Compare commits

...
Author SHA1 Message Date
Jim Miller f0a1e1d471 Plugin--Add feature to integrate with Generate Cover plugin by kiwidude. 2012-05-08 10:43:02 -05:00
Jim Miller 3719e9860c Added tag CLI-4.4.8a for changeset d38c36148dc4 2012-04-25 21:53:28 -05:00
Jim Miller ea43dffe0c Added tag calibre-plugin-1.5.16 for changeset d38c36148dc4 2012-04-25 21:53:09 -05:00
Jim Miller 0a2cff3469 Yet more fixes for poor parsing of numeric entities--this time, my poor parsing. 2012-04-25 21:52:56 -05:00
Jim Miller 3cb92f48cc Added tag FanFictionDownLoader-4.4.8 for changeset 8fc7a6cc2d87 2012-04-22 10:10:08 -05:00
Jim Miller e5cc4ebbd5 Bump Web/CLI version. 2012-04-22 10:09:44 -05:00
Jim Miller c6c67f99ca Moved tag calibre-plugin-1.5.15 to changeset a1a840bcd4c9 (from changeset bac4028b803d) 2012-04-22 09:55:58 -05:00
Jim Miller c75e62d07e Merge fimfiction changes to trunk. 2012-04-22 09:55:39 -05:00
Jim Miller e9b203eb57 Added tag calibre-plugin-1.5.15 for changeset bac4028b803d 2012-04-21 21:37:27 -05:00
Jim Miller a2eaa9fb22 Fix for ArchiveOfOurOwn site change. 2012-04-21 21:37:16 -05:00
althaine 0cf5ec9880 Updated fimfic.net adapter to use provided API 2012-04-20 20:36:20 +10:00
Jim Miller 465e25d3e6 Added tag FanFictionDownLoader-4.4.7 for changeset c8ab1f6bbd57 2012-04-19 12:19:06 -05:00
Jim Miller 0c85cf1d10 Web- Add list of all downloads feature to web service. 2012-04-19 12:18:40 -05:00
Jim Miller 7f7a1a983c Plugin-Fix setting status column with no status available(fictionalley). 2012-04-19 12:14:51 -05:00
Jim Miller 6f4be261ef Fix Japanese in CLI & web version. Broke it in 443 and didn't notice. 2012-04-18 17:54:42 -05:00
Jim Miller 04eb551d48 Added tag CLI-4.4.6 for changeset b69d6004ae25 2012-04-17 14:07:50 -05:00
Jim Miller 6299fc7582 Added tag calibre-plugin-1.5.14 for changeset b69d6004ae25 2012-04-17 14:07:29 -05:00
Jim Miller c2d7b4ecce Change plugin 'images' checkbox to add to [epubs], kludge for fimfiction images 2012-04-17 14:07:19 -05:00
Jim Miller 01b14701a0 Moved tag calibre-plugin-1.5.13 to changeset b55fabb0b8c9 (from changeset b0720fc31c10) 2012-04-11 11:11:43 -05:00
17 changed files with 416 additions and 134 deletions
+78
View File
@@ -0,0 +1,78 @@
<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01//EN">
<html>
<head>
<link href="/css/index.css" rel="stylesheet" type="text/css">
<title>FanFictionDownLoader (fanfiction.net, fanficauthors, fictionalley, ficwad to epub and HTML)</title>
<meta http-equiv="Content-Type" content="text/html; charset=UTF-8">
<script type="text/javascript">
var _gaq = _gaq || [];
_gaq.push(['_setAccount', 'UA-12136939-1']);
_gaq.push(['_trackPageview']);
(function() {
var ga = document.createElement('script'); ga.type = 'text/javascript'; ga.async = true;
ga.src = ('https:' == document.location.protocol ? 'https://ssl' : 'http://www') + '.google-analytics.com/ga.js';
var s = document.getElementsByTagName('script')[0]; s.parentNode.insertBefore(ga, s);
})();
</script>
</head>
<body>
<div id='main'>
<h1>
<a href="/" style="text-decoration: none; color: black;">FanFictionDownLoader</a>
</h1>
<script type="text/javascript"><!--
google_ad_client = "ca-pub-0320924304307555";
/* Standard */
google_ad_slot = "8974025478";
google_ad_width = 468;
google_ad_height = 60;
//-->
</script>
<script type="text/javascript"
src="http://pagead2.googlesyndication.com/pagead/show_ads.js">
</script>
<!-- <div id='yourfile'> -->
{{yourfile}}
<!-- </div> -->
<div id='helpbox'>
{% for fic in fics %}
<p>
<a href="{{ fic.url }}" title="Link to original story"><span class="recent"><i>{{ fic.title }}</i></span></a>
by <a href="{{ fic.authorUrl }}">{{ fic.author }}</a> <b>Download Count:</b> {{ fic.count }} <br />
<b>Word Count:</b> {{ fic.numWords }} <b>Chapter Count:</b> {{ fic.numChapters }}<br />
{% if fic.category %} <b>Categories:</b> {{ fic.category }} <br /> {% endif %}
{% if fic.genre %} <b>Genres:</b> {{ fic.genre }} <br /> {% endif %}
