From 5c53c8f13599c7da0f91dd1ad6029b01e5053fea Mon Sep 17 00:00:00 2001 From: Jim Miller Date: Tue, 1 Jan 2013 13:24:09 -0600 Subject: [PATCH] Remove defunct www.yourfanfiction.com, Correct ao3 extra metadata freefromtags to freeformtags. --- defaults.ini | 17 +- fanficdownloader/adapters/__init__.py | 3 +- .../adapters/adapter_archiveofourownorg.py | 2 +- .../adapters/adapter_yourfanfictioncom.py | 284 ------------------ index.html | 5 - plugin-defaults.ini | 17 +- 6 files changed, 19 insertions(+), 309 deletions(-) delete mode 100644 fanficdownloader/adapters/adapter_yourfanfictioncom.py diff --git a/defaults.ini b/defaults.ini index 806d33b..9589e8d 100644 --- a/defaults.ini +++ b/defaults.ini @@ -469,8 +469,9 @@ extratags: FanFiction,Testing,HTML #is_adult:true ## AO3 adapter defines a few extra metadata entries. -extra_valid_entries:fandoms,freefromtags,ao3categories,comments,kudos,hits,bookmarks,collections +extra_valid_entries:fandoms,freeformtags,freefromtags,ao3categories,comments,kudos,hits,bookmarks,collections fandoms_label:Fandoms +freeformtags_label:Freeform Tags freefromtags_label:Freeform Tags ao3categories_label:AO3 Categories comments_label:Comments @@ -479,11 +480,15 @@ hits_label:Hits collections_label:Collections bookmarks_label:Bookmarks +## freeformtags was previously typo'ed as freefromtags. This way, +## freefromtags will still work for people who've used it. +include_in_freefromtags:freeformtags + ## adds to titlepage_entries instead of replacing it. -#extra_titlepage_entries: fandoms,freefromtags,ao3categories,comments,kudos,hits,bookmarks +#extra_titlepage_entries: fandoms,freeformtags,ao3categories,comments,kudos,hits,bookmarks ## adds to include_subject_tags instead of replacing it. -#extra_subject_tags:fandoms,freefromtags,ao3categories +#extra_subject_tags:fandoms,freeformtags,ao3categories [ashwinder.sycophanthex.com] ## Site dedicated to these categories/characters/ships @@ -1256,12 +1261,6 @@ extracategories:Stargate: Atlantis ## this should go in your personal.ini, not defaults.ini. #is_adult:true -[www.yourfanfiction.com] -## Some sites do not require a login, but do require the user to -## confirm they are adult for adult content. In commandline version, -## this should go in your personal.ini, not defaults.ini. -#is_adult:true - [overrides] ## It may sometimes be useful to override all of the specific format, ## site and site:format sections in your private configuration. For diff --git a/fanficdownloader/adapters/__init__.py b/fanficdownloader/adapters/__init__.py index c09b7d5..dc234ba 100644 --- a/fanficdownloader/adapters/__init__.py +++ b/fanficdownloader/adapters/__init__.py @@ -73,7 +73,6 @@ import adapter_iketernalnet import adapter_onedirectionfanfictioncom import adapter_prisonbreakficnet import adapter_storiesofardacom -import adapter_yourfanfictioncom import adapter_samdeanarchivenu import adapter_destinysgatewaycom import adapter_ncisfictionnet @@ -107,6 +106,8 @@ import adapter_indeathnet import adapter_jlaunlimitedcom import adapter_qafficcom import adapter_efpfanficnet +#import adapter_buffynfaithnet +import adapter_potterficscom ## This bit of complexity allows adapters to be added by just adding ## importing. It eliminates the long if/else clauses we used to need diff --git a/fanficdownloader/adapters/adapter_archiveofourownorg.py b/fanficdownloader/adapters/adapter_archiveofourownorg.py index d99ca90..1736a3c 100644 --- a/fanficdownloader/adapters/adapter_archiveofourownorg.py +++ b/fanficdownloader/adapters/adapter_archiveofourownorg.py @@ -217,7 +217,7 @@ class ArchiveOfOurOwnOrgAdapter(BaseSiteAdapter): if a != None: genres = a.findAll('a',{'class':"tag"}) for genre in genres: - self.story.addToList('freefromtags',genre.string) + self.story.addToList('freeformtags',genre.string) self.story.addToList('genre',genre.string) a = metasoup.find('dd',{'class':"category tags"}) diff --git a/fanficdownloader/adapters/adapter_yourfanfictioncom.py