Compare commits

...
Author SHA1 Message Date
Jim Miller e4e5e4a47a Bump versions, update index.html. 2013-03-25 12:57:24 -05:00
Jim Miller 8632cfdbd6 Improvements to Reject URL list feature, fix PrefsViewer, cleanup dialogs.py. 2013-03-21 12:24:59 -05:00
Jim Miller c943ce7fce Set seriesHTML to series w/o link when no seriesUrl. 2013-03-21 10:56:03 -05:00
Jim Miller 7ccddd5a07 Check for existing Series Anthology books (by seriesUrl) on story add/update. PI 2013-03-20 10:49:43 -05:00
Jim Miller 3678bf6bf1 Add user/pass for dokuga.com. 2013-03-19 22:03:35 -05:00
Jim Miller 33bb1b2d29 Add user/pass for dokuga.com. 2013-03-19 21:58:11 -05:00
Jim Miller 3141191e43 Add user/pass for dokuga.com. 2013-03-19 21:57:52 -05:00
Jim Miller 536ea0b027 Only populate seriesHTML when series is set. 2013-03-19 19:56:25 -05:00
Jim Miller 34e03bf4eb Add seriesUrl (and generated seriesHTML) as valid metadata entries. 2013-03-19 14:22:07 -05:00
Jim Miller 48c81b1d1e Add seriesUrl (and generated seriesHTML) as valid metadata entries. 2013-03-19 14:21:14 -05:00
Jim Miller 381d3031e6 Fix default focus after hide/show. 2013-03-18 23:03:47 -05:00
Jim Miller a193e80f88 Fix drag and drop after hide/show. 2013-03-18 17:55:48 -05:00
Jim Miller 3410e20412 Restructure to make Add from URLs and Create Anthology for URLs modeless. 2013-03-18 17:31:37 -05:00
Jim Miller 7f568d54bf Added tag FanFictionDownLoader-4.4.47 for changeset ed6d76edf815 2013-03-18 11:36:28 -05:00
Jim Miller 619141ef94 Added tag calibre-plugin-1.7.14 for changeset ed6d76edf815 2013-03-18 11:36:00 -05:00
Jim Miller e6128b3174 Bump versions, add more test cases to test1.com adapter. 2013-03-18 11:31:31 -05:00
Jim Miller 875e139bcd Fixes for fimfiction.net changes. 2013-03-16 19:41:15 -05:00
Jim Miller db97d126bf Don't strip HTML entities during recursion--confuses replace_metadata. 2013-03-15 23:37:21 -05:00
Jim Miller 92597efce6 PI: Strip ',' from metadata set to int/float col by custom_columns_settings.
For favs, reviews, etc from site specific metadata.
2013-03-15 23:36:33 -05:00
Jim Miller 6b9cb35761 Added tag calibre-plugin-1.7.13 for changeset 4607b1addf58 2013-03-15 16:20:04 -05:00
Jim Miller 6630e6bb9c Bump version, don't use calibre specific OptionParser for plugin CLI. 2013-03-15 16:19:10 -05:00
Jim Miller c26bca0f6d PI only - Drag and drop emails from Thunderbird on FFDL URL box to add URLs. 2013-03-14 21:31:37 -05:00
Jim Miller 8cd3663d82 Add *plugin* CLI via calibre's cli_main feature. --PI only. (list continues)
Add "marked:ffdl_success/failed" to added/updated/failed books. --PI only.
Add "Show added/updated" pref using above. --PI only.
Preserve log page in epub across overwrites as well as updates. --PI only.
Add "add_to_" feature to ini config.  Allow higher priority sections to *add* to
 any ini param rather than replace it.
2013-03-14 17:16:26 -05:00
Jim Miller fdb45183c7 Remove BBCode, not used by adapter_fimfictionnet anymore. 2013-03-12 16:34:43 -05:00
Jim Miller 284ef7578e Remove BBCode, not used by adapter_fimfictionnet anymore. 2013-03-12 16:33:38 -05:00
Jim Miller 6589dcd4b6 Added tag FanFictionDownLoader-4.4.46 for changeset de548d8c0ba6 2013-03-04 12:02:58 -06:00
Jim Miller 81a75d2097 Added tag calibre-plugin-1.7.12 for changeset de548d8c0ba6 2013-03-04 12:02:45 -06:00
Jim Miller df09eadf81 Fix login failure for tth, add anthology=true metadata, bump version. 2013-03-04 12:02:32 -06:00
Jim Miller abde9fdf8d Page scrape story descriptions again for fimfiction.net due to API issues. 2013-03-02 15:46:47 -06:00
Jim Miller b76e50719b Use existing anthology title on update, even when a series. 2013-03-01 10:57:42 -06:00
Jim Miller 053b629d4b Added tag FanFictionDownLoader-4.4.45 for changeset 41ec08c9f675 2013-02-27 13:47:11 -06:00
Jim Miller 60a2e22c93 Moved tag calibre-plugin-1.7.11 to changeset 41ec08c9f675 (from changeset 436fc385166c) 2013-02-27 13:47:02 -06:00
Jim Miller c6127b2087 Bump versions. 2013-02-27 13:46:48 -06:00
Jim Miller e53661bb06 Added tag calibre-plugin-1.7.11 for changeset 436fc385166c 2013-02-27 13:44:48 -06:00
Jim Miller bb86f55c4a www.ficwad.com -> ficwad.com. Ficwad changed their canonical domain. 2013-02-27 13:44:34 -06:00
Jim Miller e2e086f2e5 Added tag FanFictionDownLoader-4.4.44 for changeset ee7ad490f080 2013-02-19 18:39:02 -06:00
Jim Miller 101e3d9866 Added tag calibre-plugin-1.7.10 for changeset ee7ad490f080 2013-02-19 18:38:49 -06:00
Jim Miller 6c9cfa49f8 Source URL inside anthologies, tweaks, bump versions. 2013-02-19 18:38:35 -06:00
Jim Miller 2db927665a First version with Anthology feature in Plugin. 2013-02-15 17:50:12 -06:00
Jim Miller cd8f5f2769 Some refactoring of plugin code. Mostly renaming, but some optimization, too. 2013-02-13 16:54:26 -06:00
Jim Miller 020e588527 Added tag FanFictionDownLoader-4.4.43 for changeset 2d1bca833812 2013-02-08 11:06:50 -06:00
Jim Miller 5a63bdff8f Added tag calibre-plugin-1.7.09 for changeset 2d1bca833812 2013-02-08 11:06:32 -06:00
Jim Miller f742e581c9 Include author notes in chapters on fimfiction.net. 2013-02-08 11:05:59 -06:00
88 changed files with 1703 additions and 2223 deletions
+1 -1
View File
@@ -1,6 +1,6 @@
# ffd-retief-hrd fanfictiondownloader
application: fanfictiondownloader
version: 4-4-43
version: 4-4-48
runtime: python27
api_version: 1
threadsafe: true
+27 -9
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, 9)
version = (1, 7, 15)
minimum_calibre_version = (0, 8, 57)
#: This field defines the GUI plugin class that contains all the code
@@ -80,11 +80,29 @@ class FanFictionDownLoaderBase(InterfaceActionBase):
if ac is not None:
ac.apply_settings()
# For testing, run from command line with this:
# calibre-debug -e __init__.py
#
if __name__ == '__main__':
from PyQt4.Qt import QApplication
from calibre.gui2.preferences import test_widget
app = QApplication([])
test_widget('Advanced', 'Plugins')
def cli_main(self,argv):
# I believe there's no performance hit loading these here when
# CLI--it would load everytime anyway.
from StringIO import StringIO
from calibre.library import db
from calibre_plugins.fanfictiondownloader_plugin.downloader import main as ffdl_main
from calibre_plugins.fanfictiondownloader_plugin.prefs import PrefsFacade
from calibre.utils.config import prefs as calibre_prefs
from optparse import OptionParser
parser = OptionParser('%prog --run-plugin '+self.name+' -- [options] <storyurl>')
parser.add_option('--library-path', '--with-library', default=None, help=_('Path to the calibre library. Default is to use the path stored in the settings.'))
# parser.add_option('--dont-notify-gui', default=False, action='store_true',
# help=_('Do not notify the running calibre GUI (if any) that the database has'
# ' changed. Use with care, as it can lead to database corruption!'))
pargs = [x for x in argv if x.startswith('--with-library') or x.startswith('--library-path')
or not x.startswith('-')]
opts, args = parser.parse_args(pargs)
ffdl_prefs = PrefsFacade(db(path=opts.library_path,
read_only=True))
ffdl_main(argv[1:],
parser=parser,
passed_defaultsini=StringIO(get_resources("defaults.ini")),
passed_personalini=StringIO(ffdl_prefs["personal.ini"]))
+1 -1
View File
@@ -4,7 +4,7 @@
'<a href="http://www.mobileread.com/forums/showthread.php?t=134856">Reading List</a>',
'<a href="http://www.mobileread.com/forums/showthread.php?t=126727">Extract ISBN</a>' and
'<a href="http://www.mobileread.com/forums/showthread.php?t=134000">Count Pages</a>'
plugins. bbcodeutils code contributed by Pau Sanchez.</p>
plugins.</p>
<p>
Calibre officially distributes plugins from the mobileread.com forum site.
+57 -165
View File
@@ -15,160 +15,38 @@ from PyQt4.Qt import (QDialog, QWidget, QVBoxLayout, QHBoxLayout, QLabel,
QCheckBox, QPushButton, QTabWidget, QVariant, QScrollArea,
QDialogButtonBox )
from calibre.gui2 import dynamic, info_dialog
from calibre.utils.config import JSONConfig
from calibre.gui2.ui import get_gui
from calibre_plugins.fanfictiondownloader_plugin.prefs import prefs, PREFS_NAMESPACE
from calibre_plugins.fanfictiondownloader_plugin.dialogs \
import (UPDATE, UPDATEALWAYS, OVERWRITE, collision_order, RejectListDialog,
EditTextDialog)
EditTextDialog, RejectUrlEntry)
from calibre_plugins.fanfictiondownloader_plugin.fanficdownloader.adapters \
import (getConfigSections, getNormalStoryURL)
from calibre_plugins.fanfictiondownloader_plugin.common_utils \
import ( get_library_uuid, KeyboardConfigDialog, PrefsViewerDialog )
import ( KeyboardConfigDialog, PrefsViewerDialog )
from calibre.gui2.complete import MultiCompleteLineEdit
PREFS_NAMESPACE = 'FanFictionDownLoaderPlugin'
PREFS_KEY_SETTINGS = 'settings'
# Set defaults used by all. Library specific settings continue to
# take from here.
default_prefs = {}
default_prefs['personal.ini'] = get_resources('plugin-example.ini')
default_prefs['rejecturls'] = ''
default_prefs['rejectreasons'] = '''Sucked
Boring
Dup from another site'''
default_prefs['updatemeta'] = True
default_prefs['updatecover'] = False
default_prefs['updateepubcover'] = False
default_prefs['keeptags'] = False
default_prefs['urlsfromclip'] = True
default_prefs['updatedefault'] = True
default_prefs['fileform'] = 'epub'
default_prefs['collision'] = OVERWRITE
default_prefs['deleteotherforms'] = False
default_prefs['adddialogstaysontop'] = False
default_prefs['includeimages'] = False
default_prefs['lookforurlinhtml'] = False
default_prefs['injectseries'] = False
default_prefs['send_lists'] = ''
default_prefs['read_lists'] = ''
default_prefs['addtolists'] = False
default_prefs['addtoreadlists'] = False
default_prefs['addtolistsonread'] = False
default_prefs['gcnewonly'] = False
default_prefs['gc_site_settings'] = {}
default_prefs['allow_gc_from_ini'] = True
default_prefs['countpagesstats'] = []
default_prefs['errorcol'] = ''
default_prefs['custom_cols'] = {}
default_prefs['custom_cols_newonly'] = {}
default_prefs['allow_custcol_from_ini'] = True
default_prefs['std_cols_newonly'] = {}
def set_library_config(library_config):
get_gui().current_db.prefs.set_namespaced(PREFS_NAMESPACE,
PREFS_KEY_SETTINGS,
library_config)
def get_library_config():
db = get_gui().current_db
library_id = get_library_uuid(db)
library_config = None
# Check whether this is a configuration needing to be migrated
# from json into database. If so: get it, set it, rename it in json.
if library_id in old_prefs:
#print("get prefs from old_prefs")
library_config = old_prefs[library_id]
set_library_config(library_config)
old_prefs["migrated to library db %s"%library_id] = old_prefs[library_id]
del old_prefs[library_id]
if library_config is None:
#print("get prefs from db")
library_config = db.prefs.get_namespaced(PREFS_NAMESPACE, PREFS_KEY_SETTINGS,
copy.deepcopy(default_prefs))
return library_config
# This is where all preferences for this plugin *were* stored
# Remember that this name (i.e. plugins/fanfictiondownloader_plugin) is also
# in a global namespace, so make it as unique as possible.
# You should always prefix your config file name with plugins/,
# so as to ensure you dont accidentally clobber a calibre config file
old_prefs = JSONConfig('plugins/fanfictiondownloader_plugin')
# fake out so I don't have to change the prefs calls anywhere. The
# Java programmer in me is offended by op-overloading, but it's very
# tidy.
class PrefsFacade():
def __init__(self,default_prefs):
self.default_prefs = default_prefs
self.libraryid = None
self.current_prefs = None
def _get_prefs(self):
libraryid = get_library_uuid(get_gui().current_db)
if self.current_prefs == None or self.libraryid != libraryid:
#print("self.current_prefs == None(%s) or self.libraryid != libraryid(%s)"%(self.current_prefs == None,self.libraryid != libraryid))
self.libraryid = libraryid
self.current_prefs = get_library_config()
return self.current_prefs
def __getitem__(self,k):
prefs = self._get_prefs()
if k not in prefs:
# pulls from default_prefs.defaults automatically if not set
# in default_prefs
return self.default_prefs[k]
return prefs[k]
def __setitem__(self,k,v):
prefs = self._get_prefs()
prefs[k]=v
# self._save_prefs(prefs)
def __delitem__(self,k):
prefs = self._get_prefs()
if k in prefs:
del prefs[k]
def save_to_db(self):
set_library_config(self._get_prefs())
prefs = PrefsFacade(default_prefs)
class RejectURLList:
def __init__(self,prefs):
self.prefs = prefs
self.sync_lock = threading.RLock()
self.listcache = None
def _read_list_from_text(self,text,addreasontext=None):
cache = {}
def _read_list_from_text(self,text,addreasontext=''):
cache = OrderedDict()
#print("_read_list_from_text")
for line in text.splitlines():
if ',' in line:
(rejurl,note) = line.split(',',1)
else:
(rejurl,note) = (line,'')
rejurl = getNormalStoryURL(rejurl)
if rejurl:
if addreasontext and note:
note = note +" - "+addreasontext
elif addreasontext:
note = addreasontext
cache[rejurl] = note
return cache
rue = RejectUrlEntry(line,addreasontext=addreasontext,fromline=True)
#print("rue.url:%s"%rue.url)
if rue.valid:
cache[rue.url] = rue
return cache
def _get_listcache(self):
if self.listcache == None:
@@ -176,26 +54,35 @@ class RejectURLList:
return self.listcache
def _save_list(self,listcache):
rejectlist = []
for url in listcache:
rejectlist.append("%s,%s"%(url,listcache[url]))
self.prefs['rejecturls'] = '\n'.join(rejectlist)
#print("_save_list")
self.prefs['rejecturls'] = '\n'.join([x.to_line() for x in listcache.values()])
self.prefs.save_to_db()
self.listcache = None
def clear_cache(self):
self.listcache = None
# true if url is in list.
def check(self,url):
with self.sync_lock:
listcache = self._get_listcache()
return url in listcache
def get_note(self,url):
with self.sync_lock:
listcache = self._get_listcache()
if url in listcache:
note = listcache[url]
return note
return listcache[url].note
# not found
return None
return ''
def get_full_note(self,url):
with self.sync_lock:
listcache = self._get_listcache()
if url in listcache:
return listcache[url].fullnote()
# not found
return ''
def remove(self,url):
with self.sync_lock:
@@ -205,27 +92,26 @@ class RejectURLList:
self._save_list(listcache)
def add_text(self,rejecttext,addreasontext):
self.add(self._read_list_from_text(rejecttext,addreasontext).items())
self.add(self._read_list_from_text(rejecttext,addreasontext).values())
def add(self,rejectlist,clear=False):
# rejectlist=list of (url,note) tuples.
with self.sync_lock:
if clear:
listcache={}
listcache=OrderedDict()
else:
listcache = self._get_listcache()
for (url,note) in rejectlist:
listcache[url]=note
for l in rejectlist:
listcache[l.url]=l
self._save_list(listcache)
def get_list(self):
return copy.deepcopy(self._get_listcache())
return self._get_listcache().values()
def get_reject_reasons(self):
return self.prefs['rejectreasons'].splitlines()
rejecturllist = RejectURLList(prefs)
class ConfigWidget(QWidget):
def __init__(self, plugin_action):
@@ -282,12 +168,14 @@ class ConfigWidget(QWidget):
prefs['updatecover'] = self.basic_tab.updatecover.isChecked()
prefs['updateepubcover'] = self.basic_tab.updateepubcover.isChecked()
prefs['keeptags'] = self.basic_tab.keeptags.isChecked()
prefs['showmarked'] = self.basic_tab.showmarked.isChecked()
prefs['urlsfromclip'] = self.basic_tab.urlsfromclip.isChecked()
prefs['updatedefault'] = self.basic_tab.updatedefault.isChecked()
prefs['deleteotherforms'] = self.basic_tab.deleteotherforms.isChecked()
prefs['adddialogstaysontop'] = self.basic_tab.adddialogstaysontop.isChecked()
prefs['includeimages'] = self.basic_tab.includeimages.isChecked()
prefs['lookforurlinhtml'] = self.basic_tab.lookforurlinhtml.isChecked()
prefs['checkforseriesurlid'] = self.basic_tab.checkforseriesurlid.isChecked()
prefs['injectseries'] = self.basic_tab.injectseries.isChecked()
if self.readinglist_tab:
@@ -448,6 +336,13 @@ class BasicTab(QWidget):
self.l.addSpacing(10)
self.showmarked = QCheckBox("Show added/updated books when finished?",self)
self.showmarked.setToolTip("Show added/updated books only when finished.\nYou can also manually search for 'marked:ffdl_success'.\n'marked:ffdl_failed' is also available, or search 'marked:ffdl' for both.")
self.showmarked.setChecked(prefs['showmarked'])
self.l.addWidget(self.showmarked)
self.l.addSpacing(10)
self.urlsfromclip = QCheckBox('Take URLs from Clipboard?',self)
self.urlsfromclip.setToolTip('Prefill URLs from valid URLs in Clipboard when Adding New.')
self.urlsfromclip.setChecked(prefs['urlsfromclip'])
@@ -477,6 +372,11 @@ class BasicTab(QWidget):
self.lookforurlinhtml.setChecked(prefs['lookforurlinhtml'])
self.l.addWidget(self.lookforurlinhtml)
self.checkforseriesurlid = QCheckBox("Check for existing Series Anthology books?",self)
self.checkforseriesurlid.setToolTip("Check for existings Series Anthology books using each new story's series URL before downloading.\nOffer to skip downloading if a Series Anthology is found.")