{% if fic.language %} <b>Language:</b> {{ fic.language }} <br /> {% endif %}
{% if fic.series %} <b>Series:</b> {{ fic.series }} <br /> {% endif %}
{% if fic.characters %} <b>Characters:</b> {{ fic.characters }} <br /> {% endif %}
{% if fic.status %} <b>Status:</b> {{ fic.status }} <br /> {% endif %}
{% if fic.datePublished %} <b>Published:</b> {{ fic.datePublished }} <br /> {% endif %}
{% if fic.dateUpdated %} <b>Last Updated:</b> {{ fic.dateUpdated }} <br /> {% endif %}
{% if fic.dateCreated %} <b>Last Downloaded:</b> {{ fic.dateCreated }} <br /> {% endif %}
{% if fic.rating %} <b>Rating:</b> {{ fic.rating }} <br /> {% endif %}
{% if fic.warnings %} <b>Warnings:</b> {{ fic.warnings }} <br /> {% endif %}
{% if fic.description %} <b>Summary:</b> {{ fic.description }} <br /> {% endif %}
</p>
{% endfor %}
</div>
<script type="text/javascript"><!--
google_ad_client = "ca-pub-0320924304307555";
/* Standard */
google_ad_slot = "8974025478";
google_ad_width = 468;
google_ad_height = 60;
//-->
</script>
<script type="text/javascript"
src="http://pagead2.googlesyndication.com/pagead/show_ads.js">
</script>
</div>
</body>
</html>
+3 -3
View File
@@ -1,6 +1,6 @@
# ffd-retief-hrd fanfictiondownloader
application: fanfictiondownloader
version: 4-4-5
version: 4-4-8
runtime: python27
api_version: 1
threadsafe: true
@@ -35,8 +35,8 @@ handlers:
- url: /.*
script: main.app
builtins:
- datastore_admin: on
#builtins:
#- datastore_admin: on
libraries:
- name: django
+1 -1
View File
@@ -27,7 +27,7 @@ class FanFictionDownLoaderBase(InterfaceActionBase):
description = 'UI plugin to download FanFiction stories from various sites.'
supported_platforms = ['windows', 'osx', 'linux']
author = 'Jim Miller'
version = (1, 5, 13)
version = (1, 5, 18)
minimum_calibre_version = (0, 8, 30)
#: This field defines the GUI plugin class that contains all the code
+1 -1
View File
@@ -1,6 +1,6 @@
<hr />
<p>Created by Jim Miller, borrowing heavily from Grant Drake's
<p>Plugin created by Jim Miller, borrowing heavily from Grant Drake's
'<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>'
+105 -19
View File
@@ -9,16 +9,17 @@ __docformat__ = 'restructuredtext en'
import traceback, copy
from PyQt4.Qt import (QDialog, QWidget, QVBoxLayout, QHBoxLayout, QLabel, QLineEdit, QFont,
QTextEdit, QComboBox, QCheckBox, QPushButton, QTabWidget, QVariant)
from PyQt4.Qt import (QDialog, QWidget, QVBoxLayout, QHBoxLayout, QLabel, QLineEdit, QFont, QWidget,
QTextEdit, QComboBox, QCheckBox, QPushButton, QTabWidget, QVariant, QScrollArea)
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.dialogs \
import (SKIP, ADDNEW, UPDATE, UPDATEALWAYS, OVERWRITE, OVERWRITEALWAYS,
CALIBREONLY,collision_order)
import (UPDATE, UPDATEALWAYS, OVERWRITE, collision_order)
from calibre_plugins.fanfictiondownloader_plugin.fanficdownloader.adapters import getSiteDomains
from calibre_plugins.fanfictiondownloader_plugin.common_utils \
import ( get_library_uuid, KeyboardConfigDialog )
@@ -53,6 +54,9 @@ all_prefs.defaults['addtolists'] = False
all_prefs.defaults['addtoreadlists'] = False
all_prefs.defaults['addtolistsonread'] = False
all_prefs.defaults['gc_site_settings'] = {}
all_prefs.defaults['allow_gc_from_ini'] = True
all_prefs.defaults['custom_cols'] = {}
# The list of settings to copy from all_prefs or the previous library
@@ -67,7 +71,9 @@ copylist = ['personal.ini',
'collision',
'deleteotherforms',
'adddialogstaysontop',
'includeimages']
'includeimages',
'gc_site_settings',
'allow_gc_from_ini']
# 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
@@ -87,7 +93,8 @@ class PrefsFacade():
self.all_prefs[libraryid] = dict(self._get_copylist_prefs(self.all_prefs))
else:
self.all_prefs[libraryid] = dict(self._get_copylist_prefs(self.all_prefs[self.lastlibid]))
self.lastlibid = libraryid
self.lastlibid = libraryid
return self.all_prefs[libraryid]
@@ -139,10 +146,15 @@ class ConfigWidget(QWidget):
