From 17157498a919fb1f6cbc08e051bbdc61ac7c7e66 Mon Sep 17 00:00:00 2001 From: Jim Miller Date: Mon, 11 Jan 2016 09:40:52 -0600 Subject: [PATCH] Remove defunct sg1-heliopolis.com site after down for +1 month. --- calibre-plugin/plugin-defaults.ini | 6 - fanficfare/adapters/__init__.py | 1 - .../adapters/adapter_sg1heliopoliscom.py | 258 ------------------ fanficfare/defaults.ini | 6 - 4 files changed, 271 deletions(-) delete mode 100644 fanficfare/adapters/adapter_sg1heliopoliscom.py diff --git a/calibre-plugin/plugin-defaults.ini b/calibre-plugin/plugin-defaults.ini index a1283d8..ab3d1a3 100644 --- a/calibre-plugin/plugin-defaults.ini +++ b/calibre-plugin/plugin-defaults.ini @@ -1480,12 +1480,6 @@ extraships:Sam/Dean ## Site dedicated to these categories/characters/ships extracategories:Harry Potter -[sg1-heliopolis.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 - [sheppardweir.com] ## Some sites require login (or login for some rated stories) The ## program can prompt you, or you can save it in config. In diff --git a/fanficfare/adapters/__init__.py b/fanficfare/adapters/__init__.py index 981e444..f26de18 100644 --- a/fanficfare/adapters/__init__.py +++ b/fanficfare/adapters/__init__.py @@ -75,7 +75,6 @@ import adapter_ncisfictionnet import adapter_thealphagatecom import adapter_fanfiktionde import adapter_ponyfictionarchivenet -import adapter_sg1heliopoliscom import adapter_ncisficcom import adapter_nationallibrarynet import adapter_themasquenet diff --git a/fanficfare/adapters/adapter_sg1heliopoliscom.py b/fanficfare/adapters/adapter_sg1heliopoliscom.py deleted file mode 100644 index c656b6c..0000000 --- a/fanficfare/adapters/adapter_sg1heliopoliscom.py +++ /dev/null @@ -1,258 +0,0 @@ -# -*- coding: utf-8 -*- - -# Copyright 2012 Fanficdownloader team, 2015 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 -import time -import logging -logger = logging.getLogger(__name__) -import re -import urllib2 - - -from ..htmlcleanup import stripHTML -from .. import exceptions as exceptions - -from base_adapter import BaseSiteAdapter, makeDate - -def getClass(): - return SG1HeliopolisComAdapter - -# Class name has to be unique. Our convention is camel case the -# sitename with Adapter at the end. www is skipped. -class SG1HeliopolisComAdapter(BaseSiteAdapter): - - def __init__(self, config, url): - BaseSiteAdapter.__init__(self, config, url) - - 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]) - - self.section=self.parsedUrl.path.split('/',)[1] - - # normalized story URL. - self._setURL('http://' + self.getSiteDomain() + '/'+self.section+'/viewstory.php?sid='+self.story.getMetadata('storyId')) - - # Each adapter needs to have a unique site abbreviation. - self.story.setMetadata('siteabbrev','sghp') - - # If all stories from the site fall into the same category, - # the site itself isn't likely to label them as such, so we - # do. Can't use extracategories, could be Atlantis or SG-1 - if 'atlantis' in self.section: - self.story.addToList("category","Stargate: Atlantis") - else: - self.story.addToList("category","Stargate: SG-1") - - # The date format will vary from site to site. - # http://docs.python.org/library/datetime.html#strftime-strptime-behavior - self.dateformat = "%Y.%m.%d" - - @staticmethod # must be @staticmethod, don't remove it. - def getSiteDomain(): - # The site domain. Does have www here, if it uses it. - return 'sg1-heliopolis.com' - - @classmethod - def getSiteExampleURLs(cls): - return "http://"+cls.getSiteDomain()+"/archive/viewstory.php?sid=1234 http://"+cls.getSiteDomain()+"/adult/viewstory.php?sid=1234 http://"+cls.getSiteDomain()+"/atlantis/viewstory.php?sid=1234" - - def getSiteURLPattern(self): - return r"http://sg1-heliopolis.com/(archive|adult|atlantis)?/viewstory.php\?sid=\d+$" - - - ## Getting the chapter list and the meta data, plus 'is adult' checking. - def extractChapterUrlsAndMetadata(self): - - if self.is_adult or self.getConfig("is_adult"): - # Weirdly, different sites use different warning numbers. - # If the title search below fails, there's a good chance - # you need a different number. print data at that point - # and see what the 'click here to continue' url says. - addurl = "&warning=4" - else: - addurl="" - - # index=1 makes sure we see the story chapter index. Some - # sites skip that for one-chapter stories. - url = self.url+'&index=1'+addurl - logger.debug("URL: "+url) - - try: - data = self._fetchUrl(url) - except urllib2.HTTPError, e: - if e.code == 404: - raise exceptions.StoryDoesNotExist(self.url) - else: - raise e - - m = re.search(r"'viewstory.php\?sid=\d+((?:&ageconsent=ok)?&warning=\d+)'",data) - if m != None: - if self.is_adult or self.getConfig("is_adult"): - # We tried the default and still got a warning, so - # let's pull the warning number from the 'continue' - # link and reload data. - addurl = m.group(1) - # correct stupid & error in url. - addurl = addurl.replace("&","&") - url = self.url+'&index=1'+addurl - logger.debug("URL 2nd try: "+url) - - try: - data = self._fetchUrl(url) - except urllib2.HTTPError, e: - if e.code == 404: - raise exceptions.StoryDoesNotExist(self.url) - else: - raise e - else: - raise exceptions.AdultCheckRequired(self.url) - - if "Access denied. This story has not been validated by the adminstrators of this site." in data: - raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.") - - # use BeautifulSoup HTML parser to make everything easier to find. - soup = self.make_soup(data) - # print data - - # Now go hunting for all the meta data and the chapter list. - - ## Title - a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$")) - self.story.setMetadata('title',stripHTML(a)) - - # 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+'/'+self.section+'/'+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 '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('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=1')) - 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=2')) - 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: - 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+'/'+self.section+'/'+a['href'] - - # use BeautifulSoup HTML parser to make everything easier to find. - seriessoup = self.make_soup(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) - 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._fetchUrl(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) diff --git a/fanficfare/defaults.ini b/fanficfare/defaults.ini index a7592f2..b614080 100644 --- a/fanficfare/defaults.ini +++ b/fanficfare/defaults.ini @@ -1468,12 +1468,6 @@ extraships:Sam/Dean ## Site dedicated to these categories/characters/ships extracategories:Harry Potter -[sg1-heliopolis.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 - [sheppardweir.com] ## Some sites require login (or login for some rated stories) The ## program can prompt you, or you can save it in config. In