self.checkforseriesurlid.setChecked(prefs['checkforseriesurlid'])
self.l.addWidget(self.checkforseriesurlid)
self.injectseries = QCheckBox("Inject calibre Series when none found?",self)
self.injectseries.setToolTip("If no series is found, inject the calibre series (if there is one) so it appears on the FFDL title page(not cover).")
self.injectseries.setChecked(prefs['injectseries'])
@@ -520,12 +420,8 @@ class BasicTab(QWidget):
ShowDefaultsIniDialog(self.windowIcon(),text,self).exec_()
def show_rejectlist(self):
rejectlist = []
for (url,note) in rejecturllist.get_list().items():
rejectlist.append((None,url,note,note))
d = RejectListDialog(self,
rejectlist,
rejecturllist.get_list(),
rejectreasons=rejecturllist.get_reject_reasons(),
header="Edit Reject URLs List",
show_delete=False,
@@ -535,11 +431,7 @@ class BasicTab(QWidget):
if d.result() != d.Accepted:
return
rejectlist=[]
for (bookid,url,note) in d.get_reject_list():
rejectlist.append((url,note))
rejecturllist.add(rejectlist,clear=True)
rejecturllist.add(d.get_reject_list(),clear=True)
def show_reject_reasons(self):
d = EditTextDialog(self,
@@ -554,11 +446,11 @@ class BasicTab(QWidget):
def add_reject_urls(self):
d = EditTextDialog(self,
"http://example.com?story.php?sid=5,Reason why I rejected it",
"http://example.com/story.php?sid=5,Reason why I rejected it\nhttp://example.com/story.php?sid=6,Title by Author - Reason why I rejected it",
icon=self.windowIcon(),
title="Add Reject URLs",
label="Add Reject URLs. Use: <b>http://...,note</b><br>Invalid story URLs will be ignored.",
tooltip="One URL per line, everything after <b>,</b> will be put in the note.",
label="Add Reject URLs. Use: <b>http://...,note</b> or <b>http://...,title by author - note</b><br>Invalid story URLs will be ignored.",
tooltip="One URL per line:\n<b>http://...,note</b>\n<b>http://...,title by author - note</b>",
rejectreasons=rejecturllist.get_reject_reasons(),
reasonslabel='Add this reason to all URLs added:')
d.exec_()
@@ -911,7 +803,7 @@ titleLabels = {
'ships':'Relationships',
'datePublished':'Published',
'dateUpdated':'Updated',
'dateCreated':'Packaged',
'dateCreated':'Created',
'rating':'Rating',
'warnings':'Warnings',
'numChapters':'Chapters',
@@ -922,7 +814,7 @@ titleLabels = {
'extratags':'Extra Tags',
'title':'Title',
'storyUrl':'Story URL',
'description':'Summary',
'description':'Description',
'author':'Author',
'authorUrl':'Author URL',
'formatname':'File Format',
+288 -310
View File
@@ -7,36 +7,35 @@ __license__ = 'GPL v3'
__copyright__ = '2011, Jim Miller'
__docformat__ = 'restructuredtext en'
import traceback
import traceback, re
from functools import partial
import urllib
import email
from PyQt4 import QtGui
from PyQt4.Qt import (QDialog, QTableWidget, QMessageBox, QVBoxLayout, QHBoxLayout,
QGridLayout, QPushButton, QProgressDialog, QString, QLabel,
QCheckBox, QIcon, QTextCursor, QTextEdit, QLineEdit, QInputDialog,
QComboBox, QClipboard, QVariant, QProgressDialog, QTimer,
QDialogButtonBox, QPixmap, Qt, QAbstractItemView, SIGNAL,
QTableWidgetItem )
from PyQt4.Qt import (QDialog, QTableWidget, QVBoxLayout, QHBoxLayout, QGridLayout,
QPushButton, QString, QLabel, QCheckBox, QIcon, QLineEdit,
QComboBox, QVariant, QProgressDialog, QTimer, QDialogButtonBox,
QPixmap, Qt, QAbstractItemView, SIGNAL, QTextEdit, pyqtSignal)
from calibre.gui2 import error_dialog, warning_dialog, question_dialog, info_dialog
from calibre.gui2.dialogs.confirm_delete import confirm
from calibre.gui2.complete2 import EditWithComplete
from calibre import confirm_config_name
from calibre.gui2 import dynamic
from calibre_plugins.fanfictiondownloader_plugin.fanficdownloader import adapters,writers,exceptions
from calibre_plugins.fanfictiondownloader_plugin.common_utils \
import (ReadOnlyTableWidgetItem, ReadOnlyTextIconWidgetItem, SizePersistedDialog,
ImageTitleLayout, get_icon)
SKIP='Skip'
ADDNEW='Add New Book'
UPDATE='Update EPUB if New Chapters'
UPDATEALWAYS='Update EPUB Always'
OVERWRITE='Overwrite if Newer'
OVERWRITEALWAYS='Overwrite Always'
CALIBREONLY='Update Calibre Metadata Only'
from calibre_plugins.fanfictiondownloader_plugin.fanficdownloader.geturls import get_urls_from_html, get_urls_from_text
from calibre_plugins.fanfictiondownloader_plugin.fanficdownloader.adapters import getNormalStoryURL
SKIP=u'Skip'
ADDNEW=u'Add New Book'
UPDATE=u'Update EPUB if New Chapters'
UPDATEALWAYS=u'Update EPUB Always'
OVERWRITE=u'Overwrite if Newer'
OVERWRITEALWAYS=u'Overwrite Always'
CALIBREONLY=u'Update Calibre Metadata Only'
collision_order=[SKIP,
ADDNEW,
UPDATE,
@@ -44,7 +43,66 @@ collision_order=[SKIP,
OVERWRITE,
OVERWRITEALWAYS,
CALIBREONLY,]
anthology_collision_order=[UPDATE,
UPDATEALWAYS,
OVERWRITEALWAYS]
class RejectUrlEntry:
matchpat=re.compile(r"^(?P<url>[^,]+)(,(?P<fullnote>(((?P<title>.+) by (?P<auth>.+?)( - (?P<note>.+))?)|.*)))?$")
def __init__(self,url_or_line,note=None,title=None,auth=None,
addreasontext=None,fromline=False):
self.url=url_or_line
self.note=note
self.title=title
self.auth=auth
self.valid=False
if fromline:
mc = re.match(self.matchpat,url_or_line)
if mc:
#print("mc:%s"%mc.groupdict())
(url,title,auth,note) = mc.group('url','title','auth','note')
if not mc.group('title'):
title=''
auth=''
note=mc.group('fullnote')
self.url=url
self.note=note
self.title=title
self.auth=auth
if not self.note:
if addreasontext:
self.note = addreasontext
else:
self.note = ''
else:
if addreasontext:
self.note = self.note + ' - ' + addreasontext
self.url = getNormalStoryURL(self.url)
self.valid = self.url != None
def to_line(self):
# always 'url,'
return self.url+","+self.fullnote()
def fullnote(self):
retval = ""
if self.title and self.auth:
retval = retval + "%s by %s"%(self.title,self.auth)
if self.note:
retval = retval + " - "
if self.note:
retval = retval + self.note
return retval
# This is a more than slightly kludgey way to get
# EditWithComplete to *not* alpha-order the reasons, but leave
# them in the order entered. If
@@ -69,6 +127,36 @@ class NotGoingToDownload(Exception):
class DroppableQTextEdit(QTextEdit):
def __init__(self,parent):
QTextEdit.__init__(self,parent)
def dropEvent(self,event):
# print("event:%s"%event)
mimetype='text/uri-list'
urllist=[]
filelist="%s"%event.mimeData().data(mimetype)
for f in filelist.splitlines():
#print("filename:%s"%f)
if f.endswith(".eml"):
fhandle = urllib.urlopen(f)
#print("file:\n%s\n\n"%fhandle.read())
msg = email.message_from_file(fhandle)
if msg.is_multipart():
for part in msg.walk():
#print("part type:%s"%part.get_content_type())
if part.get_content_type() == "text/html":
#print("URL list:%s"%get_urls_from_data(part.get_payload(decode=True)))
urllist.extend(get_urls_from_html(part.get_payload(decode=True)))
if part.get_content_type() == "text/plain":
#print("part content:text/plain")
# print("part content:%s"%part.get_payload(decode=True))
urllist.extend(get_urls_from_text(part.get_payload(decode=True)))
else:
urllist.extend(get_urls_from_text("%s"%msg))
if urllist:
self.append("\n".join(urllist))
return QTextEdit.dropEvent(self,event)
def canInsertFromMimeData(self, source):
if source.hasUrls():
@@ -84,12 +172,11 @@ class DroppableQTextEdit(QTextEdit):
class AddNewDialog(SizePersistedDialog):
def __init__(self, gui, prefs, icon, url_list_text):
SizePersistedDialog.__init__(self, gui, 'FanFictionDownLoader plugin:add new dialog')
self.gui = gui
go_signal = pyqtSignal(object, object, object, object)
if prefs['adddialogstaysontop']:
QDialog.setWindowFlags ( self, Qt.Dialog|Qt.WindowStaysOnTopHint )
def __init__(self, gui, prefs, icon):
SizePersistedDialog.__init__(self, gui, 'FanFictionDownLoader plugin:add new dialog')
self.prefs = prefs
self.setMinimumWidth(300)
self.l = QVBoxLayout()
@@ -98,85 +185,189 @@ class AddNewDialog(SizePersistedDialog):
self.setWindowTitle('FanFictionDownLoader')
self.setWindowIcon(icon)
self.l.addWidget(QLabel('Story URL(s), one per line:'))
self.toplabel=QLabel("Toplabel")
self.l.addWidget(self.toplabel)
self.url = DroppableQTextEdit(self)
self.url.setToolTip('URLs for stories, one per line.\nWill take URLs from clipboard, but only valid URLs.\nAdd [1,5] after the URL to limit the download to chapters 1-5.')
self.url.setToolTip("UrlTooltip")
self.url.setLineWrapMode(QTextEdit.NoWrap)
self.url.setText(url_list_text)
self.l.addWidget(self.url)
self.merge = self.newmerge = False
# elements to hide when doing merge.
self.mergehide = []
# elements to show again when doing *update* merge
self.mergeupdateshow = []
horz = QHBoxLayout()
label = QLabel('Output &Format:')
horz.addWidget(label)
self.mergehide.append(label)
self.fileform = QComboBox(self)
self.fileform.addItem('epub')
self.fileform.addItem('mobi')
self.fileform.addItem('html')
self.fileform.addItem('txt')
self.fileform.setCurrentIndex(self.fileform.findText(prefs['fileform']))
self.fileform.setToolTip('Choose output format to create. May set default from plugin configuration.')
self.fileform.activated.connect(self.set_collisions)
horz.addWidget(label)
label.setBuddy(self.fileform)
horz.addWidget(self.fileform)
self.l.addLayout(horz)
self.mergehide.append(self.fileform)
horz = QHBoxLayout()
label = QLabel('If Story Already Exists?')
horz.addWidget(label)
self.collisionlabel = QLabel("CollisionLabel")
horz.addWidget(self.collisionlabel)
self.collision = QComboBox(self)
self.collision.setToolTip("What to do if there's already an existing story with the same URL or title and author.")
self.collision.setToolTip("CollisionToolTip")
# add collision options
self.set_collisions()
i = self.collision.findText(prefs['collision'])
if i > -1:
self.collision.setCurrentIndex(i)
label.setBuddy(self.collision)
self.collisionlabel.setBuddy(self.collision)
horz.addWidget(self.collision)
self.l.addLayout(horz)
self.mergehide.append(self.collisionlabel)
self.mergehide.append(self.collision)
self.mergeupdateshow.append(self.collisionlabel)
self.mergeupdateshow.append(self.collision)
horz = QHBoxLayout()
self.updatemeta = QCheckBox('Update Calibre &Metadata?',self)
self.updatemeta.setToolTip("Update metadata for existing stories in Calibre from web site?\n(Columns set to 'New Only' in the column tabs will only be set for new books.)")
self.updatemeta.setChecked(prefs['updatemeta'])
horz.addWidget(self.updatemeta)
self.mergehide.append(self.updatemeta)
self.mergeupdateshow.append(self.updatemeta)
self.updateepubcover = QCheckBox('Update EPUB Cover?',self)
self.updateepubcover.setToolTip('Update book cover image from site or defaults (if found) <i>inside</i> the EPUB when EPUB is updated.')
self.updateepubcover.setChecked(prefs['updateepubcover'])
horz.addWidget(self.updateepubcover)
self.mergehide.append(self.updateepubcover)
self.l.addLayout(horz)
button_box = QDialogButtonBox(QDialogButtonBox.Ok | QDialogButtonBox.Cancel)
button_box.accepted.connect(self.accept)
button_box.rejected.connect(self.reject)
self.l.addWidget(button_box)
if url_list_text:
button_box.button(QDialogButtonBox.Ok).setFocus()
self.button_box = QDialogButtonBox(QDialogButtonBox.Ok | QDialogButtonBox.Cancel)
self.button_box.accepted.connect(self.ok_clicked)
self.button_box.rejected.connect(self.reject)
self.l.addWidget(self.button_box)
# invoke the
def ok_clicked(self):
self.hide()
print("ok_clicked called")
self.go_signal.emit( self.get_ffdl_options(),
self.get_urlstext(),
self.merge,
self.extrapayload )
def show_dialog(self,
url_list_text,
callback,
show=True,
merge=False,
newmerge=True,
extraoptions={},
extrapayload=None):
# rather than mutex in ffdl_plugin, just bail here if it's
# already in use.
if self.isVisible(): return
try:
self.go_signal.disconnect()
except:
pass # if not already connected.
self.go_signal.connect(callback)
self.merge = merge
self.newmerge = newmerge
self.extraoptions = extraoptions
self.extrapayload = extrapayload
if self.merge:
self.toplabel.setText('Story URL(s) for anthology, one per line:')
self.url.setToolTip('URLs for stories to include in the anthology, one per line.\nWill take URLs from clipboard, but only valid URLs.')
self.collisionlabel.setText('If Story Already Exists in Anthology?')
self.collision.setToolTip("What to do if there's already an existing story with the same URL in the anthology.")
for widget in self.mergehide:
widget.setVisible(False)
if not self.newmerge:
for widget in self.mergeupdateshow:
widget.setVisible(True)
else:
for widget in self.mergehide:
widget.setVisible(True)
self.toplabel.setText('Story URL(s), one per line:')
self.url.setToolTip('URLs for stories, one per line.\nWill take URLs from clipboard, but only valid URLs.\nAdd [1,5] after the URL to limit the download to chapters 1-5.')
self.collisionlabel.setText('If Story Already Exists?')
self.collision.setToolTip("What to do if there's already an existing story with the same URL or title and author.")
# Need to re-able after hiding/showing
self.setAcceptDrops(True)
self.url.setFocus()
if self.prefs['adddialogstaysontop']:
QDialog.setWindowFlags ( self, Qt.Dialog | Qt.WindowStaysOnTopHint )
else:
QDialog.setWindowFlags ( self, Qt.Dialog )
if not self.merge:
self.fileform.setCurrentIndex(self.fileform.findText(self.prefs['fileform']))
if self.merge and not self.newmerge:
self.set_collisions()
i = self.collision.findText(self.prefs['collision'])
if i > -1:
self.collision.setCurrentIndex(i)
self.updatemeta.setChecked(self.prefs['updatemeta'])
if not self.merge:
self.updateepubcover.setChecked(self.prefs['updateepubcover'])
self.url.setText(url_list_text)
if url_list_text:
self.button_box.button(QDialogButtonBox.Ok).setFocus()
# restore saved size.
self.resize_dialog()
if show: # so anthology update can be modal still.
self.show()
#self.resize(self.sizeHint())
def set_collisions(self):
prev=self.collision.currentText()
self.collision.clear()
for o in collision_order:
if self.fileform.currentText() == 'epub' or o not in [UPDATE,UPDATEALWAYS]:
if self.merge:
order = anthology_collision_order
else:
order = collision_order
for o in order:
if self.merge or self.fileform.currentText() == 'epub' or o not in [UPDATE,UPDATEALWAYS]:
self.collision.addItem(o)
i = self.collision.findText(prev)
if i > -1:
self.collision.setCurrentIndex(i)
def get_ffdl_options(self):
return {
retval = {
'fileform': unicode(self.fileform.currentText()),
'collision': unicode(self.collision.currentText()),
'updatemeta': self.updatemeta.isChecked(),
'updateepubcover': self.updateepubcover.isChecked(),
}
}
if self.merge:
retval['fileform']=='epub'
retval['updateepubcover']=True
if self.newmerge:
retval['updatemeta']=True
retval['collision']=ADDNEW
return dict(retval.items() + self.extraoptions.items() )
def get_urlstext(self):
return unicode(self.url.toPlainText())
@@ -193,10 +384,10 @@ class CollectURLDialog(SizePersistedDialog):
'''
Collect single url for get urls.
