Add/Integrate bloodtiesfancom, thehookupzonenet, thanks to marillapm67.

2026-05-08 12:36:11 +02:00 · 2012-09-14 17:08:22 -05:00 · 2012-09-14 17:08:22 -05:00 · bd57353601
commit bd57353601
parent 693863a28a
6 changed files with 411 additions and 14 deletions
--- a/defaults.ini
+++ b/defaults.ini
@ -405,6 +405,22 @@ extraships:Severus Snape/Hermione Granger
 #username:YourName
 #password:yourpassword

+[bloodties-fans.com]
+## Site dedicated to these categories/characters/ships
+extracategories:Blood Ties
+
+## Some sites require login (or login for some rated stories) The
+## program can prompt you, or you can save it in config.  In
+## commandline version, this should go in your personal.ini, not
+## defaults.ini.
+#username:YourName
+#password:yourpassword
+
+## Some sites also 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
+
 [castlefans.org]
 ## Site dedicated to these categories/characters/ships
 extracategories:Castle
@ -672,6 +688,22 @@ extracategories:Harry Potter
 extracharacters:Draco Malfoy,Harry Potter
 extraships:Harry Potter/Draco Malfoy

+[thehookupzone.net]
+## Site dedicated to these categories/characters/ships
+extracategories:Criminal Minds
+
+## Some sites require login (or login for some rated stories) The
+## program can prompt you, or you can save it in config.  In
+## commandline version, this should go in your personal.ini, not
+## defaults.ini.
+#username:YourName
+#password:yourpassword
+
+## Some sites also 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
+
 [themasque.net]
 ## Some sites require login (or login for some rated stories) The
 ## program can prompt you, or you can save it in config.  In
--- a/fanficdownloader/adapters/init.py
+++ b/fanficdownloader/adapters/init.py
@ -98,6 +98,8 @@ import adapter_thepetulantpoetesscom
 import adapter_wolverineandroguecom
 import adapter_sinfuldesireorg
 import adapter_merlinficdtwinscouk
+import adapter_thehookupzonenet
+import adapter_bloodtiesfancom

