Strip HTML from story titles in all the adapters that don't already.

2026-05-09 05:21:13 +02:00 · 2013-08-21 09:19:58 -05:00 · 2013-08-21 09:19:58 -05:00 · 31b7257496
commit 31b7257496
parent b5d00951de
75 changed files with 83 additions and 84 deletions
--- a/fanficdownloader/adapters/adapter_adastrafanficcom.py
+++ b/fanficdownloader/adapters/adapter_adastrafanficcom.py
@ -90,7 +90,7 @@ class AdAstraFanficComSiteAdapter(BaseSiteAdapter):

        ## Title
        a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
        
        # Find authorid and URL from... author url.
        a = soup.find('a', href=re.compile(r"viewuser.php"))
--- a/fanficdownloader/adapters/adapter_archiveofourownorg.py
+++ b/fanficdownloader/adapters/adapter_archiveofourownorg.py
@ -163,7 +163,7 @@ class ArchiveOfOurOwnOrgAdapter(BaseSiteAdapter):
        
        ## Title
        a = soup.find('a', href=re.compile(r"^/works/\d+$"))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
 		
        # Find authorid and URL from... author url.
        alist = soup.findAll('a', href=re.compile(r"^/users/\w+/pseuds/\w+"))
--- a/fanficdownloader/adapters/adapter_archiveskyehawkecom.py
+++ b/fanficdownloader/adapters/adapter_archiveskyehawkecom.py
@ -101,7 +101,7 @@ class ArchiveSkyeHawkeComAdapter(BaseSiteAdapter):
        
        ## Title
        a = soup.find('div', {'class':"story border"}).find('span',{'class':'left'})
-        title=a.text.split('"')[1]
+        title=stripHTML(a).split('"')[1]
        self.story.setMetadata('title',title)
        
        # Find authorid and URL from... author url.
--- a/fanficdownloader/adapters/adapter_ashwindersycophanthexcom.py
+++ b/fanficdownloader/adapters/adapter_ashwindersycophanthexcom.py
@ -157,7 +157,7 @@ class AshwinderSycophantHexComAdapter(BaseSiteAdapter):
        for info in asoup.findAll('table', {'width' : '100%', 'bordercolor' : re.compile(r'#')}):
            a = info.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
            if a != None:
-                self.story.setMetadata('title',a.string)
+                self.story.setMetadata('title',stripHTML(a))
                break
 		

--- a/fanficdownloader/adapters/adapter_asr3slashzoneorg.py
+++ b/fanficdownloader/adapters/adapter_asr3slashzoneorg.py
@ -128,7 +128,7 @@ class Asr3SlashzoneOrgAdapter(BaseSiteAdapter):
        
        ## Title
        a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
        
        # Find authorid and URL from... author url.
        a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
--- a/fanficdownloader/adapters/adapter_bloodtiesfancom.py
+++ b/fanficdownloader/adapters/adapter_bloodtiesfancom.py
@ -207,7 +207,7 @@ class BloodTiesFansComAdapter(BaseSiteAdapter): # XXX
        
        ## Title
        a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
        
        # Find authorid and URL from... author url.
        a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
--- a/fanficdownloader/adapters/adapter_castlefansorg.py
+++ b/fanficdownloader/adapters/adapter_castlefansorg.py
@ -180,7 +180,7 @@ class CastleFansOrgAdapter(BaseSiteAdapter): # XXX
        pagetitle = soup.find('div',{'id':'pagetitle'})
        ## Title
        a = pagetitle.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
        
        # Find authorid and URL from... author url.
        a = pagetitle.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
--- a/fanficdownloader/adapters/adapter_chaossycophanthexcom.py
+++ b/fanficdownloader/adapters/adapter_chaossycophanthexcom.py
@ -116,7 +116,7 @@ class ChaosSycophantHexComAdapter(BaseSiteAdapter):
        ## Title
        pt = soup.find('div', {'id' : 'pagetitle'})
        a = pt.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.text)
+        self.story.setMetadata('title',stripHTML(a))
        
        # Find authorid and URL from... author url.
        a = pt.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
--- a/fanficdownloader/adapters/adapter_checkmatedcom.py
+++ b/fanficdownloader/adapters/adapter_checkmatedcom.py
@ -143,11 +143,11 @@ class CheckmatedComAdapter(BaseSiteAdapter):
        # Now go hunting for all the meta data and the chapter list.