'''
def __init__(self, gui, title, url_text):
def __init__(self, gui, title, url_text, epubmerge_plugin=None):
SizePersistedDialog.__init__(self, gui, 'FanFictionDownLoader plugin:get story urls')
self.gui = gui
self.status=False
self.anthology=False
self.setMinimumWidth(300)
@@ -204,28 +395,40 @@ class CollectURLDialog(SizePersistedDialog):
self.setLayout(self.l)
self.setWindowTitle(title)
self.l.addWidget(QLabel(title),0,0,1,2)
self.l.addWidget(QLabel(title),0,0,1,3)
self.l.addWidget(QLabel("URL:"),1,0)
self.url = QLineEdit(self)
self.url.setText(url_text)
self.l.addWidget(self.url,1,1)
self.l.addWidget(self.url,1,1,1,2)
self.ok_button = QPushButton('OK', self)
self.ok_button.clicked.connect(self.ok)
self.l.addWidget(self.ok_button,2,0)
self.indiv_button = QPushButton('For Individual Books', self)
self.indiv_button.setToolTip('Get URLs and go to dialog for individual story downloads.')
self.indiv_button.clicked.connect(self.indiv)
self.l.addWidget(self.indiv_button,2,0)
self.merge_button = QPushButton('For Anthology Epub', self)
self.merge_button.setToolTip('Get URLs and go to dialog for Anthology download.\nRequires EpubMerge 1.3.1+ plugin.')
self.merge_button.clicked.connect(self.merge)
self.l.addWidget(self.merge_button,2,1)
self.merge_button.setEnabled(epubmerge_plugin!=None)
self.cancel_button = QPushButton('Cancel', self)
self.cancel_button.clicked.connect(self.cancel)
self.l.addWidget(self.cancel_button,2,1)
self.l.addWidget(self.cancel_button,2,2)
# restore saved size.
self.resize_dialog()
def ok(self):
def indiv(self):
self.status=True
self.accept()
def merge(self):
self.status=True
self.anthology=True
self.accept()
def cancel(self):
self.status=False
self.reject()
@@ -236,7 +439,6 @@ class UserPassDialog(QDialog):
'''
def __init__(self, gui, site, exception=None):
QDialog.__init__(self, gui)
self.gui = gui
self.status=False
self.l = QGridLayout()
@@ -295,7 +497,6 @@ class LoopProgressDialog(QProgressDialog):
QString(), 0, len(book_list), gui)
self.setWindowTitle(win_title)
self.setMinimumWidth(500)
self.gui = gui
self.book_list = book_list
self.foreach_function = foreach_function
self.finish_function = finish_function
@@ -344,7 +545,6 @@ class LoopProgressDialog(QProgressDialog):
def do_when_finished(self):
self.hide()
self.gui = None
# Queues a job to process these books in the background.
self.finish_function(self.book_list)
@@ -393,7 +593,6 @@ class UpdateExistingDialog(SizePersistedDialog):
def __init__(self, gui, header, prefs, icon, books,
save_size_name='fanfictiondownloader_plugin:update list dialog'):
SizePersistedDialog.__init__(self, gui, save_size_name)
self.gui = gui
self.setWindowTitle(header)
self.setWindowIcon(icon)
@@ -411,11 +610,7 @@ class UpdateExistingDialog(SizePersistedDialog):
button_layout = QVBoxLayout()
books_layout.addLayout(button_layout)
# self.move_up_button = QtGui.QToolButton(self)
# self.move_up_button.setToolTip('Move selected books up the list')
# self.move_up_button.setIcon(QIcon(I('arrow-up.png')))
# self.move_up_button.clicked.connect(self.books_table.move_rows_up)
# button_layout.addWidget(self.move_up_button)
spacerItem = QtGui.QSpacerItem(20, 40, QtGui.QSizePolicy.Minimum, QtGui.QSizePolicy.Expanding)
button_layout.addItem(spacerItem)
self.remove_button = QtGui.QToolButton(self)
@@ -425,11 +620,6 @@ class UpdateExistingDialog(SizePersistedDialog):
button_layout.addWidget(self.remove_button)
spacerItem1 = QtGui.QSpacerItem(20, 40, QtGui.QSizePolicy.Minimum, QtGui.QSizePolicy.Expanding)
button_layout.addItem(spacerItem1)
# self.move_down_button = QtGui.QToolButton(self)
# self.move_down_button.setToolTip('Move selected books down the list')
# self.move_down_button.setIcon(QIcon(I('arrow-down.png')))
# self.move_down_button.clicked.connect(self.books_table.move_rows_down)
# button_layout.addWidget(self.move_down_button)
options_layout = QHBoxLayout()
@@ -455,7 +645,6 @@ class UpdateExistingDialog(SizePersistedDialog):
i = self.collision.findText(prefs['collision'])
if i > -1:
self.collision.setCurrentIndex(i)
# self.collision.setToolTip('Overwrite will replace the existing story. Add New will create a new story with the same title and author.')
label.setBuddy(self.collision)
options_layout.addWidget(self.collision)
@@ -505,84 +694,6 @@ class UpdateExistingDialog(SizePersistedDialog):
'updateepubcover': self.updateepubcover.isChecked(),
}
def display_story_list(gui, header, prefs, icon, books,
label_text='',
save_size_name='fanfictiondownloader_plugin:display list dialog',
offer_skip=False):
all_good = True
for b in books:
if not b['good']:
all_good=False
break
##
if all_good and not dynamic.get(confirm_config_name(save_size_name), True):
return True
pass
## fake accept?
d = DisplayStoryListDialog(gui, header, prefs, icon, books,
label_text,
save_size_name,
offer_skip and all_good)
d.exec_()
return d.result() == d.Accepted
class DisplayStoryListDialog(SizePersistedDialog):
def __init__(self, gui, header, prefs, icon, books,
label_text='',
save_size_name='fanfictiondownloader_plugin:display list dialog',
offer_skip=False):
SizePersistedDialog.__init__(self, gui, save_size_name)
self.name = save_size_name
self.gui = gui
self.setWindowTitle(header)
self.setWindowIcon(icon)
layout = QVBoxLayout(self)
self.setLayout(layout)
title_layout = ImageTitleLayout(self, 'images/icon.png',
header)
layout.addLayout(title_layout)
self.books_table = StoryListTableWidget(self)
layout.addWidget(self.books_table)
options_layout = QHBoxLayout()
self.label = QLabel(label_text)
#self.label.setOpenExternalLinks(True)
#self.label.setWordWrap(True)
options_layout.addWidget(self.label)
if offer_skip:
spacerItem1 = QtGui.QSpacerItem(2, 4, QtGui.QSizePolicy.Expanding, QtGui.QSizePolicy.Minimum)
options_layout.addItem(spacerItem1)
self.again = QCheckBox('Show this again?',self)
self.again.setChecked(True)
self.again.stateChanged.connect(self.toggle)
self.again.setToolTip('Uncheck to skip review and update stories immediately when no problems.')
options_layout.addWidget(self.again)
button_box = QDialogButtonBox(QDialogButtonBox.Ok | QDialogButtonBox.Cancel)
button_box.accepted.connect(self.accept)
button_box.rejected.connect(self.reject)
options_layout.addWidget(button_box)
layout.addLayout(options_layout)
# Cause our dialog size to be restored from prefs or created on first usage
self.resize_dialog()
self.books_table.populate_table(books)
def get_books(self):
return self.books_table.get_books()
def toggle(self, *args):
dynamic[confirm_config_name(self.name)] = self.again.isChecked()
class StoryListTableWidget(QTableWidget):
def __init__(self, parent):
@@ -642,11 +753,9 @@ class StoryListTableWidget(QTableWidget):
self.setItem(row, 2, AuthorTableWidgetItem(", ".join(book['author']), ", ".join(book['author_sort'])))
url_cell = ReadOnlyTableWidgetItem(book['url'])
#url_cell.setData(Qt.UserRole, QVariant(book['url']))
self.setItem(row, 3, url_cell)
comment_cell = ReadOnlyTableWidgetItem(book['comment'])
#comment_cell.setData(Qt.UserRole, QVariant(book))
self.setItem(row, 4, comment_cell)
def get_books(self):
@@ -680,56 +789,6 @@ class StoryListTableWidget(QTableWidget):
self.selectRow(row)
self.scrollToItem(self.currentItem())
def move_rows_up(self):
self.setFocus()
rows = self.selectionModel().selectedRows()
if len(rows) == 0:
return
first_sel_row = rows[0].row()
if first_sel_row <= 0:
return
# Workaround for strange selection bug in Qt which "alters" the selection
# in certain circumstances which meant move down only worked properly "once"
selrows = []
for row in rows:
selrows.append(row.row())
selrows.sort()
for selrow in selrows:
self.swap_row_widgets(selrow - 1, selrow + 1)
scroll_to_row = first_sel_row - 1
if scroll_to_row > 0:
scroll_to_row = scroll_to_row - 1
self.scrollToItem(self.item(scroll_to_row, 0))
def move_rows_down(self):
self.setFocus()
rows = self.selectionModel().selectedRows()
if len(rows) == 0:
return
last_sel_row = rows[-1].row()
if last_sel_row == self.rowCount() - 1:
return
# Workaround for strange selection bug in Qt which "alters" the selection
# in certain circumstances which meant move down only worked properly "once"
selrows = []
for row in rows:
selrows.append(row.row())
selrows.sort()
for selrow in reversed(selrows):
self.swap_row_widgets(selrow + 2, selrow)
scroll_to_row = last_sel_row + 1
if scroll_to_row < self.rowCount() - 1:
scroll_to_row = scroll_to_row + 1
self.scrollToItem(self.item(scroll_to_row, 0))
def swap_row_widgets(self, src_row, dest_row):
self.blockSignals(True)
self.insertRow(dest_row)
for col in range(0, self.columnCount()):
self.setItem(dest_row, col, self.takeItem(src_row, col))
self.removeRow(src_row)
self.blockSignals(False)
class RejectListTableWidget(QTableWidget):
def __init__(self, parent,rejectreasons=[]):
@@ -737,85 +796,53 @@ class RejectListTableWidget(QTableWidget):
self.setSelectionBehavior(QAbstractItemView.SelectRows)
self.rejectreasons = rejectreasons
def on_headersection_clicked(self):
self.setSortingEnabled(True)
def populate_table(self, reject_list):
self.clear()
self.setAlternatingRowColors(True)
self.setRowCount(len(reject_list))
header_labels = ['URL', 'Note']
header_labels = ['URL', 'Title', 'Author', 'Note']
self.setColumnCount(len(header_labels))
self.setHorizontalHeaderLabels(header_labels)
self.horizontalHeader().setStretchLastSection(True)
#self.verticalHeader().setDefaultSectionSize(24)
self.verticalHeader().hide()
# need sortingEnbled to sort, but off to up & down.
self.connect(self.horizontalHeader(),
SIGNAL('sectionClicked(int)'),
self.on_headersection_clicked)
# it's generally recommended to enable sort after pop, not
# before. But then it needs to be sorted on a column and I'd
# rather keep the order given.
self.setSortingEnabled(True)
# row is just row number.
for row, rejectrow in enumerate(reject_list):
#print("populating table:%s"%rejectrow.to_line())
self.populate_table_row(row,rejectrow)
self.resizeColumnsToContents()
self.setMinimumColumnWidth(1, 100)
self.setMinimumColumnWidth(2, 100)
self.setMinimumColumnWidth(0, 100)
self.setMinimumColumnWidth(3, 100)
self.setMinimumSize(300, 0)
def setMinimumColumnWidth(self, col, minimum):
if self.columnWidth(col) < minimum:
self.setColumnWidth(col, minimum)
def populate_table_row(self, row, rejectrow):
(bookid,url,titleauth,oldrejnote) = rejectrow
if oldrejnote:
noteprefix = note = oldrejnote
# incase the existing note ends with one of the known reasons.
for reason in self.rejectreasons:
if noteprefix.endswith(' - '+reason):
noteprefix = noteprefix[:-len(' - '+reason)]
break
else:
noteprefix = note = titleauth
if len(noteprefix) > 0:
noteprefix = noteprefix+' - '
url_cell = ReadOnlyTableWidgetItem(url)
url_cell.setData(Qt.UserRole, QVariant(bookid))
url_cell.setToolTip('URL to add to the Reject List.')
self.setItem(row, 0, url_cell)
def populate_table_row(self, row, rej):
self.setItem(row, 0, ReadOnlyTableWidgetItem(rej.url))
self.setItem(row, 1, ReadOnlyTableWidgetItem(rej.title))
self.setItem(row, 2, ReadOnlyTableWidgetItem(rej.auth))
note_cell = EditWithComplete(self)
note_cell.lineEdit().mcompleter.model().set_items = \
partial(complete_model_set_items_kludge,
note_cell.lineEdit().mcompleter.model())
items = [note]+[ noteprefix+x for x in self.rejectreasons ]
items = [rej.note]+self.rejectreasons
note_cell.update_items_cache(items)
note_cell.show_initial_value(note)
note_cell.show_initial_value(rej.note)
note_cell.set_separator(None)
note_cell.setToolTip('Select or Edit Reject Note.')
self.setCellWidget(row, 1, note_cell)
self.setCellWidget(row, 3, note_cell)
# note_cell = QTableWidgetItem(note)
# note_cell.setToolTip('Double-click to edit note.')
# self.setItem(row, 1, note_cell)
def get_reject_list(self):
rejectrows = []
for row in range(self.rowCount()):
bookid = self.item(row, 0).data(Qt.UserRole).toPyObject()
url = unicode(self.item(row, 0).text())
note = unicode(self.cellWidget(row, 1).currentText()).strip()
rejectrows.append((bookid,url,note))
return rejectrows
def remove_selected_rows(self):
self.setFocus()
rows = self.selectionModel().selectedRows()
@@ -838,57 +865,6 @@ class RejectListTableWidget(QTableWidget):
self.selectRow(row)
self.scrollToItem(self.currentItem())
def move_rows_up(self):
self.setFocus()
rows = self.selectionModel().selectedRows()
if len(rows) == 0:
return
first_sel_row = rows[0].row()
if first_sel_row <= 0:
return
# Workaround for strange selection bug in Qt which "alters" the selection
# in certain circumstances which meant move down only worked properly "once"
selrows = []
for row in rows:
selrows.append(row.row())
selrows.sort()
for selrow in selrows:
self.swap_row_widgets(selrow - 1, selrow + 1)
scroll_to_row = first_sel_row - 1
if scroll_to_row > 0:
scroll_to_row = scroll_to_row - 1
self.scrollToItem(self.item(scroll_to_row, 0))
def move_rows_down(self):
self.setFocus()
rows = self.selectionModel().selectedRows()
if len(rows) == 0:
return
last_sel_row = rows[-1].row()
if last_sel_row == self.rowCount() - 1:
return
# Workaround for strange selection bug in Qt which "alters" the selection
# in certain circumstances which meant move down only worked properly "once"
selrows = []
for row in rows:
selrows.append(row.row())
selrows.sort()
for selrow in reversed(selrows):
self.swap_row_widgets(selrow + 2, selrow)
scroll_to_row = last_sel_row + 1
if scroll_to_row < self.rowCount() - 1:
scroll_to_row = scroll_to_row + 1
self.scrollToItem(self.item(scroll_to_row, 0))
def swap_row_widgets(self, src_row, dest_row):
self.blockSignals(True)
self.setSortingEnabled(False)
self.insertRow(dest_row)
for col in range(0, self.columnCount()):
self.setItem(dest_row, col, self.takeItem(src_row, col))
self.removeRow(src_row)
self.blockSignals(False)
class RejectListDialog(SizePersistedDialog):
def __init__(self, gui, reject_list,
rejectreasons=[],
@@ -898,7 +874,6 @@ class RejectListDialog(SizePersistedDialog):
show_all_reasons=True,
save_size_name='ffdl:reject list dialog'):
SizePersistedDialog.__init__(self, gui, save_size_name)
self.gui = gui
self.setWindowTitle(header)
self.setWindowIcon(get_icon(icon))
@@ -918,21 +893,13 @@ class RejectListDialog(SizePersistedDialog):
rejects_layout.addLayout(button_layout)
spacerItem = QtGui.QSpacerItem(20, 40, QtGui.QSizePolicy.Minimum, QtGui.QSizePolicy.Expanding)
button_layout.addItem(spacerItem)
# self.move_up_button = QtGui.QToolButton(self)
# self.move_up_button.setToolTip('Move selected books up the list')
# self.move_up_button.setIcon(QIcon(I('arrow-up.png')))
# self.move_up_button.clicked.connect(self.books_table.move_rows_up)
# button_layout.addWidget(self.move_up_button)
self.remove_button = QtGui.QToolButton(self)
self.remove_button.setToolTip('Remove selected URL(s) from the list')
self.remove_button.setIcon(get_icon('list_remove.png'))
self.remove_button.clicked.connect(self.remove_from_list)
button_layout.addWidget(self.remove_button)
# self.move_down_button = QtGui.QToolButton(self)
# self.move_down_button.setToolTip('Move selected books down the list')
# self.move_down_button.setIcon(QIcon(I('arrow-down.png')))
# self.move_down_button.clicked.connect(self.books_table.move_rows_down)
# button_layout.addWidget(self.move_down_button)
spacerItem1 = QtGui.QSpacerItem(20, 40, QtGui.QSizePolicy.Minimum, QtGui.QSizePolicy.Expanding)
button_layout.addItem(spacerItem1)
@@ -979,10 +946,21 @@ class RejectListDialog(SizePersistedDialog):
self.rejects_table.remove_selected_rows()
def get_reject_list(self):
return self.rejects_table.get_reject_list()
rejectrows = []
for row in range(self.rejects_table.rowCount()):
url = unicode(self.rejects_table.item(row, 0).text()).strip()
title = unicode(self.rejects_table.item(row, 1).text()).strip()
auth = unicode(self.rejects_table.item(row, 2).text()).strip()
note = unicode(self.rejects_table.cellWidget(row, 3).currentText()).strip()
rejectrows.append(RejectUrlEntry(url,note,title,auth,self.get_reason_text()))
return rejectrows
def get_reason_text(self):
return unicode(self.reason_edit.currentText()).strip()
try:
return unicode(self.reason_edit.currentText()).strip()
except:
# doesn't have self.reason_edit when editing existing list.
return None
def get_deletebooks(self):
return self.deletebooks.isChecked()
File diff suppressed because it is too large Load Diff
+43
View File
@@ -0,0 +1,43 @@
#!/usr/bin/env python
# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai
from __future__ import (unicode_literals, division, absolute_import,
print_function)
__license__ = 'GPL v3'
__copyright__ = '2013, Jim Miller'
__docformat__ = 'restructuredtext en'
from StringIO import StringIO
from calibre_plugins.fanfictiondownloader_plugin.fanficdownloader import adapters, exceptions
from calibre_plugins.fanfictiondownloader_plugin.fanficdownloader.configurable import Configuration
from calibre_plugins.fanfictiondownloader_plugin.prefs import (prefs)
def get_ffdl_personalini():
if prefs['includeimages']:
# this is a cheat to make it easier for users.
return '''[epub]
include_images:true
keep_summary_html:true
make_firstimage_cover:true
''' + prefs['personal.ini']
else:
return prefs['personal.ini']
def get_ffdl_config(url,fileform="epub",personalini=None):
if not personalini:
personalini = get_ffdl_personalini()
site='unknown'
try:
site = adapters.getConfigSectionFor(url)
except Exception as e:
print("Failed trying to get ini config for url(%s): %s, using section [%s] instead"%(url,e,site))
configuration = Configuration(site,fileform)
configuration.readfp(StringIO(get_resources("plugin-defaults.ini")))
configuration.readfp(StringIO(personalini))
return configuration
def get_ffdl_adapter(url,fileform="epub",personalini=None):
return adapters.getAdapter(get_ffdl_config(url,fileform,personalini),url)
+31 -4
View File
@@ -18,9 +18,9 @@ from calibre.utils.ipc.job import ParallelJob
from calibre_plugins.fanfictiondownloader_plugin.dialogs import (NotGoingToDownload,
OVERWRITE, OVERWRITEALWAYS, UPDATE, UPDATEALWAYS, ADDNEW, SKIP, CALIBREONLY)
from calibre_plugins.fanfictiondownloader_plugin.fanficdownloader import adapters, writers, exceptions
from calibre_plugins.fanfictiondownloader_plugin.fanficdownloader.configurable import Configuration
from calibre_plugins.fanfictiondownloader_plugin.fanficdownloader.epubutils import get_update_data
from calibre_plugins.fanfictiondownloader_plugin.ffdl_util import (get_ffdl_adapter, get_ffdl_config)
# ------------------------------------------------------------------------------
#
# Functions to perform downloads using worker jobs
@@ -114,9 +114,9 @@ def do_download_for_worker(book,options):
try:
book['comment'] = 'Download started...'