 ## This bit of complexity allows adapters to be added by just adding
 ## importing.  It eliminates the long if/else clauses we used to need
--- a/fanficdownloader/adapters/adapter_bloodtiesfancom.py
+++ b/fanficdownloader/adapters/adapter_bloodtiesfancom.py
@ -0,0 +1,333 @@
+# -*- coding: utf-8 -*-
+
+# Copyright 2011 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
+
+# By virtue of being recent and requiring both is_adult and user/pass,
+# adapter_fanficcastletvnet.py is the best choice for learning to
+# write adapters--especially for sites that use the eFiction system.
+# Most sites that have ".../viewstory.php?sid=123" in the story URL
+# are eFiction.
+
+# For non-eFiction sites, it can be considerably more complex, but
+# this is still a good starting point.
+
+# In general an 'adapter' needs to do these five things:
+
+# - 'Register' correctly with the downloader
+# - Site Login (if needed)
+# - 'Are you adult?' check (if needed--some do one, some the other, some both)
+# - Grab the chapter list
+# - Grab the story meta-data (some (non-eFiction) adapters have to get it from the author page)
+# - Grab the chapter texts
+
+# Search for XXX comments--that's where things are most likely to need changing.
+
+# This function is called by the downloader in all adapter_*.py files
+# in this dir to register the adapter class.  So it needs to be
+# updated to reflect the class below it.  That, plus getSiteDomain()
+# take care of 'Registering'.
+def getClass():
+    return BloodTiesFansComAdapter # XXX
+
+# Class name has to be unique.  Our convention is camel case the
+# sitename with Adapter at the end.  www is skipped.
+class BloodTiesFansComAdapter(BaseSiteAdapter): # XXX
+
+    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.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.
+        # XXX Most sites don't have the /fanfic part.  Replace all to remove it usually.
+        self._setURL('http://' + self.getSiteDomain() + '/fiction/viewstory.php?sid='+self.story.getMetadata('storyId'))
+        
+        # Each adapter needs to have a unique site abbreviation.
+        self.story.setMetadata('siteabbrev','btf') # XXX
+
+        # The date format will vary from site to site.
+        # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
+        self.dateformat = "%b %d, %Y" # XXX
+            
+    @staticmethod # must be @staticmethod, don't remove it.
+    def getSiteDomain():
+        # The site domain.  Does have www here, if it uses it.
+        return 'bloodties-fans.com' # XXX
+
+    def getSiteExampleURLs(self):
+        return "http://"+self.getSiteDomain()+"/fiction/viewstory.php?sid=1234"
+
+    def getSiteURLPattern(self):
+        return re.escape("http://"+self.getSiteDomain()+"/fiction/viewstory.php?sid=")+r"\d+$"
+
+    ## Login seems to be reasonably standard across eFiction sites.
+    def needToLoginCheck(self, data):
+        if 'Registered Users Only' in data \
+                or 'There is no such account on our website' in data \
+                or "That password doesn't match the one in our database" in data:
+            return True
+        else:
+            return False
+        
+    def performLogin(self, url):
+        params = {}
+
+        if self.password:
+            params['penname'] = self.username
+            params['password'] = self.password
+        else:
+            params['penname'] = self.getConfig("username")
+            params['password'] = self.getConfig("password")
+        params['cookiecheck'] = '1'
+        params['submit'] = 'Submit'
+    
+        loginUrl = 'http://' + self.getSiteDomain() + '/fiction/user.php?action=login'
+        logging.debug("Will now login to URL (%s) as (%s)" % (loginUrl,
+                                                              params['penname']))
+    
+        d = self._fetchUrl(loginUrl, params)
+    
+        if "Member Account" not in d : #Member Account
+            logging.info("Failed to login to URL %s as %s" % (loginUrl,
+                                                              params['penname']))
+            raise exceptions.FailedToLogin(url,params['penname'])
+            return False
+        else:
+            return True
+
+    ## 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.
+
+            # Furthermore, there's a couple sites now with more than
+            # one warning level for different ratings.  And they're
+            # fussy about it.  midnightwhispers has three: 4, 2 & 1.
+            # we'll try 1 first.
+            addurl = "&ageconsent=ok&warning=4" # XXX
+        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
+            
+        # The actual text that is used to announce you need to be an
+        # adult varies from site to site.  Again, print data before
+        # the title search to troubleshoot.
+            
+        # Since the warning text can change by warning level, let's
+        # look for the warning pass url.  nfacommunity uses
+        # &amp;warning= -- actually, so do other sites.  Must be an
+        # eFiction book.
+            
+        # viewstory.php?sid=561&amp;warning=4
+        # viewstory.php?sid=561&amp;warning=1
+        # viewstory.php?sid=561&amp;warning=2
+        #print data
+        #m = re.search(r"'viewstory.php\?sid=1882(&amp;warning=4)'",data)
+        m = re.search(r"'viewstory.php\?sid=\d+((?:&amp;ageconsent=ok)?&amp;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 &amp; error in url.
+                addurl = addurl.replace("&amp;","&")
+                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+'/'+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+'/fiction/'+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'))
+                catstext = [cat.string for cat in cats]
+                for cat in catstext:
+                    self.story.addToList('category',cat.string)
+
+            if 'Characters' in label:
+                chars = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=characters'))
+                charstext = [char.string for char in chars]
+                for char in charstext:
+                    self.story.addToList('characters',char.string)
+
+            ## 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=2')) # XXX
+                genrestext = [genre.string for genre in genres]
+                self.genre = ', '.join(genrestext)
+                for genre in genrestext:
+                    self.story.addToList('genre',genre.string)
+
+            ## 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]
+                self.warning = ', '.join(warningstext)
+                for warning in warningstext:
+                    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:
+                # there's a stray [ at the end.
+                #value = value[0:-1]
+                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+'/fiction/'+a['href']
+
+            # use BeautifulSoup HTML parser to make everything easier to find.
+            seriessoup = bs.BeautifulSoup(self._fetchUrl(series_url))
+            storyas = seriessoup.findAll('a', href=re.compile(r'^viewstory.php\?sid=\d+$'))
+            i=1
+            for a in storyas:
+                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)
--- a/fanficdownloader/adapters/adapter_thehookupzonenet.py
+++ b/fanficdownloader/adapters/adapter_thehookupzonenet.py
@ -80,11 +80,6 @@ class TheHookupZoneNetAdapter(BaseSiteAdapter): # XXX
        # Each adapter needs to have a unique site abbreviation.
        self.story.setMetadata('siteabbrev','thupz') # XXX