        ## Title
-        a = soup.findAll('span', {'class' : 'storytitle'})
-        self.story.setMetadata('title',a[0].string)
+        a = soup.find('span', {'class' : 'storytitle'})
+        self.story.setMetadata('title',stripHTML(a))

        # Find authorid and URL from... author url.
-        a = a[1].find('a', href=re.compile(r"authors.php\?name\=\w+"))
+        a = a.parent.find('a', href=re.compile(r"authors.php\?name\=\w+"))
        self.story.setMetadata('authorId',a['href'].split('=')[1])
        self.story.setMetadata('authorUrl','http://'+self.host+'/'+a['href'])
        self.story.setMetadata('author',a.string)
--- a/fanficdownloader/adapters/adapter_destinysgatewaycom.py
+++ b/fanficdownloader/adapters/adapter_destinysgatewaycom.py
@ -131,7 +131,7 @@ class DestinysGatewayComAdapter(BaseSiteAdapter):
        
        ## Title
        a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
        
        # Find authorid and URL from... author url.
        a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
--- a/fanficdownloader/adapters/adapter_dokugacom.py
+++ b/fanficdownloader/adapters/adapter_dokugacom.py
@ -164,7 +164,7 @@ class DokugaComAdapter(BaseSiteAdapter):
        aut.extract()
        
        a = a.string[:(len(a.string)-4)]
-        self.story.setMetadata('title',a)
+        self.story.setMetadata('title',stripHTML(a))

        # Find the chapters:
        chapters = soup.find('select').findAll('option')
--- a/fanficdownloader/adapters/adapter_dotmoonnet.py
+++ b/fanficdownloader/adapters/adapter_dotmoonnet.py
@ -141,7 +141,7 @@ class DotMoonNetAdapter(BaseSiteAdapter):
        
        ## Title
        a = body.find('b')
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
        
        # Find authorid and URL from... author url. http://www.dotmoon.net/board/index.php?action=profile;u=1'
        a = body.find('a', href=re.compile(r"index.php\?action=profile;u=\d+"))
--- a/fanficdownloader/adapters/adapter_dracoandginnycom.py
+++ b/fanficdownloader/adapters/adapter_dracoandginnycom.py
@ -170,7 +170,7 @@ class DracoAndGinnyComAdapter(BaseSiteAdapter):
        
        ## Title
        a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
        
        # Find authorid and URL from... author url.
        a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
--- a/fanficdownloader/adapters/adapter_dramioneorg.py
+++ b/fanficdownloader/adapters/adapter_dramioneorg.py
@ -154,7 +154,7 @@ class DramioneOrgAdapter(BaseSiteAdapter):
        
        ## Title
        a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
        
        # Find authorid and URL from... author url.
        a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
--- a/fanficdownloader/adapters/adapter_efictionestelielde.py
+++ b/fanficdownloader/adapters/adapter_efictionestelielde.py
@ -104,7 +104,7 @@ class EfictionEstelielDeAdapter(BaseSiteAdapter):
        pagetitle = soup.find('div',{'id':'pagetitle'})
        ## Title
        a = pagetitle.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
        
        # Find authorid and URL from... author url.
        a = pagetitle.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
--- a/fanficdownloader/adapters/adapter_erosnsapphosycophanthexcom.py
+++ b/fanficdownloader/adapters/adapter_erosnsapphosycophanthexcom.py
@ -132,7 +132,7 @@ class ErosnSapphoSycophantHexComAdapter(BaseSiteAdapter):
        ## Title
        pt = soup.find('div', {'id' : 'pagetitle'})
        a = pt.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.text)
+        self.story.setMetadata('title',stripHTML(a))
        
        # Find authorid and URL from... author url.
        a = pt.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
--- a/fanficdownloader/adapters/adapter_fictionalleyorg.py
+++ b/fanficdownloader/adapters/adapter_fictionalleyorg.py
@ -111,7 +111,7 @@ class FictionAlleyOrgSiteAdapter(BaseSiteAdapter):
            url=self.url
            logger.debug("Normalizing to URL: "+url)
            ## title's right there...
-            self.story.setMetadata('title',storya.string)
+            self.story.setMetadata('title',stripHTML(storya))
            data = self._fetchUrl(url)
            soup = bs.BeautifulSoup(data)
            chapterlinklist = soup.findAll('a',{'class':'chapterlink'})
@ -121,7 +121,7 @@ class FictionAlleyOrgSiteAdapter(BaseSiteAdapter):
            ## same way.
            chapsoup = bs.BeautifulSoup(chapterdata)
            storya = chapsoup.find('div',{'class':'breadcrumbs'}).findAll('a')[1]
-            self.story.setMetadata('title',storya.string)
+            self.story.setMetadata('title',stripHTML(storya))
            del chapsoup

        del chapterdata
--- a/fanficdownloader/adapters/adapter_ficwadcom.py
+++ b/fanficdownloader/adapters/adapter_ficwadcom.py
@ -116,7 +116,7 @@ class FicwadComSiteAdapter(BaseSiteAdapter):