configuration = Configuration(adapters.getConfigSectionFor(book['url']),options['fileform'])
configuration.readfp(StringIO(get_resources("plugin-defaults.ini")))
configuration.readfp(StringIO(options['personal.ini']))
configuration = get_ffdl_config(book['url'],
options['fileform'],
options['personal.ini'])
if not options['updateepubcover'] and 'epub_for_update' in book and options['collision'] in (UPDATE, UPDATEALWAYS):
configuration.set("overrides","never_make_cover","true")
@@ -153,6 +153,22 @@ def do_download_for_worker(book,options):
elif options['collision'] in (ADDNEW, SKIP, OVERWRITE, OVERWRITEALWAYS) or \
('epub_for_update' not in book and options['collision'] in (UPDATE, UPDATEALWAYS)):
# preserve logfile even on overwrite.
if 'epub_for_update' in book:
(urlignore,
chaptercountignore,
oldchaptersignore,
oldimgsignore,
oldcoverignore,
calibrebookmarkignore,
# only logfile set in adapter, so others aren't used.
adapter.logfile) = get_update_data(book['epub_for_update'])
# change the existing entries id to notid so
# write_epub writes a whole new set to indicate overwrite.
if adapter.logfile:
adapter.logfile = adapter.logfile.replace("span id","span notid")
print("write to %s"%outfile)
writer.writeStory(outfilename=outfile, forceOverwrite=True)
book['comment'] = 'Download %s completed, %s chapters.'%(options['fileform'],story.getMetadata("numChapters"))
@@ -171,6 +187,17 @@ def do_download_for_worker(book,options):
adapter.calibrebookmark,
adapter.logfile) = get_update_data(book['epub_for_update'])
# dup handling from ffdl_plugin needed for anthology updates.
if options['collision'] == UPDATE:
if chaptercount == urlchaptercount:
book['comment']="Already contains %d chapters. Reuse as is."%chaptercount
book['outfile'] = book['epub_for_update'] # for anthology merge ops.
return book
# dup handling from ffdl_plugin needed for anthology updates.
if chaptercount > urlchaptercount:
raise NotGoingToDownload("Existing epub contains %d chapters, web site only has %d. Use Overwrite to force update." % (chaptercount,urlchaptercount),'dialog_error.png')
print("Do update - epub(%d) vs url(%d)" % (chaptercount, urlchaptercount))
print("write to %s"%outfile)
+142
View File
@@ -0,0 +1,142 @@
#!/usr/bin/env python
# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai
from __future__ import (unicode_literals, division, absolute_import,
print_function)
__license__ = 'GPL v3'
__copyright__ = '2013, Jim Miller'
__docformat__ = 'restructuredtext en'
import copy
from calibre.utils.config import JSONConfig
from calibre.gui2.ui import get_gui
from calibre_plugins.fanfictiondownloader_plugin.dialogs import OVERWRITE
from calibre_plugins.fanfictiondownloader_plugin.common_utils import get_library_uuid
PREFS_NAMESPACE = 'FanFictionDownLoaderPlugin'
PREFS_KEY_SETTINGS = 'settings'
# Set defaults used by all. Library specific settings continue to
# take from here.
default_prefs = {}
default_prefs['personal.ini'] = get_resources('plugin-example.ini')
default_prefs['rejecturls'] = ''
default_prefs['rejectreasons'] = '''Sucked
Boring
Dup from another site'''
default_prefs['updatemeta'] = True
default_prefs['updatecover'] = False
default_prefs['updateepubcover'] = False
default_prefs['keeptags'] = False
default_prefs['showmarked'] = False
default_prefs['urlsfromclip'] = True
default_prefs['updatedefault'] = True
default_prefs['fileform'] = 'epub'
default_prefs['collision'] = OVERWRITE
default_prefs['deleteotherforms'] = False
default_prefs['adddialogstaysontop'] = False
default_prefs['includeimages'] = False
default_prefs['lookforurlinhtml'] = False
default_prefs['checkforseriesurlid'] = True
default_prefs['injectseries'] = False
default_prefs['send_lists'] = ''
default_prefs['read_lists'] = ''
default_prefs['addtolists'] = False
default_prefs['addtoreadlists'] = False
default_prefs['addtolistsonread'] = False
default_prefs['gcnewonly'] = False
default_prefs['gc_site_settings'] = {}
default_prefs['allow_gc_from_ini'] = True
default_prefs['countpagesstats'] = []
default_prefs['errorcol'] = ''
default_prefs['custom_cols'] = {}
default_prefs['custom_cols_newonly'] = {}
default_prefs['allow_custcol_from_ini'] = True
default_prefs['std_cols_newonly'] = {}
def set_library_config(library_config,db):
db.prefs.set_namespaced(PREFS_NAMESPACE,
PREFS_KEY_SETTINGS,
library_config)
def get_library_config(db):
library_id = get_library_uuid(db)
library_config = None
# Check whether this is a configuration needing to be migrated
# from json into database. If so: get it, set it, rename it in json.
if library_id in old_prefs:
#print("get prefs from old_prefs")
library_config = old_prefs[library_id]
set_library_config(library_config)
old_prefs["migrated to library db %s"%library_id] = old_prefs[library_id]
del old_prefs[library_id]
if library_config is None:
#print("get prefs from db")
library_config = db.prefs.get_namespaced(PREFS_NAMESPACE, PREFS_KEY_SETTINGS,
copy.deepcopy(default_prefs))
return library_config
# This is where all preferences for this plugin *were* stored
# Remember that this name (i.e. plugins/fanfictiondownloader_plugin) is also
# in a global namespace, so make it as unique as possible.
# You should always prefix your config file name with plugins/,
# so as to ensure you dont accidentally clobber a calibre config file
old_prefs = JSONConfig('plugins/fanfictiondownloader_plugin')
# fake out so I don't have to change the prefs calls anywhere. The
# Java programmer in me is offended by op-overloading, but it's very
# tidy.
class PrefsFacade():
def _get_db(self):
if self.passed_db:
return self.passed_db
else:
# In the GUI plugin we want current db so we detect when
# it's changed. CLI plugin calls need to pass db in.
return get_gui().current_db
def __init__(self,passed_db=None):
self.default_prefs = default_prefs
self.libraryid = None
self.current_prefs = None
self.passed_db=passed_db
def _get_prefs(self):
libraryid = get_library_uuid(self._get_db())
if self.current_prefs == None or self.libraryid != libraryid:
#print("self.current_prefs == None(%s) or self.libraryid != libraryid(%s)"%(self.current_prefs == None,self.libraryid != libraryid))
self.libraryid = libraryid
self.current_prefs = get_library_config(self._get_db())
return self.current_prefs
def __getitem__(self,k):
prefs = self._get_prefs()
if k not in prefs:
# pulls from default_prefs.defaults automatically if not set
# in default_prefs
return self.default_prefs[k]
return prefs[k]
def __setitem__(self,k,v):
prefs = self._get_prefs()
prefs[k]=v
# self._save_prefs(prefs)
def __delitem__(self,k):
prefs = self._get_prefs()
if k in prefs:
del prefs[k]
def save_to_db(self):
set_library_config(self._get_prefs(),self._get_db())
prefs = PrefsFacade()
+18 -8
View File
@@ -44,6 +44,9 @@ language_label:Language
characters_label:Characters
ships_label:Relationships
series_label:Series
seriesUrl_label:Series URL
## seriesHTML is series as a link to seriesUrl.
seriesHTML_label:Series
## Completed/In-Progress
status_label:Status
## Dates story first published, last updated, and downloaded(last with time).
@@ -81,7 +84,7 @@ dateUpdated_format:%%Y-%%m-%%d
## You can include extra text or HTML that will be included as-is in
## the title page. Eg: titlepage_entries: ...,<br />,summary,<br />,...
## All current formats already include title and author.
titlepage_entries: series,category,genre,language,characters,ships,status,datePublished,dateUpdated,dateCreated,rating,warnings,numChapters,numWords,site,description
titlepage_entries: seriesHTML,category,genre,language,characters,ships,status,datePublished,dateUpdated,dateCreated,rating,warnings,numChapters,numWords,site,description
## Try to collect series name and number of this story in series.
## Some sites (ab)use 'series' for reading lists and personal
@@ -270,7 +273,7 @@ output_css:
[txt]
## Add URLs since there aren't links.
titlepage_entries: series,category,genre,language,status,datePublished,dateUpdated,dateCreated,rating,warnings,numChapters,numWords,site,storyUrl, authorUrl, description
titlepage_entries: series,seriesUrl,category,genre,language,status,datePublished,dateUpdated,dateCreated,rating,warnings,numChapters,numWords,site,storyUrl, authorUrl, description
## Width to word wrap text output. 0 indicates no wrapping.
wrap_width: 78
@@ -304,13 +307,13 @@ include_logpage: false
## if in the list. You can include extra text or HTML that will be
## included as-is in each log entry. Eg: logpage_entries: ...,<br />,
## summary,<br />,...
logpage_entries: dateCreated,datePublished,dateUpdated,numChapters,numWords,status,title,author,description,category,genre,rating,warnings
logpage_entries: dateCreated,datePublished,dateUpdated,numChapters,numWords,status,series,title,author,description,category,genre,rating,warnings
## epub->mobi conversions typically don't like tables.
titlepage_use_table: false
## When using tables, make these span both columns.
wide_titlepage_entries: description, storyUrl, author URL
wide_titlepage_entries: description, storyUrl, authorUrl, seriesUrl
## output background color--only used by html and epub (and ignored in
## epub by many readers). Included below in output_css--will be
@@ -369,7 +372,7 @@ output_css:
## It can be either a 'file:' or 'http:' url.
## Note that if you enable make_firstimage_cover in [epub], but want
## to use default_cover_image for a specific site, use the site:format
## section, for example: [www.ficwad.com:epub]
## section, for example: [ficwad.com:epub]
## default_cover_image is a python string Template string with
## ${title}, ${author} etc, same as titlepage_entries. Unless
## allow_unsafe_filename is true, invalid filename chars will be
@@ -969,6 +972,13 @@ extracategories:InuYasha
extracharacters:Sesshoumaru,Kagome
extraships:Sesshoumaru/Kagome
## Some sites require login (or login for some rated stories) The
## program can prompt you, or you can save it in config. In
## commandline version, this should go in your personal.ini, not
## defaults.ini.
#username:YourName
#password:yourpassword
[www.dotmoon.net]
## Some sites require login (or login for some rated stories) The
## program can prompt you, or you can save it in config. In
@@ -1031,7 +1041,7 @@ extratags:
## for examples of how to use them.
extra_valid_entries:reviews,favs,follows
[www.ficwad.com]
[ficwad.com]
## Some sites require login (or login for some rated stories) The
## program can prompt you, or you can save it in config. In
## commandline version, this should go in your personal.ini, not
@@ -1219,12 +1229,12 @@ extraships:Harry Potter/Ginny Weasley
# www.squidge.org/peja calls it Fandom <shrug>
category_label:Fandom
# Remove numWords -- www.squidge.org/peja word counts are inaccurate
titlepage_entries: series,category,genre,language,characters,ships,status,datePublished,dateUpdated,dateCreated,rating,warnings,numChapters,site,description
titlepage_entries: seriesHTML,category,genre,language,characters,ships,status,datePublished,dateUpdated,dateCreated,rating,warnings,numChapters,site,description
[www.squidge.org/peja:txt]
## Add URLs since there aren't links.
# Remove numWords -- www.squidge.org/peja word counts are inaccurate
titlepage_entries: series,category,genre,language,status,datePublished,dateUpdated,dateCreated,rating,warnings,numChapters,site,storyUrl, authorUrl, description
titlepage_entries: series,seriesUrl,category,genre,language,status,datePublished,dateUpdated,dateCreated,rating,warnings,numChapters,site,storyUrl, authorUrl, description
[www.storiesofarda.com]
## Site dedicated to these categories/characters/ships
+34 -16
View File
@@ -32,10 +32,17 @@ if sys.version_info >= (2, 7):
loghandler.setFormatter(logging.Formatter("(=====)(levelname)s:%(message)s"))
rootlogger.addHandler(loghandler)
from fanficdownloader import adapters,writers,exceptions
from fanficdownloader.configurable import Configuration
from fanficdownloader.epubutils import get_dcsource_chaptercount, get_update_data
from fanficdownloader.geturls import get_urls_from_page
try:
from fanficdownloader import adapters,writers,exceptions
from fanficdownloader.configurable import Configuration
from fanficdownloader.epubutils import get_dcsource_chaptercount, get_update_data
from fanficdownloader.geturls import get_urls_from_page
except:
# running under calibre
from calibre_plugins.fanfictiondownloader_plugin.fanficdownloader import adapters,writers,exceptions
from calibre_plugins.fanfictiondownloader_plugin.fanficdownloader.configurable import Configuration
from calibre_plugins.fanfictiondownloader_plugin.fanficdownloader.epubutils import get_dcsource_chaptercount, get_update_data
from calibre_plugins.fanfictiondownloader_plugin.fanficdownloader.geturls import get_urls_from_page
if sys.version_info < (2, 5):
print "This program requires Python 2.5 or newer."
@@ -48,15 +55,23 @@ def writeStory(config,adapter,writeformat,metaonly=False,outstream=None):
del writer
return output_filename
def main():
def main(argv,
parser=None,
passed_defaultsini=None,
passed_personalini=None):
# read in args, anything starting with -- will be treated as --<varible>=<value>
usage = "usage: %prog [options] storyurl"
parser = OptionParser(usage)
if not parser:
parser = OptionParser("usage: %prog [options] storyurl")
parser.add_option("-f", "--format", dest="format", default="epub",
help="write story as FORMAT, epub(default), text or html", metavar="FORMAT")
help="write story as FORMAT, epub(default), mobi, text or html", metavar="FORMAT")
if passed_defaultsini:
config_help="read config from specified file(s) in addition to calibre plugin personal.ini, ~/.fanficdownloader/personal.ini, and ./personal.ini"
else:
config_help="read config from specified file(s) in addition to ~/.fanficdownloader/defaults.ini, ~/.fanficdownloader/personal.ini, ./defaults.ini, and ./personal.ini"
parser.add_option("-c", "--config",
action="append", dest="configfile", default=None,
help="read config from specified file(s) in addition to ~/.fanficdownloader/defaults.ini, ~/.fanficdownloader/personal.ini, ./defaults.ini, ./personal.ini", metavar="CONFIG")
help=config_help, metavar="CONFIG")
parser.add_option("-b", "--begin", dest="begin", default=None,
help="Begin with Chapter START", metavar="START")
parser.add_option("-e", "--end", dest="end", default=None,
@@ -69,13 +84,13 @@ def main():
help="Retrieve metadata and stop. Or, if --update-epub, update metadata title page only.",)
parser.add_option("-u", "--update-epub",
action="store_true", dest="update",
help="Update an existing epub with new chapter, give epub filename instead of storyurl.",)
help="Update an existing epub with new chapters, give epub filename instead of storyurl.",)
parser.add_option("--update-cover",
action="store_true", dest="updatecover",
help="Update cover in an existing epub, otherwise existing cover (if any) is used on update. Only valid with --update-epub.",)
parser.add_option("--force",
action="store_true", dest="force",
help="Force overwrite or update of an existing epub, download and overwrite all chapters.",)
help="Force overwrite of an existing epub, download and overwrite all chapters.",)
parser.add_option("-l", "--list",
action="store_true", dest="list",
help="Get list of valid story URLs from page given.",)
@@ -83,7 +98,7 @@ def main():
action="store_true", dest="debug",
help="Show debug output while downloading.",)
(options, args) = parser.parse_args()
(options, args) = parser.parse_args(argv)
if not options.debug:
logger = logging.getLogger("fanficdownloader")
@@ -107,12 +122,18 @@ def main():
conflist = []
homepath = join(expanduser("~"),".fanficdownloader")
if passed_defaultsini:
configuration.readfp(passed_defaultsini)
if isfile(join(homepath,"defaults.ini")):
conflist.append(join(homepath,"defaults.ini"))
if isfile("defaults.ini"):
conflist.append("defaults.ini")
if passed_personalini:
configuration.readfp(passed_personalini)
if isfile(join(homepath,"personal.ini")):
conflist.append(join(homepath,"personal.ini"))
if isfile("personal.ini"):
@@ -155,9 +176,7 @@ def main():
return
try:
adapter = adapters.getAdapter(configuration,url)
adapter.setChaptersRange(options.begin,options.end)
## Check for include_images and absence of PIL, give warning.
@@ -173,7 +192,6 @@ def main():
print "You have include_images enabled, but Python Image Library(PIL) isn't found.\nImages will be included full size in original format.\nContinue? (y/n)?"
if not sys.stdin.readline().strip().lower().startswith('y'):
return
## three tries, that's enough if both user/pass & is_adult needed,
## or a couple tries of one or the other
@@ -243,5 +261,5 @@ def main():
if __name__ == "__main__":
#import time
#start = time.time()
main()
main(sys.argv[1:])
#print("Total time seconds:%f"%(time.time()-start))
+4 -4
View File
@@ -151,9 +151,9 @@ getNormalStoryURL.__dummyconfig = None
def getAdapter(config,url):
logger.debug("trying url:"+url)
#logger.debug("trying url:"+url)
(cls,fixedurl) = getClassFor(url)
logger.debug("fixedurl:"+fixedurl)
#logger.debug("fixedurl:"+fixedurl)
if cls:
adapter = cls(config,fixedurl) # raises InvalidStoryURL
return adapter
@@ -187,11 +187,11 @@ def getClassFor(url):
cls = getClassFromList(domain)
if not cls and domain.startswith("www."):
domain = domain.replace("www.","")
logger.debug("trying site:without www: "+domain)
#logger.debug("trying site:without www: "+domain)
cls = getClassFromList(domain)
fixedurl = fixedurl.replace("http://www.","http://")
if not cls:
logger.debug("trying site:www."+domain)
#logger.debug("trying site:www."+domain)
cls = getClassFromList("www."+domain)
fixedurl = fixedurl.replace("http://","http://www.")
