Shortcuts for config/about for Mac. Handle tags inside metadata on ksarchivecom.

Some Mac versions crash if there are menu items set to not have shortcuts.
Also accept https, but change to http.

calibre-plugin/__init__.py

@@ -27,7 +27,7 @@ class FanFictionDownLoaderBase(InterfaceActionBase):
     description         = 'UI plugin to download FanFiction stories from various sites.'
     supported_platforms = ['windows', 'osx', 'linux']
     author              = 'Jim Miller'
-    version             = (1, 6, 5)
+    version             = (1, 6, 7)
     minimum_calibre_version = (0, 8, 57)
 
     #: This field defines the GUI plugin class that contains all the code

calibre-plugin/ffdl_plugin.py

@@ -143,8 +143,6 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
                                                        triggered=self.add_dialog )
 
             self.update_action = self.create_menu_item_ex(self.menu, '&Update Existing FanFiction Book(s)', image='plusplus.png',
-                                                          unique_name='Update Existing FanFiction Book(s)',
-                                                          shortcut_name='Update Existing FanFiction Book(s)',
                                                           triggered=self.update_existing)
 
             if 'Reading List' in self.gui.iactions and (prefs['addtolists'] or prefs['addtoreadlists']) :
@@ -164,37 +162,31 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
 
                 if addmenutxt:
                     self.add_send_action = self.create_menu_item_ex(self.menu, addmenutxt, image='plusplus.png',
-                                                                    unique_name=addmenutxt,
-                                                                    shortcut_name=addmenutxt,
                                                                     triggered=partial(self.update_lists,add=True))
 
                 if rmmenutxt:
                     self.add_remove_action = self.create_menu_item_ex(self.menu, rmmenutxt, image='minusminus.png',
-                                                                      unique_name=rmmenutxt,
-                                                                      shortcut_name=rmmenutxt,
                                                                       triggered=partial(self.update_lists,add=False))
                 
             self.menu.addSeparator()
             self.get_list_action = self.create_menu_item_ex(self.menu, 'Get URLs from Selected Books', image='bookmarks.png',
-                                                            unique_name='Get URLs from Selected Books',
-                                                            shortcut_name='Get URLs from Selected Books',
                                                             triggered=self.get_list_urls)
 
             self.get_list_url_action = self.create_menu_item_ex(self.menu, 'Get Story URLs from Web Page', image='view.png',
-                                                                unique_name='Get Story URLs from Web Page',
-                                                                shortcut_name='Get Story URLs from Web Page',
                                                                 triggered=self.get_urls_from_page)
 
             self.menu.addSeparator()
-            self.config_action = create_menu_action_unique(self, self.menu, '&Configure Plugin', shortcut=False,
-                                                           image= 'config.png',
-                                                           unique_name='Configure FanFictionDownLoader',
-                                                           triggered=partial(do_user_config,parent=self.gui))
+            self.config_action = self.create_menu_item_ex(self.menu, '&Configure Plugin', #shortcut=False, # causes crashes on some Macs.  
+                                                          image= 'config.png',
+                                                          unique_name='Configure FanFictionDownLoader',
+                                                          shortcut_name='Configure FanFictionDownLoader',
+                                                          triggered=partial(do_user_config,parent=self.gui))
             
-            self.about_action = create_menu_action_unique(self, self.menu, 'About Plugin', shortcut=False,
-                                                          image= 'images/icon.png',
-                                                          unique_name='About FanFictionDownLoader',
-                                                          triggered=self.about)
+            self.about_action = self.create_menu_item_ex(self.menu, 'About Plugin', #shortcut=False, # causes crashes on some Macs.  
+                                                         image= 'images/icon.png',
+                                                         unique_name='About FanFictionDownLoader', 
+                                                         shortcut_name='About FanFictionDownLoader', 
+                                                         triggered=self.about)
             
