Compare commits

...
10 changed files with 99 additions and 41 deletions
+1 -1
View File
@@ -1,6 +1,6 @@
# ffd-retief-hrd fanfictiondownloader
application: fanfictiondownloader
version: 4-4-53
version: 4-4-54
runtime: python27
api_version: 1
threadsafe: true
+1 -1
View File
@@ -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, 7, 20)
version = (1, 7, 21)
minimum_calibre_version = (0, 8, 57)
#: This field defines the GUI plugin class that contains all the code
+2 -2
View File
@@ -239,8 +239,8 @@ class SizePersistedDialog(QDialog):
self.restoreGeometry(self.geom)
def dialog_closing(self, result):
geom = bytearray(self.saveGeometry())
gprefs[self.unique_pref_name] = geom
self.geom = bytearray(self.saveGeometry())
gprefs[self.unique_pref_name] = self.geom
class ReadOnlyTableWidgetItem(QTableWidgetItem):
+1 -1
View File
@@ -258,8 +258,8 @@ class AddNewDialog(SizePersistedDialog):
# invoke the
def ok_clicked(self):
self.dialog_closing(None) # save persistent size.
self.hide()
print("ok_clicked called")
self.go_signal.emit( self.get_ffdl_options(),
self.get_urlstext(),
self.merge,
+5
View File
@@ -571,6 +571,11 @@ extraships:Spike/Buffy
#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
[dramione.org]
## Site dedicated to these categories/characters/ships
extracategories:Harry Potter
@@ -49,7 +49,6 @@ class DarkSolaceOrgAdapter(BaseSiteAdapter):
# get storyId from url--url validation guarantees query is only sid=1234
self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
logger.debug("storyId: (%s)"%self.story.getMetadata('storyId'))
# normalized story URL.
self._setURL('http://' + self.getSiteDomain() + '/elysian/viewstory.php?sid='+self.story.getMetadata('storyId'))
@@ -59,7 +58,7 @@ class DarkSolaceOrgAdapter(BaseSiteAdapter):
# The date format will vary from site to site.
# http://docs.python.org/library/datetime.html#strftime-strptime-behavior
self.dateformat = "%d %B %Y"
self.dateformat = "%B %d, %Y"
@staticmethod # must be @staticmethod, don't remove it.
def getSiteDomain():
@@ -79,7 +78,8 @@ class DarkSolaceOrgAdapter(BaseSiteAdapter):
## Login seems to be reasonably standard across eFiction sites.
def needToLoginCheck(self, data):
if 'This story contains adult content not suitable for children' in data \
or "That password doesn't match the one in our database" in data:
or "That password doesn't match the one in our database" in data \
or "Registered Users Only" in data:
return True
else:
return False
@@ -94,17 +94,16 @@ class DarkSolaceOrgAdapter(BaseSiteAdapter):
params['penname'] = self.getConfig("username")
params['password'] = self.getConfig("password")
params['rememberme'] = '1'
params['sid'] = ''
params['intent'] = ''
params['action'] = 'login'
params['submit'] = 'Submit'
loginUrl = 'http://' + self.getSiteDomain() + '/elysian/user.php'
logger.debug("Will now login to URL (%s) as (%s)" % (loginUrl,
params['penname']))
d = self._fetchUrl(loginUrl, params)
d = self._postUrl(loginUrl, params)
if "User Account Page" not in d : #Member Account
if "Member Account" not in d : #User Account Page
logger.info("Failed to login to URL %s as %s, or have no authorization to access the story" % (loginUrl, params['penname']))
raise exceptions.FailedToLogin(url,params['penname'])
return False
@@ -113,9 +112,19 @@ class DarkSolaceOrgAdapter(BaseSiteAdapter):
## 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 = "&ageconsent=ok&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
url = self.url+'&index=1'+addurl
logger.debug("URL: "+url)
try:
@@ -128,9 +137,30 @@ class DarkSolaceOrgAdapter(BaseSiteAdapter):
if self.needToLoginCheck(data):
# need to log in for this one.
addurl="&ageconsent=ok"
self.performLogin(url)
data = self._fetchUrl(url+addurl)
data = self._fetchUrl(url)
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
logger.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.")
@@ -142,33 +172,41 @@ class DarkSolaceOrgAdapter(BaseSiteAdapter):