@@ -195,6 +195,7 @@ class AdAstraFanficComSiteAdapter(BaseSiteAdapter):
for a in storyas:
if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
self.setSeries(series_name, i)
self.story.setMetadata('seriesUrl',series_url)
break
i+=1
@@ -295,6 +295,7 @@ class ArchiveOfOurOwnOrgAdapter(BaseSiteAdapter):
series_url = 'http://'+self.host+'/fanfic/'+b['href']
series_index = int(a.text.split(' ')[1])
self.setSeries(series_name, series_index)
self.story.setMetadata('seriesUrl',series_url)
except:
# I find it hard to care if the series parsing fails
@@ -68,7 +68,6 @@ class ArchiveSkyeHawkeComAdapter(BaseSiteAdapter):
@classmethod
def getAcceptDomains(cls):
# mobile.fimifction.com isn't actually a valid domain, but we can still get the story id from URLs anyway
return ['archive.skyehawke.com','www.skyehawke.com']
def getSiteExampleURLs(self):
@@ -311,6 +311,7 @@ class BloodTiesFansComAdapter(BaseSiteAdapter): # XXX
for a in storyas:
if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
self.setSeries(series_name, i)
self.story.setMetadata('seriesUrl',series_url)
break
i+=1
@@ -284,6 +284,7 @@ class CastleFansOrgAdapter(BaseSiteAdapter): # XXX
for a in storyas:
if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
self.setSeries(series_name, i)
self.story.setMetadata('seriesUrl',series_url)
break
i+=1
@@ -212,6 +212,7 @@ class ChaosSycophantHexComAdapter(BaseSiteAdapter):
for a in storyas:
if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
self.setSeries(series_name, i)
self.story.setMetadata('seriesUrl',series_url)
break
i+=1
@@ -252,6 +252,7 @@ class DarkSolaceOrgAdapter(BaseSiteAdapter):
if 'contact.php' not in a['href'] and 'index' not in a['href']:
if ('viewstory.php?sid='+self.story.getMetadata('storyId')) in a['href']:
self.setSeries(series_name, i)
self.story.setMetadata('seriesUrl',series_url)
break
i+=1
@@ -218,6 +218,7 @@ class DestinysGatewayComAdapter(BaseSiteAdapter):
for a in storyas:
if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
self.setSeries(series_name, i)
self.story.setMetadata('seriesUrl',series_url)
break
i+=1
+47 -7
View File
@@ -81,6 +81,44 @@ class DokugaComAdapter(BaseSiteAdapter):
def getSiteURLPattern(self):
return r"http://"+self.getSiteDomain()+"/(fanfiction|spark)?/story/\d+/?\d+?$"
## Login seems to be reasonably standard across eFiction sites.
def needToLoginCheck(self, data):
if 'The author has disabled anonymous viewing for this story.' in data:
return True
else:
return False
def performLogin(self, url,soup):
params = {}
if self.password:
params['username'] = self.username
params['passwd'] = self.password
else:
params['username'] = self.getConfig("username")
params['passwd'] = self.getConfig("password")
params['Submit'] = 'Submit'
# copy all hidden input tags to pick up appropriate tokens.
for tag in soup.findAll('input',{'type':'hidden'}):
params[tag['name']] = tag['value']
loginUrl = 'http://' + self.getSiteDomain() + '/fanfiction'
logger.debug("Will now login to URL (%s) as (%s)" % (loginUrl,
params['username']))
d = self._postUrl(loginUrl, params)
if "Your session has expired. Please log in again." in d:
d = self._postUrl(loginUrl, params)
if "Logout" not in d : #Member Account
logger.info("Failed to login to URL %s as %s" % (loginUrl,
params['username']))
raise exceptions.FailedToLogin(url,params['username'])
return False
else:
return True
## Getting the chapter list and the meta data, plus 'is adult' checking.
def extractChapterUrlsAndMetadata(self):
@@ -97,12 +135,18 @@ class DokugaComAdapter(BaseSiteAdapter):
raise exceptions.StoryDoesNotExist(self.url)
else:
raise e
# use BeautifulSoup HTML parser to make everything easier to find.
soup = bs.BeautifulSoup(data)
if self.needToLoginCheck(data):
# need to log in for this one.
self.performLogin(url,soup)
data = self._fetchUrl(url)
soup = bs.BeautifulSoup(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.")
# use BeautifulSoup HTML parser to make everything easier to find.
soup = bs.BeautifulSoup(data)
# print data
# Now go hunting for all the meta data and the chapter list.
@@ -218,10 +262,6 @@ class DokugaComAdapter(BaseSiteAdapter):
a=div.text.split('Words ')
if len(a)==2: self.story.setMetadata('numWords', a[1])
# grab the text for an individual chapter.
def getChapterText(self, url):
@@ -273,6 +273,7 @@ class DracoAndGinnyComAdapter(BaseSiteAdapter):
if 'contact.php' not in a['href'] and 'index' not in a['href']:
if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
self.setSeries(series_name, i)
self.story.setMetadata('seriesUrl',series_url)
break
i+=1
@@ -274,6 +274,7 @@ class DramioneOrgAdapter(BaseSiteAdapter):
for a in storyas:
if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
self.setSeries(series_name, i)
self.story.setMetadata('seriesUrl',series_url)
break
i+=1
@@ -195,6 +195,7 @@ class EfictionEstelielDeAdapter(BaseSiteAdapter):
name=seriessoup.find('div', {'id' : 'pagetitle'})
name.find('a').extract()
self.setSeries(name.text.split(' by[')[0], i)
self.story.setMetadata('seriesUrl',series_url)
i=0
break
i+=1
@@ -280,6 +280,7 @@ class EFPFanFicNet(BaseSiteAdapter):
for a in storyas:
if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId'))+'&i=1':
self.setSeries(series_name, i)
self.story.setMetadata('seriesUrl',series_url)
break
i+=1
@@ -230,6 +230,7 @@ class ErosnSapphoSycophantHexComAdapter(BaseSiteAdapter):
if 'contact.php' not in a['href'] and 'index' not in a['href']:
if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
self.setSeries(series_name, i)
self.story.setMetadata('seriesUrl',series_url)
break
i+=1
@@ -43,10 +43,10 @@ class FicwadComSiteAdapter(BaseSiteAdapter):
@staticmethod
def getSiteDomain():
return 'www.ficwad.com'
return 'ficwad.com'
def getSiteExampleURLs(self):
return "http://www.ficwad.com/story/137169"
return "http://ficwad.com/story/137169"
def getSiteURLPattern(self):
return re.escape(r"http://"+self.getSiteDomain())+"/story/\d+?$"
@@ -28,8 +28,6 @@ from .. import BeautifulSoup as bs
from ..htmlcleanup import stripHTML
from .. import exceptions as exceptions
from ..bbcodeutils.bbcodeparser import bbcodeparser
from base_adapter import BaseSiteAdapter, makeDate
def getClass():
@@ -181,10 +179,11 @@ class FimFictionNetSiteAdapter(BaseSiteAdapter):
self.setCoverImage(self.url,coverurl)
# the fimfic API gives bbcode for desc, not html.
# btw, bbcode honors newlines, html doesn't. change newlines to br tags.
self.setDescription(self.url,
bbcodeparser().parse(storyMetadata["description"]).html(doDeepCopy=False).replace('\r','').replace('\n','<br />'))
# fimf has started including extra stuff inside the description div.
descdivstr = "%s"%soup.find("div", {"class":"description"})
hrstr="<hr />"
descdivstr = '<div class="description">'+descdivstr[descdivstr.index(hrstr)+len(hrstr):]
self.setDescription(self.url,descdivstr)
# Dates are in Unix time
# Take the publish date from the first chapter posted
@@ -193,7 +192,7 @@ class FimFictionNetSiteAdapter(BaseSiteAdapter):
rawDateUpdated = storyMetadata["date_modified"]
self.story.setMetadata("dateUpdated", datetime.fromtimestamp(rawDateUpdated))
chars = soup.find("div", {"class":"story"})
chars = soup.find("div", {"class":"inner_data"})
# fimfic stopped putting the char name on or around the char
# icon now for some reason. Pull it from the image name with
# some heuristics.
@@ -219,7 +218,7 @@ class FimFictionNetSiteAdapter(BaseSiteAdapter):
def getChapterText(self, url):
logger.debug('Getting chapter text from: %s' % url)
soup = bs.BeautifulSoup(self._fetchUrl(url),selfClosingTags=('br','hr')).find('div', {'id' : 'chapter_container'})
soup = bs.BeautifulSoup(self._fetchUrl(url),selfClosingTags=('br','hr')).find('div', {'class' : 'chapter_content'})
if soup == None:
raise exceptions.FailedToDownload("Error downloading Chapter: %s! Missing required element!" % url)
return self.utf8FromSoup(url,soup)
@@ -187,6 +187,7 @@ class FineStoriesComAdapter(BaseSiteAdapter):
a = lc4.find('a', href=re.compile(r"/library/show_series.php\?id=\d+"))
i = a.parent.text.split('(')[1].split(')')[0]
self.setSeries(a.text, i)
self.story.setMetadata('seriesUrl','http://'+self.host+a['href'])
except:
pass
try:
@@ -275,6 +275,7 @@ class GrangerEnchantedCom(BaseSiteAdapter):
if 'contact.php' not in a['href'] and 'index' not in a['href']:
if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
self.setSeries(series_name, i)
self.story.setMetadata('seriesUrl',series_url)
break
i+=1
@@ -206,6 +206,7 @@ class HLFictionNetAdapter(BaseSiteAdapter):
if 'contact.php' not in a['href'] and 'index' not in a['href']:
if ('viewstory.php?sid='+self.story.getMetadata('storyId')) in a['href']:
self.setSeries(series_name, i)
self.story.setMetadata('seriesUrl',series_url)
break
i+=1
@@ -193,6 +193,7 @@ class HPFanficArchiveComAdapter(BaseSiteAdapter):
if 'contact.php' not in a['href'] and 'index' not in a['href']:
if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
self.setSeries(series_name, i)
self.story.setMetadata('seriesUrl',series_url)
break
i+=1
@@ -264,6 +264,7 @@ class ImagineEFicComAdapter(BaseSiteAdapter):
if 'contact.php' not in a['href'] and 'index' not in a['href']:
if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
self.setSeries(series_name, i)
self.story.setMetadata('seriesUrl',series_url)
break
i+=1
@@ -234,6 +234,7 @@ class JLAUnlimitedComAdapter(BaseSiteAdapter):
for a in storyas:
if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
self.setSeries(series_name, i)
self.story.setMetadata('seriesUrl',series_url)
break
i+=1
@@ -285,6 +285,7 @@ class KSArchiveComAdapter(BaseSiteAdapter): # XXX
if 'contact.php' not in a['href'] and 'index' not in a['href']:
if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
self.setSeries(series_name, i)
self.story.setMetadata('seriesUrl',series_url)
break
i+=1
@@ -225,6 +225,7 @@ class LibraryOfMoriaComAdapter(BaseSiteAdapter):
if 'contact.php' not in a['href'] and 'index' not in a['href']:
if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
self.setSeries(series_name, i)
self.story.setMetadata('seriesUrl',series_url)
break
i+=1
@@ -212,6 +212,7 @@ class LumosSycophantHexComAdapter(BaseSiteAdapter):
for a in storyas:
if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
self.setSeries(series_name, i)
self.story.setMetadata('seriesUrl',series_url)
break
i+=1
@@ -268,6 +268,7 @@ class MerlinFicDtwinsCoUk(BaseSiteAdapter):
if 'contact.php' not in a['href'] and 'index' not in a['href']:
if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
self.setSeries(series_name, i)
self.story.setMetadata('seriesUrl',series_url)
break
i+=1
@@ -260,6 +260,7 @@ class MidnightwhispersCaAdapter(BaseSiteAdapter): # XXX
if 'contact.php' not in a['href'] and 'index' not in a['href']:
if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
self.setSeries(series_name, i)
self.story.setMetadata('seriesUrl',series_url)
break
i+=1
@@ -306,6 +306,7 @@ class MuggleNetComAdapter(BaseSiteAdapter): # XXX
if 'contact.php' not in a['href'] and 'index' not in a['href']:
if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
self.setSeries(series_name, i)
self.story.setMetadata('seriesUrl',series_url)
break
i+=1
@@ -163,6 +163,7 @@ class NationalLibraryNetAdapter(BaseSiteAdapter):
if 'Series' in label:
self.setSeries(stripHTML(value.nextSibling), value.nextSibling.nextSibling.string[2:])
self.story.setMetadata('seriesUrl','http://'+self.host+'/'+value.nextSibling['href'])
asoup = bs.BeautifulSoup(self._fetchUrl(self.story.getMetadata('authorUrl')))
story=asoup.find('a', href=re.compile(r'viewstory.php\?storyid='+self.story.getMetadata('storyId')))
@@ -164,6 +164,7 @@ class NCISFicComAdapter(BaseSiteAdapter):
if 'Series' in label:
if "No Series" not in value.nextSibling.string:
self.setSeries(stripHTML(value.nextSibling), value.nextSibling.nextSibling.string[2:])
self.story.setMetadata('seriesUrl','http://'+self.host+'/'+value.nextSibling['href'])
asoup = bs.BeautifulSoup(self._fetchUrl(self.story.getMetadata('authorUrl')))
story=asoup.find('a', href=re.compile(r'viewstory.php\?storyid='+self.story.getMetadata('storyId')))
@@ -193,7 +193,7 @@ class NCISFictionNetAdapter(BaseSiteAdapter):
series_name = a.find('a').string
i = a.text.split('#')[1]
self.setSeries(series_name, i)
self.story.setMetadata('seriesUrl','http://'+self.host+'/'+a.find('a')['href'])
except:
# I find it hard to care if the series parsing fails
pass
@@ -264,6 +264,7 @@ class NfaCommunityComAdapter(BaseSiteAdapter): # XXX
if 'contact.php' not in a['href'] and 'index' not in a['href']:
if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
self.setSeries(series_name, i)
self.story.setMetadata('seriesUrl',series_url)
break
i+=1
@@ -244,6 +244,7 @@ class OneDirectionFanfictionComAdapter(BaseSiteAdapter):
for a in storyas:
if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
self.setSeries(series_name, i)
self.story.setMetadata('seriesUrl',series_url)
break
i+=1
@@ -275,6 +275,7 @@ class PommeDeSangComAdapter(BaseSiteAdapter):
if 'contact.php' not in a['href'] and 'index' not in a['href']:
if ('viewstory.php?sid='+self.story.getMetadata('storyId')) in a['href']:
self.setSeries(series_name, i)
self.story.setMetadata('seriesUrl',series_url)
break
i+=1
@@ -225,6 +225,7 @@ class PonyFictionArchiveNetAdapter(BaseSiteAdapter):
if 'contact.php' not in a['href'] and 'index' not in a['href']:
if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
self.setSeries(series_name, i)
self.story.setMetadata('seriesUrl',series_url)
break
i+=1
@@ -182,6 +182,7 @@ class PotionsAndSnitchesNetSiteAdapter(BaseSiteAdapter):
for a in storyas:
if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
self.setSeries(series_name, i)
self.story.setMetadata('seriesUrl',series_url)
break
i+=1
@@ -228,6 +228,7 @@ class PretenderCenterComAdapter(BaseSiteAdapter):
if 'contact.php' not in a['href'] and 'index' not in a['href']:
if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
self.setSeries(series_name, i)
self.story.setMetadata('seriesUrl',series_url)
break
i+=1
@@ -193,6 +193,7 @@ class PrisonBreakFicNetAdapter(BaseSiteAdapter):
for a in storyas:
if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
self.setSeries(series_name, i)
self.story.setMetadata('seriesUrl',series_url)
break
i+=1
@@ -223,6 +223,7 @@ class PsychFicComAdapter(BaseSiteAdapter):
if 'contact.php' not in a['href'] and 'index' not in a['href']:
if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
self.setSeries(series_name, i)
self.story.setMetadata('seriesUrl',series_url)
break
i+=1
@@ -236,6 +236,7 @@ class QafFicComAdapter(BaseSiteAdapter):
name=seriessoup.find('div', {'id' : 'pagetitle'})
name.find('a').extract()
self.setSeries(name.text.split(' by[')[0], i)
self.story.setMetadata('seriesUrl',series_url)
i=0
break
i+=1
@@ -207,6 +207,7 @@ class SamDeanArchiveNuAdapter(BaseSiteAdapter):
for a in storyas:
if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
self.setSeries(series_name, i)
self.story.setMetadata('seriesUrl',series_url)
break
i+=1
@@ -222,6 +222,7 @@ class ScarvesAndCoffeeNetAdapter(BaseSiteAdapter):
if 'contact.php' not in a['href'] and 'index' not in a['href']:
if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
self.setSeries(series_name, i)
self.story.setMetadata('seriesUrl',series_url)
break
i+=1
@@ -233,6 +233,7 @@ class SG1HeliopolisComAdapter(BaseSiteAdapter):
if 'contact.php' not in a['href'] and 'index' not in a['href']:
if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
self.setSeries(series_name, i)
self.story.setMetadata('seriesUrl',series_url)
break
i+=1
@@ -226,6 +226,7 @@ class SinfulDesireOrgAdapter(BaseSiteAdapter):
if 'contact.php' not in a['href'] and 'index' not in a['href']:
if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
self.setSeries(series_name, i)
self.story.setMetadata('seriesUrl',series_url)
break
i+=1
@@ -215,6 +215,7 @@ class SiyeCoUkAdapter(BaseSiteAdapter): # XXX
for a in storyas:
if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
self.setSeries(series_name, i)
self.story.setMetadata('seriesUrl',series_url)
break
i+=1
@@ -212,6 +212,7 @@ class SquidgeOrgPejaAdapter(BaseSiteAdapter):
for a in storyas:
if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
self.setSeries(series_name, i)
self.story.setMetadata('seriesUrl',series_url)
break
i+=1
@@ -204,6 +204,7 @@ class StargateAtlantisOrgAdapter(BaseSiteAdapter):
for a in storyas:
if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
self.setSeries(series_name, i)
self.story.setMetadata('seriesUrl',series_url)
break
i+=1
@@ -249,6 +249,7 @@ class SVUFictionComAdapter(BaseSiteAdapter):
if 'contact.php' not in a['href'] and 'index' not in a['href']:
if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
self.setSeries(series_name, i)
self.story.setMetadata('seriesUrl',series_url)
break
i+=1
@@ -220,6 +220,7 @@ class TenhawkPresentsComSiteAdapter(BaseSiteAdapter):
for a in storyas:
if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
self.setSeries(series_name, i)
self.story.setMetadata('seriesUrl',series_url)
break
i+=1
+44 -19
View File
@@ -101,8 +101,10 @@ Some more longer description. "I suck at summaries!" "Better than it sounds!"
}
self.story.setMetadata('language',langs[idnum%len(langs)])
self.setSeries('The Great Test',idnum)
self.story.setMetadata('seriesUrl','http://test1.com?seriesid=1')
if idnum == 0:
self.setSeries("A Nook Hyphen Test "+self.story.getMetadata('dateCreated'),idnum)
self.story.setMetadata('seriesUrl','http://test1.com?seriesid=0')
self.story.setMetadata('rating','Tweenie')
@@ -115,6 +117,10 @@ Some more longer description. "I suck at summaries!" "Better than it sounds!"
self.story.addToList('authorUrl','http://author/url')
self.story.addToList('authorUrl','http://author/url-2')
self.story.addToList('category','Power Rangers')
self.story.addToList('category','SG-1')
self.story.addToList('genre','Porn')
self.story.addToList('genre','Drama')
else:
self.story.setMetadata('authorId','98765')
self.story.setMetadata('authorUrl','http://author/url')
@@ -122,21 +128,36 @@ Some more longer description. "I suck at summaries!" "Better than it sounds!"
self.story.addToList('warnings','Swearing')
self.story.addToList('warnings','Violence')
self.story.addToList('category','Harry Potter')
self.story.addToList('category','Furbie')
self.story.addToList('category','Crossover')
self.story.addToList('category',u'Puella Magi Madoka Magica/魔法少女まどか★マギカ')
self.story.addToList('category',u'Magical Girl Lyrical Nanoha')
if self.story.getMetadata('storyId') == '80':
self.story.addToList('category',u'Rizzoli & Isles')
self.story.addToList('characters','J. Rizzoli')
elif self.story.getMetadata('storyId') == '81':
self.story.addToList('category',u'Pitch Perfect')
self.story.addToList('characters','Chloe B.')
elif self.story.getMetadata('storyId') == '83':
self.story.addToList('category',u'Rizzoli & Isles')
self.story.addToList('characters','J. Rizzoli')
self.story.addToList('category',u'Pitch Perfect')
self.story.addToList('characters','Chloe B.')
elif self.story.getMetadata('storyId') == '82':
self.story.addToList('characters','Henry (Once Upon a Time)')
self.story.addToList('category',u'Once Upon a Time (TV)')
else:
self.story.addToList('category','Harry Potter')
self.story.addToList('category','Furbie')
self.story.addToList('category','Crossover')
self.story.addToList('category',u'Puella Magi Madoka Magica/魔法少女まどか★マギカ')
self.story.addToList('category',u'Magical Girl Lyrical Nanoha')
self.story.addToList('category',u'Once Upon a Time (TV)')
self.story.addToList('characters','Bob Smith')
self.story.addToList('characters','George Johnson')
self.story.addToList('characters','Fred Smythe')
self.story.addToList('genre','Fantasy')
self.story.addToList('genre','Comedy')
self.story.addToList('genre','Sci-Fi')
self.story.addToList('genre','Noir')
self.story.addToList('characters','Bob Smith')
self.story.addToList('characters','George Johnson')
self.story.addToList('characters','Fred Smythe')
self.story.addToList('listX','xVal1')
self.story.addToList('listX','xVal2')
self.story.addToList('listX','xVal3')
@@ -162,9 +183,9 @@ Some more longer description. "I suck at summaries!" "Better than it sounds!"