        # title - first h4 tag will be title.
        titleh4 = soup.find('h4')
-        self.story.setMetadata('title', titleh4.a.string)
+        self.story.setMetadata('title', stripHTML(titleh4.a))

        # Find authorid and URL from... author url.
        a = soup.find('a', href=re.compile(r"^/author/\d+"))
--- a/fanficdownloader/adapters/adapter_fimfictionnet.py
+++ b/fanficdownloader/adapters/adapter_fimfictionnet.py
@ -117,7 +117,7 @@ class FimFictionNetSiteAdapter(BaseSiteAdapter):
            
        ## Title
        a = soup.find('a', href=re.compile(r'^/story/'+self.story.getMetadata('storyId')))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
        
        # self.story.setMetadata("title", storyMetadata["title"])
        # if not storyMetadata["title"]:
--- a/fanficdownloader/adapters/adapter_finestoriescom.py
+++ b/fanficdownloader/adapters/adapter_finestoriescom.py
@ -142,7 +142,7 @@ class FineStoriesComAdapter(BaseSiteAdapter):
        
        ## Title
        a = soup.find('a', href=re.compile(r'/s/'+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.text)
+        self.story.setMetadata('title',stripHTML(a))
        
        # Find authorid and URL from... author url.
        a = soup.find('a', href=re.compile(r"/a/\w+"))
--- a/fanficdownloader/adapters/adapter_grangerenchantedcom.py
+++ b/fanficdownloader/adapters/adapter_grangerenchantedcom.py
@ -182,7 +182,7 @@ class GrangerEnchantedCom(BaseSiteAdapter):
        
        ## Title
        a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
        
        # Find authorid and URL from... author url.
        a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
--- a/fanficdownloader/adapters/adapter_harrypotterfanfictioncom.py
+++ b/fanficdownloader/adapters/adapter_harrypotterfanfictioncom.py
@ -92,7 +92,7 @@ class HarryPotterFanFictionComSiteAdapter(BaseSiteAdapter):

        ## Title
        a = soup.find('a', href=re.compile(r'\?psid='+self.story.getMetadata('storyId')))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
        ## javascript:if (confirm('Please note. This story may contain adult themes. By clicking here you are stating that you are over 17. Click cancel if you do not meet this requirement.')) location = '?psid=290995'
        if "This story may contain adult themes." in a['href'] and not (self.is_adult or self.getConfig("is_adult")):
            raise exceptions.AdultCheckRequired(self.url)
--- a/fanficdownloader/adapters/adapter_hennethannunnet.py
+++ b/fanficdownloader/adapters/adapter_hennethannunnet.py
@ -101,7 +101,7 @@ class HennethAnnunNetAdapter(BaseSiteAdapter):
        
        ## Title
        a = soup.find('h2', {'id':'page_heading'})
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))

        # Find the chapters: chapter_view.cfm?stid=6663&amp;spordinal=1" 
        for chapter in soup.findAll('a', href=re.compile(r'chapter_view.cfm\?stid='+self.story.getMetadata('storyId')+"&spordinal=\d+$")):
--- a/fanficdownloader/adapters/adapter_hlfictionnet.py
+++ b/fanficdownloader/adapters/adapter_hlfictionnet.py
@ -106,7 +106,7 @@ class HLFictionNetAdapter(BaseSiteAdapter):
        self.story.setMetadata('author',aut.string)
        aut.extract()
        
-        self.story.setMetadata('title',a.string[:(len(a.string)-3)])
+        self.story.setMetadata('title',stripHTML(a)[:(len(a.string)-3)])

        # Find the chapters:
        chapters=soup.find('select')
--- a/fanficdownloader/adapters/adapter_hpfanficarchivecom.py
+++ b/fanficdownloader/adapters/adapter_hpfanficarchivecom.py
@ -105,7 +105,7 @@ class HPFanficArchiveComAdapter(BaseSiteAdapter):
        
        ## Title
        a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
        
        # Find authorid and URL from... author url.
        a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
--- a/fanficdownloader/adapters/adapter_iketernalnet.py
+++ b/fanficdownloader/adapters/adapter_iketernalnet.py
@ -183,7 +183,7 @@ class IkEternalNetAdapter(BaseSiteAdapter):
        
        ## Title
        a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
        
        # Find authorid and URL from... author url.
        a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
--- a/fanficdownloader/adapters/adapter_imagineeficcom.py
+++ b/fanficdownloader/adapters/adapter_imagineeficcom.py
@ -170,7 +170,7 @@ class ImagineEFicComAdapter(BaseSiteAdapter):
        
