mirror of
https://github.com/wassname/FanFicFare.git
synced 2026-09-15 11:36:30 +08:00
Compare commits
33
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
125e29091f | ||
|
|
d0c73d5444 | ||
|
|
bd8e54edcf | ||
|
|
d680a86f0c | ||
|
|
f075ae582d | ||
|
|
928ebb9751 | ||
|
|
ce262be162 | ||
|
|
6faa6850af | ||
|
|
f392c6dd77 | ||
|
|
af0dff28b4 | ||
|
|
02a75a821f | ||
|
|
c06028b498 | ||
|
|
de4b95af9b | ||
|
|
5366355d96 | ||
|
|
264853d768 | ||
|
|
d82b399738 | ||
|
|
59446d23dc | ||
|
|
6fcbdd8a8d | ||
|
|
1348525d25 | ||
|
|
40bac62c5e | ||
|
|
362f15f9fa | ||
|
|
b833041dc4 | ||
|
|
fa67220b86 | ||
|
|
4f412eb89f | ||
|
|
6a4aa4340e | ||
|
|
dc785b911e | ||
|
|
d403f916a9 | ||
|
|
29fe1a6e24 | ||
|
|
131a08c0dc | ||
|
|
fbd26c16e0 | ||
|
|
34ebba40d0 | ||
|
|
7ce8436208 | ||
|
|
b247e4fc7b |
@@ -1,6 +1,6 @@
|
||||
# ffd-retief-hrd fanfictiondownloader
|
||||
application: fanfictiondownloader
|
||||
version: 4-4-97
|
||||
version: 4-5-02
|
||||
runtime: python27
|
||||
api_version: 1
|
||||
threadsafe: true
|
||||
|
||||
@@ -42,7 +42,7 @@ class FanFictionDownLoaderBase(InterfaceActionBase):
|
||||
description = _('UI plugin to download FanFiction stories from various sites.')
|
||||
supported_platforms = ['windows', 'osx', 'linux']
|
||||
author = 'Jim Miller'
|
||||
version = (1, 8, 16)
|
||||
version = (1, 8, 21)
|
||||
minimum_calibre_version = (1, 13, 0)
|
||||
|
||||
#: This field defines the GUI plugin class that contains all the code
|
||||
|
||||
@@ -970,7 +970,8 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
|
||||
if book_id and mi: # book_id and mi only set if matched by title/author.
|
||||
liburl = self.get_story_url(db,book_id)
|
||||
if book['url'] != liburl and prefs['checkforurlchange'] and \
|
||||
not (book['url'].replace('https','http') == liburl and 'fanfiction.net' in liburl):
|
||||
not (book['url'].replace('https','http') == liburl): # several sites have been changing to
|
||||
# https now. Don't flag when that's the only change.
|
||||
# special case for ffnet urls change to https.
|
||||
if not question_dialog(self.gui, _('Change Story URL?'),'''
