mirror of
https://github.com/wassname/FanFicFare.git
synced 2026-09-15 11:36:30 +08:00
Compare commits
26
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
83db111ba7 | ||
|
|
2eb8c27c80 | ||
|
|
a79066750c | ||
|
|
3857a6a89b | ||
|
|
016d4af149 | ||
|
|
a4e499866e | ||
|
|
5736f4f181 | ||
|
|
e04453d73f | ||
|
|
c3778502dc | ||
|
|
925b12e776 | ||
|
|
62ed503d10 | ||
|
|
7e35d0b710 | ||
|
|
20c7e7f075 | ||
|
|
9f61cff7cd | ||
|
|
cb5587b0c7 | ||
|
|
f2a74c9ffc | ||
|
|
eb0f013550 | ||
|
|
6674e19f94 | ||
|
|
29b1ca9a7e | ||
|
|
7cae65300a | ||
|
|
88fe13f603 | ||
|
|
a9b6989341 | ||
|
|
a54277058c | ||
|
|
4c27e19aa8 | ||
|
|
6f5ed2bcac | ||
|
|
cc0bccd420 |
@@ -1,6 +1,6 @@
|
||||
# ffd-retief-hrd fanfictiondownloader
|
||||
application: fanfictiondownloader
|
||||
version: 4-4-68
|
||||
version: 4-4-71
|
||||
runtime: python27
|
||||
api_version: 1
|
||||
threadsafe: true
|
||||
|
||||
@@ -26,7 +26,7 @@ class FanFictionDownLoaderBase(InterfaceActionBase):
|
||||
description = 'UI plugin to download FanFiction stories from various sites.'
|
||||
supported_platforms = ['windows', 'osx', 'linux']
|
||||
author = 'Jim Miller'
|
||||
version = (1, 7, 37)
|
||||
version = (1, 7, 42)
|
||||
minimum_calibre_version = (0, 8, 57)
|
||||
|
||||
#: This field defines the GUI plugin class that contains all the code
|
||||
|
||||
@@ -7,13 +7,14 @@ __license__ = 'GPL v3'
|
||||
__copyright__ = '2012, Jim Miller'
|
||||
__docformat__ = 'restructuredtext en'
|
||||
|
||||
import time, os, copy, threading, re, platform
|
||||
import time, os, copy, threading, re, platform, sys
|
||||
from StringIO import StringIO
|
||||
from functools import partial
|
||||
from datetime import datetime
|
||||
from string import Template
|
||||
import urllib
|
||||
import email
|
||||
import traceback
|
||||
|
||||
from PyQt4.Qt import (QApplication, QMenu, QToolButton, QTimer)
|
||||
|
||||
@@ -1003,7 +1004,7 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
|
||||
mi = db.get_metadata(book_id,index_is_id=True)
|
||||
if not book['series'] and mi.series != None:
|
||||
book['calibre_series'] = (mi.series,mi.series_index)
|
||||
print("calibre_series:%s [%s]"%book['calibre_series'])
|
||||
#print("calibre_series:%s [%s]"%book['calibre_series'])
|
||||
|
||||
if book['good']: # there shouldn't be any !'good' books at this point.
|
||||
# if still 'good', make a temp file to write the output to.
|
||||
@@ -1108,7 +1109,17 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
|
||||
|
||||
if options['collision'] == CALIBREONLY or \
|
||||
( (options['updatemeta'] or book['added']) and book['good'] ):
|
||||
self.update_metadata(db, book['calibre_id'], book, mi, options)
|
||||
try:
|
||||
self.update_metadata(db, book['calibre_id'], book, mi, options)
|
||||
except:
|
||||
det_msg = "".join(traceback.format_exception(*sys.exc_info()))+"\nStory Details:\n%s"%pretty_book(book)
|
||||
print("Error Updating Metadata:\n%s"%det_msg)
|
||||
error_dialog(self.gui,
|
||||
"Error Updating Metadata",
|
||||
"<p>An error has occurred while FFDL was updating calibre's metadata for <a href='%s'>%s</a>.</p>"%(book['url'],book['title'])+
|
||||
"The ebook has been updated, but the metadata has not.",
|
||||
det_msg=det_msg,
|
||||
show=True)
|
||||
|
||||
def update_books_finish(self, book_list, options={}, showlist=True):
|
||||
'''Notify calibre about updated rows, update external plugins
|
||||
@@ -1159,11 +1170,20 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
|
||||
self.gui.library_view.sort_by_named_field('marked', True)
|
||||
|
||||
self.gui.status_bar.show_message(_('Finished Adding/Updating %d books.'%(len(update_list) + len(add_list))), 3000)
|
||||
|
||||
|
||||
1+1
|
||||
|
||||
print("all done, remove temp dir.")