             # Before we finalize, make sure we delete any actions for menus that are no longer displayed
             for menu_id, unique_name in self.old_actions_unique_map.iteritems():
@@ -220,12 +212,12 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
     def create_menu_item_ex(self, parent_menu, menu_text, image=None, tooltip=None,
                            shortcut=None, triggered=None, is_checked=None, shortcut_name=None,
                            unique_name=None):
-        #print("create_menu_item_ex before %s"%unique_name)
+        #print("create_menu_item_ex before %s"%menu_text)
         ac = create_menu_action_unique(self, parent_menu, menu_text, image, tooltip,
                                        shortcut, triggered, is_checked, shortcut_name, unique_name)
         self.actions_unique_map[ac.calibre_shortcut_unique_name] = ac.calibre_shortcut_unique_name
         self.menu_actions.append(ac)
-        #print("create_menu_item_ex after %s"%unique_name)
+        #print("create_menu_item_ex after %s"%menu_text)
         return ac
 
     def plugin_button(self):

defaults.ini

@@ -229,10 +229,12 @@ background_color: ffffff
 ## Allow customization of CSS.  Make sure to keep at least one space
 ## at the start of each line and to escape % to %%.  Also need
 ## background_color to be in the same section, if included in CSS.
+## 'adobe-text-layout: optimizeSpeed;' prevents hyphenation on newer Nooks
 output_css: 
  body { background-color: #%(background_color)s;
         text-align: justify;
-        margin: 2%%; }
+        margin: 2%%;
+	adobe-text-layout: optimizeSpeed; }
  pre { font-size: x-small; }
  sml { font-size: small; }
  h1 { text-align: center; }
@@ -704,6 +706,12 @@ cover_exclusion_regexp:/stories/999/images/.*?_trophy.png
 ## this should go in your personal.ini, not defaults.ini.
 #is_adult:true
 
+[www.sinful-desire.org]
+## Some sites do not require a login, but do require the user to
+## confirm they are adult for adult content.  In commandline version,
+## this should go in your personal.ini, not defaults.ini.
+#is_adult:true
+
 [www.siye.co.uk]
 
 [www.squidge.org/peja]

fanficdownloader/adapters/__init__.py

@@ -96,6 +96,7 @@ import adapter_dracoandginnycom
 import adapter_scarvesandcoffeenet
 import adapter_thepetulantpoetesscom
 import adapter_wolverineandroguecom
+import adapter_sinfuldesireorg
 
 ## This bit of complexity allows adapters to be added by just adding
 ## importing.  It eliminates the long if/else clauses we used to need
@@ -116,7 +117,7 @@ for x in imports():
             
 def getAdapter(config,url,fileform=None):
     ## fix up leading protocol.
-    fixedurl = re.sub(r"(?i)^[htp]+[:/]+","http://",url.strip())
+    fixedurl = re.sub(r"(?i)^[htps]+[:/]+","http://",url.strip())
     if not fixedurl.startswith("http"):
         fixedurl = "http://%s"%url
     ## remove any trailing '#' locations.

fanficdownloader/adapters/adapter_ksarchivecom.py

@@ -167,7 +167,7 @@ class KSArchiveComAdapter(BaseSiteAdapter): # XXX
         a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
         self.story.setMetadata('authorId',a['href'].split('=')[1])
         self.story.setMetadata('authorUrl','http://'+self.host+'/'+a['href'])
-        self.story.setMetadata('author',a.string)
+        self.story.setMetadata('author',stripHTML(a))
 
         # Find the chapters:
         for chapter in soup.findAll('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"&chapter=\d+$")):
@@ -190,7 +190,7 @@ class KSArchiveComAdapter(BaseSiteAdapter): # XXX
         labels = soup.findAll('span',{'class':'label'})
         for labelspan in labels:
             value = labelspan.nextSibling
-            label = labelspan.string
+            label = stripHTML(labelspan)
 
             if 'Summary' in label:
                 ## Everything until the next span class='label'
@@ -215,50 +215,50 @@ class KSArchiveComAdapter(BaseSiteAdapter): # XXX
 
             if 'Categories' in label:
                 cats = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=categories'))
-                catstext = [cat.string for cat in cats]
+                catstext = [stripHTML(cat) for cat in cats]
                 for cat in catstext:
                     # ran across one story with an empty <a href="browse.php?type=categories&amp;catid=1"></a>
                     # tag in the desc once.
                     if cat and cat.strip() in ('Poetry','Essays'):
-                        self.story.addToList('category',cat.string)
+                        self.story.addToList('category',stripHTML(cat))
 
             if 'Characters' in label:
                 self.story.addToList('characters','Kirk')
                 self.story.addToList('characters','Spock')
                 chars = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=characters'))
-                charstext = [char.string for char in chars]
+                charstext = [stripHTML(char) for char in chars]
                 for char in charstext:
-                    self.story.addToList('characters',char.string)
+                    self.story.addToList('characters',stripHTML(char))
 