|
||||
<h3>%s</h3>
|
||||
|
||||
+31
-1
@@ -219,7 +219,32 @@ connect_timeout:60.0
|
||||
# .*-Centered=>
|
||||
# characters=>Sam W\.=>Sam Witwicky&&category=>Transformers
|
||||
# characters=>Sam W\.=>Sam Winchester&&category=>Supernatural
|
||||
|
||||
|
||||
## Include/Exclude metadata
|
||||
##
|
||||
## You can use the include/exclude metadata features to either limit
|
||||
## the values of particular metadata lists to specific values or to
|
||||
## exclude specific values. Further, you can conditionally apply each
|
||||
## line depending on other metadata, use exact strings or regular
|
||||
## expressions(regex) to match values, and negate matches.
|
||||
##
|
||||
## The settings are:
|
||||
## include_metadata_pre
|
||||
## exclude_metadata_pre
|
||||
## include_metadata_post
|
||||
## exclude_metadata_post
|
||||
##
|
||||
## The form of each line is:
|
||||
## metakey[,metakey]==exactvalue
|
||||
## metakey[,metakey]=~regex
|
||||
## metakey[,metakey]==exactvalue&&conditionalkey==exactcondvalue
|
||||
## metakey[,metakey]=~regex&&conditionalkey==exactcondvalue
|
||||
## metakey[,metakey]==exactvalue&&conditionalkey=~condregex
|
||||
##
|
||||
## This is fairly complicated, so it's documented on its own wiki
|
||||
## page:
|
||||
## https://code.google.com/p/fanficdownloader/wiki/InExcludeMetadataFeature
|
||||
|
||||
## Some readers don't show horizontal rule (<hr />) tags correctly.
|
||||
## This replaces them all with a centered '* * *'. (Note centering
|
||||
## doesn't work on some devices either.)
|
||||
@@ -1314,6 +1339,11 @@ extra_valid_entries:reviews,favs,follows
|
||||
## when updating to enforce accurate chapters.
|
||||
#do_update_hook:false
|
||||
|
||||
## fimfiction.net is reported to misinterprete some BBCode with
|
||||
## blockquotes incorrectly. This fixes those instances and defaults
|
||||
## to on, but can be switched off if it is found to cause problems.
|
||||
fix_fimf_blockquotes:true
|
||||
|
||||
## Site dedicated to these categories/characters/ships
|
||||
extracategories:My Little Pony: Friendship is Magic
|
||||
|
||||
|
||||
+1
-1
@@ -292,7 +292,7 @@ def main(argv,
|
||||
else:
|
||||
# regular download
|
||||
if options.metaonly:
|
||||
print adapter.getStoryMetadataOnly()
|
||||
print adapter.getStoryMetadataOnly().getAllMetadata()
|
||||
|
||||
output_filename=writeStory(configuration,adapter,options.format,options.metaonly)
|
||||
|
||||
|
||||
Binary file not shown.
@@ -145,10 +145,13 @@ class ArchiveOfOurOwnOrgAdapter(BaseSiteAdapter):
|
||||
|
||||
except urllib2.HTTPError, e:
|
||||
if e.code == 404:
|
||||
raise exceptions.StoryDoesNotExist(self.meta)
|
||||
raise exceptions.StoryDoesNotExist(self.url)
|
||||
else:
|
||||
raise e
|
||||
|
||||
|
||||
if "Sorry, we couldn't find the work you were looking for." in data:
|
||||
raise exceptions.StoryDoesNotExist(self.url)
|
||||
|
||||
if self.needToLoginCheck(data):
|
||||
# need to log in for this one.
|
||||
self.performLogin(url,data)
|
||||
|
||||
@@ -182,6 +182,11 @@ class DarkSolaceOrgAdapter(BaseSiteAdapter):
|
||||
|
||||
# first a tag in pagetitle is title
|
||||
self.story.setMetadata('title',stripHTML(div.find('a')))
|
||||
div.find('a').extract()
|
||||
# only thing left in div(pagetitle) now should be 'by' and rating.
|
||||
rating = stripHTML(div)
|
||||
if '[' in rating:
|
||||
self.story.setMetadata('rating', rating[rating.index('[')+1:-1])
|
||||
|
||||
for chapa in soup.findAll('a', href=re.compile(r'viewstory.php\?sid='+
|
||||
self.story.getMetadata('storyId')+'&chapter=\d+')):
|
||||
@@ -234,31 +239,28 @@ class DarkSolaceOrgAdapter(BaseSiteAdapter):
|
||||
self.setDescription(url,svalue)
|
||||
#self.story.setMetadata('description',stripHTML(svalue))
|
||||
|
||||
if 'Rated' in label:
|
||||
self.story.setMetadata('rating', value[:len(value)-2])
|
||||
|
||||
if 'Word count' in label:
|
||||
self.story.setMetadata('numWords', value)
|
||||
|
||||
if 'Categories' in label:
|
||||
cats = labelspan.parent.findAll('a',href=re.compile(r'categories.php\?catid=\d+'))
|
||||
cats = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=categories'))
|
||||
for cat in cats:
|
||||
self.story.addToList('category',cat.string)
|
||||
|
||||
if 'Characters' in label:
|
||||
for char in value.string.split(', '):
|
||||
if not 'None' in char:
|
||||
self.story.addToList('characters',char)
|
||||
chars = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=characters'))
|
||||
for char in chars:
|
||||
self.story.addToList('characters',char.string)
|
||||
|
||||
if 'Genre' in label:
|
||||
for genre in value.string.split(', '):
|
||||
if not 'None' in genre:
|
||||
self.story.addToList('genre',genre)
|
||||
genres = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=1'))
|
||||
for genre in genres:
|
||||
self.story.addToList('genre',genre.string)
|
||||
|
||||
if 'Warnings' in label:
|
||||
for warning in value.string.split(', '):
|
||||
if not 'None' in warning:
|
||||
self.story.addToList('warnings',warning)
|
||||
warnings = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=2'))
|
||||
for warning in warnings:
|
||||
self.story.addToList('warnings',warning.string)
|
||||
|
||||
if 'Completed' in label:
|
||||
if 'Yes' in value:
|
||||
|
||||
@@ -133,6 +133,7 @@ class FictionPadSiteAdapter(BaseSiteAdapter):
|
||||
author = tables['users'][0]
|
||||
story = tables['stories'][0]
|
||||
story_ver = tables['story_versions'][0]
|
||||
print("story:%s"%story)
|
||||
|
||||
self.story.setMetadata('authorId',author['id'])
|
||||
self.story.setMetadata('author',author['display_name'])
|
||||
@@ -151,7 +152,8 @@ class FictionPadSiteAdapter(BaseSiteAdapter):
|
||||
self.story.setMetadata('comments',story['comments_count'])
|
||||
self.story.setMetadata('views',story['views_count'])
|
||||
self.story.setMetadata('likes',int(story['likes'])) # no idea why they floated these.