        ## Title
        a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
        
        # Find authorid and URL from... author url.
        a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
--- a/fanficdownloader/adapters/adapter_indeathnet.py
+++ b/fanficdownloader/adapters/adapter_indeathnet.py
@ -109,7 +109,7 @@ class InDeathNetAdapter(BaseSiteAdapter):
        ## Title
        h = soup.find('a', id="blog_title")
        t = h.find('span')
-        self.story.setMetadata('title',t.contents[0].string.strip())
+        self.story.setMetadata('title',stripHTML(t.contents[0]).strip())
 		
        s = t.find('div')        
        if s != None:
@ -122,9 +122,6 @@ class InDeathNetAdapter(BaseSiteAdapter):
        self.story.setMetadata('authorUrl',a['href'])
        self.story.setMetadata('author',m.group('name'))

-
-
-
        # Find the chapters:
        chapters=soup.findAll('a', title="View entry", href=re.compile(r'http://www.indeath.net/blog/'+self.story.getMetadata('storyId')+"/entry\-(\d+)\-([^/]*)/$"))

--- a/fanficdownloader/adapters/adapter_libraryofmoriacom.py
+++ b/fanficdownloader/adapters/adapter_libraryofmoriacom.py
@ -129,7 +129,7 @@ class LibraryOfMoriaComAdapter(BaseSiteAdapter):
        
        ## Title
        a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
        
        # Find authorid and URL from... author url.
        a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
--- a/fanficdownloader/adapters/adapter_lumossycophanthexcom.py
+++ b/fanficdownloader/adapters/adapter_lumossycophanthexcom.py
@ -116,7 +116,7 @@ class LumosSycophantHexComAdapter(BaseSiteAdapter):
        ## Title
        pt = soup.find('div', {'id' : 'pagetitle'})
        a = pt.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.text)
+        self.story.setMetadata('title',stripHTML(a))
        
        # Find authorid and URL from... author url.
        a = pt.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
--- a/fanficdownloader/adapters/adapter_mediaminerorg.py
+++ b/fanficdownloader/adapters/adapter_mediaminerorg.py
@ -107,10 +107,10 @@ class MediaMinerOrgSiteAdapter(BaseSiteAdapter):
        for font in title.findAll('font'):
            font.extract() # removes 'font' tags from inside the td.        
        if title.has_key('colspan'):
-            titlet = title.text
+            titlet = stripHTML(title)
        else:
            ## No colspan, it's part chapter title--even if it's a one-shot.
-            titlet = ':'.join(title.text.split(':')[:-1]) # strip trailing 'Chapter X' or chapter title
+            titlet = ':'.join(stripHTML(title).split(':')[:-1]) # strip trailing 'Chapter X' or chapter title
        self.story.setMetadata('title',titlet)
        ## The story title is difficult to reliably parse from the
        ## story pages.  Getting it from the author page is, but costs
--- a/fanficdownloader/adapters/adapter_merlinficdtwinscouk.py
+++ b/fanficdownloader/adapters/adapter_merlinficdtwinscouk.py
@ -170,7 +170,7 @@ class MerlinFicDtwinsCoUk(BaseSiteAdapter):
        
        ## Title
        a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
        
        # Find authorid and URL from... author url.
        a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
--- a/fanficdownloader/adapters/adapter_mugglenetcom.py
+++ b/fanficdownloader/adapters/adapter_mugglenetcom.py
@ -193,7 +193,7 @@ class MuggleNetComAdapter(BaseSiteAdapter): # XXX
        
        ## Title
        a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
        
        # Find authorid and URL from... author url.
        a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
--- a/fanficdownloader/adapters/adapter_nationallibrarynet.py
+++ b/fanficdownloader/adapters/adapter_nationallibrarynet.py
@ -104,7 +104,7 @@ class NationalLibraryNetAdapter(BaseSiteAdapter):
        
        ## Title
        a = soup.find('h1')
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
        
        # Find authorid and URL from... author url.
        a = soup.find('a', href=re.compile(r"authorresults.php\?author=\d+"))
--- a/fanficdownloader/adapters/adapter_ncisficcom.py
+++ b/fanficdownloader/adapters/adapter_ncisficcom.py
@ -103,7 +103,7 @@ class NCISFicComAdapter(BaseSiteAdapter):
        
        ## Title
        a = soup.find('h1')
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
        
        # Find authorid and URL from... author url.
        a = soup.find('a', href=re.compile(r"authorresults.php\?author=\d+"))
--- a/fanficdownloader/adapters/adapter_netraptororg.py
+++ b/fanficdownloader/adapters/adapter_netraptororg.py
@ -97,7 +97,7 @@ class NetRaptorOrgAdapter(BaseSiteAdapter):
        ## Title
        pagetitle = soup.find('div',{'id':'pagetitle'})
        a = pagetitle.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
        
