ensure all args are
+        # bytestrings.
+        def a(x):
+            return os.path.basename(x).encode('ascii')
+
+        exe = PDFTOHTML.encode(filesystem_encoding) if isinstance(PDFTOHTML,
+                unicode) else PDFTOHTML
+
+        cmd = [exe, b'-enc', b'UTF-8', b'-noframes', b'-p', b'-nomerge',
+                b'-nodrm', b'-q', a(pdfsrc), a(index)]
+
+        if isbsd:
+            cmd.remove(b'-nodrm')
+        if no_images:
+            cmd.append(b'-i')
+
+        logf = PersistentTemporaryFile(u'pdftohtml_log')
         try:
             p = popen(cmd, stderr=logf._fd, stdout=logf._fd,
                     stdin=subprocess.PIPE)
         except OSError as err:
             if err.errno == errno.ENOENT:
-                raise ConversionError(_('Could not find pdftohtml, check it is in your PATH'))
+                raise ConversionError(
+                    _('Could not find pdftohtml, check it is in your PATH'))
             else:
                 raise
 
@@ -70,6 +82,10 @@ def pdftohtml(output_dir, pdf_path, no_images):
         logf.flush()
         logf.close()
         out = open(logf.name, 'rb').read().strip()
+        try:
+            os.remove(pdfsrc)
+        except:
+            pass
         if ret != 0:
             raise ConversionError(out)
         if out:
@@ -84,3 +100,4 @@ def pdftohtml(output_dir, pdf_path, no_images):
             i.seek(0)
             i.truncate()
             i.write(raw)
+