|
||||
|
||||
1+1
|
||||
|
||||
remove_dir(options['tdir'])
|
||||
|
||||
print("Count Pages:prefs:%s\nCP plugin available %s\nids:%s"%(prefs['countpagesstats'],'Count Pages' in self.gui.iactions,all_ids))
|
||||
1+1
|
||||
|
||||
print("removed temp dir.")
|
||||
|
||||
|
||||
if 'Count Pages' in self.gui.iactions and len(prefs['countpagesstats']) and len(all_ids):
|
||||
cp_plugin = self.gui.iactions['Count Pages']
|
||||
cp_plugin.count_statistics(all_ids,prefs['countpagesstats'])
|
||||
@@ -1371,8 +1391,8 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
|
||||
oldmi = db.get_metadata(book_id,index_is_id=True)
|
||||
if prefs['keeptags']:
|
||||
old_tags = db.get_tags(book_id)
|
||||
print("old_tags:%s"%old_tags)
|
||||
print("mi.tags:%s"%mi.tags)
|
||||
#print("old_tags:%s"%old_tags)
|
||||
#print("mi.tags:%s"%mi.tags)
|
||||
# remove old Completed/In-Progress only if there's a new one.
|
||||
if 'Completed' in mi.tags or 'In-Progress' in mi.tags:
|
||||
old_tags = filter( lambda x : x not in ('Completed', 'In-Progress'), old_tags)
|
||||
@@ -1386,9 +1406,8 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
|
||||
for t in list(mi.tags) + list(old_tags):
|
||||
foldedcase_tags[t.lower()] = t
|
||||
|
||||
mi.tags = foldedcase_tags.values()
|
||||
|
||||
print("mi.tags:%s"%mi.tags)
|
||||
mi.tags = foldedcase_tags.values()
|
||||
#print("mi.tags:%s"%mi.tags)
|
||||
|
||||
if book['all_metadata']['langcode']:
|
||||
mi.languages=[book['all_metadata']['langcode']]
|
||||
@@ -1421,12 +1440,14 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
|
||||
pass
|
||||
|
||||
db.set_metadata(book_id,mi)
|
||||
# mi.authors gets run through the string_to_authors and split on '&' ',' 'and' and 'with'
|
||||
db.set_authors(book_id,book['author']) # author is a list.
|
||||
|
||||
# do configured column updates here.
|
||||
#print("all_metadata: %s"%book['all_metadata'])
|
||||
custom_columns = self.gui.library_view.model().custom_columns
|
||||
|
||||
print("prefs['custom_cols'] %s"%prefs['custom_cols'])
|
||||
#print("prefs['custom_cols'] %s"%prefs['custom_cols'])
|
||||
for col, meta in prefs['custom_cols'].iteritems():
|
||||
#print("setting %s to %s"%(col,meta))
|
||||
if col not in custom_columns:
|
||||
@@ -1445,18 +1466,15 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
|
||||
continue
|
||||
label = coldef['label']
|
||||
if coldef['datatype'] in ('enumeration','text','comments','datetime','series'):
|
||||
print("1 db.set_custom(%s,%s,%s)"%(book_id, book['all_metadata'][meta], label))
|
||||
db.set_custom(book_id, book['all_metadata'][meta], label, commit=False)
|
||||
elif coldef['datatype'] in ('int','float'):
|
||||
num = unicode(book['all_metadata'][meta]).replace(",","")
|
||||
print("2 db.set_custom(%s,%s,%s)"%(book_id, num, label))
|
||||
db.set_custom(book_id, num, label=label, commit=False)
|
||||
elif coldef['datatype'] == 'bool' and meta.startswith('status-'):
|
||||
if meta == 'status-C':
|
||||
val = book['all_metadata']['status'] == 'Completed'
|
||||
if meta == 'status-I':
|
||||
val = book['all_metadata']['status'] == 'In-Progress'
|
||||
print("3 db.set_custom(%s,%s,%s)"%(book_id, val, label))
|
||||
db.set_custom(book_id, val, label=label, commit=False)
|
||||
|
||||
configuration = None
|
||||
@@ -1471,14 +1489,11 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
|
||||
if "," in custcol:
|
||||
(custcol,flag) = map( lambda x: x.strip(), custcol.split(",") )
|
||||
|
||||