-        # 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","Criminal Minds") # XXX
-
        # The date format will vary from site to site.
        # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
        self.dateformat = "%b %d, %Y" # XXX
--- a/index.html
+++ b/index.html
@ -54,18 +54,11 @@
 	      much easier. </p>
 	  </div>
 	  <!-- put announcements here, h3 is a good title size. -->
-	  <h3>New Site / Features / Fixes</h3>
+	  <h3>New Sites</h3>
 	  <p>
-	    New site merlinfic.dtwins.co.uk, thanks Ida.
+	    New sites bloodties-fans.com and thehookupzone.net, thanks Marillapm!
 	  </p>
 	  <p>
-	    New feature options strip_chapter_numbers and add_chapter_numbers can be turned on to
-	    normalize numbers in front of chapter titles.
-	  </p>
-	  <p>
-	    Fixed BBCode in fimfiction.net story summaries.  Also improved handling of html
-	    in story summaries.
-	  </p>
 	  <p>
 	    Questions?  Check out our 
 	    <a href="http://code.google.com/p/fanficdownloader/wiki/FanFictionDownloaderFAQs">FAQs</a>.
@ -541,6 +534,16 @@
 	    Use the URL of the story's chapter list, such as
 	    <br /><a href="http://merlinfic.dtwins.co.uk/viewstory.php?sid=1234">http://merlinfic.dtwins.co.uk/viewstory.php?sid=1234</a>
 	  </dd>
+	  <dt>bloodties-fans.com</dt>
+	  <dd>
+	    Use the URL of the story's chapter list, such as
+	    <br /><a href="http://bloodties-fans.com/fiction/viewstory.php?sid=1234">http://bloodties-fans.com/fiction/viewstory.php?sid=1234</a>
+	  </dd>
+	  <dt>thehookupzone.net</dt>
+	  <dd>
+	    Use the URL of the story's chapter list, such as
+	    <br /><a href="http://thehookupzone.net/CriminalMinds/viewstory.php?sid=1234">http://thehookupzone.net/CriminalMinds/viewstory.php?sid=1234</a>
+	  </dd>
 	</dl>
 	<p>
 	  A few additional things to know, which will make your life substantially easier:
--- a/plugin-defaults.ini
+++ b/plugin-defaults.ini
@ -390,6 +390,22 @@ extraships:Severus Snape/Hermione Granger
 #username:YourName
 #password:yourpassword

+[bloodties-fans.com]
+## Site dedicated to these categories/characters/ships
+extracategories:Blood Ties
+
+## Some sites require login (or login for some rated stories) The
+## program can prompt you, or you can save it in config.  In
+## commandline version, this should go in your personal.ini, not
+## defaults.ini.
+#username:YourName
+#password:yourpassword
+
+## Some sites also 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
+
 [castlefans.org]
 ## Site dedicated to these categories/characters/ships
 extracategories:Castle
@ -657,6 +673,22 @@ extracategories:Harry Potter
 extracharacters:Draco Malfoy,Harry Potter
 extraships:Harry Potter/Draco Malfoy

+[thehookupzone.net]
+## Site dedicated to these categories/characters/ships
+extracategories:Criminal Minds
+
+## Some sites require login (or login for some rated stories) The
+## program can prompt you, or you can save it in config.  In
+## commandline version, this should go in your personal.ini, not
+## defaults.ini.
+#username:YourName
+#password:yourpassword
+
+## Some sites also 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
+
 [themasque.net]
 ## Some sites require login (or login for some rated stories) The
 ## program can prompt you, or you can save it in config.  In