self.personalini_tab = PersonalIniTab(self, plugin_action)
tab_widget.addTab(self.personalini_tab, 'personal.ini')
self.list_tab = ListTab(self, plugin_action)
tab_widget.addTab(self.list_tab, 'Reading Lists')
self.readinglist_tab = ReadingListTab(self, plugin_action)
tab_widget.addTab(self.readinglist_tab, 'Reading Lists')
if 'Reading List' not in plugin_action.gui.iactions:
self.list_tab.setEnabled(False)
self.readinglist_tab.setEnabled(False)
self.generatecover_tab = GenerateCoverTab(self, plugin_action)
tab_widget.addTab(self.generatecover_tab, 'Generate Cover')
if 'Generate Cover' not in plugin_action.gui.iactions:
self.generatecover_tab.setEnabled(False)
self.columns_tab = ColumnsTab(self, plugin_action)
tab_widget.addTab(self.columns_tab, 'Custom Columns')
@@ -165,15 +177,15 @@ class ConfigWidget(QWidget):
prefs['adddialogstaysontop'] = self.basic_tab.adddialogstaysontop.isChecked()
prefs['includeimages'] = self.basic_tab.includeimages.isChecked()
if self.list_tab:
if self.readinglist_tab:
# lists
prefs['send_lists'] = ', '.join(map( lambda x : x.strip(), filter( lambda x : x.strip() != '', unicode(self.list_tab.send_lists_box.text()).split(','))))
prefs['read_lists'] = ', '.join(map( lambda x : x.strip(), filter( lambda x : x.strip() != '', unicode(self.list_tab.read_lists_box.text()).split(','))))
prefs['send_lists'] = ', '.join(map( lambda x : x.strip(), filter( lambda x : x.strip() != '', unicode(self.readinglist_tab.send_lists_box.text()).split(','))))
prefs['read_lists'] = ', '.join(map( lambda x : x.strip(), filter( lambda x : x.strip() != '', unicode(self.readinglist_tab.read_lists_box.text()).split(','))))
# print("send_lists: %s"%prefs['send_lists'])
# print("read_lists: %s"%prefs['read_lists'])
prefs['addtolists'] = self.list_tab.addtolists.isChecked()
prefs['addtoreadlists'] = self.list_tab.addtoreadlists.isChecked()
prefs['addtolistsonread'] = self.list_tab.addtolistsonread.isChecked()
prefs['addtolists'] = self.readinglist_tab.addtolists.isChecked()
prefs['addtoreadlists'] = self.readinglist_tab.addtoreadlists.isChecked()
prefs['addtolistsonread'] = self.readinglist_tab.addtolistsonread.isChecked()
# personal.ini
ini = unicode(self.personalini_tab.ini.toPlainText())
@@ -183,6 +195,16 @@ class ConfigWidget(QWidget):
# if they've removed everything, reset to default.
prefs['personal.ini'] = get_resources('plugin-example.ini')
# Generate Covers tab
gc_site_settings = {}
for (site,combo) in self.generatecover_tab.gc_dropdowns.iteritems():
val = unicode(combo.itemData(combo.currentIndex()).toString())
if val != 'none':
gc_site_settings[site] = val
#print("gc_site_settings[%s]:%s"%(site,gc_site_settings[site]))
prefs['gc_site_settings'] = gc_site_settings
prefs['allow_gc_from_ini'] = self.generatecover_tab.allow_gc_from_ini.isChecked()
# Custom Columns tab
colsmap = {}
for (col,combo) in self.columns_tab.custcol_dropdowns.iteritems():
@@ -191,7 +213,7 @@ class ConfigWidget(QWidget):
colsmap[col] = val
#print("colsmap[%s]:%s"%(col,colsmap[col]))
prefs['custom_cols'] = colsmap
def edit_shortcuts(self):
self.save_settings()
# Force the menus to be rebuilt immediately, so we have all our actions registered
@@ -283,10 +305,10 @@ class BasicTab(QWidget):
# this is a cheat to make it easier for users to realize there's a new include_images features.
self.includeimages = QCheckBox("Include images in EPUBs?",self)
self.includeimages.setToolTip("Download and include images in EPUB stories. This is equivalent to adding:\n\n[defaults]\ninclude_images:true\nkeep_summary_html:true\nmake_firstimage_cover:true\n\n ...to the top of personal.ini. Your settings in personal.ini will override this.")
self.includeimages.setToolTip("Download and include images in EPUB stories. This is equivalent to adding:\n\n[epub]\ninclude_images:true\nkeep_summary_html:true\nmake_firstimage_cover:true\n\n ...to the top of personal.ini. Your settings in personal.ini will override this.")