print("meta:(%s) => custcol:(%s), flag(%s) "%(meta,custcol,flag))
|
||||
|
||||
if meta not in book['all_metadata']:
|
||||
print("No value for %s, skipping custom column(%s) update."%(meta,custcol))
|
||||
continue
|
||||
|
||||
if custcol not in custom_columns:
|
||||
print("No custom column(%s), skipping."%(custcol))
|
||||
continue
|
||||
else:
|
||||
coldef = custom_columns[custcol]
|
||||
@@ -1493,7 +1508,6 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
|
||||
val = unicode(book['all_metadata'][meta]).replace(",","")
|
||||
else:
|
||||
val = book['all_metadata'][meta]
|
||||
print("4 db.set_custom(%s,%s,%s)"%(book_id, val, label))
|
||||
db.set_custom(book_id, val, label=label, commit=False)
|
||||
|
||||
if flag == 'a':
|
||||
@@ -1510,22 +1524,33 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
|
||||
if book['all_metadata'][meta]:
|
||||
vallist = [book['all_metadata'][meta]]
|
||||
|
||||
print("5 db.set_custom(%s,%s,%s)"%(book_id, ", ".join(vallist), label))
|
||||
db.set_custom(book_id, ", ".join(vallist), label=label, commit=False)
|
||||
|
||||
# set author link if found. All current adapters have authorUrl, except anonymous on AO3.
|
||||
# Moved down so author's already in the DB.
|
||||
if 'authorUrl' in book['all_metadata']:
|
||||
authurls = book['all_metadata']['authorUrl'].split(", ")
|
||||
for i, auth in enumerate(book['author']):
|
||||
#print("===Update author url for %s to %s"%(auth,authurls[i]))
|
||||
autid=db.get_author_id(auth)
|
||||
db.set_link_field_for_author(autid, unicode(authurls[i]),
|
||||
commit=False, notify=False)
|
||||
authorlist = [ a.replace('&',';') for a in book['author'] ]
|
||||
if hasattr(db, 'new_api'): # new_api starts in calibre 1.0.0
|
||||
authorids = db.new_api.get_item_ids('authors',authorlist)
|
||||
authordata = db.new_api.author_data(authorids.values())
|
||||
# print("\n\nauthorids:%s"%authorids)
|
||||
# print("authordata:%s"%authordata)
|
||||
|
||||
print("About to call db.commit()")
|
||||
author_id_to_link_map = dict()
|
||||
for i, author in enumerate(authorlist):
|
||||
author_id_to_link_map[authorids[author]] = authurls[i]
|
||||
|
||||
# print("author_id_to_link_map:%s\n\n"%author_id_to_link_map)
|
||||
db.new_api.set_link_for_authors(author_id_to_link_map)
|
||||
else:
|
||||
# keep for pre-calibre 1.0.0
|
||||
for i, auth in enumerate(authorlist):
|
||||
#print("===Update author url for %s to %s"%(auth,authurls[i]))
|
||||
autid=db.get_author_id(auth)
|
||||
db.set_link_field_for_author(autid, unicode(authurls[i]),
|
||||
commit=False, notify=False)
|
||||
db.commit()
|
||||
print("After call db.commit()")
|
||||
|
||||
if 'Generate Cover' in self.gui.iactions and (book['added'] or not prefs['gcnewonly']):
|
||||
|
||||
@@ -1917,3 +1942,17 @@ def split_text_to_urls(urls):
|
||||
def escapehtml(txt):
|
||||
return txt.replace("&","&").replace(">",">").replace("<","<")
|
||||
|
||||
def pretty_book(d, indent=0, spacer=' '):
|
||||
kindent = spacer * indent
|
||||
|
||||
# if isinstance(d, list):
|
||||
# return '\n'.join([(pretty_book(v, indent, spacer)) for v in d])
|
||||
|
||||
if isinstance(d, dict):
|
||||
for k in ('password','username'):
|
||||
if k in d and d[k]:
|
||||
d[k]='<was set, removed for security>'
|
||||
return '\n'.join(['%s%s:\n%s' % (kindent, k, pretty_book(v, indent + 1, spacer))
|
||||
for k, v in d.items()])
|
||||
return "%s%s"%(kindent, d)
|
||||
|
||||
|
||||
+26
-5
@@ -16,7 +16,22 @@
|
||||
[defaults]
