Backup_Repos/FanFicFare
1
0
Fork 0
mirror of https://github.com/JimmXinu/FanFicFare.git synced 2026-05-05 11:00:47 +02:00
Code Issues Projects Releases Wiki Activity

Add new AccessDenied exception for one line output in CLI.

Browse source
This commit is contained in:
Jim Miller 2016-02-10 12:19:02 -06:00
parent 138de3ac3a
commit 20a789566f
63 changed files with 423 additions and 64 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
fanficfare/adapters/adapter_ashwindersycophanthexcom.py
View file

@ -131,7 +131,7 @@ class AshwinderSycophantHexComAdapter(BaseSiteAdapter):
data = self._fetchUrl(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.")
raise exceptions.AccessDenied(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 = self.make_soup(data)

2
fanficfare/adapters/adapter_asr3slashzoneorg.py
View file

@ -119,7 +119,7 @@ class Asr3SlashzoneOrgAdapter(BaseSiteAdapter):
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.")
raise exceptions.AccessDenied(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 = self.make_soup(data)

2
fanficfare/adapters/adapter_bloodtiesfancom.py
View file

@ -198,7 +198,7 @@ class BloodTiesFansComAdapter(BaseSiteAdapter): # XXX
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.")
raise exceptions.AccessDenied(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 = self.make_soup(data)

2
fanficfare/adapters/adapter_chaossycophanthexcom.py
View file

@ -106,7 +106,7 @@ class ChaosSycophantHexComAdapter(BaseSiteAdapter):
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.")
raise exceptions.AccessDenied(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 = self.make_soup(data)

2
fanficfare/adapters/adapter_csiforensicscom.py
View file

@ -105,7 +105,7 @@ class CSIForensicsComAdapter(BaseSiteAdapter):
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.")
raise exceptions.AccessDenied(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 = self.make_soup(data)

2
fanficfare/adapters/adapter_destinysgatewaycom.py
View file

@ -122,7 +122,7 @@ class DestinysGatewayComAdapter(BaseSiteAdapter):
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.")
raise exceptions.AccessDenied(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 = self.make_soup(data)

2
fanficfare/adapters/adapter_dokugacom.py
View file

@ -147,7 +147,7 @@ class DokugaComAdapter(BaseSiteAdapter):
soup = self.make_soup(data)
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.")
raise exceptions.AccessDenied(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
# print data
# Now go hunting for all the meta data and the chapter list.

2
fanficfare/adapters/adapter_dracoandginnycom.py
View file

@ -161,7 +161,7 @@ class DracoAndGinnyComAdapter(BaseSiteAdapter):
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.")
raise exceptions.AccessDenied(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 = self.make_soup(data)

2
fanficfare/adapters/adapter_dramioneorg.py
View file

@ -146,7 +146,7 @@ class DramioneOrgAdapter(BaseSiteAdapter):
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.")
raise exceptions.AccessDenied(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 = self.make_soup(data)

2
fanficfare/adapters/adapter_efictionestelielde.py
View file

@ -91,7 +91,7 @@ class EfictionEstelielDeAdapter(BaseSiteAdapter):
raise e
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.")
raise exceptions.AccessDenied(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
# Now go hunting for all the meta data and the chapter list.

2
fanficfare/adapters/adapter_efpfanficnet.py
View file

@ -127,7 +127,7 @@ class EFPFanFicNet(BaseSiteAdapter):
data = self._fetchUrl(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.")
# raise exceptions.AccessDenied(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 = self.make_soup(data)

2
fanficfare/adapters/adapter_erosnsapphosycophanthexcom.py
View file

@ -122,7 +122,7 @@ class ErosnSapphoSycophantHexComAdapter(BaseSiteAdapter):
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.")
raise exceptions.AccessDenied(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 = self.make_soup(data)

2
fanficfare/adapters/adapter_fanficcastletvnet.py
View file

@ -177,7 +177,7 @@ class FanficCastleTVNetAdapter(BaseSiteAdapter): # XXX
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.")
raise exceptions.AccessDenied(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 = self.make_soup(data)

