mirror of
https://github.com/JimmXinu/FanFicFare.git
synced 2026-02-09 17:15:38 +01:00
New site: trekiverse.org/efiction/
This commit is contained in:
Jim Miller
parent
9c85563ffd
commit
77e2d7beff
4 changed files with 364 additions and 0 deletions
21
defaults.ini
21
defaults.ini
|
|
@ -1085,6 +1085,27 @@ extracategories:Stargate: SG-1
|
|||
## this should go in your personal.ini, not defaults.ini.
|
||||
#is_adult:true
|
||||
|
||||
[trekiverse.org]
|
||||
## Site dedicated to these categories/characters/ships
|
||||
extracategories:Star Trek
|
||||
|
||||
## Some sites require login (or login for some rated stories) The
|
||||
## program can prompt you, or you can save it in config. In
|
||||
## commandline version, this should go in your personal.ini, not
|
||||
## defaults.ini.
|
||||
#username:YourName
|
||||
#password:yourpassword
|
||||
|
||||
## Some sites also 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
|
||||
|
||||
extra_valid_entries:awards
|
||||
awards_label:Awards
|
||||
|
||||
cover_exclusion_regexp:art/.*Awards.jpg
|
||||
|
||||
[www.adastrafanfic.com]
|
||||
## Site dedicated to these categories/characters/ships
|
||||
extracategories:Star Trek
|
||||
|
|
|
|||
|
|
@ -121,6 +121,7 @@ import adapter_simplyundeniablecom
|
|||
import adapter_scarheadnet
|
||||
import adapter_fictionpadcom
|
||||
import adapter_storiesonlinenet
|
||||
import adapter_trekiverseorg
|
||||
|
||||
## This bit of complexity allows adapters to be added by just adding
|
||||
## importing. It eliminates the long if/else clauses we used to need
|
||||
|
|
|
|||
321
fanficdownloader/adapters/adapter_trekiverseorg.py
Normal file
321
fanficdownloader/adapters/adapter_trekiverseorg.py
Normal file
|
|
@ -0,0 +1,321 @@
|
|||
# -*- coding: utf-8 -*-
|
||||
|
||||
# Copyright 2013 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 TrekiverseOrgAdapter
|
||||
|
||||
# Class name has to be unique. Our convention is camel case the
|
||||
# sitename with Adapter at the end. www is skipped.
|
||||
class TrekiverseOrgAdapter(BaseSiteAdapter):
|
||||
|
||||
def __init__(self, config, url):
|
||||
BaseSiteAdapter.__init__(self, config, url)
|
||||
|
||||
self.decode = ["iso-8859-1",
|
||||
"Windows-1252"] # 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])
|
||||
|
||||
# normalized story URL.
|
||||
self._setURL("http://"+self.getSiteDomain()\
|
||||
+"/efiction/viewstory.php?sid="+self.story.getMetadata('storyId'))
|
||||
|
||||
# Each adapter needs to have a unique site abbreviation.
|
||||
self.story.setMetadata('siteabbrev','trkvs')
|
||||
|
||||
# The date format will vary from site to site.
|
||||
# http://docs.python.org/library/datetime.html#strftime-strptime-behavior
|
||||
self.dateformat = "%d/%m/%Y"
|
||||
|
||||
@staticmethod # must be @staticmethod, don't remove it.
|
||||
def getSiteDomain():
|
||||
# The site domain.
|
||||
return 'trekiverse.org'
|
||||
|
||||
@classmethod
|
||||
def getSiteExampleURLs(self):
|
||||
return "http://"+self.getSiteDomain()+"/efiction/viewstory.php?sid=1234"
|
||||
|
||||
def getSiteURLPattern(self):
|
||||
return r'http://trekiverse\.org/efiction/viewstory\.php\?sid=\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
|
||||
|
||||
def performLogin(self, url):
|
||||
params = {}
|
||||
|
||||
if self.password:
|
||||
params['penname'] = self.username
|
||||
params['password'] = self.password
|
||||
else:
|
||||
params['penname'] = self.getConfig("username")
|
||||
params['password'] = self.getConfig("password")
|
||||
params['cookiecheck'] = '1'
|
||||
params['submit'] = 'Submit'
|
||||
|
||||
loginUrl = 'http://' + self.getSiteDomain() + '/efiction/user.php?action=login'
|
||||
logger.debug("Will now login to URL (%s) as (%s)" % (loginUrl,
|
||||
params['penname']))
|
||||
|
||||
d = self._fetchUrl(loginUrl, params)
|
||||
|
||||
if "Member Account" not in d : #Member Account
|
||||
logger.info("Failed to login to URL %s as %s" % (loginUrl,
|
||||
params['penname']))
|
||||
raise exceptions.FailedToLogin(url,params['penname'])
|
||||
return False
|
||||
else:
|
||||
return True
|
||||
|
||||
|
||||
## 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 = "&index=1&ageconsent=ok&warning=5"
|
||||
else:
|
||||
addurl="&index=1"
|
||||
|
||||
# index=1 makes sure we see the story chapter index. Some
|
||||
# sites skip that for one-chapter stories.
|
||||
url = self.url+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
|
||||
|
||||
if self.needToLoginCheck(data):
|
||||
# need to log in for this one.
|
||||
self.performLogin(url)
|
||||
data = self._fetchUrl(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)
|
||||
|
||||
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 = bs.BeautifulSoup(data)