             ## Not all sites use Genre, but there's no harm to
             ## leaving it in.  Check to make sure the type_id number
             ## is correct, though--it's site specific.
             if 'Genre' in label:
                 genres = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=1')) # XXX
-                genrestext = [genre.string for genre in genres]
+                genrestext = [stripHTML(genre) for genre in genres]
                 self.genre = ', '.join(genrestext)
                 for genre in genrestext:
-                    self.story.addToList('genre',genre.string)
+                    self.story.addToList('genre',stripHTML(genre))
 
             ## In addition to Genre (which is very site specific) KSA
             ## has 'Story Type', which is much more what most sites
             ## call genre.
             if 'Story Type' in label:
                 genres = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=5')) # XXX
-                genrestext = [genre.string for genre in genres]
+                genrestext = [stripHTML(genre) for genre in genres]
                 self.genre = ', '.join(genrestext)
                 for genre in genrestext:
-                    self.story.addToList('genre',genre.string)
+                    self.story.addToList('genre',stripHTML(genre))
 
             ## Not all sites use Warnings, but there's no harm to
             ## leaving it in.  Check to make sure the type_id number
             ## is correct, though--it's site specific.
             if 'Warnings' in label:
                 warnings = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=2')) # XXX
-                warningstext = [warning.string for warning in warnings]
+                warningstext = [stripHTML(warning) for warning in warnings]
                 self.warning = ', '.join(warningstext)
                 for warning in warningstext:
-                    self.story.addToList('warnings',warning.string)
+                    self.story.addToList('warnings',stripHTML(warning))
 
             if 'Completed' in label:
                 if 'Yes' in value:
@@ -277,7 +277,7 @@ class KSArchiveComAdapter(BaseSiteAdapter): # XXX
         try:
             # Find Series name from series URL.
             a = soup.find('a', href=re.compile(r"viewseries.php\?seriesid=\d+"))
-            series_name = a.string
+            series_name = stripHTML(a)
             series_url = 'http://'+self.host+'/'+a['href']
 