2
fanficfare/adapters/adapter_fanfictionjunkiesde.py
View file

@ -170,7 +170,7 @@ class FanfictionJunkiesDeAdapter(BaseSiteAdapter): # XXX
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.")
raise exceptions.AccessDenied(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 = self.make_soup(data)

2
fanficfare/adapters/adapter_finestoriescom.py
View file

@ -126,7 +126,7 @@ class FineStoriesComAdapter(BaseSiteAdapter):
data = self._fetchUrl(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.")
raise exceptions.AccessDenied(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 = self.make_soup(data)

2
fanficfare/adapters/adapter_grangerenchantedcom.py
View file

@ -173,7 +173,7 @@ class GrangerEnchantedCom(BaseSiteAdapter):
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.")
raise exceptions.AccessDenied(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 = self.make_soup(data)

2
fanficfare/adapters/adapter_harrypotterfanfictioncom.py
View file

@ -86,7 +86,7 @@ class HarryPotterFanFictionComSiteAdapter(BaseSiteAdapter):
raise e
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.")
raise exceptions.AccessDenied(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 = self.make_soup(data)

2
fanficfare/adapters/adapter_hlfictionnet.py
View file

@ -90,7 +90,7 @@ class HLFictionNetAdapter(BaseSiteAdapter):
raise e
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.")
raise exceptions.AccessDenied(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 = self.make_soup(data)

2
fanficfare/adapters/adapter_hpfanficarchivecom.py
View file

@ -91,7 +91,7 @@ class HPFanficArchiveComAdapter(BaseSiteAdapter):
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.")
raise exceptions.AccessDenied(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 = self.make_soup(data)

2
fanficfare/adapters/adapter_iketernalnet.py
View file

@ -173,7 +173,7 @@ class IkEternalNetAdapter(BaseSiteAdapter):
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.")
raise exceptions.AccessDenied(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 = self.make_soup(data)

2
fanficfare/adapters/adapter_imagineeficcom.py
View file

@ -161,7 +161,7 @@ class ImagineEFicComAdapter(BaseSiteAdapter):
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.")
raise exceptions.AccessDenied(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 = self.make_soup(data)

2
fanficfare/adapters/adapter_ksarchivecom.py
View file

@ -148,7 +148,7 @@ class KSArchiveComAdapter(BaseSiteAdapter): # XXX
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.")
raise exceptions.AccessDenied(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 = self.make_soup(data)

2
fanficfare/adapters/adapter_lumossycophanthexcom.py
View file

@ -106,7 +106,7 @@ class LumosSycophantHexComAdapter(BaseSiteAdapter):
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.")
raise exceptions.AccessDenied(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 = self.make_soup(data)

2
fanficfare/adapters/adapter_merlinficdtwinscouk.py
View file

@ -161,7 +161,7 @@ class MerlinFicDtwinsCoUk(BaseSiteAdapter):
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.")
raise exceptions.AccessDenied(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 = self.make_soup(data)

2
fanficfare/adapters/adapter_midnightwhispersca.py
View file

@ -144,7 +144,7 @@ class MidnightwhispersCaAdapter(BaseSiteAdapter): # XXX
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.")
raise exceptions.AccessDenied(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 = self.make_soup(data)

2
fanficfare/adapters/adapter_mugglenetcom.py
View file

@ -184,7 +184,7 @@ class MuggleNetComAdapter(BaseSiteAdapter): # XXX
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.")
raise exceptions.AccessDenied(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 = self.make_soup(data)

2
fanficfare/adapters/adapter_nationallibrarynet.py
View file

@ -95,7 +95,7 @@ class NationalLibraryNetAdapter(BaseSiteAdapter):
raise e
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.")
raise exceptions.AccessDenied(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 = self.make_soup(data)

2
fanficfare/adapters/adapter_ncisficcom.py
View file

@ -94,7 +94,7 @@ class NCISFicComAdapter(BaseSiteAdapter):
raise e
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.")
raise exceptions.AccessDenied(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 = self.make_soup(data)