('Chapter 3, Over Cinnabar',self.url+"&chapter=4"),
('Chapter 4',self.url+"&chapter=5"),
('Chapter 5',self.url+"&chapter=6"),
#('Chapter 6',self.url+"&chapter=7"),
#('Chapter 7',self.url+"&chapter=8"),
#('Chapter 8',self.url+"&chapter=9"),
('Chapter 6',self.url+"&chapter=7"),
('Chapter 7',self.url+"&chapter=8"),
('Chapter 8',self.url+"&chapter=9"),
#('Chapter 9',self.url+"&chapter=0"),
#('Chapter 0',self.url+"&chapter=a"),
#('Chapter a',self.url+"&chapter=b"),
@@ -187,9 +208,6 @@ Some more longer description. "I suck at summaries!" "Better than it sounds!"
def getChapterText(self, url):
logger.debug('Getting chapter text from: %s' % url)
if self.story.getMetadata('storyId') == '667':
raise exceptions.FailedToDownload("Error downloading Chapter: %s!" % url)
if self.story.getMetadata('storyId').startswith('670') or \
self.story.getMetadata('storyId').startswith('672'):
time.sleep(1.0)
@@ -202,7 +220,7 @@ Some more longer description. "I suck at summaries!" "Better than it sounds!"
<p>http://test1.com?sid=664 - Crazy string title</p>
<p>http://test1.com?sid=665 - raises AdultCheckRequired</p>
<p>http://test1.com?sid=666 - raises StoryDoesNotExist</p>
<p>http://test1.com?sid=667 - raises FailedToDownload on chapter 1</p>
<p>http://test1.com?sid=667 - raises FailedToDownload on chapters 2+</p>
<p>http://test1.com?sid=668 - raises FailedToLogin unless username='Me'</p>
<p>http://test1.com?sid=669 - Succeeds with Updated Date=now</p>
<p>http://test1.com?sid=670 - Succeeds, but sleeps 2sec on each chapter</p>
@@ -211,7 +229,10 @@ Some more longer description. "I suck at summaries!" "Better than it sounds!"
<p>http://test1.com?sid=671 - Succeeds, but sleeps 2sec metadata only</p>
<p>http://test1.com?sid=672 - Succeeds, quick meta, sleeps 2sec chapters only</p><p>http://test1.com?sid=0 - Succeeds, generates some text specifically for testing hyphenation problems with Nook STR/STRwG</p><p>Odd sid's will be In-Progress, evens complete. sid&lt;10 will be assigned one of four languages and included in a series.</p>
<p>http://test1.com?sid=672 - Succeeds, quick meta, sleeps 2sec chapters only</p>
<p>http://test1.com?sid=673 - Succeeds, multiple authors, extra categories, genres</p>
<p>http://test1.com?sid=0 - Succeeds, generates some text specifically for testing hyphenation problems with Nook STR/STRwG</p>
<p>Odd sid's will be In-Progress, evens complete. sid&lt;10 will be assigned one of four languages and included in a series.</p>
</div>
'''
elif self.story.getMetadata('storyId') == '0':
@@ -226,9 +247,13 @@ Some more longer description. "I suck at summaries!" "Better than it sounds!"
<br />
'''
else:
if self.story.getMetadata('storyId') == '667':
raise exceptions.FailedToDownload("Error downloading Chapter: %s!" % url)
text=u'''
<div>
<h3>Chapter title from site</h3>
<p>Timestamp:'''+datetime.datetime.now().strftime("%Y-%m-%d %H:%M:%S")+'''</p>
<p>Lorem '''+self.crazystring+u''' <i>italics</i>, <b>bold</b>, <u>underline</u> consectetur adipisicing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non proident, sunt in culpa qui officia deserunt mollit anim id est laborum.</p>
br breaks<br><br>
Puella Magi Madoka Magica/魔法少女まどかマギカ
@@ -189,6 +189,7 @@ class TheAlphaGateComAdapter(BaseSiteAdapter):
for a in storyas:
if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
self.setSeries(series_name, i)
self.story.setMetadata('seriesUrl',series_url)
break
i+=1
@@ -283,6 +283,7 @@ class TheHookupZoneNetAdapter(BaseSiteAdapter): # XXX
for a in storyas:
if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
self.setSeries(series_name, i)
self.story.setMetadata('seriesUrl',series_url)
break
i+=1
@@ -263,6 +263,7 @@ class TheQuidditchPitchOrgAdapter(BaseSiteAdapter): # XXX
for a in storyas:
if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
self.setSeries(series_name, i)
self.story.setMetadata('seriesUrl',series_url)
break
i+=1
@@ -227,6 +227,7 @@ class TheWritersCoffeeShopComSiteAdapter(BaseSiteAdapter):
for a in storyas:
if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
self.setSeries(series_name, i)
self.story.setMetadata('seriesUrl',series_url)
break
i+=1
@@ -100,8 +100,8 @@ class TwistingTheHellmouthSiteAdapter(BaseSiteAdapter):
if "Stories Published" not in d : #Member Account
logger.info("Failed to login to URL %s as %s" % (loginUrl,
params['penname']))
raise exceptions.FailedToLogin(url,params['penname'])
params['urealname']))
raise exceptions.FailedToLogin(self.url,params['urealname'])
return False
else:
return True
@@ -255,9 +255,7 @@ class TwistingTheHellmouthSiteAdapter(BaseSiteAdapter):
pseries.text)
if m:
self.setSeries(m.group('series'),m.group('num'))
return
self.story.setMetadata('seriesUrl',"http://"+self.host+pseries.find('a')['href'])
def getChapterText(self, url):
logger.debug('Getting chapter text from: %s' % url)
@@ -163,6 +163,7 @@ class TwilightArchivesComAdapter(BaseSiteAdapter):
for a in storyas:
if a['href'] == ('/read/'+self.story.getMetadata('storyId')):
self.setSeries(series_name, i)
self.story.setMetadata('seriesUrl',series_url)
break
i+=1
@@ -217,6 +217,7 @@ class TwilightedNetSiteAdapter(BaseSiteAdapter):
for a in storyas:
if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
self.setSeries(series_name, i)
self.story.setMetadata('seriesUrl',series_url)
break
i+=1
@@ -246,6 +246,7 @@ class TwiwriteNetSiteAdapter(BaseSiteAdapter):
for a in storyas:
if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
self.setSeries(series_name, i)
self.story.setMetadata('seriesUrl',series_url)
break
i+=1
@@ -206,6 +206,7 @@ class WalkingThePlankOrgAdapter(BaseSiteAdapter):
for a in storyas:
if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
self.setSeries(series_name, i)
self.story.setMetadata('seriesUrl',series_url)
break
i+=1
@@ -204,6 +204,7 @@ class WhoficComSiteAdapter(BaseSiteAdapter):
for a in storyas:
if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
self.setSeries(series_name, i)
self.story.setMetadata('seriesUrl',series_url)
break
i+=1
@@ -277,6 +277,7 @@ class WizardTalesNetAdapter(BaseSiteAdapter):
if 'contact.php' not in a['href'] and 'index' not in a['href']:
if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
self.setSeries(series_name, i)
self.story.setMetadata('seriesUrl',series_url)
break
i+=1
@@ -194,6 +194,7 @@ class WolverineAndRogueComAdapter(BaseSiteAdapter):
if 'contact.php' not in a['href'] and 'index' not in a['href']:
if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
self.setSeries(series_name, i)
self.story.setMetadata('seriesUrl',series_url)
break
i+=1
@@ -196,6 +196,7 @@ class WraithBaitComAdapter(BaseSiteAdapter):
for a in storyas:
if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
self.setSeries(series_name, i)
self.story.setMetadata('seriesUrl',series_url)
break
i+=1
-325
View File
@@ -1,325 +0,0 @@
#!/usr/bin/python
# -*- coding: UTF-8 -*-
#
# Author: Pau Sanchez (contact@pausanchez.com)
# Version: v1.0
# Last Modified: 2010/09/15
#
# For the latest version check out:
# http://www.codigomanso.com/en/projects
#
# My blog:
# http://www.codigomanso.com/en/ - English Version
# http://www.codigomanso.com/es/ - Spanish Version
#
import sys
import os
import re
import urllib
class bbcode2html:
'''
This class gets a parsed BBCode and transforms it to valid HTML
Useful functions of this class:
html
convertToHTML
Example:
> parser = bbcodeparser ()
> parser.parse ('[b]bold[/b]')
> bbcode2html (parser).html()
<b>bold</b>
# This is faster for huge strings but changes the parser object internally
> bbcode2html (parser).html(doDeepCopy = False)
<b>bold</b>
'''
def __init__ (self, parser):
self._parser = parser
return
def html (self, allowClassAttr = False, doDeepCopy = True, parser = None):
'''
Convert current parsed code to HTML
Example:
code = bbcodeparser ('[b]bold[/b]')
code.html() -> '<b>bold</b>'
'''
if parser is None:
parser = self._parser
tokens = parser
if instanceof (parser, bbcodeparser):
tokens = parser.getTokens()
return bbcode2html.convertToHTML (tokens, allowClassAttr = allowClassAttr, doDeepCopy = doDeepCopy)
@staticmethod
def htmlString (string):
toReplace = {
u'<' : '&lt;',
u'>' : '&gt;',
u'"' : "&quot;",
u'&' : "&amp;"
}
for entity in toReplace:
string = string.replace(entity, toReplace[entity])
return string
@staticmethod
def getValidTags ():
simpleTags = ['b', 'u', 'i', 'sup', 'sub', 'ul', 'ol', 'li', 'table', 'tr', 'th', 'td', 'h1', 'h2', 'h3', 'h4', 'h5', 'h6']
validTags = {
'p' : { 'color' : 'color', 'size' : 'size', 'font' : 'font' },
'color' : { 'color' : 'color' },
'size' : { 'size' : 'size' },
'font' : { 'font' : 'font' },
'img' : { 'alt' : 'alt', 'title' : 'title', 'width' : 'width' , 'height' : 'height', 'img' : 'img'},
'url' : { 'href' : 'href', 'url' : 'href', 'link' : 'href', 'title' : 'title' },
's' : { },
'code' : { },
'quote' : { },
'list' : { 'list' : 'type' },
'email' : { 'email': 'href'},
'google' : { 'google': 'google'},
'wikipedia' : { 'wikipedia' : 'wikipedia', 'language' : 'language', 'lang' : 'lang'}
}
for tag in simpleTags:
validTags[tag] = { }
return validTags
@staticmethod
def convertToHTML (tokens, allowClassAttr = False, validTags = None, doDeepCopy = True):
'''
Convert internally parsed BBCode to XHTML
@doDeepCopy
True: it does a deep copy of tokens so this list will remain unchanged
False: tokens will be modified internally, but the output will be produced like 5x faster
it's a good idea to use False only when this is the last operation
'''
# do a deep copy
if doDeepCopy:
import copy
tokens = copy.deepcopy (tokens)
# filter invalid tags and attributes
if validTags is None:
validTags = bbcode2html.getValidTags()
bbcode2html._filterInvalidTagsAndAttributes (tokens, validTags, allowClassAttr)
# Start to convert
index = 0
tokenLength = len (tokens)
# use a list for the output (an order of magnitude faster than using string concatenation)
htmlList = []
lastListOpener = []
while index < tokenLength:
if isinstance (tokens [index], basestring):
htmlList.append (bbcode2html.htmlString (tokens [index]))
index += 1
continue
token = tokens[index]
tag = token['tag'] # opening or closing simple tag. e.g: 'b', '/b', '/u', ...
tagName = (tag[1:] if tag[0] == '/' else tag)
tagOpener = (u'/' if tag[0] == '/' else u'')
tokenArgs = (token['args'] if 'args' in token else {})
# opening or closing simple tag COLOR / SIZE
if (tagName in ['p', 'color', 'size', 'font']):
style = ''
style += ((u' color: ' + tokenArgs['color'] + u';') if ('color' in tokenArgs) else '')
style += ((u' font-size: ' + tokenArgs['size'] + u'pt;') if ('size' in tokenArgs) else '')
style += ((u' font-family: ' + tokenArgs['font'] + u';') if ('font' in tokenArgs) else '')
style = style.strip()
pArgs = {}
if style != '':
pArgs ['style'] = style
if 'class' in tokenArgs:
pArgs ['class'] = tokenArgs['class']
if ('args' not in token) and (tagName != 'p'):
if (tagOpener == '/'): # if closing tag, close it
htmlList.append (u'</span>')
index += 1
continue
if tagName != 'p':
tag = tagOpener + u'span'
htmlList.append (bbcode2html.xml (tag, pArgs))
# IMG tag
elif tag == 'img' and (index+2 < tokenLength):
if 'img' in tokenArgs:
# has the form of <width>x<height> ?
sizeMatch = re.match (u'^\s*(\d+)[xX](\d+)\s*$', tokenArgs['img'])
if sizeMatch is not None:
tokenArgs['width'] = sizeMatch.group(1)
tokenArgs['height'] = sizeMatch.group(2)
# then assume is the alternative text
else:
tokenArgs['alt'] = tokenArgs['img']
del tokenArgs['img']
# add the source of the image
tokenArgs ['src'] = tokens[index+1]
# [img]http://www.whatever.com/pic.jpg[/img]
htmlList.append (
bbcode2html.xml ('img', tokenArgs, soloTag=True)
)
index += 2 # skip next token and closing tag
# URL tag
elif tag == 'url':
if ('args' not in token) and (index+2 < tokenLength):
# [url]http://www.google.com[/url]
htmlList.append (bbcode2html.xml ('a', { 'href' : tokens[index+1] }))
else:
# [url=http://www.google.com]Google[/url]
# [url link=http://www.google.com title="This is Google"]Google[/url]
htmlList.append (bbcode2html.xml ('a', tokenArgs))
# URL closing tag (sometimes needed)
elif (tag == '/url') or (tag == '/email'):
htmlList.append (u'</a>')
# Email tag
elif tag == 'email':
if ('args' not in token) and (index+2 < tokenLength):
# [email]asdf@asdf.com]
htmlList.append (bbcode2html.xml ('a', { 'href' : u'mailto:' + tokens[index+1].strip() }))
else:
# [email=asdf@asfd.com]john smith[/email]
if 'href' in tokenArgs:
tokenArgs['href'] = u'mailto:' + tokenArgs['href']
htmlList.append (bbcode2html.xml ('a', tokenArgs))
elif tagName == 'list':
if tagOpener == '/':
htmlList.append (bbcode2html.xml (u'/' + lastListOpener.pop()))
else:
if ('type' not in tokenArgs):
htmlList.append (bbcode2html.xml (tagOpener + u'ul', tokenArgs))
lastListOpener.append ('ul')
else:
htmlList.append (bbcode2html.xml (tagOpener + u'ol', tokenArgs))
lastListOpener.append ('ol')
elif tagName == '*':
htmlList.append (bbcode2html.xml (tagOpener + u'li', tokenArgs))
elif (tagName == 's'):
tokenArgs['style'] = 'text-decoration: line-through;'
htmlList.append (bbcode2html.xml (tagOpener + u'span', tokenArgs))
elif (tagName == 'code'):
htmlList.append (bbcode2html.xml (tagOpener + u'pre', tokenArgs))
elif (tagName == 'quote'):
htmlList.append (bbcode2html.xml (tagOpener + u'blockquote', tokenArgs))
elif (tagName == 'google'):
htmlList.append (
bbcode2html.xml (
tagOpener + u'a',
{'href' : 'http://www.google.com/search?q=' + urllib.quote_plus (tokens[index+1])},
tokens[index+1]
)
)
index += 2
elif (tagName == 'wikipedia'):
subdomain = 'www'
for arg in ['lang', 'language', 'wikipedia']:
if arg in tokenArgs:
subdomain = tokenArgs[arg]
htmlList.append (
bbcode2html.xml (
tagOpener + u'a',
{'href' : 'http://' + subdomain + '.wikipedia.org/wiki/' + tokens[index+1].replace (' ', '_')},
tokens[index+1]
)
)
index += 2
elif (tagName in validTags):
htmlList.append (
bbcode2html.xml (tag, tokenArgs)
)
else:
# ignore this tag
pass
index += 1
return ''.join (htmlList)
@staticmethod
def _filterInvalidTagsAndAttributes (tokens, validTags, allowClassAttr):
'''
Helper function to filter out invalid attributes from the tokens list
'''
# add 'class' attribute as valid (mapping 'class' itself)
if allowClassAttr:
for attr in validTags:
validTags[attr]['class'] = 'class'
# remove invalid attributes from tokens
for tindex in range(0, len(tokens)):
if isinstance (tokens[tindex], dict) and ('args' in tokens[tindex]) and (tokens[tindex]['tag'] in validTags):
validList = validTags[tokens[tindex]['tag']]
filteredArgs = {}
for arg in tokens[tindex]['args']:
if arg in validList:
# rename the argument
filteredArgs[validList[arg]] = tokens[tindex]['args'][arg]
else:
pass # do not include this arg in the filteredArgs
tokens[tindex]['args'] = filteredArgs
return
@staticmethod
def xml (tag, attrs = {}, text = None, soloTag = False):
'''
Helper function to produce valid XML output
'''
xml = u'<' + tag.lower()
# make sure we sort attributes alphabetically (for deterministic output)
# Faster but non-deterministic:
# for (key, value) in attrs.iteritems():
# xml += u' ' + key + u'="' + value + u'"'
for key in sorted (attrs.keys()):
xml += u' ' + key + u'="' + attrs[key] + u'"'
# close tag
if text is None:
if soloTag:
xml += u' />'
else:
xml += u'>'
else:
xml += u'>' + text + u'</' + tag.lower() + '>'
return xml
@@ -1,77 +0,0 @@
#!/usr/bin/python
# -*- coding: UTF-8 -*-
#
# Author: Pau Sanchez (contact@pausanchez.com)
# Version: v1.0
# Last Modified: 2010/09/15
#
# For the latest version check out:
# http://www.codigomanso.com/en/projects
#
# My blog:
# http://www.codigomanso.com/en/ - English Version
# http://www.codigomanso.com/es/ - Spanish Version
#
import sys
import os
import re
import hashlib
class bbcodebuilder:
'''
This class helps to build BBCode programmatically.
