diff --git a/calibre-plugin/plugin-defaults.ini b/calibre-plugin/plugin-defaults.ini index 33070893..9336f3cf 100644 --- a/calibre-plugin/plugin-defaults.ini +++ b/calibre-plugin/plugin-defaults.ini @@ -3500,18 +3500,6 @@ add_to_output_css: table { border: 1px solid; border-collapse: collapse; } .author-note-portlet { border: 1px solid; border-collapse: collapse; padding: 0.5em } -[www.scarvesandcoffee.net] -## 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 - -## Site dedicated to these categories/characters/ships -extracategories:Glee -extracharacters:Kurt Hummel,Blaine Anderson - -website_encodings:Windows-1252,utf8 - [www.scribblehub.com] use_basic_cache:true extra_valid_entries:views, averageWords, fandoms diff --git a/fanficfare/adapters/__init__.py b/fanficfare/adapters/__init__.py index 14d91521..42f1f688 100644 --- a/fanficfare/adapters/__init__.py +++ b/fanficfare/adapters/__init__.py @@ -70,7 +70,6 @@ from . import adapter_darksolaceorg from . import adapter_finestoriescom from . import adapter_hlfictionnet from . import adapter_dracoandginnycom -from . import adapter_scarvesandcoffeenet from . import adapter_wolverineandroguecom from . import adapter_thehookupzonenet from . import adapter_efpfanficnet diff --git a/fanficfare/adapters/adapter_scarvesandcoffeenet.py b/fanficfare/adapters/adapter_scarvesandcoffeenet.py deleted file mode 100644 index bb19ef4c..00000000 --- a/fanficfare/adapters/adapter_scarvesandcoffeenet.py +++ /dev/null @@ -1,242 +0,0 @@ -# -*- coding: utf-8 -*- - -# Copyright 2012 Fanficdownloader team, 2020 FanFicFare 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. -# - -# Software: eFiction -from __future__ import absolute_import -import logging -logger = logging.getLogger(__name__) -import re -from ..htmlcleanup import stripHTML -from .. import exceptions as exceptions - -# py2 vs py3 transition -from ..six import text_type as unicode - -from .base_adapter import BaseSiteAdapter, makeDate - -def getClass(): - return ScarvesAndCoffeeNetAdapter - -# Class name has to be unique. Our convention is camel case the -# sitename with Adapter at the end. www is skipped. -class ScarvesAndCoffeeNetAdapter(BaseSiteAdapter): - - def __init__(self, config, url): - BaseSiteAdapter.__init__(self, config, url) - - 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]) - - - # 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','scacf') - - # The date format will vary from site to site. - # http://docs.python.org/library/datetime.html#strftime-strptime-behavior - self.dateformat = "%m/%d/%Y" - - @staticmethod # must be @staticmethod, don't remove it. - def getSiteDomain(): - # The site domain. Does have www here, if it uses it. - return 'www.scarvesandcoffee.net' - - @classmethod - def getSiteExampleURLs(cls): - return "http://"+cls.getSiteDomain()+"/viewstory.php?sid=1234" - - def getSiteURLPattern(self): - return re.escape("http://"+self.getSiteDomain()+"/viewstory.php?sid=")+r"\d+$" - - ## Login seems to be reasonably standard across eFiction sites. - def needToLoginCheck(self, data): - if 'Registered Users Only' in data \ - or 'There is no such account on our website' in data \ - or "That password doesn't match the one in our database" in data: - return True - else: - return False - - ## Getting the chapter list and the meta data, plus 'is adult' checking. - def extractChapterUrlsAndMetadata(self): - - if self.is_adult or self.getConfig("is_adult"): - # Weirdly, different sites use different warning numbers. - # If the title search below fails, there's a good chance - # you need a different number. print data at that point - # and see what the 'click here to continue' url says. - addurl = "&ageconsent=ok&warning=20" - else: - addurl="" - - # index=1 makes sure we see the story chapter index. Some - # sites skip that for one-chapter stories. - url = self.url+'&index=1'+addurl - logger.debug("URL: "+url) - - data = self.get_request(url) - - m = re.search(r"'viewstory.php\?sid=\d+((?:&ageconsent=ok)?