b/fanficdownloader/adapters/adapter_yourfanfictioncom.py deleted file mode 100644 index f11e7a3..0000000 --- a/fanficdownloader/adapters/adapter_yourfanfictioncom.py +++ /dev/null @@ -1,284 +0,0 @@ -# -*- coding: utf-8 -*- - -# Copyright 2012 Fanficdownloader team -# -# Licensed under the Apache License, Version 2.0 (the "License"); -# you may not use this file except in compliance with the License. -# You may obtain a copy of the License at -# -# http://www.apache.org/licenses/LICENSE-2.0 -# -# Unless required by applicable law or agreed to in writing, software -# distributed under the License is distributed on an "AS IS" BASIS, -# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. -# See the License for the specific language governing permissions and -# limitations under the License. -# - -import time -import logging -logger = logging.getLogger(__name__) -import re -import urllib2 - -from .. import BeautifulSoup as bs -from ..htmlcleanup import stripHTML -from .. import exceptions as exceptions - -from base_adapter import BaseSiteAdapter, makeDate - -def getClass(): - return YourFanfictionComAdapter - -# Class name has to be unique. Our convention is camel case the -# sitename with Adapter at the end. www is skipped. -class YourFanfictionComAdapter(BaseSiteAdapter): - - def __init__(self, config, url): - BaseSiteAdapter.__init__(self, config, url) - - # yourfanfiction.com blocks the default user-agent. However, - # when asked, they said it was just general anti-spam, not - # targeted as us and offered to 'whitelist our IP'. Clearly, - # that wouldn't work, but it does let me do this in good - # conscience: - self.opener.addheaders = [('User-agent', 'FFDL/1.6')] - - self.decode = ["Windows-1252", - "utf8"] # 1252 is a superset of iso-8859-1. - # Most sites that claim to be - # iso-8859-1 (and some that claim to be - # utf8) are really windows-1252. - self.username = "NoneGiven" # if left empty, site doesn't return any message at all. - self.password = "" - self.is_adult=False - - # get storyId from url--url validation guarantees query is only sid=1234 - self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1]) - logger.debug("storyId: (%s)"%self.story.getMetadata('storyId')) - - # normalized story URL. - self._setURL('http://' + self.getSiteDomain() + '/viewstory.php?sid='+self.story.getMetadata('storyId')) - - # Each adapter needs to have a unique site abbreviation. - self.story.setMetadata('siteabbrev','yff') - - # The date format will vary from site to site. - # http://docs.python.org/library/datetime.html#strftime-strptime-behavior - self.dateformat = "%d %b %Y" - - @staticmethod # must be @staticmethod, don't remove it. - def getSiteDomain(): - # The site domain. Does have www here, if it uses it. - return 'www.yourfanfiction.com' - - def getSiteExampleURLs(self): - return "http://"+self.getSiteDomain()+"/viewstory.php?sid=1234" - - def getSiteURLPattern(self): - return re.escape("http://"+self.getSiteDomain()+"/viewstory.php?sid=")+r"\d+$" - - ## Getting the chapter list and the meta data, plus 'is adult' checking. - def extractChapterUrlsAndMetadata(self): - - if self.is_adult or self.getConfig("is_adult"): - # Weirdly, different sites use different warning numbers. - # If the title search below fails, there's a good chance - # you need a different number. print data at that point - # and see what the 'click here to continue' url says. - addurl = "&ageconsent=ok&warning=4" - else: - addurl="" - - # index=1 makes sure we see the story chapter index. Some - # sites skip that for one-chapter stories. - url = self.url+'&index=1'+addurl - logger.debug("URL: "+url) - - try: - data = self._fetchUrl(url) - except urllib2.HTTPError, e: - if e.code == 404: - raise exceptions.StoryDoesNotExist(self.url) - else: - raise e - - # The actual text that is used to announce you need to be an - # adult varies from site to site. Again, print data before - # the title search to troubleshoot. - - # Since the warning text can change by warning level, let's - # look for the warning pass url. ksarchive uses - # &warning= -- actually, so do other sites. Must be an - # eFiction book. - - # viewstory.php?sid=1882&warning=4 - # viewstory.php?sid=1654&ageconsent=ok&warning=5 - #print data - #m = re.search(r"'viewstory.php\?sid=1882(&warning=4)'",data) - m = re.search(r"'viewstory.php\?sid=\d+((&ageconsent=ok)?