self.includeimages.setChecked(prefs['includeimages'])
self.l.addWidget(self.includeimages)
self.l.insertStretch(-1)
def set_collisions(self):
@@ -372,7 +394,7 @@ class ShowDefaultsIniDialog(QDialog):
self.ok_button.clicked.connect(self.hide)
self.l.addWidget(self.ok_button)
class ListTab(QWidget):
class ReadingListTab(QWidget):
def __init__(self, parent_dialog, plugin_action):
self.parent_dialog = parent_dialog
@@ -432,6 +454,70 @@ class ListTab(QWidget):
self.l.insertStretch(-1)
class GenerateCoverTab(QWidget):
def __init__(self, parent_dialog, plugin_action):
self.parent_dialog = parent_dialog
self.plugin_action = plugin_action
QWidget.__init__(self)
self.l = QVBoxLayout()
self.setLayout(self.l)
try:
gc_plugin = plugin_action.gui.iactions['Generate Cover']
gc_settings = gc_plugin.get_saved_setting_names()
except KeyError:
gc_settings= []
label = QLabel('The Generate Cover plugin can create cover images for books using various metadata and configurations. If you have GC installed, FFDL can run GC on new downloads and metadata updates. Pick a GC setting by site or Default.')
label.setWordWrap(True)
self.l.addWidget(label)
self.l.addSpacing(5)
scrollable = QScrollArea()
scrollcontent = QWidget()
scrollable.setWidget(scrollcontent)
scrollable.setWidgetResizable(True)
self.l.addWidget(scrollable)
self.sl = QVBoxLayout()
scrollcontent.setLayout(self.sl)
self.gc_dropdowns = {}
sitelist = getSiteDomains()
sitelist.sort()
sitelist.insert(0,u"Default")
for site in sitelist:
horz = QHBoxLayout()
label = QLabel(site)
if site == u"Default":
s = "On Metadata update, run Generate Cover with this setting, if not selected for specific site."
else:
s = "On Metadata update, run Generate Cover with this setting for site (%s)."%site
label.setToolTip(s)
horz.addWidget(label)
dropdown = QComboBox(self)
dropdown.setToolTip(s)
dropdown.addItem('',QVariant('none'))
for setting in gc_settings:
dropdown.addItem(setting,QVariant(setting))
self.gc_dropdowns[site] = dropdown
if site in prefs['gc_site_settings']:
dropdown.setCurrentIndex(dropdown.findData(QVariant(prefs['gc_site_settings'][site])))
horz.addWidget(dropdown)
self.sl.addLayout(horz)
self.allow_gc_from_ini = QCheckBox('Allow generate_cover_settings from personal.ini to override.',self)
self.allow_gc_from_ini.setToolTip("The INI parameter generate_cover_settings allows you to choose a GC setting based on metadata rather than site,\nbut it's much more complex. generate_cover_settings is ignored when this is off.")
self.allow_gc_from_ini.setChecked(prefs['allow_gc_from_ini'])
self.l.addWidget(self.allow_gc_from_ini)
self.l.insertStretch(-1)
class OtherTab(QWidget):
def __init__(self, parent_dialog, plugin_action):
+46 -5
View File
@@ -7,11 +7,12 @@ __license__ = 'GPL v3'
__copyright__ = '2012, Jim Miller'
__docformat__ = 'restructuredtext en'
import time, os, copy, threading
import time, os, copy, threading, re
from ConfigParser import SafeConfigParser
from StringIO import StringIO
from functools import partial
from datetime import datetime
from string import Template
from PyQt4.Qt import (QApplication, QMenu, QToolButton)
@@ -420,7 +421,7 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
options['personal.ini'] = prefs['personal.ini']
if prefs['includeimages']:
# this is a cheat to make it easier for users.
options['personal.ini'] = '''[defaults]
options['personal.ini'] = '''[epub]
include_images:true
keep_summary_html:true
make_firstimage_cover:true
@@ -772,7 +773,6 @@ make_firstimage_cover:true
epubmi = get_metadata(existingepub,'EPUB')
if epubmi.cover_data[1] is not None:
db.set_cover(book_id, epubmi.cover_data[1])
#mi.cover = epubmi.cover_data[1]
# set author link if found. All current adapters have authorUrl.
if 'authorUrl' in book['all_metadata']:
@@ -793,7 +793,8 @@ make_firstimage_cover:true
print("%s not an existing column, skipping."%col)
continue
coldef = custom_columns[col]
if not meta.startswith('status-') and meta not in book['all_metadata']:
if not meta.startswith('status-') and meta not in book['all_metadata'] or \
meta.startswith('status-') and 'status' not in book['all_metadata']:
print("No value for %s, skipping."%meta)
continue
if meta not in permitted_values[coldef['datatype']]:
@@ -811,8 +812,48 @@ make_firstimage_cover:true
if meta == 'status-I':
val = book['all_metadata']['status'] == 'In-Progress'
db.set_custom(book_id, val, label=label, commit=False)
db.commit()
if 'Generate Cover' in self.gui.iactions:
gc_plugin = self.gui.iactions['Generate Cover']
setting_name = None
if prefs['allow_gc_from_ini']:
ffdlconfig = SafeConfigParser()
ffdlconfig.readfp(StringIO(get_resources("plugin-defaults.ini")))
ffdlconfig.readfp(StringIO(prefs['personal.ini']))
adapter = adapters.getAdapter(ffdlconfig,book['url'],options['fileform'])