|
||||
self.story.setMetadata('dislikes',int(story['dislikes']))
|
||||
if 'dislikes' in story:
|
||||
self.story.setMetadata('dislikes',int(story['dislikes']))
|
||||
|
||||
if story_ver['is_complete']:
|
||||
self.story.setMetadata('status', 'Completed')
|
||||
|
||||
@@ -59,7 +59,7 @@ class FimFictionNetSiteAdapter(BaseSiteAdapter):
|
||||
return "http://www.fimfiction.net/story/1234/story-title-here http://www.fimfiction.net/story/1234/ http://www.fimfiction.com/story/1234/1/ http://mobile.fimfiction.net/story/1234/1/story-title-here/chapter-title-here"
|
||||
|
||||
def getSiteURLPattern(self):
|
||||
return r"http://(www|mobile)\.fimfiction\.(net|com)/story/\d+/?.*"
|
||||
return r"https?://(www|mobile)\.fimfiction\.(net|com)/story/\d+/?.*"
|
||||
|
||||
def extractChapterUrlsAndMetadata(self):
|
||||
|
||||
@@ -85,7 +85,7 @@ class FimFictionNetSiteAdapter(BaseSiteAdapter):
|
||||
|
||||
# Unfortunately, we still need to load the story index
|
||||
# page to parse the characters. And chapters, now, too.
|
||||
data = self._fetchUrl(self.url)
|
||||
data = self.do_fix_blockquotes(self._fetchUrl(self.url))
|
||||
soup = bs.BeautifulSoup(data)
|
||||
except urllib2.HTTPError, e:
|
||||
if e.code == 404:
|
||||
@@ -283,12 +283,21 @@ class FimFictionNetSiteAdapter(BaseSiteAdapter):
|
||||
print("Existing epub has %s chapters\nNewest chapter is %s. Discarding old chapters from there on."%(len(self.oldchapters), self.newestChapterNum+1))
|
||||
self.oldchapters = self.oldchapters[:self.newestChapterNum]
|
||||
return len(self.oldchapters)
|
||||
|
||||
|
||||
def do_fix_blockquotes(self,data):
|
||||
if self.getConfig('fix_fimf_blockquotes'):
|
||||
# <p class="double"><blockquote>
|
||||
# </blockquote></p>
|
||||
# include > in re groups so there's always something in the group.
|
||||
data = re.sub(r'<p([^>]*>\s*)<blockquote([^>]*>)',r'<blockquote\2<p\1',data)
|
||||
data = re.sub(r'</blockquote(>\s*)</p>',r'</p\1</blockquote>',data)
|
||||
return data
|
||||
|
||||
def getChapterText(self, url):
|
||||
logger.debug('Getting chapter text from: %s' % url)
|
||||
|
||||
soup = bs.BeautifulSoup(self._fetchUrl(url),selfClosingTags=('br','hr')).find('div', {'class' : 'chapter_content'})
|
||||
|
||||
data = self.do_fix_blockquotes(self._fetchUrl(url))
|
||||
soup = bs.BeautifulSoup(data,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)
|
||||
|
||||
@@ -42,16 +42,19 @@ class LiteroticaSiteAdapter(BaseSiteAdapter):
|
||||
|
||||
self.story.setMetadata('siteabbrev','litero')
|
||||
|
||||
# get storyId from url--url validation guarantees query is only sid=1234
|
||||
self.story.setMetadata('storyId',self.parsedUrl.path.split('/',)[2])
|
||||
# normalize to first chapter. Not sure if they ever have more than 2 digits.
|
||||
storyid = self.parsedUrl.path.split('/',)[2]
|
||||
if re.match(r'-ch\d\d$',storyid):
|
||||
storyid = storyid[:-2]+'01'
|
||||
self.story.setMetadata('storyId',storyid)
|
||||
|
||||
self.origurl = url
|
||||
if "http://www.i." in self.origurl:
|
||||
if "//www.i." in self.origurl:
|
||||
## accept m(mobile)url, but use www.
|
||||
self.origurl = self.origurl.replace("http://www.i.","http://www.")