# Now go hunting for all the meta data and the chapter list.
## Title and author
a = soup.find('div', {'id' : 'pagetitle'})
div = soup.find('div', {'id' : 'pagetitle'})
aut = a.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
aut = div.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
self.story.setMetadata('authorId',aut['href'].split('=')[1])
self.story.setMetadata('authorUrl','http://'+self.host+'/elysian/'+aut['href'])
self.story.setMetadata('author',aut.string)
aut.extract()
self.story.setMetadata('title',a.string[:(len(a.string)-3)])
# first a tag in pagetitle is title
self.story.setMetadata('title',stripHTML(div.find('a')))
# Find the chapters:
chapters=soup.find('select', {'name' : 'chapter'})
if chapters != None:
for chapter in chapters.findAll('option'):
self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+'/elysian/viewstory.php?sid='+self.story.getMetadata('storyId')+'&chapter='+chapter['value']))
else:
self.chapterUrls.append((self.story.getMetadata('title'),url))
# chapters=soup.find('select', {'name' : 'chapter'})
# if chapters != None:
# for chapter in chapters.findAll('option'):
# self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+'/elysian/viewstory.php?sid='+self.story.getMetadata('storyId')+'&chapter='+chapter['value']))
# else:
# self.chapterUrls.append((self.story.getMetadata('title'),url+"&chapter=1"))
for chapa in soup.findAll('a', href=re.compile(r'viewstory.php\?sid='+
self.story.getMetadata('storyId')+'&chapter=\d+')):
self.chapterUrls.append((stripHTML(chapa),'http://'+self.host+'/elysian/'+chapa['href']))
self.story.setMetadata('numChapters',len(self.chapterUrls))
asoup = bs.BeautifulSoup(self._fetchUrl(self.story.getMetadata('authorUrl')))
for list in asoup.findAll('div', {'class' : re.compile('listbox\s+')}):
a = list.find('a', href=re.compile(r'viewstory.php\?sid='))
if a != None:
if 'viewstory.php?sid='+self.story.getMetadata('storyId') in a['href']:
break
# for metalist in asoup.findAll('div', {'class' : re.compile('listbox\s+')}):
# a = metalist.find('a', href=re.compile(r'viewstory.php\?sid='))
# if a != None:
# if 'viewstory.php?sid='+self.story.getMetadata('storyId') in a['href']:
# break
metalist = asoup.find('a', href=re.compile(r'viewstory.php\?sid='+
self.story.getMetadata('storyId')+'($|[^\d])')).parent.parent
# eFiction sites don't help us out a lot with their meta data
# formating, so it's a little ugly.
@@ -182,7 +220,7 @@ class DarkSolaceOrgAdapter(BaseSiteAdapter):
# <span class="label">Rated:</span> NC-17<br /> etc
labels = list.findAll('span', {'class' : 'classification'})
labels = metalist.findAll('span', {'class' : 'label'})
for labelspan in labels:
label = labelspan.text
value = labelspan.nextSibling
@@ -190,7 +228,7 @@ class DarkSolaceOrgAdapter(BaseSiteAdapter):
if 'Summary' in label:
## Everything until the next span class='label'
svalue = ""
while not (defaultGetattr(value,'class') == 'classification' or "Chapters: " in stripHTML(value)):
while not (defaultGetattr(value,'class') == 'label' or "Chapters: " in stripHTML(value)):
svalue += str(value)
value = value.nextSibling
self.setDescription(url,svalue)
@@ -238,7 +276,7 @@ class DarkSolaceOrgAdapter(BaseSiteAdapter):
try:
# Find Series name from series URL.
a = list.find('a', href=re.compile(r"series.php\?seriesid=\d+"))
a = metalist.find('a', href=re.compile(r"series.php\?seriesid=\d+"))
series_name = a.string
series_url = 'http://'+self.host+'/elysian/'+a['href']
@@ -265,8 +303,7 @@ class DarkSolaceOrgAdapter(BaseSiteAdapter):
logger.debug('Getting chapter text from: %s' % url)
soup = bs.BeautifulStoneSoup(self._fetchUrl(url),
selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
soup = bs.BeautifulSoup(self._fetchUrl(url))
div = soup.find('div', {'id' : 'story'})
+12 -2
View File
@@ -37,10 +37,20 @@ class Configuration(ConfigParser.SafeConfigParser):
def __init__(self, site, fileform):
ConfigParser.SafeConfigParser.__init__(self)
self.sectionslist = ['defaults']
self.addConfigSection(site)
if site.startswith("www."):
sitewith = site
sitewithout = site.replace("www.","")
else:
sitewith = "www."+site
sitewithout = site
self.addConfigSection(sitewith)
self.addConfigSection(sitewithout)
if fileform:
self.addConfigSection(fileform)
self.addConfigSection(site+":"+fileform)
self.addConfigSection(sitewith+":"+fileform)
self.addConfigSection(sitewithout+":"+fileform)
self.addConfigSection("overrides")
self.validEntries = [
+2 -2
View File
@@ -105,9 +105,9 @@ def get_urls_from_text(data,configuration=None,normalize=False):
# 'are you old enough' links, and 'Report This' links.
# The 'normalized' set prevents duplicates.
if 'story.php' in href:
m = re.search(r"(?P<sid>(view)?story\.php\?(sid|psid|no|story|stid)=\d+)",a['href'])
m = re.search(r"(?P<sid>(view)?story\.php\?(sid|psid|no|story|stid)=\d+)",href)
if m != None:
href = form_url(None,m.group('sid'))
href = form_url(href,m.group('sid'))
try:
href = href.replace('&index=1','')
adapter = adapters.getAdapter(configuration,href)
+3 -2
View File
@@ -57,7 +57,8 @@
<h3>Changes:</h3>
<p>
<ul>
<li>Yet another fix for fanfiction.net changes.</li>
<li>Fixes for dark-solace.org/elysian changes.</li>
<li>Allow ini section names both with and without www. IE, [www.fanfiction.net] and [fanfiction.net] will both work now. If both are included, the section without www overrides the section with it.</li>
</ul>
</p>
<p>
@@ -68,7 +69,7 @@
If you have any problems with this application, please
report them in
the <a href="http://groups.google.com/group/fanfic-downloader">FanFictionDownLoader Google Group</a>. The
<a href="http://4-4-52.fanfictiondownloader.appspot.com">Previous Version</a> is also available for you to use if necessary.
<a href="http://4-4-53.fanfictiondownloader.appspot.com">Previous Version</a> is also available for you to use if necessary.
</p>
<div id='error'>
{{ error_message }}
+5
View File
@@ -537,6 +537,11 @@ extraships:Spike/Buffy
#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
[dramione.org]
## Site dedicated to these categories/characters/ships
extracategories:Harry Potter