The function names are used as the tag name, then the first parameter
is the string that goes inside the tags and any extra parameter is
appended as a parameter to the tag
Examples:
> bbcode = bbcodebuilder() # create a instance!
> print bbcode.b ('bold')
[b]bold[/b]
> print bbcode.color ('this goes in red', 'red')
[color=red]this goes in red[/color]
> print bbcode.url ('Google', 'http://www.google.com')
[url=http://www.google.com]Google[/url]
> print bbcode.alist('item 1', 'item 2')
[list=a]
[*]item 1
[*]item 2
[/list]
This solution is based on the recipe found on:
http://code.activestate.com/recipes/576831-simple-bbcode-support/
'''
def __getattr__(self, name):
'''
This is a generic getter that returns a function which gets the first parameter
as the string that goes between the tags, and extra parameters as tag parameters.
The name of the attribute is used as the tag name
'''
class bbcodebuilder_helper:
def __init__(self, name):
self._name = name
def __call__(self, string, *args):
return u'[{0}{1}]{2}[/{0}]'.format(self._name, (u'=' + u','.join(map(str, args))) if args else u'', string)
return bbcodebuilder_helper (name)
def list(self, *items):
return u'[list]' + u''.join(map(lambda item: u"\n [*]" + item, items)) + u"\n[/list]"
def nlist(self, *items):
return u'[list=1]' + u''.join(map(lambda item: u"\n [*]" + item, items)) + u"\n[/list]"
def alist(self, *items):
return u'[list=a]' + u''.join(map(lambda item: u"\n [*]" + item, items)) + u"\n[/list]"
@@ -1,258 +0,0 @@
#!/usr/bin/python
# -*- coding: utf-8 -*-
#
# Author: Pau Sanchez (contact@pausanchez.com)
# Version: v1.0
# Last Modified: 2010/09/15
#
# For the latest version check out:
# http://www.codigomanso.com/en/projects
#
# My blog:
# http://www.codigomanso.com/en/ - English Version
# http://www.codigomanso.com/es/ - Spanish Version
#
import sys
import os
import re
import hashlib
class bbcodeparser:
'''
This class parses BBCode into a internal structure to allow later processing and
conversion to HTML.
The parser tries to fix invalid code (like unclosed tags)
Useful URLs:
http://en.wikipedia.org/wiki/BBCode
http://www.bbcode.org/reference.php
Example:
> bbcode = bbcodeparser ()
> bbcode.parse ('[b]text in bold[/b]').html()
<b>text in bold</b>
# dump HTML
> bbcode.parse ('[p][color=red]text in red').html()
<p><span style="color:red;">text in red</span></p>
# dump fixed BBCode
> bbcode.parse ('[p][color=red]text in red').bbcode()
[p][color=red]text in red[/color][/p]
> bbcode.parse ('This [b][i]code[/b] will be fixed[/invalid]').bbcode()
This [b][i]code[/i][/b] will be fixed
# dump fixed bbcode
> str (bbcodeparse ('This [b][i]code[/b] will be fixed[/invalid]'))
This [b][i]code[/i][/b] will be fixed
'''
_bbcode = ''
_tokens = []
def __init__ (self, bbcode = '', fixInvalidCode = True):
''' Initialize and parse bbcode string (if any is given)
'''
self.parse (bbcode, fixInvalidCode)
return
def __str__ (self):
return self.bbcode()
def parse (self, bbcode = None, fixInvalidCode = True):
'''
It will parse and return the token list, trying to fix tags if
fixInvalidCode is True
It will return the current object to allow chaining
Example:
code = bbcode()
code.parse ('<b>bold</b>', True) ->
code.parse ('<b>bold<i>italics</b>', True) -> internally will add the missing '</i>'
'''
if bbcode is not None:
self._bbcode = bbcode
self._tokens = self.tokenize (bbcode)
if fixInvalidCode:
self._tokens = self.fixWrongTags (self._tokens)
return self
# return ALL tokens
def getTokens (self):
return self._tokens
def bbcode (self):
'''
Dump BBCode again. This is useful for dumping valid BBCode
'''
bbcode = []
for token in self._tokens:
if token is None:
continue
if isinstance (token, basestring):
bbcode.append (token.replace (u'[', u'\[').replace (u']', u'\]'))
continue
tag = token['tag'] # opening or closing simple tag. e.g: 'b', '/b', '/u', ...
tagOpener = (u'/' if tag[0] == u'/' else u'')
if (tagOpener == '/') or ('args' not in token):
bbcode.append (u'[' + tag + u']')
else:
# process args
argstr = ''
# the arg with the same name as the tag repersents the '=whatever'
if tag in token['args']:
if re.match ('\s|"', token['args'][tag]) is None:
argstr = u'=' + token['args'][tag]
else:
argstr = u'="' + token['args'][tag].replace (u'"', u'\"') + u'"'
for (k,v) in token['args'].iteritems():
if k == tag: # already processed
continue
argstr += ' ' + k + u'="' + v.replace (u'"', u'\"') + u'"'
bbcode.append (u'[' + tag + argstr + ']')
return u''.join (bbcode)
def html (self, allowClassAttr = False, doDeepCopy = True):
'''
Convert current parsed code to HTML
@allowClassAttr
Is something like [b class="asdf"] allowed?
@doDeepCopy
True: it does a deep copy of tokens so this list will remain unchanged
False: tokens will be modified internally, but the output will be produced like 5x faster
it's a good idea to use False when the string parsed is huge and this is the
last operation on the string
Example:
code = bbcode ('[b]bold[/b]')
code.html() -> '<b>bold</b>'
'''
from bbcode2html import bbcode2html
return bbcode2html.convertToHTML (self._tokens, allowClassAttr = allowClassAttr, doDeepCopy = doDeepCopy)
@staticmethod
def fixWrongTags (inTokenList):
''' Add missing tokens that have not been closed properly and try to fix some scenarios
'''
opened = []
outTokenList = []
for token in inTokenList:
# normal string... do nothing
if isinstance(token, basestring):
outTokenList.append (token)
else:
# if starts with '/' is closing a tag
if token['tag'][0] == '/':
while (len (opened) > 0) and (opened[-1] != token['tag'][1:]):
outTokenList.append ({'tag' : '/' + opened[-1] })
del opened[-1]
if len(opened):
del opened[-1]
outTokenList.append (token)
# opening tag
else:
# if I open the same tag I opened before, close it, and open it again
if (len(opened) > 0) and (token['tag'] == opened[-1]):
outTokenList.append ({'tag' : '/' + opened[-1] })
else:
opened.append (token['tag'])
outTokenList.append (token)
# close all elements that have not been closed
while len(opened):
outTokenList.append ({'tag' : '/' + opened[-1] })
del opened[-1]
return outTokenList
@staticmethod
def tokenize(code):
'''
Tokenize BBCode tags and parameters
Return the token list using a internal format. See the example:
[
{ 'tag' : 'p', 'args' : { 'font' : 'arial' } },
'This is ',
{ 'tag' : 'url', 'args' : {'url' : 'http://www.google.com'} },
'a link to google',
{ 'tag' : '/url' },
{ 'tag' : '/p' }
]
'''
re_tags = re.compile (r'(\[[^]]+\])', re.DOTALL | re.UNICODE)
re_tagName = re.compile (r'\[([^]=\s]+)([^]]*)\]', re.DOTALL | re.UNICODE)
#re_tagArgs = re.compile (r'\s*([^=]*)=(("([^"]+)")|([^\s]+))', re.DOTALL | re.UNICODE)
re_tagArgs = re.compile (r'\s*([\w]*)=(("([^"]+)")|([^\s]+))', re.DOTALL | re.UNICODE)
# get a unique name and replace escaped braces encode utf8 to
# prevent CLI/Web from barfing on unicode chars. Not sure why
# this even needs to be 'unique' like this, but that's the way
# they wrote it.
unique = hashlib.md5(code.encode('utf8')).hexdigest()
code = code.replace ('\[', unique+'_OPEN_BRACE')
code = code.replace ('\]', unique+'_CLOSE_BRACE')
splitted = re_tags.split(code)
outTokenList = []
for token in splitted:
if len(token) == 0:
continue
if token[0] == '[':
match = re_tagName.match (token)
if match:
tagName = match.group(1)
tagArgs = match.group(2)
tagToken = { 'tag' : tagName.lower() }
# parse arguments (if any)
if len(tagArgs) > 0:
allArgs = re_tagArgs.findall(tagArgs)
tagArgs = {}
for arg in allArgs:
# if the argument has no name, use the tagName itself
argName = (arg[0] if arg[0] != '' else tagName)
argValue = (arg[3] if (arg[1][0] == '"') else arg[4])
tagArgs[argName.lower()] = argValue.replace ('\"', '"')
tagToken['args'] = tagArgs
outTokenList.append (tagToken)
# no match, append the text as it is
else:
outTokenList.append (token)
# append the text as it is
else:
outTokenList.append (token)
# restore escaped braces back (once code is parsed)
restoredTokenList = []
for token in outTokenList:
if isinstance (token, basestring):
token = token.replace (unique+'_OPEN_BRACE', '[').replace (unique+'_CLOSE_BRACE', ']')
restoredTokenList.append (token)
return restoredTokenList
-81
View File
@@ -1,81 +0,0 @@
AUTHOR
Pau Sanchez
http://www.codigomanso.com/
VERSION:
bbcodeutils v1.0
LICENSE
This code is licensed under Creative Commons Attribution 3.0
http://creativecommons.org/licenses/by/3.0/
You can use this python module or any part of the code you want as long as you add
my name as a contributor to your project.
DESCRIPTION
This module can be used to produce HTML from BBCode, to generate BBCode or to fix invalid BBCode.
The classes are:
- bbcodeparser
- bbcodebuilder
- bbcode2html
You can use bbcodeparser to parse BBCode and to produce output in any format you want.
Open the python file to find more information and examples of use of each class. It can
be a good idea to check the test.py for examples
To run the unit tests:
> python test.py
To run the performance test:
> python test.py BBCodeTests.performanceTest
EXAMPLES OF BBCode:
[b] -> bold
[u] -> underline
[i] -> italic
[center] -> center the text inside
[color=XXX] -> change color of text
[size=XXX] -> change size of text
Lists:
[ul] -> unordered list
[ol] -> ordered list
[li] -> list item
[list] -> start unordered list
[*] -> list item
[list=1] -> start a list of numbers
[list=a] -> start a list of alphabetic characters
Advanced:
[url] -> link to url
[url=http://link/url/]text[/url]
[url link=http://link/url/ title="This is the title"]text[/url]
[img]http://to/image[/img]
[img=230x330]http://to/image[/img]
[img="Alt text here"]http://to/image[/img]
[img="Alt text here" width=320 height=240]http://to/image[/img]
[email]asdf@asdf.com[/email]
[email=john@asdf.com]John Smith[/email]
[google]search this[/google]
[wikipedia]Tom Hanks[/wikipedia]
[wikipedia lang=es]Tom Hanks[/wikipedia]
Tables:
[table]
[tr]
[th]
[td]
Advanced:
[google]
[wikipedia]
-420
View File
@@ -1,420 +0,0 @@
#!/usr/bin/python
# -*- coding: UTF-8 -*-
#
# Author: Pau Sanchez (contact@pausanchez.com)
# Version: v1.0
# Last Modified: 2010/09/15
#
# For the latest version check out:
# http://www.codigomanso.com/en/projects
#
# My blog:
# http://www.codigomanso.com/en/ - English Version
# http://www.codigomanso.com/es/ - Spanish Version
#
from bbcodeparser import bbcodeparser
from bbcodebuilder import bbcodebuilder
import random
import unittest
class BBCodeTests(unittest.TestCase):
def setUp (self):
self.bbcode = bbcodeparser()
return
def testConstructor (self):
self.assertEqual (bbcodeparser ('whatever').html(), 'whatever')
self.assertEqual (bbcodeparser ('[b]bold[/b]').html(), '<b>bold</b>')
self.assertEqual (str (bbcodeparser ('[b]bold[/b]')), '[b]bold[/b]')
return
def testBold (self):
self.assertEqual (self.bbcode.parse ('whatever').html(), 'whatever')
self.assertEqual (self.bbcode.parse ('[b]bold[/b]').html(), '<b>bold</b>')
self.assertEqual (self.bbcode.parse ('[B]bold[/b]').html(), '<b>bold</b>')
self.assertEqual (self.bbcode.parse ('this is [B]bold[/B]').html(), 'this is <b>bold</b>')
return
def testItalic (self):
self.assertEqual (self.bbcode.parse ('[i]italic[/i]').html(), '<i>italic</i>')
return
def testUnderline (self):
self.assertEqual (self.bbcode.parse ('[u]italic[/u]').html(), '<u>italic</u>')
return
def testURLs (self):
self.assertEqual (
self.bbcode.parse ('[url]http://www.google.com[/url]').html(),
'<a href="http://www.google.com">http://www.google.com</a>'
)
self.assertEqual (
self.bbcode.parse ('[url=http://www.google.com]Google[/url]').html(),
'<a href="http://www.google.com">Google</a>'
)
self.assertEqual (
self.bbcode.parse ('[url="http://www.google.com"]Google[/url]').html(),
'<a href="http://www.google.com">Google</a>'
)
self.assertEqual (
self.bbcode.parse ('[url="http://www.google.com" title="Search Engine"]Google[/url]').html(),
'<a href="http://www.google.com" title="Search Engine">Google</a>'
)
self.assertEqual (
self.bbcode.parse ('[url link="http://www.google.com"]Google[/url]').html(),
'<a href="http://www.google.com">Google</a>'
)
return
def testPTag (self):
self.assertEqual (
self.bbcode.parse ('[p color=#0000ff]blue[/p]').html(),
u'<p style="color: #0000ff;">blue</p>'
)
self.assertEqual (
self.bbcode.parse ('[p size=12]12pt font[/p]').html(),
u'<p style="font-size: 12pt;">12pt font</p>'
)
self.assertEqual (
self.bbcode.parse ('[p font=arial]arial[/p]').html(),
u'<p style="font-family: arial;">arial</p>'
)
self.assertEqual (
self.bbcode.parse ('[p font=arial color=blue size=14]blue 14pt arial').html(),
u'<p style="color: blue; font-size: 14pt; font-family: arial;">blue 14pt arial</p>'
)
self.assertEqual (
self.bbcode.parse ('[p class=whatever]text[/p]').html(),
u'<p>text</p>'
)
return
def testColorTag (self):
self.assertEqual (
self.bbcode.parse ('[color=#0000ff]blue[/color]').html(),
u'<span style="color: #0000ff;">blue</span>'
)
return
def testSizeTag (self):
self.assertEqual (
self.bbcode.parse ('[size=12]12pt font[/size]').html(),
u'<span style="font-size: 12pt;">12pt font</span>'
)
return
def testEmail(self):
self.assertEqual (
self.bbcode.parse ('[email]asdf@asdf.com[/email]').html(),
u'<a href="mailto:asdf@asdf.com">asdf@asdf.com</a>'
)
self.assertEqual (
self.bbcode.parse ('[email=john@smith.com]John Smith[/email]').html(),
u'<a href="mailto:john@smith.com">John Smith</a>'
)
return
def testImgTag (self):
self.assertEqual (
self.bbcode.parse ('[img]http://www.codigomanso.com/image.jpg[/img]').html(),
u'<img src="http://www.codigomanso.com/image.jpg" />'
)
self.assertEqual (
self.bbcode.parse ('[img="This is the ALT of the image"]http://www.codigomanso.com/image.jpg[/img]').html(),
u'<img alt="This is the ALT of the image" src="http://www.codigomanso.com/image.jpg" />'
)
self.assertEqual (
self.bbcode.parse ('[img=320x200]http://www.codigomanso.com/image.jpg[/img]').html(),
u'<img height="200" src="http://www.codigomanso.com/image.jpg" width="320" />'
)
self.assertEqual (
self.bbcode.parse ('[img=320x200 title="Image Test"]http://www.codigomanso.com/image.jpg[/img]').html(),
u'<img height="200" src="http://www.codigomanso.com/image.jpg" title="Image Test" width="320" />'
)
self.assertEqual (
self.bbcode.parse ('[img="whatever" width=320 height="212" title="Image Test"]http://www.codigomanso.com/image.jpg[/img]').html(),
u'<img alt="whatever" height="212" src="http://www.codigomanso.com/image.jpg" title="Image Test" width="320" />'
)
return
def testGoogleURL (self):
self.assertEqual (
self.bbcode.parse ('[google]asdf[/google]').html(),
u'<a href="http://www.google.com/search?q=asdf">asdf</a>'
)
self.assertEqual (
self.bbcode.parse ('[google]Tom Hanks[/google]').html(),
u'<a href="http://www.google.com/search?q=Tom+Hanks">Tom Hanks</a>'
)
return
def testWikipediaURL (self):
self.assertEqual (
self.bbcode.parse ('[wikipedia]Tom Hanks[/wikipedia]').html(),
u'<a href="http://www.wikipedia.org/wiki/Tom_Hanks">Tom Hanks</a>'
)
self.assertEqual (
self.bbcode.parse ('[wikipedia language=en]Tom Hanks[/wikipedia]').html(),
u'<a href="http://en.wikipedia.org/wiki/Tom_Hanks">Tom Hanks</a>'
)
self.assertEqual (
self.bbcode.parse ('[wikipedia lang=es]Tom Hanks[/wikipedia]').html(),
u'<a href="http://es.wikipedia.org/wiki/Tom_Hanks">Tom Hanks</a>'
)
self.assertEqual (
self.bbcode.parse ('[wikipedia=es]Tom Hanks[/wikipedia]').html(),
u'<a href="http://es.wikipedia.org/wiki/Tom_Hanks">Tom Hanks</a>'
)
return
def testListTags (self):
self.assertEqual (
self.bbcode.parse ('[ul][li]item 1[/li][li]item 2[/li][/ul]').html(),
u'<ul><li>item 1</li><li>item 2</li></ul>'
)
self.assertEqual (
self.bbcode.parse ('[ol][li]item 1[/li][li]item 2[/li][/ol]').html(),
u'<ol><li>item 1</li><li>item 2</li></ol>'
)
self.assertEqual (
self.bbcode.parse ('[list][li]item 1[/li][li]item 2[/li][/list]').html(),
u'<ul><li>item 1</li><li>item 2</li></ul>'
)
self.assertEqual (
self.bbcode.parse ('[list][*]item 1[*]item 2[/list]').html(),
u'<ul><li>item 1</li><li>item 2</li></ul>'
)
self.assertEqual (
self.bbcode.parse ('[list=1][li]item 1[/li][li]item 2[/li][/list]').html(),
u'<ol type="1"><li>item 1</li><li>item 2</li></ol>'
)
return
def testInvalidCode (self):
self.assertEqual (self.bbcode.parse ('[invalid]valid text[/invalid]').html(), 'valid text')
self.assertEqual (
self.bbcode.parse ('[b]bold and [i]italics[/b]').html(),
'<b>bold and <i>italics</i></b>'
)
self.assertEqual (
self.bbcode.parse ('[/b]invalid[/b][/p]').html(),
'invalid'
)
self.assertEqual (
self.bbcode.parse ('[p][b]bold').html(),
'<p><b>bold</b></p>'
)
self.assertEqual (
self.bbcode.parse ('[p][b]a <b>').html(),
'<p><b>a &lt;b&gt;</b></p>'
)
self.assertEqual (
self.bbcode.parse ('[ol][li]item 1[li]item 2[/li][/ol]').html(),
u'<ol><li>item 1</li><li>item 2</li></ol>'
)
self.assertEqual (
self.bbcode.parse ('[b]\[b\] stands for [b]bold[/b]').html(),
u'<b>[b] stands for </b><b>bold</b>'
)
return
def testEscapedBrackets (self):
self.assertEqual (
self.bbcode.parse ('\[b\]not bold\[/b\]').html(),
u'[b]not bold[/b]'
)
self.assertEqual (
self.bbcode.parse ('[b]\[b\] stands for bold[/b]').html(),
u'<b>[b] stands for bold</b>'
)
self.assertEqual (
self.bbcode.parse ('\[b\][b]stands for bold[/b]').html(),
u'[b]<b>stands for bold</b>'
)
self.assertEqual (
self.bbcode.parse ('\[b\][b]stands for bold[/b] just like <b> in HTML').html(),
u'[b]<b>stands for bold</b> just like &lt;b&gt; in HTML'
)
def testBigExample (self):
inputText = """check this out
[h1 class=circle]heading[/h1]
[p size=14 color=blue font="verdana, Times New Roman"]This is [b] bold [/b] and this [i]italic[/i] and this is [color=red]red[/color] and this is [color="red"]also red[/color].