|
||||
|
||||
## [defaults] section applies to all formats and sites but may be
|
||||
## overridden at several levels
|
||||
## overridden at several levels. Example:
|
||||
|
||||
## [defaults]
|
||||
## titlepage_entries: category,genre, status
|
||||
## [www.whofic.com]
|
||||
## # overrides defaults.
|
||||
## titlepage_entries: category,genre, status,dateUpdated,rating
|
||||
## [epub]
|
||||
## # overrides defaults & site section
|
||||
## titlepage_entries: category,genre, status,datePublished,dateUpdated,dateCreated
|
||||
## [www.whofic.com:epub]
|
||||
## # overrides defaults, site section & format section
|
||||
## titlepage_entries: category,genre, status,datePublished
|
||||
## [overrides]
|
||||
## # overrides all other sections
|
||||
## titlepage_entries: category
|
||||
|
||||
## Some sites also require the user to confirm they are adult for
|
||||
## adult content. Uncomment by removing '#' in front of is_adult.
|
||||
@@ -152,6 +167,9 @@ extratags: FanFiction
|
||||
#extraships:
|
||||
#extrawarnings:
|
||||
|
||||
## Add this to genre if there's more than one category.
|
||||
#add_genre_when_multi_category: Crossover
|
||||
|
||||
## number of seconds to sleep between calls to the story site. May by
|
||||
## useful if pulling large numbers of stories or if the site is slow.
|
||||
#slow_down_sleep_time:0.5
|
||||
@@ -259,6 +277,8 @@ sort_ships:false
|
||||
## you added calibre_author: keep_in_order_calibre_author:true
|
||||
#keep_in_order_author:true
|
||||
|
||||
## User-agent
|
||||
#user_agent:FFDL/1.7
|
||||
|
||||
## Each output format has a section that overrides [defaults]
|
||||
[html]
|
||||
@@ -447,8 +467,8 @@ nook_img_fix:true
|
||||
## mobi TOC cannot be turned off right now.
|
||||
#include_tocpage: true
|
||||
|
||||
## Each site has a section that overrides [defaults] *and* the format
|
||||
## sections test1.com specifically is not a real story site. Instead,
|
||||
## Each site has a section that overrides [defaults].
|
||||
## test1.com specifically is not a real story site. Instead,
|
||||
## it is a fake site for testing configuration and output. It uses
|
||||
## URLs like: http://test1.com?sid=12345
|
||||
[test1.com]
|
||||
@@ -505,7 +525,8 @@ extratags: FanFiction,Testing,HTML
|
||||
#is_adult:true
|
||||
|
||||
## AO3 adapter defines a few extra metadata entries.
|
||||
extra_valid_entries:fandoms,freeformtags,freefromtags,ao3categories,comments,kudos,hits,bookmarks,collections
|
||||
## If there's ever more than 4 series, add series04,series04Url etc.
|
||||
extra_valid_entries:fandoms,freeformtags,freefromtags,ao3categories,comments,kudos,hits,bookmarks,collections,series00,series01,series02,series03,series00Url,series01Url,series02Url,series03Url
|
||||
fandoms_label:Fandoms
|
||||
freeformtags_label:Freeform Tags
|
||||
freefromtags_label:Freeform Tags
|
||||
@@ -521,7 +542,7 @@ bookmarks_label:Bookmarks
|
||||
include_in_freefromtags:freeformtags
|
||||
|
||||
## adds to titlepage_entries instead of replacing it.
|
||||
#extra_titlepage_entries: fandoms,freeformtags,ao3categories,comments,kudos,hits,bookmarks
|
||||
#extra_titlepage_entries: fandoms,freeformtags,ao3categories,comments,kudos,hits,bookmarks,series00,series01,series02,series03,series00Url,series01Url,series02Url,series03Url
|
||||
|
||||
## adds to include_subject_tags instead of replacing it.
|
||||
#extra_subject_tags:fandoms,freeformtags,ao3categories
|
||||
|
||||
@@ -210,10 +210,7 @@ class ArchiveOfOurOwnOrgAdapter(BaseSiteAdapter):
|
||||
if a != None:
|
||||
warnings = a.findAll('a',{'class':"tag"})
|
||||
for warning in warnings:
|
||||
if warning.string == "Author Chose Not To Use Archive Warnings":
|
||||
warning.string = "No Archive Warnings Apply"
|
||||
if warning.string != "No Archive Warnings Apply":
|
||||
self.story.addToList('warnings',warning.string)
|
||||
self.story.addToList('warnings',warning.string)
|
||||
|
||||
a = metasoup.find('dd',{'class':"freeform tags"})
|
||||
if a != None:
|
||||
@@ -288,19 +285,19 @@ class ArchiveOfOurOwnOrgAdapter(BaseSiteAdapter):
|
||||
self.story.setMetadata('dateUpdated', makeDate(stripHTML(value), self.dateformat))
|
||||
|
||||
|
||||
try:
|
||||
# Find Series name from series URL.
|
||||
a = metasoup.find('dd',{'class':"series"})
|
||||
b = a.find('a', href=re.compile(r"/series/\d+"))
|
||||
series_name = b.string
|
||||
series_url = 'http://'+self.host+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
|
||||
pass
|
||||
# Find Series name from series URL.
|
||||
ddseries = metasoup.find('dd',{'class':"series"})
|
||||
|
||||
if ddseries:
|
||||
for i, a in enumerate(ddseries.findAll('a', href=re.compile(r"/series/\d+"))):
|
||||
series_name = stripHTML(a)
|
||||
series_url = 'http://'+self.host+a['href']
|
||||
series_index = int(stripHTML(a.previousSibling).replace(', ','').split(' ')[1]) # "Part # of" or ", Part #"
|
||||
self.story.setMetadata('series%02d'%i,"%s [%s]"%(series_name,series_index))
|
||||
self.story.setMetadata('series%02dUrl'%i,series_url)
|
||||
if i == 0:
|
||||
self.setSeries(series_name, series_index)
|
||||
self.story.setMetadata('seriesUrl',series_url)
|
||||
|
||||
# grab the text for an individual chapter.
|
||||
def getChapterText(self, url):
|
||||
|
||||
@@ -199,7 +199,7 @@ class FanFictionNetSiteAdapter(BaseSiteAdapter):
|
||||
for g in genrelist:
|
||||
#logger.debug("g:(%s)"%g)
|
||||
if g.strip() not in ffnetgenres:
|
||||
logger.info("g not in ffnetgenres")
|
||||
#logger.info("g not in ffnetgenres")
|
||||
goodgenres=False
|
||||
if goodgenres:
|
||||
self.story.extendList('genre',genrelist)
|
||||
@@ -266,11 +266,11 @@ class FanFictionNetSiteAdapter(BaseSiteAdapter):
|
||||
return
|
||||
|
||||
def getChapterText(self, url):
|
||||
logger.debug('Getting chapter text from: %s' % url)
|
||||
time.sleep(0.5) ## ffnet(and, I assume, fpcom) tends to fail
|
||||
time.sleep(5.0) ## ffnet(and, I assume, fpcom) tends to fail
|
||||
## more if hit too fast. This is in
|
||||
## additional to what ever the
|
||||
## slow_down_sleep_time setting is.
|
||||
logger.debug('Getting chapter text from: %s' % url)
|
||||
data = self._fetchUrl(url)
|
||||
|
||||
if "Please email this error message in full to <a href='mailto:support@fanfiction.com'>support@fanfiction.com</a>" in data:
|
||||
|
||||
@@ -131,55 +131,55 @@ class HarryPotterFanFictionComSiteAdapter(BaseSiteAdapter):
|
||||
|
||||
## Finding the metadata is a bit of a pain. Most of the meta
|
||||
## data is in a center.table without a bgcolor.
|
||||
for center in soup.findAll('center'):
|
||||
table = center.find('table',{'bgcolor':None})
|
||||
if table:
|
||||
metastr = stripHTML(str(table)).replace('\n',' ').replace('\t',' ')
|
||||
# Rating: 12+ Story Reviews: 3
|
||||
# Chapters: 3
|
||||
# Characters: Andromeda, Ted, Bellatrix, R. Lestrange, Lucius, Narcissa, OC
|
||||
# Genre(s): Fluff, Romance, Young Adult Era: OtherPairings: Other Pairing, Lucius/Narcissa
|
||||
# Status: Completed
|
||||
# First Published: 2010.09.02
|
||||
# Last Published Chapter: 2010.09.28
|
||||
# Last Updated: 2010.09.28
|
||||
# Favorite Story Of: 1 users
|
||||
# Warnings: Scenes of a Mild Sexual Nature
|
||||
#for center in soup.findAll('center'):
|
||||
table = soup.find('table',{'class':'storymaininfo'})
|
||||
if table:
|
||||
metastr = stripHTML(str(table)).replace('\n',' ').replace('\t',' ')
|
||||
# Rating: 12+ Story Reviews: 3
|
||||
# Chapters: 3
|
||||
# Characters: Andromeda, Ted, Bellatrix, R. Lestrange, Lucius, Narcissa, OC
|
||||