# template => regexp to match => GC Setting to use.
# generate_cover_settings:
# ${category} => Buffy:? the Vampire Slayer => Buffy
for line in adapter.getConfig('generate_cover_settings').splitlines():
if "=>" in line:
(template,regexp,setting) = map( lambda x: x.strip(), line.split("=>") )
value = Template(template).substitute(book['all_metadata']).encode('utf8')
print("%s(%s) => %s => %s"%(template,value,regexp,setting))
if re.search(regexp,value):
setting_name = setting
break
if setting_name:
print("Generate Cover Setting from generate_cover_settings(%s)"%line)
if setting_name not in gc_plugin.get_saved_setting_names():
print("GC Name %s not found, discarding! (check personal.ini for typos)"%setting_name)
setting_name = None
if not setting_name and book['all_metadata']['site'] in prefs['gc_site_settings']:
setting_name = prefs['gc_site_settings'][book['all_metadata']['site']]
if not setting_name and 'Default' in prefs['gc_site_settings']:
setting_name = prefs['gc_site_settings']['Default']
if setting_name:
print("Running Generate Cover with settings %s."%setting_name)
realmi = db.get_metadata(book_id, index_is_id=True)
gc_plugin.generate_cover_for_book(realmi,saved_setting_name=setting_name)
def _get_clean_reading_lists(self,lists):
if lists == None or lists.strip() == "" :
+3
View File
@@ -100,6 +100,9 @@ def getAdapter(config,url,fileform=None):
# No adapter found.
raise exceptions.UnknownSite( url, [cls.getSiteDomain() for cls in __class_list] )
def getSiteDomains():
return [cls.getSiteDomain() for cls in __class_list]
def getClassFor(domain):
for cls in __class_list:
if cls.matchesSite(domain):
@@ -101,7 +101,7 @@ class ArchiveOfOurOwnOrgAdapter(BaseSiteAdapter):
# Now go hunting for all the meta data and the chapter list.
## Title
a = soup.find('a', href=re.compile(r"^/works/\w+"))
a = soup.find('a', href=re.compile(r"^/works/\d+$"))
self.story.setMetadata('title',a.string)
# Find authorid and URL from... author url.
@@ -20,7 +20,8 @@ import logging
import re
import urllib2
import cookielib as cl
import datetime
from datetime import datetime
import json
from .. import BeautifulSoup as bs
from ..htmlcleanup import stripHTML
@@ -36,7 +37,7 @@ class FimFictionNetSiteAdapter(BaseSiteAdapter):
def __init__(self, config, url):
BaseSiteAdapter.__init__(self, config, url)
self.story.setMetadata('siteabbrev','fimficnet')
self.story.setMetadata('storyId',self.parsedUrl.path.split('/',)[2])
self.story.setMetadata('storyId', self.parsedUrl.path.split('/',)[2])
self._setURL("http://"+self.getSiteDomain()+"/story/"+self.story.getMetadata('storyId')+"/")
self.is_adult = False
@@ -74,6 +75,10 @@ class FimFictionNetSiteAdapter(BaseSiteAdapter):
self.opener = urllib2.build_opener(cookieproc)
try:
apiResponse = urllib2.urlopen("http://www.fimfiction.net/api/story.php?story=%s" % (self.story.getMetadata("storyId"))).read()
apiData = json.loads(apiResponse)
# Unfortunately, we still need to load the story index page to parse the characters
data = self._fetchUrl(self.url)
except urllib2.HTTPError, e:
if e.code == 404:
@@ -87,9 +92,12 @@ class FimFictionNetSiteAdapter(BaseSiteAdapter):
if "/images/missing_story.png" in data:
raise exceptions.StoryDoesNotExist(self.url)
if "Invalid story id" in apiData.values():
raise exceptions.StoryDoesNotExist(self.url)
if "This story has been marked as having adult content." in data:
raise exceptions.AdultCheckRequired(self.url)
if self.password:
params = {}
params['password'] = self.password
@@ -100,95 +108,56 @@ class FimFictionNetSiteAdapter(BaseSiteAdapter):
raise exceptions.FailedToDownload("%s requires story password and fail_on_password is true."%self.url)
else:
raise exceptions.FailedToLogin(self.url,"Story requires individual password",passwdonly=True)
storyMetadata = apiData["story"]
self.story.setMetadata("title", storyMetadata["title"])
self.story.setMetadata("author", storyMetadata["author"]["name"])
self.story.setMetadata("authorId", storyMetadata["author"]["id"])
self.story.setMetadata("authorUrl", "http://%s/user/%s" % (self.getSiteDomain(), storyMetadata["author"]["name"]))
soup = bs.BeautifulSoup(data).find("div", {"class":"content_box post_content_box"})
titleheader = soup.find("h2")
title = titleheader.find("a", href=re.compile(r'^/story/')).text
author = titleheader.find("a", href=re.compile(r'^/user/')).text
self.story.setMetadata("title", title)
self.story.setMetadata("author", author)
self.story.setMetadata("authorId", author) # The author's name will be unique
self.story.setMetadata("authorUrl", "http://%s/user/%s" % (self.getSiteDomain(),author))
chapters = [{"chapterTitle": chapter["title"], "chapterURL": chapter["link"]} for chapter in storyMetadata["chapters"]]
for chapter in chapters:
self.chapterUrls.append((chapter["chapterTitle"], chapter["chapterURL"]))
self.story.setMetadata("numChapters", len(self.chapterUrls))
chapterDates = []
for chapter in soup.findAll("a", {"class":"chapter_link"}):
chapterDates.append(chapter.span.extract().text.strip("()"))