        # Find authorid and URL from... author url.
        a = pagetitle.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
--- a/fanficdownloader/adapters/adapter_nfacommunitycom.py
+++ b/fanficdownloader/adapters/adapter_nfacommunitycom.py
@ -156,7 +156,7 @@ class NfaCommunityComAdapter(BaseSiteAdapter): # XXX
        
        ## Title
        a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
        
        # Find authorid and URL from... author url.
        a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
--- a/fanficdownloader/adapters/adapter_nhamagicalworldsus.py
+++ b/fanficdownloader/adapters/adapter_nhamagicalworldsus.py
@ -115,7 +115,7 @@ class NHAMagicalWorldsUsAdapter(BaseSiteAdapter):
            a = info.find('a')
            if 'viewstory.php?sid='+self.story.getMetadata('storyId') == a['href'] or \
                    ('viewstory.php?sid='+self.story.getMetadata('storyId')+'&') in a['href']:
-                self.story.setMetadata('title',a.string)
+                self.story.setMetadata('title',stripHTML(a))
                break
 		

--- a/fanficdownloader/adapters/adapter_nickandgregnet.py
+++ b/fanficdownloader/adapters/adapter_nickandgregnet.py
@ -101,7 +101,7 @@ class NickAndGregNetAdapter(BaseSiteAdapter):

        ## Title
        a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
        
        # Find authorid and URL from... author url.
        a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
--- a/fanficdownloader/adapters/adapter_occlumencysycophanthexcom.py
+++ b/fanficdownloader/adapters/adapter_occlumencysycophanthexcom.py
@ -158,7 +158,7 @@ class OcclumencySycophantHexComAdapter(BaseSiteAdapter):
        for info in asoup.findAll('table', {'class' : 'border'}):
            a = info.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
            if a != None:
-                self.story.setMetadata('title',a.text)
+                self.story.setMetadata('title',stripHTML(a))
                break
 		

--- a/fanficdownloader/adapters/adapter_onedirectionfanfictioncom.py
+++ b/fanficdownloader/adapters/adapter_onedirectionfanfictioncom.py
@ -158,7 +158,7 @@ class OneDirectionFanfictionComAdapter(BaseSiteAdapter):
        
        ## Title
        a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
        
        # Find authorid and URL from... author url.
        a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
--- a/fanficdownloader/adapters/adapter_phoenixsongnet.py
+++ b/fanficdownloader/adapters/adapter_phoenixsongnet.py
@ -136,7 +136,7 @@ class PhoenixSongNetAdapter(BaseSiteAdapter):
        ## Title
        b = soup.find('div', {'id' : 'nav25'})
        a = b.find('a', href=re.compile(r'fanfiction/story/'+self.story.getMetadata('storyId')+"/$"))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
        
        # Find authorid and URL from... author url.  /fanfiction/stories.php?psid=125
        a = b.find('a', href=re.compile(r"/fanfiction/stories.php\?psid=\d+"))
--- a/fanficdownloader/adapters/adapter_pommedesangcom.py
+++ b/fanficdownloader/adapters/adapter_pommedesangcom.py
@ -180,7 +180,7 @@ class PommeDeSangComAdapter(BaseSiteAdapter):
        
        ## Title
        a = soup.find('a', href=re.compile('viewstory.php\?sid=\d+'))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
        
        # Find authorid and URL from... author url.
        a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
--- a/fanficdownloader/adapters/adapter_ponyfictionarchivenet.py
+++ b/fanficdownloader/adapters/adapter_ponyfictionarchivenet.py
@ -136,7 +136,7 @@ class PonyFictionArchiveNetAdapter(BaseSiteAdapter):
        
        ## Title
        a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
        
        # Find authorid and URL from... author url.
        a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
--- a/fanficdownloader/adapters/adapter_potionsandsnitchesnet.py
+++ b/fanficdownloader/adapters/adapter_potionsandsnitchesnet.py
@ -83,7 +83,7 @@ class PotionsAndSnitchesNetSiteAdapter(BaseSiteAdapter):

        ## Title
        a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
        
        # Find authorid and URL from... author url.
        a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
--- a/fanficdownloader/adapters/adapter_potterficscom.py
+++ b/fanficdownloader/adapters/adapter_potterficscom.py
@ -147,7 +147,7 @@ class PotterFicsComAdapter(BaseSiteAdapter):
        #find first metadata block
        mb = cell.div.findNextSibling('div')
        #Get meta...
-        self.story.setMetadata('title', mb.b.string)
+        self.story.setMetadata('title', stripHTML(mb.b))
        #strip out brackets on rating
        self.story.setMetadata('rating', mb.span.string[1:-1])
        #Completion status is denoted by the presence of this image:
--- a/fanficdownloader/adapters/adapter_potterheadsanonymouscom.py
+++ b/fanficdownloader/adapters/adapter_potterheadsanonymouscom.py
@ -181,7 +181,7 @@ class PotterHeadsAnonymousComAdapter(BaseSiteAdapter):
        