# Genre(s): Fluff, Romance, Young Adult Era: OtherPairings: Other Pairing, Lucius/Narcissa
|
||||
# Status: Completed
|
||||
# First Published: 2010.09.02
|
||||
# Last Published Chapter: 2010.09.28
|
||||
# Last Updated: 2010.09.28
|
||||
# Favorite Story Of: 1 users
|
||||
# Warnings: Scenes of a Mild Sexual Nature
|
||||
|
||||
m = re.match(r".*?Status: Completed.*?",metastr)
|
||||
if m:
|
||||
self.story.setMetadata('status','Completed')
|
||||
else:
|
||||
self.story.setMetadata('status','In-Progress')
|
||||
m = re.match(r".*?Status: Completed.*?",metastr)
|
||||
if m:
|
||||
self.story.setMetadata('status','Completed')
|
||||
else:
|
||||
self.story.setMetadata('status','In-Progress')
|
||||
|
||||
m = re.match(r".*?Rating: (.+?) Story Reviews.*?",metastr)
|
||||
if m:
|
||||
self.story.setMetadata('rating', m.group(1))
|
||||
m = re.match(r".*?Rating: (.+?) Story Reviews.*?",metastr)
|
||||
if m:
|
||||
self.story.setMetadata('rating', m.group(1))
|
||||
|
||||
m = re.match(r".*?Genre\(s\): (.+?) Era.*?",metastr)
|
||||
if m:
|
||||
for g in m.group(1).split(','):
|
||||
self.story.addToList('genre',g)
|
||||
|
||||
m = re.match(r".*?Characters: (.+?) Genre.*?",metastr)
|
||||
if m:
|
||||
for g in m.group(1).split(','):
|
||||
self.story.addToList('characters',g)
|
||||
|
||||
m = re.match(r".*?Warnings: (.+).*?",metastr)
|
||||
if m:
|
||||
for w in m.group(1).split(','):
|
||||
if w != 'Now Warnings':
|
||||
self.story.addToList('warnings',w)
|
||||
|
||||
m = re.match(r".*?First Published: ([0-9\.]+).*?",metastr)
|
||||
if m:
|
||||
self.story.setMetadata('datePublished',makeDate(m.group(1), "%Y.%m.%d"))
|
||||
m = re.match(r".*?Genre\(s\): (.+?) Era.*?",metastr)
|
||||
if m:
|
||||
for g in m.group(1).split(','):
|
||||
self.story.addToList('genre',g)
|
||||
|
||||
m = re.match(r".*?Characters: (.+?) Genre.*?",metastr)
|
||||
if m:
|
||||
for g in m.group(1).split(','):
|
||||
self.story.addToList('characters',g)
|
||||
|
||||
m = re.match(r".*?Warnings: (.+).*?",metastr)
|
||||
if m:
|
||||
for w in m.group(1).split(','):
|
||||
if w != 'Now Warnings':
|
||||
self.story.addToList('warnings',w)
|
||||
|
||||
m = re.match(r".*?First Published: ([0-9\.]+).*?",metastr)
|
||||
if m:
|
||||
self.story.setMetadata('datePublished',makeDate(m.group(1), "%Y.%m.%d"))
|
||||
|
||||
# Updated can have more than one space after it. <shrug>
|
||||
m = re.match(r".*?Last Updated: ([0-9\.]+).*?",metastr)
|
||||
if m:
|
||||
self.story.setMetadata('dateUpdated',makeDate(m.group(1), "%Y.%m.%d"))
|
||||
# Updated can have more than one space after it. <shrug>
|
||||
m = re.match(r".*?Last Updated: ([0-9\.]+).*?",metastr)
|
||||
if m:
|
||||
self.story.setMetadata('dateUpdated',makeDate(m.group(1), "%Y.%m.%d"))
|
||||
|
||||
def getChapterText(self, url):
|
||||
|
||||
|
||||
@@ -37,11 +37,6 @@ class HPFanficArchiveComAdapter(BaseSiteAdapter):
|
||||
def __init__(self, config, url):
|
||||
BaseSiteAdapter.__init__(self, config, url)
|
||||
|
||||
# hpfanficarchive.com blocks the default user-agent. However,
|
||||
# when asked, they said it was just general anti-spam, not
|
||||
# targeted at us. That lets me do this in good conscience:
|
||||
self.opener.addheaders = [('User-agent', 'FFDL/1.7')]
|
||||
|
||||
self.decode = ["Windows-1252",
|
||||
"utf8"] # 1252 is a superset of iso-8859-1.