2
fanficfare/adapters/adapter_ncisfictionnet.py
View file

@ -100,7 +100,7 @@ class NCISFictionNetAdapter(BaseSiteAdapter):
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.")
raise exceptions.AccessDenied(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 = self.make_soup(data)

2
fanficfare/adapters/adapter_nfacommunitycom.py
View file

@ -148,7 +148,7 @@ class NfaCommunityComAdapter(BaseSiteAdapter): # XXX
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.")
raise exceptions.AccessDenied(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 = self.make_soup(data)

2
fanficfare/adapters/adapter_nickandgregnet.py
View file

@ -96,7 +96,7 @@ class NickAndGregNetAdapter(BaseSiteAdapter):
raise e
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.")
raise exceptions.AccessDenied(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 = self.make_soup(data)

2
fanficfare/adapters/adapter_occlumencysycophanthexcom.py
View file

@ -131,7 +131,7 @@ class OcclumencySycophantHexComAdapter(BaseSiteAdapter):
data = self._fetchUrl(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.")
raise exceptions.AccessDenied(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 = self.make_soup(data)

2
fanficfare/adapters/adapter_onedirectionfanfictioncom.py
View file

@ -150,7 +150,7 @@ class OneDirectionFanfictionComAdapter(BaseSiteAdapter):
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.")
raise exceptions.AccessDenied(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 = self.make_soup(data)

2
fanficfare/adapters/adapter_pommedesangcom.py
View file

@ -171,7 +171,7 @@ class PommeDeSangComAdapter(BaseSiteAdapter):
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.")
raise exceptions.AccessDenied(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 = self.make_soup(data)

2
fanficfare/adapters/adapter_ponyfictionarchivenet.py
View file

@ -127,7 +127,7 @@ class PonyFictionArchiveNetAdapter(BaseSiteAdapter):
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.")
raise exceptions.AccessDenied(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 = self.make_soup(data)

2
fanficfare/adapters/adapter_potionsandsnitches.py
View file

@ -77,7 +77,7 @@ class PotionsAndSnitchesOrgSiteAdapter(BaseSiteAdapter):
raise e
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.")
raise exceptions.AccessDenied(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 = self.make_soup(data)

2
fanficfare/adapters/adapter_potterheadsanonymouscom.py
View file

@ -170,7 +170,7 @@ class PotterHeadsAnonymousComAdapter(BaseSiteAdapter):
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.")
raise exceptions.AccessDenied(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 = self.make_soup(data)

2
fanficfare/adapters/adapter_pretendercentrecom.py
View file

@ -125,7 +125,7 @@ class PretenderCenterComAdapter(BaseSiteAdapter):
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.")
raise exceptions.AccessDenied(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 = self.make_soup(data)

2
fanficfare/adapters/adapter_psychficcom.py
View file

@ -121,7 +121,7 @@ class PsychFicComAdapter(BaseSiteAdapter):
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.")
raise exceptions.AccessDenied(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 = self.make_soup(data)

2
fanficfare/adapters/adapter_qafficcom.py
View file

@ -122,7 +122,7 @@ class QafFicComAdapter(BaseSiteAdapter):
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.")
raise exceptions.AccessDenied(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 = self.make_soup(data)

2
fanficfare/adapters/adapter_samandjacknet.py
View file

@ -198,7 +198,7 @@ class SamAndJackNetAdapter(BaseSiteAdapter): # XXX
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.")
raise exceptions.AccessDenied(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 = self.make_soup(data)

2
fanficfare/adapters/adapter_samdeanarchivenu.py
View file

@ -94,7 +94,7 @@ class SamDeanArchiveNuAdapter(BaseSiteAdapter):
raise e
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.")
raise exceptions.AccessDenied(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 = self.make_soup(data)

2
fanficfare/adapters/adapter_scarheadnet.py
View file

@ -170,7 +170,7 @@ class ScarHeadNetAdapter(BaseSiteAdapter):
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.")
raise exceptions.AccessDenied(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 = self.make_soup(data)

