mirror of
https://github.com/JimmXinu/FanFicFare.git
synced 2026-01-07 00:25:59 +01:00
Remove site: ponyfictionarchive.net - Moved to AO3
This commit is contained in:
Jim Miller
parent
ffaa3bf82a
commit
28141ce9d1
4 changed files with 0 additions and 264 deletions
|
|
@ -2348,17 +2348,6 @@ extracharacters:Severus Snape
|
|||
|
||||
website_encodings:Windows-1252,utf8
|
||||
|
||||
[ponyfictionarchive.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:My Little Pony: Friendship is Magic
|
||||
|
||||
website_encodings:Windows-1252,utf8
|
||||
|
||||
[pretendercentre.com]
|
||||
## Some sites do not require a login, but do require the user to
|
||||
## confirm they are adult for adult content. In commandline version,
|
||||
|
|
|
|||
|
|
@ -62,7 +62,6 @@ from . import adapter_dokugacom
|
|||
from . import adapter_storiesofardacom
|
||||
from . import adapter_ncisfictioncom
|
||||
from . import adapter_fanfiktionde
|
||||
from . import adapter_ponyfictionarchivenet
|
||||
from . import adapter_themasquenet
|
||||
from . import adapter_pretendercentrecom
|
||||
from . import adapter_darksolaceorg
|
||||
|
|
|
|||
|
|
@ -1,241 +0,0 @@
|
|||
# -*- coding: utf-8 -*-
|
||||
|
||||
# Copyright 2012 Fanficdownloader team, 2018 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 PonyFictionArchiveNetAdapter
|
||||
|
||||
# Class name has to be unique. Our convention is camel case the
|
||||
# sitename with Adapter at the end. www is skipped.
|
||||
class PonyFictionArchiveNetAdapter(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.
|
||||
if "explicit" in self.parsedUrl.netloc:
|
||||
self._setURL('https://explicit.' + self.getSiteDomain() + '/viewstory.php?sid='+self.story.getMetadata('storyId'))
|
||||
self.dateformat = "%d/%b/%y"
|
||||
else:
|
||||
self._setURL('https://' + self.getSiteDomain() + '/viewstory.php?sid='+self.story.getMetadata('storyId'))
|
||||
self.dateformat = "%d %b %Y"
|
||||
|
||||
# Each adapter needs to have a unique site abbreviation.
|
||||
self.story.setMetadata('siteabbrev','pffa')
|
||||
|
||||
@staticmethod # must be @staticmethod, don't remove it.
|
||||
def getSiteDomain():
|
||||
# The site domain. Does have www here, if it uses it.
|
||||
return 'ponyfictionarchive.net'
|
||||
|
||||
@classmethod
|
||||
def getAcceptDomains(cls):
|
||||
return ['www.ponyfictionarchive.net','ponyfictionarchive.net','explicit.ponyfictionarchive.net']
|
||||
|
||||
@classmethod
|
||||
def getSiteExampleURLs(cls):
|
||||
return "https://"+cls.getSiteDomain()+"/viewstory.php?sid=1234 https://explicit."+cls.getSiteDomain()+"/viewstory.php?sid=1234"
|
||||
|
||||
def getSiteURLPattern(self):
|
||||
return r"https?://(www\.|explicit\.)?"+re.escape(self.getSiteDomain()+"/viewstory.php?sid=")+r"\d+$"
|
||||
|
||||
|
||||
## Getting the chapter list and the meta data, plus 'is adult' checking.
|
||||
def extractChapterUrlsAndMetadata(self):
|
||||
|
||||
if self.is_adult or self.getConfig("is_adult"):
|
||||
# Weirdly, different sites use different warning numbers.
|
||||
# If the title search below fails, there's a good chance
|
||||
# you need a different number. print data at that point
|
||||
# and see what the 'click here to continue' url says.
|
||||
addurl = "&warning=9"
|
||||
else:
|
||||
addurl=""