|
||||
# Most sites that claim to be
|
||||
|
||||
@@ -37,11 +37,6 @@ class NCISFictionNetAdapter(BaseSiteAdapter):
|
||||
def __init__(self, config, url):
|
||||
BaseSiteAdapter.__init__(self, config, url)
|
||||
|
||||
# ncisfiction.net blocks the default user-agent. However,
|
||||
# when asked, they said it was just general anti-spam, not
|
||||
# targeted at us. That lets me do this in good conscience:
|
||||
self.opener.addheaders = [('User-agent', 'FFDL/1.7')]
|
||||
|
||||
self.decode = ["iso-8859-1",
|
||||
"Windows-1252"] # 1252 is a superset of iso-8859-1.
|
||||
# Most sites that claim to be
|
||||
|
||||
@@ -77,6 +77,8 @@ class BaseSiteAdapter(Configurable):
|
||||
self.is_adult=False
|
||||
|
||||
self.opener = u2.build_opener(u2.HTTPCookieProcessor(),GZipProcessor())
|
||||
## Specific UA because too many sites are blocking the default python UA.
|
||||
self.opener.addheaders = [('User-agent', self.getConfig('user_agent'))]
|
||||
self.storyDone = False
|
||||
self.metadataDone = False
|
||||
self.story = Story(configuration)
|
||||
|
||||
@@ -411,6 +411,9 @@ class Story(Configurable):
|
||||
if not value in self.metadata[listname]:
|
||||
self.metadata[listname].append(value)
|
||||
|
||||
if listname == 'category' and self.getConfig('add_genre_when_multi_category') and len(self.metadata[listname]) > 1:
|
||||
self.addToList('genre',self.getConfig('add_genre_when_multi_category'))
|
||||
|
||||
def isList(self,listname):
|
||||
'Everything set with an include_in_* is considered a list.'
|
||||
return self.hasConfig("include_in_"+listname) or \
|
||||
|
||||
+15
-2
@@ -53,13 +53,26 @@
|
||||
<p>Hi, {{ nickname }}! This is FanFictionDownLoader, which makes reading stories from various websites
|
||||
much easier. </p>
|
||||
</div>
|
||||
<!-- put announcements here, h3 is a good title size. -->
|
||||
<!-- put announcements here, h3 is a good title size.
|
||||
<h3>Changes:</h3>
|
||||
<p>
|
||||
<ul>
|
||||
<li>Minor optimizations.</li>
|
||||
<li>Better doc section override order in ini files.</li>
|
||||
<li>Additional series as site specific data for AO3.</li>
|
||||
<li>Fix for AO3 stories without series.</li>
|
||||
<li>Fixes for changes to harrypotterfanfictioncom.</li>
|
||||
<li>Add User-agent="FFDL/1.7" for all adapters for fanfiction.net changes.<br>
|
||||
(Remove from specific adapters.)</li>
|
||||
</ul>
|
||||
</p>
|
||||
-->
|
||||
<h3>fanfiction.net</h3>
|
||||
<p>
|
||||
Fanfiction.net appears to be blocking access from Google
|
||||
App Engine IPs, which prevents this web service. There's
|
||||
nothing I can do about it. At the time of writing, the
|
||||
latest CLI and calibre plugin versions worked.
|
||||
</p>
|
||||
|
||||
<p>
|
||||
Questions? Check out our
|
||||
|
||||
+27
-5
@@ -16,7 +16,22 @@
|
||||
[defaults]