2
fanficfare/adapters/adapter_scarvesandcoffeenet.py
View file

@ -130,7 +130,7 @@ class ScarvesAndCoffeeNetAdapter(BaseSiteAdapter):
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.")
raise exceptions.AccessDenied(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 = self.make_soup(data)

2
fanficfare/adapters/adapter_sheppardweircom.py
View file

@ -169,7 +169,7 @@ class SheppardWeirComAdapter(BaseSiteAdapter): # XXX
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.")
raise exceptions.AccessDenied(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 = self.make_soup(data)

2
fanficfare/adapters/adapter_sinfuldesireorg.py
View file

@ -121,7 +121,7 @@ class SinfulDesireOrgAdapter(BaseSiteAdapter):
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.")
raise exceptions.AccessDenied(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 = self.make_soup(data)

2
fanficfare/adapters/adapter_storiesonlinenet.py
View file

@ -139,7 +139,7 @@ class StoriesOnlineNetAdapter(BaseSiteAdapter):
data = self._fetchUrl(url+":i",usecache=False)
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.")
raise exceptions.AccessDenied(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
elif "Error! The story you're trying to access is being filtered by your choice of contents filtering." in data:
raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Error! The story you're trying to access is being filtered by your choice of contents filtering.")

2
fanficfare/adapters/adapter_tenhawkpresentscom.py
View file

@ -134,7 +134,7 @@ class TenhawkPresentsComSiteAdapter(BaseSiteAdapter):
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.")
raise exceptions.AccessDenied(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 = self.make_soup(data)

2
fanficfare/adapters/adapter_thealphagatecom.py
View file

@ -90,7 +90,7 @@ class TheAlphaGateComAdapter(BaseSiteAdapter):
raise e
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.")
raise exceptions.AccessDenied(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 = self.make_soup(data)

2
fanficfare/adapters/adapter_themasquenet.py
View file

@ -168,7 +168,7 @@ class TheMasqueNetAdapter(BaseSiteAdapter):
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.")
raise exceptions.AccessDenied(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 = self.make_soup(data)

2
fanficfare/adapters/adapter_thepetulantpoetesscom.py
View file

@ -129,7 +129,7 @@ class ThePetulantPoetessComAdapter(BaseSiteAdapter):
data = self._fetchUrl(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.")
raise exceptions.AccessDenied(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 = self.make_soup(data)

2
fanficfare/adapters/adapter_tokrafandomnetcom.py
View file

@ -122,7 +122,7 @@ class TokraFandomnetComAdapter(BaseSiteAdapter):
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.")
raise exceptions.AccessDenied(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 = self.make_soup(data)

2
fanficfare/adapters/adapter_trekiverseorg.py
View file

@ -165,7 +165,7 @@ class TrekiverseOrgAdapter(BaseSiteAdapter):
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.")
raise exceptions.AccessDenied(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 = self.make_soup(data)

9
fanficfare/adapters/adapter_tthfanficorg.py
View file

@ -172,17 +172,22 @@ class TwistingTheHellmouthSiteAdapter(BaseSiteAdapter):
descurl=authorurl
authorsoup = self.make_soup(authordata)
# author can have several pages, scan until we find it.
while( not authorsoup.find('a', href=re.compile(r"^/Story-"+self.story.getMetadata('storyId')+'/')) ):
# find('a', href=re.compile(r"^/Story-"+self.story.getMetadata('storyId')+'/')) ):
logger.info("authsoup:%s"%authorsoup)
while( not authorsoup.find('div', {'id':'st'+self.story.getMetadata('storyId'), 'class':re.compile(r"storylistitem")}) ):
nextarrow = authorsoup.find('a', {'class':'arrowf'})
if not nextarrow:
## if rating is set lower than story, it won't be
## visible on author lists unless. The *story* is
## visible via the url, just not the entry on
## author list.
raise exceptions.AdultCheckRequired(self.url)
logger.info("Story Not Found on Author List--Assuming needs Adult.")
raise exceptions.FailedToDownload("Story Not Found on Author List--Assume needs Adult?")
# raise exceptions.AdultCheckRequired(self.url)
nextpage = 'http://'+self.host+nextarrow['href']
logger.debug("**AUTHOR** nextpage URL: "+nextpage)
authordata = self._fetchUrl(nextpage)
logger.info("authsoup:%s"%authorsoup)
descurl=nextpage
authorsoup = self.make_soup(authordata)
except urllib2.HTTPError, e:

2
fanficfare/adapters/adapter_twcslibrarynet.py
View file

@ -127,7 +127,7 @@ class TheWritersCoffeeShopComSiteAdapter(BaseSiteAdapter):
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.")
raise exceptions.AccessDenied(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
# problems with some stories, but only in calibre. I suspect
# issues with different SGML parsers in python. This is a

2
fanficfare/adapters/adapter_twilightarchivescom.py
View file

@ -90,7 +90,7 @@ class TwilightArchivesComAdapter(BaseSiteAdapter):
raise e
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.")
raise exceptions.AccessDenied(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 = self.make_soup(data)

2
fanficfare/adapters/adapter_twilightednet.py
View file

@ -118,7 +118,7 @@ class TwilightedNetSiteAdapter(BaseSiteAdapter):
data = self._fetchUrl(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.")
raise exceptions.AccessDenied(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
# problems with some stories, but only in calibre. I suspect
# issues with different SGML parsers in python. This is a

2
fanficfare/adapters/adapter_walkingtheplankorg.py
View file

@ -106,7 +106,7 @@ class WalkingThePlankOrgAdapter(BaseSiteAdapter):
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.")
raise exceptions.AccessDenied(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 = self.make_soup(data)

2
fanficfare/adapters/adapter_wolverineandroguecom.py
View file

@ -90,7 +90,7 @@ class WolverineAndRogueComAdapter(BaseSiteAdapter):
raise e
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.")
raise exceptions.AccessDenied(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 = self.make_soup(data)

2
fanficfare/adapters/adapter_wraithbaitcom.py
View file

@ -102,7 +102,7 @@ class WraithBaitComAdapter(BaseSiteAdapter):
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.")
raise exceptions.AccessDenied(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 = self.make_soup(data)

