Improve Die Zeit (subscription)

resources/recipes/zeitde_sub.recipe

@@ -2,9 +2,9 @@
 # -*- coding: utf-8 mode: python -*-
 
 __license__   = 'GPL v3'
-__copyright__ = '2010, Steffen Siebert <calibre at steffensiebert.de>'
+__copyright__ = '2010-2011, Steffen Siebert <calibre at steffensiebert.de>'
 __docformat__ = 'restructuredtext de'
-__version__   = '1.1'
+__version__   = '1.2'
 
 """
 Die Zeit EPUB
@@ -13,21 +13,43 @@ Die Zeit EPUB
 import os, urllib2, zipfile, re
 from calibre.web.feeds.news import BasicNewsRecipe
 from calibre.ptempfile import PersistentTemporaryFile
+from calibre import walk
 
 class ZeitEPUBAbo(BasicNewsRecipe):
 
-    title = u'Zeit Online Premium'
+    title = u'Die Zeit'
     description = u'Das EPUB Abo der Zeit (needs subscription)'
     language = 'de'
     lang = 'de-DE'
 
-    __author__ = 'Steffen Siebert'
+    __author__ = 'Steffen Siebert and Tobias Isenberg'
     needs_subscription = True
 
     conversion_options = {
-        'no_default_epub_cover' : True
+        'no_default_epub_cover' : True,
+        # fixing the wrong left margin
+        'mobi_ignore_margins' : True,
     }
 
+    preprocess_regexps    = [
+        # filtering for correct dashes
+        (re.compile(r' - '), lambda match: ' – '), # regular "Gedankenstrich"
+        (re.compile(r' -,'), lambda match: ' –,'), # "Gedankenstrich" before a comma
+        (re.compile(r'(?<=\d)-(?=\d)'), lambda match: '–'), # number-number
+        # filtering for unicode characters that are missing on the Kindle,
+        # try to replace them with meaningful work-arounds
+        (re.compile(u'\u2080'), lambda match: '<span style="font-size: 50%;">0</span>'), # subscript-0
+        (re.compile(u'\u2081'), lambda match: '<span style="font-size: 50%;">1</span>'), # subscript-1
+        (re.compile(u'\u2082'), lambda match: '<span style="font-size: 50%;">2</span>'), # subscript-2
+        (re.compile(u'\u2083'), lambda match: '<span style="font-size: 50%;">3</span>'), # subscript-3
+        (re.compile(u'\u2084'), lambda match: '<span style="font-size: 50%;">4</span>'), # subscript-4
+        (re.compile(u'\u2085'), lambda match: '<span style="font-size: 50%;">5</span>'), # subscript-5
+        (re.compile(u'\u2086'), lambda match: '<span style="font-size: 50%;">6</span>'), # subscript-6
+        (re.compile(u'\u2087'), lambda match: '<span style="font-size: 50%;">7</span>'), # subscript-7
+        (re.compile(u'\u2088'), lambda match: '<span style="font-size: 50%;">8</span>'), # subscript-8
+        (re.compile(u'\u2089'), lambda match: '<span style="font-size: 50%;">9</span>'), # subscript-9
+    ]
+
     def build_index(self):
         domain = "http://premium.zeit.de"
         url = domain + "/abovorteile/cgi-bin/_er_member/p4z.fpl?ER_Do=getUserData&ER_NextTemplate=login_ok"
@@ -55,9 +77,36 @@ class ZeitEPUBAbo(BasicNewsRecipe):
         zfile.extractall(self.output_dir)
 
         tmp.close()
+
         index = os.path.join(self.output_dir, 'content.opf')
 
         self.report_progress(1,_('epub downloaded and extracted'))
 
+        # doing regular expression filtering
+        for path in walk('.'):
+            (shortname, extension) = os.path.splitext(path)
+            if extension.lower() in ('.html', '.htm', '.xhtml'):
+                with open(path, 'r+b') as f:
+                    raw = f.read()
+                    raw = raw.decode('utf-8')
+                    for pat, func in self.preprocess_regexps:
+                        raw = pat.sub(func, raw)
+                    f.seek(0)
+                    f.truncate()
+                    f.write(raw.encode('utf-8'))
+
+        # adding real cover
+        self.report_progress(0,_('trying to download cover image (titlepage)'))
+        self.download_cover()
+        self.conversion_options["cover"] = self.cover_path
+
         return index
 
+    # getting url of the cover
+    def get_cover_url(self):
+        try:
+            inhalt = self.index_to_soup('http://www.zeit.de/inhalt')
+            cover_url = inhalt.find('div', attrs={'class':'singlearchive clearfix'}).img['src'].replace('icon_','')
+        except:
+            cover_url = 'http://images.zeit.de/bilder/titelseiten_zeit/1946/001_001.jpg'
+        return cover_url