|
||||
|
||||
## [defaults] section applies to all formats and sites but may be
|
||||
## overridden at several levels
|
||||
## overridden at several levels. Example:
|
||||
|
||||
## [defaults]
|
||||
## titlepage_entries: category,genre, status
|
||||
## [www.whofic.com]
|
||||
## # overrides defaults.
|
||||
## titlepage_entries: category,genre, status,dateUpdated,rating
|
||||
## [epub]
|
||||
## # overrides defaults & site section
|
||||
## titlepage_entries: category,genre, status,datePublished,dateUpdated,dateCreated
|
||||
## [www.whofic.com:epub]
|
||||
## # overrides defaults, site section & format section
|
||||
## titlepage_entries: category,genre, status,datePublished
|
||||
## [overrides]
|
||||
## # overrides all other sections
|
||||
## titlepage_entries: category
|
||||
|
||||
## Some sites also require the user to confirm they are adult for
|
||||
## adult content. Uncomment by removing '#' in front of is_adult.
|
||||
@@ -124,6 +139,9 @@ extratags: FanFiction
|
||||
#extraships:
|
||||
#extrawarnings:
|
||||
|
||||
## Add this to genre if there's more than one category.
|
||||
#add_genre_when_multi_category: Crossover
|
||||
|
||||
## number of seconds to sleep between calls to the story site. May by
|
||||
## useful if pulling large numbers of stories or if the site is slow.
|
||||
#slow_down_sleep_time:0.5
|
||||
@@ -246,6 +264,9 @@ sort_ships:false
|
||||
## you added calibre_author: keep_in_order_calibre_author:true
|
||||
#keep_in_order_author:true
|
||||
|
||||
## User-agent
|
||||
#user_agent:FFDL/1.7
|
||||
|
||||
|
||||
## Each output format has a section that overrides [defaults]
|
||||
[html]
|
||||
@@ -416,8 +437,8 @@ nook_img_fix:true
|
||||
## mobi TOC cannot be turned off right now.
|
||||
#include_tocpage: true
|
||||
|
||||
## Each site has a section that overrides [defaults] *and* the format
|
||||
## sections test1.com specifically is not a real story site. Instead,
|
||||
## Each site has a section that overrides [defaults].
|
||||
## test1.com specifically is not a real story site. Instead,
|
||||
## it is a fake site for testing configuration and output. It uses
|
||||
## URLs like: http://test1.com?sid=12345
|
||||
[test1.com]
|
||||
@@ -474,7 +495,8 @@ extratags: FanFiction,Testing,HTML
|
||||
#is_adult:true
|
||||
|
||||
## AO3 adapter defines a few extra metadata entries.
|
||||
extra_valid_entries:fandoms,freeformtags,freefromtags,ao3categories,comments,kudos,hits,bookmarks,collections
|
||||
## If there's ever more than 4 series, add series04,series04Url etc.
|
||||
extra_valid_entries:fandoms,freeformtags,freefromtags,ao3categories,comments,kudos,hits,bookmarks,collections,series00,series01,series02,series03,series00Url,series01Url,series02Url,series03Url
|
||||
fandoms_label:Fandoms
|
||||
freeformtags_label:Freeform Tags
|
||||
freefromtags_label:Freeform Tags
|
||||
@@ -490,7 +512,7 @@ bookmarks_label:Bookmarks
|
||||
include_in_freefromtags:freeformtags
|
||||
|
||||
## adds to titlepage_entries instead of replacing it.
|
||||
#extra_titlepage_entries: fandoms,freeformtags,ao3categories,comments,kudos,hits,bookmarks
|
||||
#extra_titlepage_entries: fandoms,freeformtags,ao3categories,comments,kudos,hits,bookmarks,series00,series01,series02,series03,series00Url,series01Url,series02Url,series03Url
|
||||
|
||||
## adds to include_subject_tags instead of replacing it.
|
||||
#extra_subject_tags:fandoms,freeformtags,ao3categories
|
||||
|
||||
@@ -2,6 +2,24 @@
|
||||
## like. Uncomment options by removing the '#' in front of them.
|
||||
|
||||
[defaults]
|
||||
## [defaults] section applies to all formats and sites but may be
|
||||
## overridden at several levels. Example:
|
||||
|
||||
## [defaults]
|
||||
## titlepage_entries: category,genre, status
|
||||
## [www.whofic.com]
|
||||
## # overrides defaults.
|
||||
## titlepage_entries: category,genre, status,dateUpdated,rating
|
||||
## [epub]
|
||||
## # overrides defaults & site section
|
||||
## titlepage_entries: category,genre, status,datePublished,dateUpdated,dateCreated
|
||||
## [www.whofic.com:epub]
|
||||
## # overrides defaults, site section & format section
|
||||
## titlepage_entries: category,genre, status,datePublished
|
||||
## [overrides]
|
||||
## # overrides all other sections
|
||||
## titlepage_entries: category
|
||||
|
||||
## Some sites also require the user to confirm they are adult for
|
||||
## adult content. Uncomment by removing '#' in front of is_adult.
|
||||
#is_adult:true
|
||||
@@ -15,6 +33,9 @@
|
||||
#strip_chapter_numbers:true
|
||||
#add_chapter_numbers:true
|
||||
|
||||
## Add this to genre if there's more than one category.
|
||||
#add_genre_when_multi_category: Crossover
|
||||
|
||||
[epub]
|
||||
## include images from img tags in the body and summary of stories.
|
||||
## Images will be converted to jpg for size if possible. Images work
|
||||
|
||||
Reference in New Issue
Block a user