345
fanficfare/adapters/base_xenforoforum_adapter.py-new Normal file
View file

@ -0,0 +1,345 @@
# -*- coding: utf-8 -*-
# Copyright 2015 FanFicFare 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 traceback
logger = logging.getLogger(__name__)
import re
import urllib2
from ..htmlcleanup import stripHTML
from .. import exceptions as exceptions
from base_adapter import BaseSiteAdapter, makeDate
logger = logging.getLogger(__name__)
class BaseXenForoForumAdapter(BaseSiteAdapter):
def __init__(self, config, url):
#logger.info("init url: "+url)
BaseSiteAdapter.__init__(self, config, url)
self.decode = ["utf8",
"Windows-1252"] # 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.
# get storyId from url--url validation guarantees query is only sid=1234
self.story.setMetadata('storyId',self.parsedUrl.path.split('/',)[2])
# get storyId from url--url validation guarantees query correct
m = re.match(self.getSiteURLPattern(),url)
if m:
#logger.debug("groupdict:%s"%m.groupdict())
if m.group('post'):
self.story.setMetadata('storyId',m.group('post'))
self._setURL(self.getURLPrefix() + '/posts/'+m.group('post')+'/')
else:
self.story.setMetadata('storyId',m.group('id'))
# normalized story URL.
self._setURL(self.getURLPrefix() + '/'+m.group('tp')+'/'+self.story.getMetadata('storyId')+'/')
else:
raise exceptions.InvalidStoryURL(url,
self.getSiteDomain(),
self.getSiteExampleURLs())
# Each adapter needs to have a unique site abbreviation.
self.story.setMetadata('siteabbrev','fsb')
# The date format will vary from site to site.
# http://docs.python.org/library/datetime.html#strftime-strptime-behavior
self.dateformat = "%b %d, %Y at %I:%M %p"
@classmethod
def getConfigSections(cls):
"Only needs to be overriden if has additional ini sections."
return ['base_xenforoforum',cls.getConfigSection()]
@classmethod
def getURLPrefix(cls):
# The site domain. Does have www here, if it uses it.
return 'https://' + cls.getSiteDomain()
@classmethod
def getSiteExampleURLs(cls):
return cls.getURLPrefix()+"/threads/some-story-name.123456/ "+cls.getURLPrefix()+"/posts/123456/"
def getSiteURLPattern(self):
return r"https?://"+re.escape(self.getSiteDomain())+r"/(?P<tp>threads|posts)/(.+\.)?(?P<id>\d+)/?[^#]*?(#post-(?P<post>\d+))?$"
def use_pagecache(self):
'''
adapters that will work with the page cache need to implement
this and change it to True.
'''
return True
def performLogin(self):
params = {}
if self.password:
params['login'] = self.username
params['password'] = self.password
else:
params['login'] = self.getConfig("username")
params['password'] = self.getConfig("password")
params['register'] = '0'
params['cookie_check'] = '1'
params['_xfToken'] = ''
params['redirect'] = 'https://' + self.getSiteDomain() + '/'
if not params['password']:
return
## https://forum.questionablequesting.com/login/login
loginUrl = 'https://' + self.getSiteDomain() + '/login/login'
logger.debug("Will now login to URL (%s) as (%s)" % (loginUrl,
params['login']))
# soup = self.make_soup(self._fetchUrl(loginUrl))
# params['ctkn']=soup.find('input', {'name':'ctkn'})['value']
# params[soup.find('input', {'id':'password'})['name']] = params['password']
d = self._fetchUrl(loginUrl, params)
if "Log Out" not in d :
logger.info("Failed to login to URL %s as %s" % (loginUrl,
params['login']))
raise exceptions.FailedToLogin(self.url,params['login'])
return False
else:
return True
## Getting the chapter list and the meta data, plus 'is adult' checking.
def extractChapterUrlsAndMetadata(self):
useurl = self.url
logger.info("url: "+useurl)
try:
(data,opened) = self._fetchUrlOpened(useurl)
useurl = opened.geturl()
logger.info("use useurl: "+useurl)
except urllib2.HTTPError, e:
if e.code == 404:
raise exceptions.StoryDoesNotExist(self.url)
elif e.code == 403:
self.performLogin()
(data,opened) = self._fetchUrlOpened(useurl)
useurl = opened.geturl()
logger.info("use useurl: "+useurl)
else:
raise
# use BeautifulSoup HTML parser to make everything easier to find.
soup = self.make_soup(data)