|
||||
self.origurl = self.origurl.replace("//www.i.","//www.")
|
||||
|
||||
# normalized story URL.
|
||||
self._setURL("http://"+self.getSiteDomain()\
|
||||
self._setURL(url[:url.index('//')+2]+self.getSiteDomain()\
|
||||
+"/s/"+self.story.getMetadata('storyId'))
|
||||
|
||||
# The date format will vary from site to site.
|
||||
@@ -69,10 +72,10 @@ class LiteroticaSiteAdapter(BaseSiteAdapter):
|
||||
@classmethod
|
||||
def getSiteExampleURLs(self):
|
||||
#return "http://www.literotica.com/s/story-title http://www.literotica.com/stories/showstory.php?id=1234 http://www.i.literotica.com/stories/showstory.php?id=1234"
|
||||
return "http://www.literotica.com/s/story-title"
|
||||
return "http://www.literotica.com/s/story-title https://www.literotica.com/s/story-title"
|
||||
|
||||
def getSiteURLPattern(self):
|
||||
return r"http://www(\.i)?\.literotica\.com/s/([a-zA-Z0-9_-]+)"
|
||||
return r"https?://www(\.i)?\.literotica\.com/s/([a-zA-Z0-9_-]+)"
|
||||
|
||||
def extractChapterUrlsAndMetadata(self):
|
||||
|
||||
@@ -97,20 +100,24 @@ class LiteroticaSiteAdapter(BaseSiteAdapter):
|
||||
# author
|
||||
a = soup1.find("span", "b-story-user-y")
|
||||
self.story.setMetadata('authorId', urlparse.parse_qs(a.a['href'].split('?')[1])['uid'])
|
||||
self.story.setMetadata('authorUrl', a.a['href'])
|
||||
authorurl = a.a['href']
|
||||
if authorurl.startswith('//'):
|
||||
authorurl = self.parsedUrl.scheme+':'+authorurl
|
||||
self.story.setMetadata('authorUrl', authorurl)
|
||||
self.story.setMetadata('author', a.text)
|
||||
|
||||
# get the author page
|
||||
try:
|
||||
dataAuth = self._fetchUrl(a.a['href'])
|
||||
dataAuth = self._fetchUrl(authorurl)
|
||||
soupAuth = bs.BeautifulSoup(dataAuth)
|
||||
except urllib2.HTTPError, e:
|
||||
if e.code == 404:
|
||||
raise exceptions.StoryDoesNotExist(a.a['href'])
|
||||
raise exceptions.StoryDoesNotExist(authorurl)
|
||||
else:
|
||||
raise e
|
||||
|
||||
storyLink = soupAuth.find('a', href=url1)
|
||||
## site has started using //domain.name/asdf urls remove https?: from front
|
||||
storyLink = soupAuth.find('a', href=url1[url1.index(':')+1:])
|
||||
|
||||
if storyLink is not None:
|
||||
# pull the published date from the author page
|
||||
@@ -166,7 +173,10 @@ class LiteroticaSiteAdapter(BaseSiteAdapter):
|
||||
self.story.setMetadata('datePublished',makeDate(stripHTML(row.find('td',{'class':'dt'})), self.dateformat))
|
||||
while row['class'] == 'sl':