self.chapterUrls.append((chapter.text.strip(), "http://"+self.getSiteDomain() + chapter['href']))
self.story.setMetadata('numChapters',len(self.chapterUrls))
for character in [character_icon['title'] for character_icon in soup.findAll("a", {"class":"character_icon"})]:
self.story.addToList("characters", character)
for category in [category.text for category in soup.find("div", {"class":"categories"}).findAll("a")]:
self.story.addToList("genre", category)
self.story.addToList("category", "My Little Pony")
# The very last list element in the list of chapters contains the status, rating and word count e.g.:
#
# <li>
# Incomplete | Rating:
# <span style="color:#c78238;">Teen</span>
# <div class="word_count"><b>5,203</b>words total</div>
# </li>
#
status_bar = soup.findAll('li')[-1]
# In the case of fimfiction.net, possible statuses are 'Completed', 'Incomplete', 'On Hiatus' and 'Cancelled'
# For the sake of bringing it in line with the other adapters, 'Incomplete' and 'On Hiatus' become 'In-Progress'
# and 'Complete' beomes 'Completed'. 'Cancelled' seems an important enough (not to mention more strictly true)
# status to leave unchanged.
status = status_bar.text.split("|")[0].strip().replace("Incomplete", "In-Progress").replace("On Hiatus", "In-Progress").replace("Complete", "Completed")
self.story.setMetadata('status', status)
self.story.setMetadata('rating', status_bar.span.text)
# This way is less elegant, perhaps, but more robust in face of format changes.
numWords = status_bar.find("div",{"class":"word_count"}).b.text
self.story.setMetadata('numWords', numWords)
description_soup = soup.find("div", {"class":"description"})
# Sometimes the description has an expanding element
# This removes the ellipsis and the expand button
try:
description_soup.find('span', {"id":re.compile(r"description_more_elipses_\d+")}).extract() # Web designer can't spell 'ellipsis'
description_soup.find('a', {"class":"more"}).extract()
except:
pass
status = storyMetadata["status"].replace("Incomplete", "In-Progress").replace("On Hiatus", "In-Progress").replace("Complete", "Completed")
self.story.setMetadata("status", status)
self.story.setMetadata("rating", storyMetadata["content_rating_text"])
for category in storyMetadata["categories"]:
if storyMetadata["categories"][category]:
self.story.addToList("genre", category)
self.story.addToList("category", "My Little Pony")
self.story.setMetadata("numWords", str(storyMetadata["words"]))
# fimfic is the first site with an explicit cover image.
story_img = soup.find('img',{'class':'story_image'})
if self.getConfig('include_images') and story_img:
self.story.addImgUrl(self,self.url,story_img['src'],self._fetchUrlRaw,cover=True)
self.setDescription(self.url,description_soup.text)
#self.story.setMetadata('description', description_soup.text)
if self.getConfig('include_images') and "image" in storyMetadata.keys():
coverurl = storyMetadata["image"]
if coverurl.startswith('//static.fimfiction.net'): # fix for img urls missing 'http:'
coverurl = "http:"+coverurl
self.story.addImgUrl(self,self.url,coverurl,self._fetchUrlRaw,cover=True)
self.setDescription(self.url, storyMetadata["description"])
# Unfortunately, nowhere on the page is the year mentioned.
# Best effort to deal with this:
# Use this year, if that's a date in the future, subtract one year.
# Their earliest story is Jun, so they'll probably change the date
# around then.
now = datetime.datetime.now()
# Dates are in Unix time
# Take the publish date from the first chapter posted
rawDatePublished = storyMetadata["chapters"][0]["date_modified"]
self.story.setMetadata("datePublished", datetime.fromtimestamp(rawDatePublished))
rawDateUpdated = storyMetadata["date_modified"]
self.story.setMetadata("dateUpdated", datetime.fromtimestamp(rawDateUpdated))
dateUpdated_soup = bs.BeautifulSoup(data).find("div", {"class":"calendar"})
dateUpdated_soup.find('span').extract()
dateUpdated = makeDate("%s%s"%(now.year,dateUpdated_soup.text), "%Y%b%d")
if dateUpdated > now :
dateUpdated = dateUpdated.replace(year=now.year-1)
self.story.setMetadata("dateUpdated", dateUpdated)
# Get the date of creation from the first chapter
if len(chapterDates) > 0:
datePublished_text = chapterDates[0]
day, month = datePublished_text.split()
day = re.sub(r"[^\d.]+", '', day)
datePublished = makeDate("%s%s%s"%(now.year,month,day), "%Y%b%d")
if datePublished > now :
datePublished = datePublished.replace(year=now.year-1)
self.story.setMetadata("datePublished", datePublished)
else:
self.story.setMetadata("datePublished", dateUpdated)
soup = bs.BeautifulSoup(data).find("div", {"class":"story"})
for character in [character_icon["title"] for character_icon in soup.findAll("a", {"class":"character_icon"})]:
self.story.addToList("characters", character)
def getChapterText(self, url):
logging.debug('Getting chapter text from: %s' % url)
+3 -2
View File
@@ -179,11 +179,12 @@ Some more longer description. "I suck at summaries!" "Better than it sounds!"