a = soup.find('h3',{'class':'userText'}).find('a')
self.story.addToList('authorId',a['href'].split('/')[1])
self.story.addToList('authorUrl',self.getURLPrefix()+'/'+a['href'])
self.story.addToList('author',a.text)
h1 = soup.find('div',{'class':'titleBar'}).h1
self.story.setMetadata('title',stripHTML(h1))
if '#' in useurl:
anchorid = useurl.split('#')[1]
soup = soup.find('li',id=anchorid)
else:
# try threadmarks if no '#' in url
# Use a post specific URL to get first post without using threadmarks.
threadmarksa = soup.find('a',{'class':'threadmarksTrigger'})
if threadmarksa:
soupmarks = self.make_soup(self._fetchUrl(self.getURLPrefix()+'/'+threadmarksa['href']))
markas = []
ol = soupmarks.find('ol',{'class':'overlayScroll'})
if ol:
markas = ol.find_all('a')
else:
## SV changed their threadmarks. Not isolated to
## SV only incase SB or QQ make the same change.
markas = soupmarks.find('div',{'class':'threadmarks'}).find_all('a',{'class':'PreviewTooltip'})
if markas:
self.chapterUrls.append(("First Post",useurl))
for (atag,url,name) in [ (x,x['href'],stripHTML(x)) for x in markas ]:
date = self.make_date(atag.find_next_sibling('div',{'class':'extra'}))
if not self.story.getMetadataRaw('datePublished') or date < self.story.getMetadataRaw('datePublished'):
self.story.setMetadata('datePublished', date)
if not self.story.getMetadataRaw('dateUpdated') or date > self.story.getMetadataRaw('dateUpdated'):
self.story.setMetadata('dateUpdated', date)
self.chapterUrls.append((name,self.getURLPrefix()+'/'+url))
# https://forums.spacebattles.com/threads/aberration-worm-d-d.369992/
if re.match(rr"https?://"+re.escape(self.getSiteDomain())+r"/(?P<tp>threads|posts)/(.+\.)?(?P<id>\d+)/?[^#]*?$",url)
m = re.match(,url)
if url == useurl and 'First Post' == self.chapterUrls[0][0]:
# remove "First Post" if included in list.
logger.debug("delete dup 'First Post' chapter: %s %s"%self.chapterUrls[0])
del self.chapterUrls[0]
## only use tags if threadmarks for chapters.
## a bit arbitrary, but likely.
for tag in soup.findAll('a',{'class':'tag'}):
tstr = stripHTML(tag)
if self.getConfig('capitalize_forumtags'):
tstr = tstr.title()
self.story.addToList('forumtags',tstr)
soup = soup.find('li',{'class':'message'}) # limit first post for date stuff below. ('#' posts above)
# Now go hunting for the 'chapter list'.
bq = soup.find('blockquote') # assume first posting contains TOC urls.
bq.name='div'
for iframe in bq.find_all('iframe'):
iframe.extract() # calibre book reader & editor don't like iframes to youtube.
for qdiv in bq.find_all('div',{'class':'quoteExpand'}):
qdiv.extract() # Remove <div class="quoteExpand">click to expand</div>
self.setDescription(useurl,bq)
# otherwise, use first post links--include first post since
# that's often also the first chapter.
if not self.chapterUrls:
self.chapterUrls.append(("First Post",useurl))
for (url,name) in [ (x['href'],stripHTML(x)) for x in bq.find_all('a') ]:
#logger.debug("found chapurl:%s"%url)
if not url.startswith('http'):
url = self.getURLPrefix()+'/'+url
if ( url.startswith(self.getURLPrefix()) or
url.startswith('http://'+self.getSiteDomain()) or
url.startswith('https://'+self.getSiteDomain()) ) and ('/posts/' in url or '/threads/' in url):
# brute force way to deal with SB's http->https change when hardcoded http urls.
url = url.replace('http://'+self.getSiteDomain(),self.getURLPrefix())
url = re.sub(r'(^[\'"]+|[\'"]+$)','',url) # strip leading or trailing '" from incorrect quoting.
url = re.sub(r'like$','',url) # strip 'like' if incorrect 'like' link instead of proper post URL.
logger.debug("(ch:%s)used chapurl:%s"%(len(self.chapterUrls)+1,url))
self.chapterUrls.append((name,url))
if url == useurl and 'First Post' == self.chapterUrls[0][0]:
# remove "First Post" if included in list.
logger.debug("delete dup 'First Post' chapter: %s %s"%self.chapterUrls[0])
del self.chapterUrls[0]
# Didn't use threadmarks, so take created/updated dates
# from the 'first' posting created and updated.
date = self.make_date(soup.find('a',{'class':'datePermalink'}))