        ## Title
        a = pagetitle.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
        
        # Find authorid and URL from... author url.
        a = pagetitle.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
--- a/fanficdownloader/adapters/adapter_pretendercentrecom.py
+++ b/fanficdownloader/adapters/adapter_pretendercentrecom.py
@ -134,7 +134,7 @@ class PretenderCenterComAdapter(BaseSiteAdapter):
        
        ## Title
        a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.text)
+        self.story.setMetadata('title',stripHTML(a))
        
        # Find authorid and URL from... author url.
        a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
--- a/fanficdownloader/adapters/adapter_psychficcom.py
+++ b/fanficdownloader/adapters/adapter_psychficcom.py
@ -130,7 +130,7 @@ class PsychFicComAdapter(BaseSiteAdapter):
        
        ## Title
        a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
        
        # Find authorid and URL from... author url.
        a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
--- a/fanficdownloader/adapters/adapter_qafficcom.py
+++ b/fanficdownloader/adapters/adapter_qafficcom.py
@ -138,7 +138,7 @@ class QafFicComAdapter(BaseSiteAdapter):
        self.story.setMetadata('author',aut.string)
        aut.extract()
        
-        self.story.setMetadata('title',a.string[:(len(a.string)-3)])
+        self.story.setMetadata('title',stripHTML(a)[:(len(a.string)-3)])

        # Find the chapters:
        chapters=soup.find('select')
--- a/fanficdownloader/adapters/adapter_restrictedsectionorg.py
+++ b/fanficdownloader/adapters/adapter_restrictedsectionorg.py
@ -126,10 +126,12 @@ class RestrictedSectionOrgSiteAdapter(BaseSiteAdapter):
        
        self.story.setMetadata('authorId',ahref.split('=')[1])
        self.story.setMetadata('authorUrl','http://'+self.host+'/'+ahref)
-        self.story.setMetadata('author',a.string)
+        self.story.setMetadata('author',stripHTML(a))

        # title, remove byauthorname.
-        self.story.setMetadata('title',h2.text[:h2.text.index("by"+a.string)])
+        auth=stripHTML(a)
+        title=stripHTML(h2)
+        self.story.setMetadata('title',title[:title.index(" by "+auth)])

        dates = soup.findAll('span', {'class':'date'})
        if dates: # only for multi-chapter
--- a/fanficdownloader/adapters/adapter_samdeanarchivenu.py
+++ b/fanficdownloader/adapters/adapter_samdeanarchivenu.py
@ -110,7 +110,7 @@ class SamDeanArchiveNuAdapter(BaseSiteAdapter):
        self.story.setMetadata('author',aut.string)
        aut.extract()
        
-        self.story.setMetadata('title',a.string[:(len(a.string)-3)])
+        self.story.setMetadata('title',stripHTML(a)[:(len(stripHTML(a))-3)])

        # Find the chapters:
        chapters=soup.find('select')
--- a/fanficdownloader/adapters/adapter_scarheadnet.py
+++ b/fanficdownloader/adapters/adapter_scarheadnet.py
@ -181,7 +181,7 @@ class ScarHeadNetAdapter(BaseSiteAdapter):
        
        ## Title
        a = pagetitle.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
        
        # Find authorid and URL from... author url.
        a = pagetitle.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
--- a/fanficdownloader/adapters/adapter_scarvesandcoffeenet.py
+++ b/fanficdownloader/adapters/adapter_scarvesandcoffeenet.py
@ -139,7 +139,7 @@ class ScarvesAndCoffeeNetAdapter(BaseSiteAdapter):
        
        ## Title
        a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
        
        # Find authorid and URL from... author url.
        a = soup.find('div',{"id":"pagetitle"}).find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
--- a/fanficdownloader/adapters/adapter_sg1heliopoliscom.py
+++ b/fanficdownloader/adapters/adapter_sg1heliopoliscom.py
@ -140,7 +140,7 @@ class SG1HeliopolisComAdapter(BaseSiteAdapter):
        
        ## Title
        a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
        
        # Find authorid and URL from... author url.
        a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
--- a/fanficdownloader/adapters/adapter_simplyundeniablecom.py
+++ b/fanficdownloader/adapters/adapter_simplyundeniablecom.py
@ -143,7 +143,7 @@ class SimplyUndeniableComAdapter(BaseSiteAdapter):
        