|
||||
|
||||
# Now go hunting for all the meta data and the chapter list.
|
||||
|
||||
## Title and author
|
||||
a = soup.find('div', {'id' : 'pagetitle'})
|
||||
aut = a.find('a', href=re.compile(r"^viewuser\.php\?uid="))
|
||||
self.story.setMetadata('authorId',aut['href'].split('=')[1])
|
||||
self.story.setMetadata('authorUrl','http://'+self.host+'/efiction/'+aut['href'])
|
||||
self.story.setMetadata('author',aut.string)
|
||||
|
||||
ttl = a.find('a', href=re.compile(r'^viewstory.php\?sid=%s$'%self.story.getMetadata('storyId')))
|
||||
self.story.setMetadata('title',ttl.string)
|
||||
|
||||
# Find the chapters:
|
||||
outputdiv = soup.find('div', {'id':'output'})
|
||||
# (amp;)? because it should be &, but is escaped to & in URL.
|
||||
# viewstory.php?sid=35&chapter=3
|
||||
chapters=outputdiv.findAll('a', href=re.compile(r'^viewstory.php\?sid=%s&(amp;)?chapter=\d+$'%self.story.getMetadata('storyId')))
|
||||
if len(chapters)==0:
|
||||
raise exceptions.FailedToDownload(self.getSiteDomain() +" says: No php/html chapters found.")
|
||||
if len(chapters)==1:
|
||||
self.chapterUrls.append((self.story.getMetadata('title'),'http://'+self.host+'/efiction/'+chapters[0]['href']))
|
||||
else:
|
||||
for chapter in chapters:
|
||||
# just in case there's tags, like <i> in chapter titles.
|
||||
self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+'/efiction/'+chapter['href']))
|
||||
|
||||
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.
|
||||
|
||||
def defaultGetattr(d,k):
|
||||
try:
|
||||
return d[k]
|
||||
except:
|
||||
return ""
|
||||
|
||||
# <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 '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 (<p> w/o </p>) leads
|
||||
# to all labels being included.
|
||||
svalue=svalue[:svalue.find('<span class="label">')]
|
||||
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'))
|
||||
catstext = [cat.string for cat in cats]
|
||||
for cat in catstext:
|
||||
self.story.addToList('category',cat.string)
|
||||
|
||||
if 'Characters' in label:
|
||||
chars = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=characters'))
|
||||
charstext = [char.string for char in chars]
|
||||
for char in charstext:
|
||||
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=9'))
|
||||
genrestext = [genre.string for genre in genres]
|
||||
self.genre = ', '.join(genrestext)
|
||||
for genre in genrestext:
|
||||
self.story.addToList('genre',genre.string)
|
||||
|
||||
if 'Awards' in label:
|
||||
awards = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=12'))
|
||||
awardstext = [award.string for award in awards]
|
||||
self.award = ', '.join(awardstext)
|
||||
for award in awardstext:
|
||||
self.story.addToList('awards',award.string)
|
||||
|
||||
if 'Pairing' in label:
|
||||
ships = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=10'))
|
||||
shipstext = [ship.string for ship in ships]
|
||||
self.ship = ', '.join(shipstext)
|
||||
for ship in shipstext:
|
||||
self.story.addToList('ships',ship.string)
|
||||
|
||||
if 'Warnings' in label:
|
||||
warnings = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=11'))
|
||||
warningstext = [warning.string for warning in warnings]
|
||||
self.warning = ', '.join(warningstext)
|
||||
for warning in warningstext:
|
||||
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(value.strip(), "%d %b %Y"))
|
||||
|
||||
if 'Updated' in label:
|
||||
self.story.setMetadata('dateUpdated', makeDate(value.strip(), "%d %b %Y"))
|
||||
|
||||
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+'/efiction/'+a['href']
|
||||
|
||||
# use BeautifulSoup HTML parser to make everything easier to find.
|
||||
seriessoup = bs.BeautifulSoup(self._fetchUrl(series_url))
|
||||
storyas = seriessoup.findAll('a', href=re.compile(r'^viewstory.php\?sid=\d+$'))
|
||||
i=1
|
||||
for a in storyas:
|
||||
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 = bs.BeautifulSoup(self._fetchUrl(url)) # 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)
|
||||
|
||||
notesdiv = soup.find('div', {'class':'noteinfo'})
|
||||
if notesdiv != None:
|
||||
div.insert(0,"<hr>")
|
||||
div.insert(0,notesdiv)
|
||||
div.insert(0,"<hr>")
|
||||
|
||||
return self.utf8FromSoup(url,div)
|
||||
|
|
@ -1070,6 +1070,27 @@ extracategories:Stargate: SG-1
|
|||
## this should go in your personal.ini, not defaults.ini.
|
||||
#is_adult:true
|
||||
|
||||
[trekiverse.org]
|
||||
## Site dedicated to these categories/characters/ships
|
||||
extracategories:Star Trek
|
||||
|
||||
## Some sites require login (or login for some rated stories) The
|
||||
## program can prompt you, or you can save it in config. In
|
||||
## commandline version, this should go in your personal.ini, not
|
||||
## defaults.ini.
|
||||
#username:YourName
|
||||
#password:yourpassword
|
||||
|
||||
## Some sites also 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
|
||||
|
||||
extra_valid_entries:awards
|
||||
awards_label:Awards
|
||||
|
||||
cover_exclusion_regexp:art/.*Awards.jpg
|
||||
|
||||
[www.adastrafanfic.com]
|
||||
## Site dedicated to these categories/characters/ships
|
||||
extracategories:Star Trek
|
||||
|
|
|
|||
Loading…
Reference in a new issue