             # use BeautifulSoup HTML parser to make everything easier to find.

fanficdownloader/adapters/adapter_sinfuldesireorg.py

@@ -0,0 +1,253 @@
+# -*- coding: utf-8 -*-
+
+# Copyright 2012 Fanficdownloader team
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+import time
+import logging
+import re
+import urllib2
+
+from .. import BeautifulSoup as bs
+from ..htmlcleanup import stripHTML
+from .. import exceptions as exceptions
+
+from base_adapter import BaseSiteAdapter,  makeDate
+
+def getClass():
+    return SinfulDesireOrgAdapter
+
+# Class name has to be unique.  Our convention is camel case the
+# sitename with Adapter at the end.  www is skipped.
+class SinfulDesireOrgAdapter(BaseSiteAdapter):
+
+    def __init__(self, config, url):
+        BaseSiteAdapter.__init__(self, config, url)
+
+        self.decode = ["Windows-1252",
+                       "utf8"] # 1252 is a superset of iso-8859-1.
+                               # Most sites that claim to be
+                               # iso-8859-1 (and some that claim to be
+                               # utf8) are really windows-1252.
+        self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
+        self.password = ""
+        self.is_adult=False
+        
+        # get storyId from url--url validation guarantees query is only sid=1234
+        self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
+        logging.debug("storyId: (%s)"%self.story.getMetadata('storyId'))
+        
+        # normalized story URL.
+        self._setURL('http://' + self.getSiteDomain() + '/archive/viewstory.php?sid='+self.story.getMetadata('storyId'))
+        
+        # Each adapter needs to have a unique site abbreviation.
+        self.story.setMetadata('siteabbrev','snds')
+
+        # If all stories from the site fall into the same category,
+        # the site itself isn't likely to label them as such, so we
+        # do.
+        self.story.addToList("category","Supernatural")
+
+        # The date format will vary from site to site.
+        # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
+        self.dateformat = "%m/%d/%Y"
+            
+    @staticmethod # must be @staticmethod, don't remove it.
+    def getSiteDomain():
+        # The site domain.  Does have www here, if it uses it.
+        return 'www.sinful-desire.org'
+
+    def getSiteExampleURLs(self):
+        return "http://"+self.getSiteDomain()+"/archive/viewstory.php?sid=1234"
+
+    def getSiteURLPattern(self):
+        return re.escape("http://"+self.getSiteDomain()+"/archive/viewstory.php?sid=")+r"\d+$"
+
+    ## Getting the chapter list and the meta data, plus 'is adult' checking.
+    def extractChapterUrlsAndMetadata(self):
+
+        if self.is_adult or self.getConfig("is_adult"):
+            # Weirdly, different sites use different warning numbers.
+            # If the title search below fails, there's a good chance
+            # you need a different number.  print data at that point
+            # and see what the 'click here to continue' url says.
+            addurl = "&warning=5"
+        else:
+            addurl=""
+
+        # index=1 makes sure we see the story chapter index.  Some
+        # sites skip that for one-chapter stories.
+        url = self.url+'&index=1'+addurl
+        logging.debug("URL: "+url)
+
+        try:
+            data = self._fetchUrl(url)
+        except urllib2.HTTPError, e:
+            if e.code == 404:
+                raise exceptions.StoryDoesNotExist(self.url)
+            else:
+                raise e
+
+        m = re.search(r"'viewstory.php\?sid=\d+((?:&ageconsent=ok)?&warning=\d+)'",data)
+        if m != None:
+            if self.is_adult or self.getConfig("is_adult"):
+                # We tried the default and still got a warning, so
+                # let's pull the warning number from the 'continue'
+                # link and reload data.
+                addurl = m.group(1)
+                # correct stupid & error in url.
+                addurl = addurl.replace("&","&")
+                url = self.url+'&index=1'+addurl
+                logging.debug("URL 2nd try: "+url)
+
+                try:
+                    data = self._fetchUrl(url)
+                except urllib2.HTTPError, e:
+                    if e.code == 404:
+                        raise exceptions.StoryDoesNotExist(self.url)
+                    else:
+                        raise e    
+            else:
+                raise exceptions.AdultCheckRequired(self.url)
+            
+        if "Access denied. This story has not been validated by the adminstrators of this site." in data:
+            raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
+            
+        # use BeautifulSoup HTML parser to make everything easier to find.
+        soup = bs.BeautifulSoup(data)
+        # print data
+
+        # Now go hunting for all the meta data and the chapter list.
+        
+        ## Title
+        a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
+        self.story.setMetadata('title',a.string)
+        
+        # Find authorid and URL from... author url.
+        a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
+        self.story.setMetadata('authorId',a['href'].split('=')[1])
+        self.story.setMetadata('authorUrl','http://'+self.host+'/archive/'+a['href'])
+        self.story.setMetadata('author',a.string)
+
+        # Find the chapters:
+        for chapter in soup.findAll('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"&chapter=\d+$")):
+            # just in case there's tags, like <i> in chapter titles.
+            self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+'/archive/'+chapter['href']+addurl))
+
+        self.story.setMetadata('numChapters',len(self.chapterUrls))
+
+        # eFiction sites don't help us out a lot with their meta data
+        # formating, so it's a little ugly.
+
+        # utility method
+        def defaultGetattr(d,k):
+            try:
+                return d[k]
+            except:
+                return ""
+
+        # <span class="label">Rated:</span> NC-17<br /> etc
+        labels = soup.findAll('span',{'class':'label'})
+        for labelspan in labels:
+            value = labelspan.nextSibling
+            label = labelspan.string
+
+            if 'Summary' in label:
+                ## Everything until the next span class='label'
+                svalue = ""
+                while not defaultGetattr(value,'class') == 'label':
+                    svalue += str(value)
+                    value = value.nextSibling
+                self.setDescription(url,svalue)
+                #self.story.setMetadata('description',stripHTML(svalue))
+
+            if 'Rated' in label:
+                self.story.setMetadata('rating', value)
+
+            if 'Word count' in label:
+                self.story.setMetadata('numWords', value)
+
+            if 'Categories' in label:
+                cats = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=categories'))
+                for cat in cats:
+                    self.story.addToList('category',cat.string)
+
+            if 'Characters' in label:
+                chars = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=characters'))
+                for char in chars:
+                    self.story.addToList('characters',char.string)
+
+            if 'Genre' in label:
+                genres = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=1'))
+                for genre in genres:
+                    self.story.addToList('genre',genre.string)
+                genres = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=3'))
+                for genre in genres:
+                    self.story.addToList('genre',genre.string)
+
+            if 'Warnings' in label:
+                warnings = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=2'))
+                for warning in warnings:
+                    self.story.addToList('warnings',warning.string)
+
+            if 'Completed' in label:
+                if 'Yes' in value:
+                    self.story.setMetadata('status', 'Completed')
+                else:
+                    self.story.setMetadata('status', 'In-Progress')
+
+            if 'Published' in label:
+                self.story.setMetadata('datePublished', makeDate(stripHTML(value), self.dateformat))
+            
+            if 'Updated' in label:
+                self.story.setMetadata('dateUpdated', makeDate(stripHTML(value), self.dateformat))
+
+        try:
+            # Find Series name from series URL.
+            a = soup.find('a', href=re.compile(r"viewseries.php\?seriesid=\d+"))
+            series_name = a.string
+            series_url = 'http://'+self.host+'/archive/'+a['href']
+
+            # use BeautifulSoup HTML parser to make everything easier to find.
+            seriessoup = bs.BeautifulSoup(self._fetchUrl(series_url))
+            # can't use ^viewstory...$ in case of higher rated stories with javascript href.
+            storyas = seriessoup.findAll('a', href=re.compile(r'viewstory.php\?sid=\d+'))
+            i=1
+            for a in storyas:
+                # skip 'report this' and 'TOC' links
+                if 'contact.php' not in a['href'] and 'index' not in a['href']:
+                    if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
+                        self.setSeries(series_name, i)
+                        break
+                    i+=1
+            
+        except:
+            # I find it hard to care if the series parsing fails
+            pass
+            
+    # grab the text for an individual chapter.
+    def getChapterText(self, url):
+
+        logging.debug('Getting chapter text from: %s' % url)
+
+        soup = bs.BeautifulStoneSoup(self._fetchUrl(url),
+                                     selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
+        
+        div = soup.find('div', {'id' : 'story'})
+
+        if None == div:
+            raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
+    
+        return self.utf8FromSoup(url,div)