|
||||
# pages include full URLs.
|
||||
self.chapterUrls.append((row.a.string,row.a['href']))
|
||||
chapurl = row.a['href']
|
||||
if chapurl.startswith('//'):
|
||||
chapurl = self.parsedUrl.scheme+':'+chapurl
|
||||
self.chapterUrls.append((row.a.string,chapurl))
|
||||
if not row.nextSibling:
|
||||
break
|
||||
row = row.nextSibling
|
||||
@@ -203,7 +213,7 @@ class LiteroticaSiteAdapter(BaseSiteAdapter):
|
||||
# get story text
|
||||
story1 = soup1.find('div', 'b-story-body-x').p
|
||||
story1.name='div'
|
||||
story1.append('<br>')
|
||||
story1.append('<br />')
|
||||
storytext = self.utf8FromSoup(url,story1)
|
||||
|
||||
# find num pages
|
||||
@@ -220,7 +230,7 @@ class LiteroticaSiteAdapter(BaseSiteAdapter):
|
||||
[comment.extract() for comment in soup2.findAll(text=lambda text:isinstance(text, bs.Comment))]
|
||||
story2 = soup2.find('div', 'b-story-body-x').p
|
||||
story2.name='div'
|
||||
story2.append('<br>')
|
||||
story2.append('<br />')
|
||||
storytext += self.utf8FromSoup(url,story2)
|
||||
except urllib2.HTTPError, e:
|
||||
if e.code == 404:
|
||||
|
||||
@@ -192,7 +192,7 @@ class OneDirectionFanfictionComAdapter(BaseSiteAdapter):
|
||||
if 'Summary' in label:
|
||||
## Everything until the next span class='label'
|
||||
svalue = ""
|
||||
while not defaultGetattr(value,'class') == 'label':
|
||||
while value and not defaultGetattr(value,'class') == 'label':
|
||||
svalue += str(value)
|
||||
value = value.nextSibling
|
||||
self.setDescription(url,svalue)
|
||||
|
||||
@@ -62,7 +62,7 @@ class SquidgeOrgPejaAdapter(BaseSiteAdapter):
|
||||
|
||||
|
||||
# normalized story URL.
|
||||
self._setURL('http://' + self.getSiteDomain() + '/peja/cgi-bin/viewstory.php?sid='+self.story.getMetadata('storyId'))
|
||||
self._setURL('https://' + self.getSiteDomain() + '/peja/cgi-bin/viewstory.php?sid='+self.story.getMetadata('storyId'))
|
||||
|
||||
# Each adapter needs to have a unique site abbreviation.
|
||||
self.story.setMetadata('siteabbrev','wwomb')
|
||||
@@ -83,10 +83,10 @@ class SquidgeOrgPejaAdapter(BaseSiteAdapter):
|
||||
|
||||
@classmethod
|
||||
def getSiteExampleURLs(self):
|
||||
return "http://"+self.getSiteDomain()+"/peja/cgi-bin/viewstory.php?sid=1234"
|
||||
return "https://"+self.getSiteDomain()+"/peja/cgi-bin/viewstory.php?sid=1234"
|
||||
|
||||
def getSiteURLPattern(self):
|
||||
return re.escape("http://"+self.getSiteDomain()+"/")+"~?"+re.escape("peja/cgi-bin/viewstory.php?sid=")+r"\d+$"
|
||||
return r"https?"+re.escape("://"+self.getSiteDomain()+"/")+r"~?"+re.escape("peja/cgi-bin/viewstory.php?sid=")+r"\d+$"
|
||||
|
||||
## Getting the chapter list and the meta data, plus 'is adult' checking.
|
||||
def extractChapterUrlsAndMetadata(self):
|
||||
@@ -116,7 +116,7 @@ class SquidgeOrgPejaAdapter(BaseSiteAdapter):
|
||||
# Find authorid and URL from... author url.
|
||||
author = soup.find('div', {'id':"pagetitle"}).find('a')
|
||||
self.story.setMetadata('authorId',author['href'].split('=')[1])
|
||||
self.story.setMetadata('authorUrl','http://'+self.host+'/peja/cgi-bin/'+author['href'])
|
||||
self.story.setMetadata('authorUrl','https://'+self.host+'/peja/cgi-bin/'+author['href'])
|
||||
self.story.setMetadata('author',author.string)
|
||||
|
||||
authorSoup = bs.BeautifulSoup(self._fetchUrl(self.story.getMetadata('authorUrl')))
|
||||
@@ -131,7 +131,7 @@ class SquidgeOrgPejaAdapter(BaseSiteAdapter):
|
||||
chapterselect=soup.find('select',{'name':'chapter'})
|
||||
if chapterselect:
|
||||
for ch in chapterselect.findAll('option'):
|
||||
self.chapterUrls.append((stripHTML(ch),'http://'+self.host+'/peja/cgi-bin/viewstory.php?sid='+self.story.getMetadata('storyId')+'&chapter='+ch['value']))
|
||||
self.chapterUrls.append((stripHTML(ch),'https://'+self.host+'/peja/cgi-bin/viewstory.php?sid='+self.story.getMetadata('storyId')+'&chapter='+ch['value']))
|
||||
else:
|
||||
self.chapterUrls.append((title,url))
|
||||
|
||||
@@ -207,7 +207,7 @@ class SquidgeOrgPejaAdapter(BaseSiteAdapter):
|
||||
# http://www.squidge.org/peja/cgi-bin/series.php?seriesid=254
|
||||
a = titleblock.find('a', href=re.compile(r"series.php\?seriesid=\d+"))
|
||||
series_name = a.string
|
||||
series_url = 'http://'+self.host+'/peja/cgi-bin/'+a['href']
|
||||
series_url = 'https://'+self.host+'/peja/cgi-bin/'+a['href']