<div>
<h3>Chapter title from site</h3>
<p><center>Centered text</center></p>
<p>Lorem '''+self.crazystring+''' <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>
<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
<a href="http://code.google.com/p/fanficdownloader/wiki/FanFictionDownLoaderPluginWithReadingList" title="Tilt-a-Whirl by Jim &amp; Sarah, on Flickr"><img src="http://i.imgur.com/bo8eD.png"></a><br/>
br breaks<br><br>
Don't&#8212e;ver&#8212d;o&#8212;that&#8212a;gain, &#27861; &#xE9;
<hr>
horizontal rules
<hr size=1 noshade>
+15 -4
View File
@@ -19,12 +19,21 @@ import re
def _unirepl(match):
"Return the unicode string for a decimal number"
if match.group(1)=='x':
if match.group(1).startswith('x'):
radix=16
s = match.group(1)[1:]
else:
radix=10
value = int(match.group(2), radix)
return "%s%s"%(unichr(value),match.group(3))
s = match.group(1)
try:
value = int(s, radix)
retval = "%s%s"%(unichr(value),match.group(2))
except:
# This way, at least if there's more of entities out there
# that fail, it doesn't blow the entire download.
print "Numeric entity translation failed, skipping: &#x%s%s"%(match.group(1),match.group(2))
retval = ""
return retval
def _replaceNumberEntities(data):
# The same brokenish entity parsing in SGMLParser that inserts ';'
@@ -32,7 +41,9 @@ def _replaceNumberEntities(data):
# entities, including part of the next word if it's a-z.
# "Don't&#8212ever&#8212do&#8212that&#8212again," becomes
# "Don't&#8212e;ver&#8212d;o&#8212;that&#8212a;gain,"
p = re.compile(r'&#(x?)([0-9a-fA-F]{,4})([0-9a-fA-F]*);')
# Also need to allow for 5 digit decimal entities &#27861;
# Last expression didn't allow for 2 digit hex correctly: &#xE9;
p = re.compile(r'&#(x[0-9a-fA-F]{,4}|[0-9]{,5})([0-9a-fA-F]*?);')
return p.sub(_unirepl, data)
def _replaceNotEntities(data):
+6 -5
View File
@@ -218,7 +218,7 @@ class Story:
value = re.sub(p,v,value)
return value
def getMetadata(self, key, removeallentities=False):
def getMetadata(self, key, removeallentities=False, doreplacements=True):
value = None
if self.getLists().has_key(key):
value = ', '.join(self.getList(key))
@@ -232,21 +232,22 @@ class Story:
if key == "datePublished" or key == "dateUpdated":
value = value.strftime("%Y-%m-%d")
value=self.doReplacments(value)
if doreplacements:
value=self.doReplacments(value)
if removeallentities and value != None:
return removeAllEntities(value)
else:
return value
def getAllMetadata(self, removeallentities=False):
def getAllMetadata(self, removeallentities=False, doreplacements=True):
'''
All single value *and* list value metadata as strings.
'''
allmetadata = {}
for k in self.metadata.keys():
allmetadata[k] = self.getMetadata(k, removeallentities)
allmetadata[k] = self.getMetadata(k, removeallentities, doreplacements)
for l in self.listables.keys():
allmetadata[l] = self.getMetadata(l, removeallentities)
allmetadata[l] = self.getMetadata(l, removeallentities, doreplacements)
return allmetadata
+24
View File
@@ -13,8 +13,23 @@
# limitations under the License.
#
import pickle, copy
from google.appengine.ext import db
class ObjectProperty(db.Property):
data_type = db.Blob
def get_value_for_datastore(self, model_instance):
value = self.__get__(model_instance, model_instance.__class__)
pickled_val = pickle.dumps(value,protocol=pickle.HIGHEST_PROTOCOL)
if value is not None: return db.Blob(pickled_val)
def make_value_from_datastore(self, value):
if value is not None: return pickle.loads(value)
def default_value(self):
return copy.copy(self.default)
class DownloadMeta(db.Model):
user = db.UserProperty()
url = db.StringProperty()
@@ -37,3 +52,12 @@ class DownloadData(db.Model):
class UserConfig(db.Model):
user = db.UserProperty()
config = db.BlobProperty()
class SavedMeta(db.Model):
url = db.StringProperty()
title = db.StringProperty()
author = db.StringProperty()
date = db.DateTimeProperty(auto_now_add=True)
count = db.IntegerProperty()
meta = ObjectProperty()
+11 -3
View File
@@ -54,9 +54,14 @@
much easier. </p>
</div>
<!-- put announcements here, h3 is a good title size. -->
<h3>New Site Added</h3>
<h3>Latest Changes</h3>
<p>
Support for archive.skyehawke.com has been added. Thanks to Ida Leter for implementing this.