&warning=\d+)'",data) - if m != None: - if self.is_adult or self.getConfig("is_adult"): - # We tried the default and still got a warning, so - # let's pull the warning number from the 'continue' - # link and reload data. - addurl = m.group(1) - # correct stupid & error in url. - # explicitly put ageconsent because google appengine regexp doesn't include it for some reason. - addurl = addurl.replace("&","&")+'&ageconsent=ok' - url = self.url+'&index=1'+addurl - logger.debug("URL 2nd try: "+url) - - try: - data = self._fetchUrl(url) - except urllib2.HTTPError, e: - if e.code == 404: - raise exceptions.StoryDoesNotExist(self.url) - else: - raise e - else: - raise exceptions.AdultCheckRequired(self.url) - - if "Access denied. This story has not been validated by the adminstrators of this site." in data: - raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.") - - # because for some reason, this works while simple 'print data' errors on ascii conversion. - # loopdata = data - # chklen=5000 - # while len(loopdata) > 0: - # if len(loopdata) < 5000: - # chklen = len(loopdata) - # logger.info("loopdata: %s" % loopdata[:chklen]) - # loopdata = loopdata[chklen:] - - # use BeautifulSoup HTML parser to make everything easier to find. - soup = bs.BeautifulSoup(data) - - # Now go hunting for all the meta data and the chapter list. - - ## Title - a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$")) - self.story.setMetadata('title',a.string) - - # Find authorid and URL from... author url. - a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+")) - self.story.setMetadata('authorId',a['href'].split('=')[1]) - self.story.setMetadata('authorUrl','http://'+self.host+'/'+a['href']) - self.story.setMetadata('author',a.string) - - # Find the chapters: - for chapter in soup.findAll('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"&chapter=\d+$")): - # just in case there's tags, like in chapter titles. - self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+'/'+chapter['href']+addurl)) - - self.story.setMetadata('numChapters',len(self.chapterUrls)) - - # eFiction sites don't help us out a lot with their meta data - # formating, so it's a little ugly. - - # utility method - def defaultGetattr(d,k): - try: - return d[k] - except: - return "" - - # Rated: NC-17
etc - labels = soup.findAll('span',{'class':'label'}) - for labelspan in labels: - value = labelspan.nextSibling - label = labelspan.string - - if 'Summary' in label: - ## Everything until the next span class='label' - svalue = "" - while value and not defaultGetattr(value,'class') == 'label': - svalue += str(value) - value = value.nextSibling - # sometimes poorly formated desc (

w/o

) leads - # to all labels being included. - self.setDescription(url,svalue) - #self.story.setMetadata('description',stripHTML(svalue)) - - if 'Rated' in label: - self.story.setMetadata('rating', value) - - if 'Word count' in label: - self.story.setMetadata('numWords', value) - - if 'Categories' in label: - 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: - 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: - genres = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=5')) - for genre in genres: - self.story.addToList('genre',genre.string) - - if 'Tags' in label: - genres = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=7')) - for genre in genres: - self.story.addToList('genre',genre.string) - - if 'Warnings' in label: - warnings = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=6')) - for warning in warnings: - self.story.addToList('warnings',warning.string) - - if 'Completed' in label: - if 