|
||||
|
||||
# use BeautifulSoup HTML parser to make everything easier to find.
|
||||
seriessoup = bs.BeautifulSoup(self._fetchUrl(series_url))
|
||||
|
||||
@@ -66,7 +66,7 @@ class StoriesOnlineNetAdapter(BaseSiteAdapter):
|
||||
return "http://"+self.getSiteDomain()+"/s/1234 http://"+self.getSiteDomain()+"/s/1234:4010"
|
||||
|
||||
def getSiteURLPattern(self):
|
||||
return re.escape("http://"+self.getSiteDomain())+r"/s/\d+((:\d+)?(;\d+)?$|(:i)?$)"
|
||||
return re.escape("http://"+self.getSiteDomain())+r"/s/\d+((:\d+)?(;\d+)?$|(:i)?$)?"
|
||||
|
||||
## Login seems to be reasonably standard across eFiction sites.
|
||||
def needToLoginCheck(self, data):
|
||||
@@ -171,7 +171,7 @@ class StoriesOnlineNetAdapter(BaseSiteAdapter):
|
||||
|
||||
a = asoup.findAll('td', {'class' : 'lc2'})
|
||||
for lc2 in a:
|
||||
if lc2.find('a')['href'] == '/s/'+self.story.getMetadata('storyId'):
|
||||
if lc2.find('a', href=re.compile(r'^/s/'+self.story.getMetadata('storyId'))):
|
||||
i=1
|
||||
break
|
||||
if a[len(a)-1] == lc2:
|
||||
|
||||
@@ -188,9 +188,9 @@ class BaseSiteAdapter(Configurable):
|
||||
try:
|
||||
return self._decode(self._fetchUrlRaw(url,parameters))
|
||||
except u2.HTTPError, he:
|
||||
excpt=he
|
||||
if he.code == 404:
|
||||
logger.warn("Caught an exception reading URL: %s Exception %s."%(unicode(url),unicode(he)))
|
||||
excpt=he
|
||||
break # break out on 404
|
||||
except Exception, e:
|
||||
excpt=e
|
||||
|
||||
@@ -221,6 +221,65 @@ langs = {
|
||||
"Devanagari":"hi",
|
||||
}
|
||||
|
||||
class InExMatch:
|
||||
keys = []
|
||||
regex = None
|
||||
match = None
|
||||
negate = False
|
||||
|
||||
def __init__(self,line):
|
||||
if "=~" in line:
|
||||
(self.keys,self.match) = line.split("=~")
|
||||
self.match = self.match.replace('\s',' ')
|
||||
self.regex = re.compile(self.match)
|
||||
elif "!~" in line:
|
||||
(self.keys,self.match) = line.split("!~")
|
||||
self.match = self.match.replace('\s',' ')
|
||||
self.regex = re.compile(self.match)
|
||||
self.negate = True
|
||||
elif "==" in line:
|
||||
(self.keys,self.match) = line.split("==")
|
||||
self.match = self.match.replace('\s',' ')
|
||||
elif "!=" in line:
|
||||
(self.keys,self.match) = line.split("!=")
|
||||
self.match = self.match.replace('\s',' ')
|
||||
self.negate = True
|
||||
self.keys = map( lambda x: x.strip(), self.keys.split(",") )
|
||||
|
||||
# For conditional, only one key
|
||||
def is_key(self,key):
|
||||
return key == self.keys[0]
|
||||
|
||||
# For conditional, only one key
|
||||
def key(self):
|
||||
return self.keys[0]
|
||||
|
||||
def in_keys(self,key):
|
||||
return key in self.keys
|
||||
|
||||
def is_match(self,value):
|
||||
retval = False
|
||||
if self.regex:
|
||||
if self.regex.search(value):
|
||||
retval = True
|
||||
#print(">>>>>>>>>>>>>%s=~%s r: %s,%s=%s"%(self.match,value,self.negate,retval,self.negate != retval))
|
||||
else:
|
||||
retval = self.match == value
|
||||
#print(">>>>>>>>>>>>>%s==%s r: %s,%s=%s"%(self.match,value,self.negate,retval, self.negate != retval))
|
||||
|
||||
return self.negate != retval
|
||||
|
||||
def __str__(self):
|
||||
if self.negate:
|
||||
f='!'