Fix for 'Hide this banner' title issue on Archive of Our
Own.
</p>
<p>
Changed implementation of fimfiction to use provided API,
thanks to Althaine.
</p>
<p>
Questions? Check out our
@@ -66,7 +71,7 @@
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://4-4-4.fanfictiondownloader.appspot.com">Previous Version</a> is also available for you to use if necessary.
<a href="http://4-4-7.fanfictiondownloader.appspot.com">Previous Version</a> is also available for you to use if necessary.
</p>
<div id='error'>
{{ error_message }}
@@ -96,6 +101,9 @@
<p>
Or see your personal list of <a href="/recent">previously downloaded fanfics</a>.
</p>
<p>
See a list of downloaded fanfics by all users by <a href="/allrecent">most popular</a> or <a href="/allrecent?bydate=1">most recent</a>.
</p>
</div>
</form>
{% else %}
+3 -8
View File
@@ -1,6 +1,6 @@
indexes:
# AUTOGENERATED
# notAUTOGENERATED
# This index.yaml is automatically updated whenever the dev_appserver
# detects that a new type of query is run. If you want to manage the
@@ -21,13 +21,8 @@ indexes:
- name: date
direction: desc
- kind: DownloadedFanfic
- kind: SavedMeta
properties:
- name: cleared
- name: date
- kind: DownloadedFanfic
properties:
- name: user
- name: count
- name: date
direction: desc
+51
View File
@@ -303,6 +303,39 @@ class RecentFilesServer(webapp2.RequestHandler):
path = os.path.join(os.path.dirname(__file__), 'recent.html')
self.response.out.write(template.render(path, template_values))
class AllRecentFilesServer(webapp2.RequestHandler):
def get(self):
user = users.get_current_user()
if not user:
self.redirect(users.create_login_url(self.request.uri))
return
q = SavedMeta.all()
if self.request.get('bydate'):
q.order('-date')
else:
q.order('-count')
fics = q.fetch(200)
logging.info("Recent fetched %d downloads for user %s."%(len(fics),user.nickname()))
sendslugs = []
for fic in fics:
ficslug = FicSlug(fic)
sendslugs.append(ficslug)
template_values = dict(fics = sendslugs, nickname = user.nickname())
path = os.path.join(os.path.dirname(__file__), 'allrecent.html')
self.response.out.write(template.render(path, template_values))
class FicSlug():
def __init__(self,savedmeta):
self.url = savedmeta.url
self.count = savedmeta.count
for k, v in savedmeta.meta.iteritems():
setattr(self,k,v)
class FanfictionDownloader(UserConfigServer):
def get(self):
self.post()
@@ -464,6 +497,8 @@ class FanfictionDownloaderTask(UserConfigServer):
download.url = adapter.getStory().getMetadata('storyUrl')
download.put()
allmeta = adapter.getStory().getAllMetadata(removeallentities=True,doreplacements=False)
outbuffer = StringIO()
writer.writeStory(outbuffer)
data = outbuffer.getvalue()
@@ -495,6 +530,21 @@ class FanfictionDownloaderTask(UserConfigServer):
download.completed=True
download.put()
smetal = SavedMeta.all().filter('url =', allmeta['storyUrl'] ).fetch(1)
if smetal and smetal[0]:
smeta = smetal[0]
smeta.count += 1
else:
smeta=SavedMeta()
smeta.count = 1
smeta.url = allmeta['storyUrl']
smeta.title = allmeta['title']
smeta.author = allmeta['author']
smeta.meta = allmeta
smeta.date = datetime.datetime.now()
smeta.put()
logging.info("Download finished OK")
del data
@@ -563,6 +613,7 @@ app = webapp2.WSGIApplication([('/', MainHandler),
('/fdown', FanfictionDownloader),
(r'/file.*', FileServer),
('/status', FileStatusServer),
('/allrecent', AllRecentFilesServer),
('/recent', RecentFilesServer),
('/editconfig', EditConfigServer),
('/clearrecent', ClearRecentServer),
+14
View File
@@ -127,6 +127,20 @@ extratags: FanFiction
## doesn't work on some devices either.)
#replace_hr: false
## If you have the Generate Cover plugin installed, you can use the
## generate_cover_settings parameter to intelligently decide which GC
## setting to run. There are three parts 1) a template of which
## 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]
## 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.
#generate_cover_settings:
# ${category} => Buffy:? [tT]he Vampire Slayer => BuffyCover
# ${category} => Star Trek => StarTrekCover
## Each output format has a section that overrides [defaults]
[html]