        ## Title
        a = soup.find('h1')
-        self.story.setMetadata('title',a.text)
+        self.story.setMetadata('title',stripHTML(a))
        
        # Find authorid and URL from... author url.
        a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
@ -155,7 +155,7 @@ class SimplyUndeniableComAdapter(BaseSiteAdapter):
        for info in asoup.findAll('table', {'cellpadding' : '5'}):
            a = info.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
            if a != None:
-                self.story.setMetadata('title',a.string)
+                self.story.setMetadata('title',stripHTML(a))
                break
                
        # Find the chapters:
--- a/fanficdownloader/adapters/adapter_sinfuldesireorg.py
+++ b/fanficdownloader/adapters/adapter_sinfuldesireorg.py
@ -130,7 +130,7 @@ class SinfulDesireOrgAdapter(BaseSiteAdapter):
        
        ## Title
        a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
        
        # Find authorid and URL from... author url.
        a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
--- a/fanficdownloader/adapters/adapter_squidgeorgpeja.py
+++ b/fanficdownloader/adapters/adapter_squidgeorgpeja.py
@ -122,7 +122,7 @@ class SquidgeOrgPejaAdapter(BaseSiteAdapter):
        # formating, so it's a little ugly.

        title = authorSoup.find('a',{'href':'viewstory.php?sid='+self.story.getMetadata('storyId')})
-        self.story.setMetadata('title',title.string)
+        self.story.setMetadata('title',stripHTML(title))
        titleblock=title.parent.parent
        
        chapterselect=soup.find('select',{'name':'chapter'})
--- a/fanficdownloader/adapters/adapter_stargateatlantisorg.py
+++ b/fanficdownloader/adapters/adapter_stargateatlantisorg.py
@ -106,7 +106,7 @@ class StargateAtlantisOrgAdapter(BaseSiteAdapter):
        self.story.setMetadata('author',aut.string)
        aut.extract()
        
-        self.story.setMetadata('title',a.string[:(len(a.string)-3)])
+        self.story.setMetadata('title',stripHTML(a)[:(len(stripHTML(a))-3)])

        # Find the chapters:
        chapters=soup.findAll('div', {'class' : 'content'})
--- a/fanficdownloader/adapters/adapter_storiesofardacom.py
+++ b/fanficdownloader/adapters/adapter_storiesofardacom.py
@ -104,7 +104,7 @@ class StoriesOfArdaComAdapter(BaseSiteAdapter):
        asoup = bs.BeautifulSoup(self._fetchUrl(self.story.getMetadata('authorUrl')))
        
        a.find('em').extract()
-        self.story.setMetadata('title',a.text)
+        self.story.setMetadata('title',stripHTML(a))

        # Find the chapters: chapterview.asp?sid=7000&cid=30919
        chapters=soup.findAll('a', href=re.compile(r'chapterview.asp\?sid='+self.story.getMetadata('storyId')+"&cid=\d+$"))
--- a/fanficdownloader/adapters/adapter_tenhawkpresentscom.py
+++ b/fanficdownloader/adapters/adapter_tenhawkpresentscom.py
@ -133,7 +133,7 @@ class TenhawkPresentsComSiteAdapter(BaseSiteAdapter):

        ## Title
        a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
        
        # Find authorid and URL from... author url.
        a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
--- a/fanficdownloader/adapters/adapter_thealphagatecom.py
+++ b/fanficdownloader/adapters/adapter_thealphagatecom.py
@ -99,7 +99,7 @@ class TheAlphaGateComAdapter(BaseSiteAdapter):
        
        ## Title
        a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
        
        # Find authorid and URL from... author url.
        a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
--- a/fanficdownloader/adapters/adapter_thehookupzonenet.py
+++ b/fanficdownloader/adapters/adapter_thehookupzonenet.py
@ -179,7 +179,7 @@ class TheHookupZoneNetAdapter(BaseSiteAdapter): # XXX
        
        ## Title
        a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
        
        # Find authorid and URL from... author url.
        a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
--- a/fanficdownloader/adapters/adapter_themasquenet.py
+++ b/fanficdownloader/adapters/adapter_themasquenet.py
@ -177,7 +177,7 @@ class TheMasqueNetAdapter(BaseSiteAdapter):
        