'Yes' in value: - self.story.setMetadata('status', 'Completed') - else: - self.story.setMetadata('status', 'In-Progress') - - if 'Published' in label: - self.story.setMetadata('datePublished', makeDate(stripHTML(value), self.dateformat)) - - if 'Updated' in label: - # there's a stray [ at the end. - #value = value[0:-1] - self.story.setMetadata('dateUpdated', makeDate(stripHTML(value), self.dateformat)) - - try: - # Find Series name from series URL. - a = soup.find('a', href=re.compile(r"viewseries.php\?seriesid=\d+")) - series_name = a.string - series_url = 'http://'+self.host+'/'+a['href'] - - # use BeautifulSoup HTML parser to make everything easier to find. - seriessoup = bs.BeautifulSoup(self._fetchUrl(series_url)) - # can't use ^viewstory...$ in case of higher rated stories with javascript href. - storyas = seriessoup.findAll('a', href=re.compile(r'viewstory.php\?sid=\d+')) - i=1 - for a in storyas: - # skip 'report this' and 'TOC' links - if 'contact.php' not in a['href'] and 'index' not in a['href']: - if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')): - self.setSeries(series_name, i) - break - i+=1 - - except: - # I find it hard to care if the series parsing fails - pass - - # grab the text for an individual chapter. - def getChapterText(self, url): - - logger.debug('Getting chapter text from: %s' % url) - - soup = bs.BeautifulStoneSoup(self._fetchUrl(url), - selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags. - - div = soup.find('div', {'id' : 'story'}) - - if None == div: - raise exceptions.FailedToDownload("Error downloading Chapter: %s! Missing required element!" % url) - - return self.utf8FromSoup(url,div) diff --git a/index.html b/index.html index 138c233..3c20dc3 100644 --- a/index.html +++ b/index.html @@ -389,11 +389,6 @@ Use the URL of the story's first chapter, such as
http://samdean.archive.nu/viewstory.php?sid=1234 -
www.yourfanfiction.com
-
- Use the URL of the story's first chapter, such as -
http://www.yourfanfiction.com/viewstory.php?sid=1234 -
www.destinysgateway.com
Use the URL of the story's first chapter, such as diff --git a/plugin-defaults.ini b/plugin-defaults.ini index a1c951b..34108e4 100644 --- a/plugin-defaults.ini +++ b/plugin-defaults.ini @@ -433,8 +433,9 @@ extratags: FanFiction,Testing,HTML #is_adult:true ## AO3 adapter defines a few extra metadata entries. -extra_valid_entries:fandoms,freefromtags,ao3categories,comments,kudos,hits,bookmarks,collections +extra_valid_entries:fandoms,freeformtags,freefromtags,ao3categories,comments,kudos,hits,bookmarks,collections fandoms_label:Fandoms +freeformtags_label:Freeform Tags freefromtags_label:Freeform Tags ao3categories_label:AO3 Categories comments_label:Comments @@ -443,11 +444,15 @@ hits_label:Hits collections_label:Collections bookmarks_label:Bookmarks +## freeformtags was previously typo'ed as freefromtags. This way, +## freefromtags will still work for people who've used it. +include_in_freefromtags:freeformtags + ## adds to titlepage_entries instead of replacing it. -#extra_titlepage_entries: fandoms,freefromtags,ao3categories,comments,kudos,hits,bookmarks +#extra_titlepage_entries: fandoms,freeformtags,ao3categories,comments,kudos,hits,bookmarks ## adds to include_subject_tags instead of replacing it. -#extra_subject_tags:fandoms,freefromtags,ao3categories +#extra_subject_tags:fandoms,freeformtags,ao3categories [ashwinder.sycophanthex.com] ## Site dedicated to these categories/characters/ships @@ -1233,12 +1238,6 @@ extracategories:Stargate: Atlantis ## this should go in your personal.ini, not defaults.ini. #is_adult:true -[www.yourfanfiction.com] -## Some sites do not require a login, but do require the user to -## confirm they are adult for adult content. In commandline version, -## this should go in your personal.ini, not defaults.ini. -#is_adult:true - [overrides] ## It may sometimes be useful to override all of the specific format, ## site and site:format sections in your private configuration. For