|
||||
|
||||
# index=1 makes sure we see the story chapter index. Some
|
||||
# sites skip that for one-chapter stories.
|
||||
url = self.url+'&index=1'+addurl
|
||||
logger.debug("URL: "+url)
|
||||
|
||||
data = self.get_request(url)
|
||||
|
||||
m = re.search(r"'viewstory.php\?sid=\d+((?:&ageconsent=ok)?&warning=\d+)'",data)
|
||||
if m != None:
|
||||
if self.is_adult or self.getConfig("is_adult"):
|
||||
# We tried the default and still got a warning, so
|
||||
# let's pull the warning number from the 'continue'
|
||||
# link and reload data.
|
||||
addurl = m.group(1)
|
||||
# correct stupid & error in url.
|
||||
addurl = addurl.replace("&","&")
|
||||
url = self.url+'&index=1'+addurl
|
||||
logger.debug("URL 2nd try: "+url)
|
||||
|
||||
data = self.get_request(url)
|
||||
else:
|
||||
raise exceptions.AdultCheckRequired(self.url)
|
||||
|
||||
if "Access denied. This story has not been validated by the adminstrators of this site." in data:
|
||||
raise exceptions.AccessDenied(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
|
||||
|
||||
soup = self.make_soup(data)
|
||||
# print data
|
||||
|
||||
|
||||
## Title
|
||||
a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
|
||||
self.story.setMetadata('title',stripHTML(a))
|
||||
|
||||
# Find authorid and URL from... author url.
|
||||
a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
|
||||
self.story.setMetadata('authorId',a['href'].split('=')[1])
|
||||
self.story.setMetadata('authorUrl','https://'+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 <i> in chapter titles.
|
||||
self.add_chapter(chapter,'https://'+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 ""
|
||||
|
||||
genres = soup.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=1'))
|
||||
for genre in genres:
|
||||
self.story.addToList('genre',genre.string)
|
||||
|
||||
warnings = soup.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=3'))
|
||||
for warning in warnings:
|
||||
self.story.addToList('warnings',warning.string)
|
||||
|
||||
status = soup.find('a',href=re.compile(r'browse.php\?type=class&type_id=2'))
|
||||
if status: # apparently this site can have stories with neither In-Progress or Complete.
|
||||
self.story.setMetadata('status',status.string)
|
||||
|
||||
try:
|
||||
# explicit.site and .site have some differences now...
|
||||
section = soup.findAll('span', {'class' : 'General'})[1]
|
||||
self.story.setMetadata('rating', section.previousSibling.previousSibling.string)
|
||||
|
||||
value = section.nextSibling
|
||||
svalue = ""
|
||||
while 'label' not in defaultGetattr(value,'class'):
|
||||
svalue += unicode(value)
|
||||
value = value.nextSibling
|
||||
self.setDescription(url,svalue)
|
||||
|
||||
except:
|
||||
# find rating in data
|
||||
# <br /> • Mature • <br />
|
||||
lead = "<br /> • "
|
||||
trail = " • <br />"
|
||||
rating = data[data.index(lead)+len(lead):data.index(trail)]
|
||||
if len(rating)<20: # minor sanity check.
|
||||
self.story.setMetadata('rating',rating)
|
||||
descstr = data[data.index(trail)+len(trail):] # from desc on
|
||||
descstr = descstr[:descstr.index('<span class="label">')] # remove after desc.
|
||||
self.setDescription(url,descstr)
|
||||
|
||||
# <span class="label">Rated:</span> NC-17<br /> etc
|
||||
labels = soup.findAll('span',{'class':'label'})
|
||||
for labelspan in labels:
|
||||
value = labelspan.nextSibling
|
||||
label = labelspan.string
|
||||
|
||||
if 'Word count' in label:
|
||||
self.story.setMetadata('numWords', value)
|
||||
|
||||
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 = 'https://'+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)
|
||||
|
|
@ -2343,17 +2343,6 @@ extracharacters:Severus Snape
|
|||
|
||||
website_encodings:Windows-1252,utf8
|
||||
|
||||
[ponyfictionarchive.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:My Little Pony: Friendship is Magic
|
||||
|
||||
website_encodings:Windows-1252,utf8
|
||||
|
||||
[pretendercentre.com]
|
||||
## Some sites do not require a login, but do require the user to
|
||||
## confirm they are adult for adult content. In commandline version,
|
||||
|
|
|
|||
Loading…
Reference in a new issue