|
||||
else:
|
||||
f='='
|
||||
if self.regex:
|
||||
s='~'
|
||||
else:
|
||||
s='='
|
||||
return u'InExMatch(%s %s%s %s)'%(self.keys,f,s,self.match)
|
||||
|
||||
class Story(Configurable):
|
||||
|
||||
def __init__(self, configuration):
|
||||
@@ -231,6 +290,7 @@ class Story(Configurable):
|
||||
except:
|
||||
self.metadata = {'version':'4.4'}
|
||||
self.replacements = []
|
||||
self.in_ex_cludes = {}
|
||||
self.chapters = [] # chapters will be tuples of (title,html)
|
||||
self.imgurls = []
|
||||
self.imgtuples = []
|
||||
@@ -252,6 +312,15 @@ class Story(Configurable):
|
||||
|
||||
self.setReplace(self.getConfig('replace_metadata'))
|
||||
|
||||
in_ex_clude_list = ['include_metadata_pre','exclude_metadata_pre',
|
||||
'include_metadata_post','exclude_metadata_post']
|
||||
for ie in in_ex_clude_list:
|
||||
ies = self.getConfig(ie)
|
||||
# print("%s %s"%(ie,ies))
|
||||
if ies:
|
||||
iel = []
|
||||
self.in_ex_cludes[ie] = self.set_in_ex_clude(ies)
|
||||
|
||||
def setMetadata(self, key, value, condremoveentities=True):
|
||||
## still keeps < < and &
|
||||
if condremoveentities:
|
||||
@@ -269,6 +338,56 @@ class Story(Configurable):
|
||||
self.addToList('lastupdate',value.strftime("Last Update Year/Month: %Y/%m"))
|
||||
self.addToList('lastupdate',value.strftime("Last Update: %Y/%m/%d"))
|
||||
|
||||
|
||||
## metakey[,metakey]=~pattern
|
||||
## metakey[,metakey]==string
|
||||
## *for* part lines. Effect only when trailing conditional key=~regexp matches
|
||||
## metakey[,metakey]=~pattern[&&metakey=~regexp]
|
||||
## metakey[,metakey]==string[&&metakey=~regexp]
|
||||
## metakey[,metakey]=~pattern[&&metakey==string]
|
||||
## metakey[,metakey]==string[&&metakey==string]
|
||||
def set_in_ex_clude(self,setting):
|
||||
dest = []
|
||||
# print("set_in_ex_clude:"+setting)
|
||||
for line in setting.splitlines():
|
||||
if line:
|
||||
(match,condmatch)=(None,None)
|
||||
if "&&" in line:
|
||||
(line,conditional) = line.split("&&")
|
||||
condmatch = InExMatch(conditional)
|
||||
match = InExMatch(line)
|
||||
dest.append([match,condmatch])
|
||||
return dest
|
||||
|
||||
def do_in_ex_clude(self,which,value,key):
|
||||
if value and which in self.in_ex_cludes:
|
||||
include = 'include' in which
|
||||
keyfound = False
|
||||
found = False
|
||||
for (match,condmatch) in self.in_ex_cludes[which]:
|
||||
keyfndnow = False
|
||||
if match.in_keys(key):
|
||||
# key in keys and either no conditional, or conditional matched
|
||||
if condmatch == None or condmatch.is_key(key):
|
||||
keyfndnow = True
|
||||
else:
|
||||
condval = self.getMetadata(condmatch.key())
|
||||
keyfndnow = condmatch.is_match(condval)
|
||||
keyfound |= keyfndnow
|
||||
# print("match:%s %s\ncondmatch:%s %s\n\tkeyfound:%s\n\tfound:%s"%(
|
||||
# match,value,condmatch,condval,keyfound,found))
|
||||
if keyfndnow:
|
||||
found = isinstance(value,basestring) and match.is_match(value)
|
||||
if found:
|
||||
# print("match:%s %s\n\tkeyfndnow:%s\n\tfound:%s"%(
|
||||
# match,value,keyfndnow,found))
|
||||
if not include:
|
||||
value = None
|
||||
break
|
||||
if include and keyfound and not found:
|
||||
value = None
|
||||
return value
|
||||
|
||||
|
||||
## Two or three part lines. Two part effect everything.
|
||||
## Three part effect only those key(s) lists.
|
||||
@@ -301,6 +420,10 @@ class Story(Configurable):
|
||||
self.replacements.append([metakeys,regexp,replacement,condkey,condregexp])
|
||||
|
||||
def doReplacements(self,value,key):
|
||||
value = self.do_in_ex_clude('include_metadata_pre',value,key)
|
||||
value = self.do_in_ex_clude('exclude_metadata_pre',value,key)
|
||||
# if key=='characters' and value=='Bilbo':
|
||||
# value = ''
|
||||
for (metakeys,regexp,replacement,condkey,condregexp) in self.replacements:
|
||||
if (metakeys == None or key in metakeys) \
|
||||
and isinstance(value,basestring) \
|
||||
@@ -312,6 +435,8 @@ class Story(Configurable):
|
||||
|
||||
if doreplace:
|
||||
value = regexp.sub(replacement,value)
|
||||
value = self.do_in_ex_clude('include_metadata_post',value,key)
|
||||
value = self.do_in_ex_clude('exclude_metadata_post',value,key)
|
||||
return value
|
||||
|
||||
def getMetadataRaw(self,key):
|
||||
|
||||
+3
-2
@@ -64,7 +64,8 @@
|
||||
<h3>Changes:</h3>
|
||||
<p>
|
||||
<ul>
|
||||
<li>Add Pairing for hpfanficarchive.com</li>
|
||||
<li>Fix for dark-solace.org Rating.</li>
|
||||
<li>Fix for literotica.com URLs.</li>
|
||||
</ul>
|
||||
</p>
|
||||
<p>
|
||||
@@ -75,7 +76,7 @@
|
||||
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://4-4-96.fanfictiondownloader.appspot.com">Previous Version</a> is also available for you to use if necessary.
|
||||
<a href="http://4-5-01.fanfictiondownloader.appspot.com">Previous Version</a> is also available for you to use if necessary.
|
||||
</p>
|
||||
<div id='error'>
|
||||
{{ error_message }}
|
||||
|
||||
+31
-1
@@ -186,7 +186,32 @@ connect_timeout:60.0
|
||||
# .*-Centered=>
|
||||
# characters=>Sam W\.=>Sam Witwicky&&category=>Transformers
|
||||
# characters=>Sam W\.=>Sam Winchester&&category=>Supernatural
|
||||
|
||||
|
||||
## Include/Exclude metadata
|
||||
##
|
||||
## You can use the include/exclude metadata features to either limit
|
||||
## the values of particular metadata lists to specific values or to
|
||||
## exclude specific values. Further, you can conditionally apply each
|
||||
## line depending on other metadata, use exact strings or regular
|
||||
## expressions(regex) to match values, and negate matches.
|
||||
##
|
||||
## The settings are:
|
||||
## include_metadata_pre
|
||||
## exclude_metadata_pre
|
||||
## include_metadata_post
|
||||
## exclude_metadata_post
|
||||
##
|
||||
## The form of each line is:
|
||||
## metakey[,metakey]==exactvalue
|
||||
## metakey[,metakey]=~regex
|
||||
## metakey[,metakey]==exactvalue&&conditionalkey==exactcondvalue
|
||||
## metakey[,metakey]=~regex&&conditionalkey==exactcondvalue
|
||||
## metakey[,metakey]==exactvalue&&conditionalkey=~condregex
|
||||
##
|
||||
## This is fairly complicated, so it's documented on its own wiki
|
||||
## page:
|
||||
## https://code.google.com/p/fanficdownloader/wiki/InExcludeMetadataFeature
|
||||
|
||||
## Some readers don't show horizontal rule (<hr />) tags correctly.
|
||||
## This replaces them all with a centered '* * *'. (Note centering
|
||||
## doesn't work on some devices either.)
|
||||
@@ -1307,6 +1332,11 @@ extra_valid_entries:reviews,favs,follows
|
||||
## when updating to enforce accurate chapters.
|
||||
#do_update_hook:false
|
||||
|
||||
## fimfiction.net is reported to misinterprete some BBCode with
|
||||
## blockquotes incorrectly. This fixes those instances and defaults
|
||||
## to on, but can be switched off if it is found to cause problems.
|
||||
fix_fimf_blockquotes:true
|
||||
|
||||
## Site dedicated to these categories/characters/ships
|
||||
extracategories:My Little Pony: Friendship is Magic
|
||||
|
||||
|
||||
Reference in New Issue
Block a user