&warning=\d+)'",data) - if m != None: - if self.is_adult or self.getConfig("is_adult"): - # We tried the default and still got a warning, so - # let's pull the warning number from the 'continue' - # link and reload data. - addurl = m.group(1) - # correct stupid & error in url. - addurl = addurl.replace("&","&") - url = self.url+'&index=1'+addurl - logger.debug("URL 2nd try: "+url) - - data = self.get_request(url) - else: - raise exceptions.AdultCheckRequired(self.url) - - if "Access denied. This story has not been validated by the adminstrators of this site." in data: - raise exceptions.AccessDenied(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.") - - soup = self.make_soup(data) - # print data - - - ## Title - a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$")) - self.story.setMetadata('title',stripHTML(a)) - - # Find authorid and URL from... author url. - a = soup.find('div',{"id":"pagetitle"}).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')+r"&chapter=\d+$")): - # just in case there's tags, like in chapter titles. - self.add_chapter(chapter,'http://'+self.host+'/'+chapter['href']+addurl) - - - # eFiction sites don't help us out a lot with their meta data - # formating, so it's a little ugly. - - # utility method - def defaultGetattr(d,k): - try: - return d[k] - except: - return "" - - # Rated: NC-17
etc - labels = soup.findAll('span',{'class':'label'}) - for labelspan in labels: - value = labelspan.nextSibling - label = labelspan.string - - if 'Summary' in label: - ## Everything until the next span class='label' - svalue = "" - while 'label' not in defaultGetattr(value,'class'): - svalue += unicode(value) - value = value.nextSibling - self.setDescription(url,svalue) - #self.story.setMetadata('description',stripHTML(svalue)) - - if 'Rated' in label: - self.story.setMetadata('rating', value) - - if 'Word count' in label: - self.story.setMetadata('numWords', value) - - if 'Categories' in label: - cats = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=categories')) - for cat in cats: - self.story.addToList('genre',cat.string) - - if 'Characters' in label: - chars = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=characters')) - for char in chars: - self.story.addToList('characters',char.string) - - if 'Completed' in label: - if 'Yes' in value: - self.story.setMetadata('status', 'Completed') - else: - self.story.setMetadata('status', 'In-Progress') - - if 'Published' in label: - self.story.setMetadata('datePublished', makeDate(stripHTML(value), self.dateformat)) - - if 'Updated' in label: - self.story.setMetadata('dateUpdated', makeDate(stripHTML(value), self.dateformat)) - - try: - # Find Series name from series URL. - a = soup.find('a', href=re.compile(r"viewseries.php\?seriesid=\d+")) - series_name = a.string - series_url = 'http://'+self.host+'/'+a['href'] - - seriessoup = self.make_soup(self.get_request(series_url)) - # can't use ^viewstory...$ 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) - self.story.setMetadata('seriesUrl',series_url) - 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 = self.make_soup(self.get_request(url)) - - 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) - - def get_urls_from_page(self,url,normalize): - from ..geturls import get_urls_from_html - # this way it uses User-Agent or other special settings. - data = self.get_request(url,usecache=False) - ## I can't find when or why exactly this was added, but it was - ## in the old code, so here it remains. - soup = self.make_soup(data) - series = self.get_series_from_page(url,data) - if series: - return series - else: - return {'urllist':get_urls_from_html(soup.find('div',{'id':'mainpage'}), - url, - configuration=self.configuration, - normalize=normalize)} diff --git a/fanficfare/defaults.ini b/fanficfare/defaults.ini index ff1dc2f2..2751382e 100644 --- a/fanficfare/defaults.ini +++ b/fanficfare/defaults.ini @@ -3470,18 +3470,6 @@ add_to_output_css: table { border: 1px solid; border-collapse: collapse; } .author-note-portlet { border: 1px solid; border-collapse: collapse; padding: 0.5em } -[www.scarvesandcoffee.net] -## 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 - -## Site dedicated to these categories/characters/ships -extracategories:Glee -extracharacters:Kurt Hummel,Blaine Anderson - -website_encodings:Windows-1252,utf8 - [www.scribblehub.com] use_basic_cache:true extra_valid_entries:views, averageWords, fandoms