        ## Title
        a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
        
        # Find authorid and URL from... author url.
        a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
--- a/fanficdownloader/adapters/adapter_thepetulantpoetesscom.py
+++ b/fanficdownloader/adapters/adapter_thepetulantpoetesscom.py
@ -165,7 +165,7 @@ class ThePetulantPoetessComAdapter(BaseSiteAdapter):
            for info in asoup.findAll('td', {'class' : 'highlightcolor1'}):
                a = info.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
                if a != None:
-                    self.story.setMetadata('title',a.text)                
+                    self.story.setMetadata('title',stripHTML(a))
                    found = 1
                    break
            index=index+1
--- a/fanficdownloader/adapters/adapter_thequidditchpitchorg.py
+++ b/fanficdownloader/adapters/adapter_thequidditchpitchorg.py
@ -165,7 +165,7 @@ class TheQuidditchPitchOrgAdapter(BaseSiteAdapter): # XXX
        
        ## Title
        a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
        
        # Find authorid and URL from... author url.
        a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
--- a/fanficdownloader/adapters/adapter_tokrafandomnetcom.py
+++ b/fanficdownloader/adapters/adapter_tokrafandomnetcom.py
@ -131,7 +131,7 @@ class TokraFandomnetComAdapter(BaseSiteAdapter):
        
        ## Title
        a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
        
        # Find authorid and URL from... author url.
        a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
--- a/fanficdownloader/adapters/adapter_twilightarchivescom.py
+++ b/fanficdownloader/adapters/adapter_twilightarchivescom.py
@ -100,7 +100,7 @@ class TwilightArchivesComAdapter(BaseSiteAdapter):
        
        ## Title
        a = soup.find('h1')
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
        
        # Find the chapters:
        chapters=soup.find('ol', {'class' : 'chapters'})
--- a/fanficdownloader/adapters/adapter_twilightednet.py
+++ b/fanficdownloader/adapters/adapter_twilightednet.py
@ -130,7 +130,7 @@ class TwilightedNetSiteAdapter(BaseSiteAdapter):

        ## Title
        a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
        
        # Find authorid and URL from... author url.
        a = soup.find('a', href=re.compile(r"viewuser.php"))
--- a/fanficdownloader/adapters/adapter_twiwritenet.py
+++ b/fanficdownloader/adapters/adapter_twiwritenet.py
@ -144,7 +144,7 @@ class TwiwriteNetSiteAdapter(BaseSiteAdapter):
        
        ## Title
        a = pagetitlediv.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
        
        # Find authorid and URL from... author url.
        a = pagetitlediv.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
--- a/fanficdownloader/adapters/adapter_walkingtheplankorg.py
+++ b/fanficdownloader/adapters/adapter_walkingtheplankorg.py
@ -115,7 +115,7 @@ class WalkingThePlankOrgAdapter(BaseSiteAdapter):
        
        ## Title
        a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
        
        # Find authorid and URL from... author url.
        a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
--- a/fanficdownloader/adapters/adapter_whoficcom.py
+++ b/fanficdownloader/adapters/adapter_whoficcom.py
@ -70,7 +70,7 @@ class WhoficComSiteAdapter(BaseSiteAdapter):
                raise e

        # pull title(title) and author from the HTML title.
-        title = soup.find('title').string
+        title = stripHTML(soup.find('title'))
        logger.debug('Title: %s' % title)
        title = title.split('::')[1].strip()
        self.story.setMetadata('title',title.split(' by ')[0].strip())
--- a/fanficdownloader/adapters/adapter_wizardtalesnet.py
+++ b/fanficdownloader/adapters/adapter_wizardtalesnet.py
@ -171,7 +171,7 @@ class WizardTalesNetAdapter(BaseSiteAdapter):
        ## Title
        pt = soup.find('div', {'id' : 'pagetitle'})
        a = pt.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.text)
+        self.story.setMetadata('title',stripHTML(a))
        
        # Find authorid and URL from... author url.
        a = pt.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
--- a/fanficdownloader/adapters/adapter_wolverineandroguecom.py
+++ b/fanficdownloader/adapters/adapter_wolverineandroguecom.py
@ -101,7 +101,7 @@ class WolverineAndRogueComAdapter(BaseSiteAdapter):
        ## Title
        pt = soup.find('div', {'id' : 'pagetitle'})
        a = pt.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.text)
+        self.story.setMetadata('title',stripHTML(a))
        
        # Find authorid and URL from... author url.
        a = pt.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
--- a/fanficdownloader/adapters/adapter_wraithbaitcom.py
+++ b/fanficdownloader/adapters/adapter_wraithbaitcom.py
@ -113,7 +113,7 @@ class WraithBaitComAdapter(BaseSiteAdapter):
        ## Title
        pt = soup.find('div', {'id' : 'pagetitle'})
        a = pt.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
        
        # Find authorid and URL from... author url.
        alist = pt.findAll('a', href=re.compile(r"viewuser.php\?uid=\d+"))