if date:
self.story.setMetadata('datePublished', date)
self.story.setMetadata('dateUpdated', date) # updated overwritten below if found.
date = self.make_date(soup.find('div',{'class':'editDate'}))
if date:
self.story.setMetadata('dateUpdated', date)
self.story.setMetadata('numChapters',len(self.chapterUrls))
def make_date(self,parenttag): # forums use a BS thing where dates
# can appear different if recent.
datestr=None
try:
datetag = parenttag.find('span',{'class':'DateTime'})
if datetag:
datestr = datetag['title']
else:
datetag = parenttag.find('abbr',{'class':'DateTime'})
if datetag:
datestr="%s at %s"%(datetag['data-datestring'],datetag['data-timestring'])
# Apr 24, 2015 at 4:39 AM
# May 1, 2015 at 5:47 AM
datestr = re.sub(r' (\d[^\d])',r' 0\1',datestr) # add leading 0 for single digit day & hours.
return makeDate(datestr, self.dateformat)
except:
logger.debug('No date found in %s'%parenttag)
return None
# grab the text for an individual chapter.
def getChapterText(self, url):
logger.debug('Getting chapter text from: %s' % url)
## there's some history of stories with links to the wrong
## page. This changes page#post URLs to perma-link URLs.
## Which will be redirected back to page#posts, but the
## *correct* ones.
# http://forums.sufficientvelocity.com/threads/harry-potter-and-the-not-fatal-at-all-cultural-exchange-program.330/page-4#post-39915
# https://forums.sufficientvelocity.com/posts/39915/
if '#post-' in url:
url = self.getURLPrefix()+'/posts/'+url.split('#post-')[1]+'/'
## Same as above except for for case where author mistakenly
## used the reply link instead of normal link to post.
# "http://forums.spacebattles.com/threads/manager-worm-story-thread-iv.301602/reply?quote=15962513"
# https://forums.spacebattles.com/posts/
if 'reply?quote=' in url:
url = self.getURLPrefix()+'/posts/'+url.split('reply?quote=')[1]+'/'
try:
origurl = url
(data,opened) = self._fetchUrlOpened(url)
url = opened.geturl()
if '#' in origurl and '#' not in url:
url = url + origurl[origurl.index('#'):]
logger.debug("chapter URL redirected to: %s"%url)
soup = self.make_soup(data)
if '#' in url:
anchorid = url.split('#')[1]
soup = soup.find('li',id=anchorid)
bq = soup.find('blockquote')
bq.name='div'
for iframe in bq.find_all('iframe'):
iframe.extract() # calibre book reader & editor don't like iframes to youtube.
for qdiv in bq.find_all('div',{'class':'quoteExpand'}):
qdiv.extract() # Remove <div class="quoteExpand">click to expand</div>
except Exception as e:
if self.getConfig('continue_on_chapter_error'):
bq = self.make_soup("""<div>
<p><b>Error</b></p>
<p>FanFicFare failed to download this chapter. Because you have
<b>continue_on_chapter_error</b> set to <b>true</b> in your personal.ini, the download continued.</p>
<p>Chapter URL:<br>%s</p>
<p>Error:<br><pre>%s</pre></p>
</div>"""%(url,traceback.format_exc()))
else:
raise
# XenForo uses <base href="https://forums.spacebattles.com/" />
return self.utf8FromSoup(self.getURLPrefix()+'/',bq)
def normalize_forum_url(url):
'''
Take URLs of form:
https://forums.spacebattles.com/threads/heredity-ii-worm-au.311819/page-72#post-20211500
"/threads/some-story-name.123456/ "+cls.getURLPrefix()+"/posts/123456/"
'''

8
fanficfare/cli.py
View file

@ -365,12 +365,14 @@ def do_download(arg,
del adapter
except exceptions.InvalidStoryURL, isu:
except exceptions.InvalidStoryURL as isu:
print isu
except exceptions.StoryDoesNotExist, dne:
except exceptions.StoryDoesNotExist as dne:
print dne
except exceptions.UnknownSite, us:
except exceptions.UnknownSite as us:
print us
except exceptions.AccessDenied as ad:
print ad
if __name__ == '__main__':

7
fanficfare/exceptions.py
View file

@ -24,6 +24,13 @@ class FailedToDownload(Exception):
def __str__(self):
return self.error
class AccessDenied(Exception):
def __init__(self,error):
self.error=error
def __str__(self):
return self.error
class RejectImage(Exception):
def __init__(self,error):
self.error=error