[/p]
fix [b][i]bold [font=verdana][size=12]and[/size][/font] italic[/b]
[img]http://www.codigomanso.com/b.jpg[/img]
[url]http://www.codigomanso.com/[/url]
[url=http://www.codigomanso.com/]Codigo Manso[/url]
[uRl link=http://www.codigomanso.com title="Codigo Manso Blog"]Codigo Manso[/url]
[ul]
[Li]item 1[/Li]
[li]item 2[/LI]
[/UL]
[list=1 ]
[*]item 1
[*]item 2
[/list]
[table class="big"]
[tr]
[th]big[/th]
[/tr]
[/table]
[invalid class="extra"]whatever[/invalid]"""
out = self.bbcode.parse (inputText).html(allowClassAttr = True)
self.assertEquals (out, '''check this out
<h1 class="circle">heading</h1>
<p style="color: blue; font-size: 14pt; font-family: verdana, Times New Roman;">This is <b> bold </b> and this <i>italic</i> and this is <span style="color: red;">red</span> and this is <span style="color: red;">also red</span>.
</p>
fix <b><i>bold <span style="font-family: verdana;"><span style="font-size: 12pt;">and</span></span> italic</i></b>
<img src="http://www.codigomanso.com/b.jpg" />
<a href="http://www.codigomanso.com/">http://www.codigomanso.com/</a>
<a href="http://www.codigomanso.com/">Codigo Manso</a>
<a href="http://www.codigomanso.com" title="Codigo Manso Blog">Codigo Manso</a>
<ul>
<li>item 1</li>
<li>item 2</li>
</ul>
<ol type="1">
<li>item 1
</li><li>item 2
</li></ol>
<table class="big">
<tr>
<th>big</th>
</tr>
</table>
whatever''')
def testBBCodeDumper (self):
self.assertEquals (
self.bbcode.parse ('[b]bold[/b]').bbcode(),
'[b]bold[/b]'
)
self.assertEquals (
self.bbcode.parse ('[color=red]text in red[/color]').bbcode(),
'[color=red]text in red[/color]'
)
self.assertEquals (
self.bbcode.parse ('[p][color=red]text in red').bbcode(),
'[p][color=red]text in red[/color][/p]'
)
self.assertEquals (
self.bbcode.parse ('This [b][i]code[/b] will be fixed[/invalid]').bbcode(),
'This [b][i]code[/i][/b] will be fixed'
)
self.assertEquals (
self.bbcode.parse ('\[[url]http://www.codigomanso.com/en[/url]\]').bbcode(),
"\[[url]http://www.codigomanso.com/en[/url]\]"
)
def performanceTest(self):
'''
This test checks the performance of parse and html operations
To run this test type:
> python test.py BBCodeTests.performanceTest
'''
inputText = """check this out
[h1 class=circle]heading[/h1]
[p size=14 color=blue font="verdana, Times New Roman"]This is [b] bold [/b] and this [i]italic[/i] and this is [color=red]red[/color] and this is [color="red"]also red[/color].
[/p]
fix [b][i]bold [font=verdana][size=12]and[/size][/font] italic[/b]
[img]http://www.codigomanso.com/b.jpg[/img]
[url]http://www.codigomanso.com/[/url]
[url=http://www.codigomanso.com/]Codigo Manso[/url]
[uRl link=http://www.codigomanso.com title="Codigo Manso Blog"]Codigo Manso[/url]
[ul]
[Li]item 1[/Li]
[li]item 2[/LI]
[/UL]
[list=1 ]
[*]item 1
[*]item 2
[/list]
[table class="big"]
[tr]
[th]big[/th]
[/tr]
[/table]
[invalid class="extra"]whatever[/invalid]"""
import time
start = time.time()
for i in range(0, 12):
inputText += inputText
print "len(inputText) = %.2f MB (took %.2f seconds)" % (len(inputText)/(1024.0*1024.0), time.time() - start)
bbcode = bbcodeparser()
start = time.time()
bbcode.parse (inputText)
total = (time.time() - start)
print "time (bbcode.parse()) = %f" % total
print " >> %.2f chars/second" % (len(inputText) / total)
start = time.time()
bbcode.html(doDeepCopy = False)
total = (time.time() - start)
print "time (bbcode.html()) = %f" % total
print " >> %.2f chars/second" % (len(inputText) / total)
return
def testCodeBuilder (self):
bbcode = bbcodebuilder ()
self.assertEquals (bbcode.b ('bold'), u'[b]bold[/b]')
self.assertEquals (bbcode.color ('this goes in red', 'red'), u'[color=red]this goes in red[/color]')
self.assertEquals (bbcode.url ('Google', 'http://www.google.com'), u'[url=http://www.google.com]Google[/url]')
self.assertEquals (bbcode.alist('item 1', 'item 2'), u"[list=a]\n [*]item 1\n [*]item 2\n[/list]")
return
if __name__ == '__main__':
unittest.main()
+18 -3
View File
@@ -50,6 +50,7 @@ class Configuration(ConfigParser.SafeConfigParser):
'characters',
'ships',
'series',
'seriesUrl',
'status',
'datePublished',
'dateUpdated',
@@ -75,6 +76,7 @@ class Configuration(ConfigParser.SafeConfigParser):
'langcode',
'output_css',
'authorHTML',
'seriesHTML',
'lastupdate'
]
@@ -94,7 +96,12 @@ class Configuration(ConfigParser.SafeConfigParser):
#print("found %s in section [%s]"%(key,section))
return True
except:
pass
try:
self.get(section,"add_to_"+key)
#print("found add_to_%s in section [%s]"%(key,section))
return True
except:
pass
return False
@@ -106,16 +113,24 @@ class Configuration(ConfigParser.SafeConfigParser):
if val and val.lower() == "false":
val = False
#print "getConfig(%s)=[%s]%s" % (key,section,val)
return val
break
except (ConfigParser.NoOptionError, ConfigParser.NoSectionError), e:
pass
for section in self.sectionslist[::-1]:
# 'martian smiley' [::-1] reverses list by slicing whole list with -1 step.
try:
val = val + self.get(section,"add_to_"+key)
#print "getConfig(add_to_%s)=[%s]%s" % (key,section,val)
except (ConfigParser.NoOptionError, ConfigParser.NoSectionError), e:
pass
return val
# split and strip each.
def getConfigList(self, key):
vlist = self.getConfig(key).split(',')
vlist = [ v.strip() for v in vlist ]
vlist = filter( lambda x : x !='', [ v.strip() for v in vlist ])
#print "vlist("+key+"):"+str(vlist)
return vlist
+37 -2
View File
@@ -27,8 +27,6 @@ from configurable import Configuration
def get_urls_from_page(url,configuration=None):
normalized = set() # normalized url
retlist = [] # orig urls.
if not configuration:
configuration = Configuration("test1.com","EPUB")
@@ -56,6 +54,16 @@ def get_urls_from_page(url,configuration=None):
opener = u2.build_opener(u2.HTTPCookieProcessor(),GZipProcessor())
data = opener.open(url).read()
return get_urls_from_html(data,url)
def get_urls_from_html(data,url=None,configuration=None):
normalized = set() # normalized url
retlist = [] # orig urls.
if not configuration:
configuration = Configuration("test1.com","EPUB")
soup = BeautifulSoup(data)
for a in soup.findAll('a'):
@@ -81,6 +89,33 @@ def get_urls_from_page(url,configuration=None):
return retlist
def get_urls_from_text(data,configuration=None):
normalized = set() # normalized url
retlist = [] # orig urls.
if not configuration:
configuration = Configuration("test1.com","EPUB")
for href in re.findall('http[s]?://(?:[a-zA-Z]|[0-9]|[$-_@.&+]|[!*\(\),]|(?:%[0-9a-fA-F][0-9a-fA-F]))+', data):
# this (should) catch normal story links, some javascript
# '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'])
if m != None:
href = form_url(None,m.group('sid'))
try:
href = href.replace('&index=1','')
adapter = adapters.getAdapter(configuration,href)
if adapter.story.getMetadata('storyUrl') not in normalized:
normalized.add(adapter.story.getMetadata('storyUrl'))
retlist.append(href)
except:
pass
return retlist
def form_url(parenturl,url):
url = url.strip() # ran across an image with a space in the
# src. Browser handled it, so we'd better, too.
+14 -6
View File
@@ -352,7 +352,7 @@ class Story(Configurable):
allmetadata = {}
# special handling for authors/authorUrls
authlinkhtml="<a class='authorlink' href='%s'>%s</a>"
linkhtml="<a class='%slink' href='%s'>%s</a>"
if self.isList('author'): # more than one author, assume multiple authorUrl too.
htmllist=[]
for i, v in enumerate(self.getList('author')):
@@ -366,12 +366,18 @@ class Story(Configurable):
aurl=removeAllEntities(aurl)
auth=removeAllEntities(auth)
htmllist.append(authlinkhtml%(aurl,auth))
htmllist.append(linkhtml%('author',aurl,auth))
self.setMetadata('authorHTML',', '.join(htmllist))
else:
self.setMetadata('authorHTML',authlinkhtml%(self.getMetadata('authorUrl', removeallentities, doreplacements),
self.getMetadata('author', removeallentities, doreplacements)))
self.setMetadata('authorHTML',linkhtml%('author',self.getMetadata('authorUrl', removeallentities, doreplacements),
self.getMetadata('author', removeallentities, doreplacements)))
if self.getMetadataRaw('seriesUrl') != None:
self.setMetadata('seriesHTML',linkhtml%('series',self.getMetadata('seriesUrl', removeallentities, doreplacements),
self.getMetadata('series', removeallentities, doreplacements)))
elif self.getMetadataRaw('series') != None:
self.setMetadata('seriesHTML',self.getMetadataRaw('series'))
for k in self.getValidMetaList():
if self.isList(k) and keeplists:
allmetadata[k] = self.getList(k, removeallentities, doreplacements)
@@ -415,11 +421,13 @@ class Story(Configurable):
# includelist prevents infinite recursion of include_in_'s
if self.hasConfig("include_in_"+listname) and listname not in includelist:
for k in self.getConfigList("include_in_"+listname):
retlist.extend(self.getList(k,removeallentities,doreplacements,includelist=includelist+[listname]))
retlist.extend(self.getList(k,removeallentities=False,
doreplacements=doreplacements,includelist=includelist+[listname]))
else:
if not self.isList(listname):
retlist = [self.getMetadata(listname,removeallentities, doreplacements)]
retlist = [self.getMetadata(listname,removeallentities=False,
doreplacements=doreplacements)]
else:
retlist = self.getMetadataRaw(listname)
+3 -4
View File
@@ -57,9 +57,8 @@
<h3>Changes:</h3>
<p>
<ul>
<li>New site: www.henneth-annun.net -- Thanks Ida!</li>
<li>New site: www.psychfic.com -- Thanks Ida!</li>
<li>Now accepting www.skyehawke.com/archive URLs for archive.skyehawke.com stories.</li>
<li>Add seriesUrl (and generated seriesHTML) as valid metadata entries. The default series on title_page is now a link.</li>
<li>Add user/pass for dokuga.com.</li>
</ul>
</p>
<p>
@@ -70,7 +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://4-4-42.fanfictiondownloader.appspot.com">Previous Version</a> is also available for you to use if necessary.
<a href="http://4-4-47.fanfictiondownloader.appspot.com">Previous Version</a> is also available for you to use if necessary.
</p>
<div id='error'>
{{ error_message }}
+1 -1
View File
@@ -27,7 +27,7 @@ if __name__=="__main__":
exclude=['*.pyc','*~','*.xcf','*[0-9].png']
# from top dir. 'w' for overwrite
createZipFile(filename,"w",
['plugin-defaults.ini','plugin-example.ini','epubmerge.py','fanficdownloader'],
['plugin-defaults.ini','plugin-example.ini','fanficdownloader','downloader.py','defaults.ini'],
exclude=exclude)
#from calibre-plugin dir. 'a' for append
os.chdir('calibre-plugin')
+21 -9
View File
@@ -44,6 +44,9 @@ language_label:Language
characters_label:Characters
ships_label:Relationships
series_label:Series
seriesUrl_label:Series URL
## seriesHTML is series as a link to seriesUrl.
seriesHTML_label:Series
## Completed/In-Progress
status_label:Status
## Dates story first published, last updated, and downloaded(last with time).
@@ -81,7 +84,7 @@ dateUpdated_format:%%Y-%%m-%%d
## You can include extra text or HTML that will be included as-is in
## the title page. Eg: titlepage_entries: ...,<br />,summary,<br />,...
## All current formats already include title and author.
titlepage_entries: series,category,genre,language,characters,ships,status,datePublished,dateUpdated,dateCreated,rating,warnings,numChapters,numWords,site,description
titlepage_entries: seriesHTML,category,genre,language,characters,ships,status,datePublished,dateUpdated,dateCreated,rating,warnings,numChapters,numWords,site,description
## Try to collect series name and number of this story in series.
## Some sites (ab)use 'series' for reading lists and personal
@@ -157,7 +160,7 @@ extratags: FanFiction
## metadata part(s) to look at, 2) a regular expression to match the
## template, and 3) the name of the GC setting to use, which must
## match exactly. Use this parameter in [defaults], or by site eg,
## [www.ficwad.com]
## [ficwad.com]
## Make sure to keep at least one space at the start of each line and
## to escape % to %%, if used.
## template => regexp to match => GC Setting to use.
@@ -249,7 +252,7 @@ output_css:
[txt]
## Add URLs since there aren't links.
titlepage_entries: series,category,genre,language,status,datePublished,dateUpdated,dateCreated,rating,warnings,numChapters,numWords,site,storyUrl, authorUrl, description
titlepage_entries: series,seriesUrl,category,genre,language,status,datePublished,dateUpdated,dateCreated,rating,warnings,numChapters,numWords,site,storyUrl, authorUrl, description
## Width to word wrap text output. 0 indicates no wrapping.
wrap_width: 78
@@ -269,6 +272,8 @@ include_tocpage: false
## dateUpdated,numChapters,numWords at a minimum) will be shown.
## Great for tracking when chapters came out and when the description,
## etc changed.
## Plugin will now preserve the log page when the epub is overwritten,
## too.
include_logpage: false
## If set to 'smart', logpage will only be included if the story is
## status:In-Progress or already had a logpage. That way you don't
@@ -280,13 +285,13 @@ include_logpage: false
## if in the list. You can include extra text or HTML that will be
## included as-is in each log entry. Eg: logpage_entries: ...,<br />,
## summary,<br />,...
logpage_entries: dateCreated,datePublished,dateUpdated,numChapters,numWords,status,title,author,description,category,genre,rating,warnings
logpage_entries: dateCreated,datePublished,dateUpdated,numChapters,numWords,status,series,title,author,description,category,genre,rating,warnings
## epub->mobi conversions typically don't like tables.
titlepage_use_table: false
## When using tables, make these span both columns.
wide_titlepage_entries: description, storyUrl, author URL
wide_titlepage_entries: description, storyUrl, authorUrl, seriesUrl
## output background color--only used by html and epub (and ignored in
## epub by many readers). Included below in output_css--will be
@@ -344,7 +349,7 @@ output_css:
## It can be either a 'file:' or 'http:' url.
## Note that if you enable make_firstimage_cover in [epub], but want
## to use default_cover_image for a specific site, use the site:format
## section, for example: [www.ficwad.com:epub]
## section, for example: [ficwad.com:epub]
## default_cover_image is a python string Template string with
## ${title}, ${author} etc, same as titlepage_entries. Unless
## allow_unsafe_filename is true, invalid filename chars will be
@@ -949,6 +954,13 @@ extracategories:InuYasha
extracharacters:Sesshoumaru,Kagome
extraships:Sesshoumaru/Kagome
## Some sites require login (or login for some rated stories) The
## program can prompt you, or you can save it in config. In
## commandline version, this should go in your personal.ini, not
## defaults.ini.
#username:YourName
#password:yourpassword
[www.dotmoon.net]
## Some sites require login (or login for some rated stories) The
## program can prompt you, or you can save it in config. In
@@ -1008,7 +1020,7 @@ extratags:
## for examples of how to use them.
extra_valid_entries:reviews,favs,follows
[www.ficwad.com]
[ficwad.com]
## Some sites require login (or login for some rated stories) The
## program can prompt you, or you can save it in config. In
## commandline version, this should go in your personal.ini, not
@@ -1196,12 +1208,12 @@ extraships:Harry Potter/Ginny Weasley
# www.squidge.org/peja calls it Fandom <shrug>
category_label:Fandom
# Remove numWords -- www.squidge.org/peja word counts are inaccurate
titlepage_entries: series,category,genre,language,characters,ships,status,datePublished,dateUpdated,dateCreated,rating,warnings,numChapters,site,description
titlepage_entries: seriesHTML,category,genre,language,characters,ships,status,datePublished,dateUpdated,dateCreated,rating,warnings,numChapters,site,description
[www.squidge.org/peja:txt]
## Add URLs since there aren't links.
# Remove numWords -- www.squidge.org/peja word counts are inaccurate
titlepage_entries: series,category,genre,language,status,datePublished,dateUpdated,dateCreated,rating,warnings,numChapters,site,storyUrl, authorUrl, description
titlepage_entries: series,seriesUrl,category,genre,language,status,datePublished,dateUpdated,dateCreated,rating,warnings,numChapters,site,storyUrl, authorUrl, description
[www.storiesofarda.com]
## Site dedicated to these categories/characters/ships
+1 -1
View File
@@ -51,7 +51,7 @@
## default is false
#collect_series: true
[www.ficwad.com]
[ficwad.com]
#username:YourUsername
#password:YourPassword