index.html

@@ -57,8 +57,8 @@
 	  <h3>New Sites</h3>
 	  <p>
 	    Now supporing www.dracoandginny.com,
-	    www.scarvesandcoffee.net, www.thepetulantpoetess.com and
-	    www.wolverineandrogue.com.  Thanks, Ida!
+	    www.scarvesandcoffee.net, www.thepetulantpoetess.com,
+	    www.wolverineandrogue.com and www.sinful-desire.com.  Thanks, Ida!
 	  </p>
 	  <p>
 	    FFDL now supports over 70 different fanfiction sites.
@@ -528,6 +528,11 @@
 	    Use the URL of the story's chapter list, such as
 	    <br /><a href="http://www.wolverineandrogue.com/wrfa/viewstory.php?sid=1234">http://www.wolverineandrogue.com/wrfa/viewstory.php?sid=1234</a>
 	  </dd>
+	  <dt>www.sinful-desire.org</dt>
+	  <dd>
+	    Use the URL of the story's chapter list, such as
+	    <br /><a href="http://www.sinful-desire.org/archive/viewstory.php?sid=1234">http://www.sinful-desire.org/archive/viewstory.php?sid=1234</a>
+	  </dd>
 	</dl>
 	<p>
 	  A few additional things to know, which will make your life substantially easier:

plugin-defaults.ini

@@ -19,7 +19,7 @@
 ## overridden at several levels
 
 ## Some sites also require the user to confirm they are adult for
-## adult content.
+## adult content.  Uncomment by removing '#' in front of is_adult.
 #is_adult:true
 
 ## All available titlepage_entries and the label used for them:
@@ -214,10 +214,12 @@ background_color: ffffff
 ## Allow customization of CSS.  Make sure to keep at least one space
 ## at the start of each line and to escape % to %%.  Also need
 ## background_color to be in the same section, if included in CSS.
+## 'adobe-text-layout: optimizeSpeed;' prevents hyphenation on newer Nooks
 output_css: 
  body { background-color: #%(background_color)s;
         text-align: justify;
-        margin: 2%%; }
+        margin: 2%%;
+	adobe-text-layout: optimizeSpeed; }
  pre { font-size: x-small; }
  sml { font-size: small; }
  h1 { text-align: center; }
@@ -686,6 +688,12 @@ cover_exclusion_regexp:/stories/999/images/.*?_trophy.png
 ## this should go in your personal.ini, not defaults.ini.
 #is_adult:true
 
+[www.sinful-desire.org]
+## Some sites do not require a login, but do require the user to
+## confirm they are adult for adult content.  In commandline version,
+## this should go in your personal.ini, not defaults.ini.
+#is_adult:true
+
 [www.siye.co.uk]
 
 [www.squidge.org/peja]