diff --git a/fanficdownloader/adapters/__init__.py b/fanficdownloader/adapters/__init__.py index 9507af66..c5f9b3de 100644 --- a/fanficdownloader/adapters/__init__.py +++ b/fanficdownloader/adapters/__init__.py @@ -101,7 +101,6 @@ import adapter_merlinficdtwinscouk import adapter_thehookupzonenet import adapter_bloodtiesfancom import adapter_indeathnet -import adapter_jlaunlimitedcom import adapter_qafficcom import adapter_efpfanficnet import adapter_potterficscom diff --git a/fanficdownloader/adapters/adapter_jlaunlimitedcom.py b/fanficdownloader/adapters/adapter_jlaunlimitedcom.py deleted file mode 100644 index f9e57ee6..00000000 --- a/fanficdownloader/adapters/adapter_jlaunlimitedcom.py +++ /dev/null @@ -1,260 +0,0 @@ -# -*- coding: utf-8 -*- - -# Copyright 2011 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 JLAUnlimitedComAdapter - - -class JLAUnlimitedComAdapter(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 = "" # 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')) - - self._setURL('http://' + self.getSiteDomain() + '/eFiction1.1/viewstory.php?sid='+self.story.getMetadata('storyId')) - - # Each adapter needs to have a unique site abbreviation. - self.story.setMetadata('siteabbrev','jla') - - # 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.jlaunlimited.com' - - def getSiteExampleURLs(self): - return "http://"+self.getSiteDomain()+"/eFiction1.1/viewstory.php?sid=1234" - - def getSiteURLPattern(self): - return re.escape("http://"+self.getSiteDomain()+"/eFiction1.1/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" # XXX - 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 - - # Assume that if there is a url with 'warning=#' in the page then it is a 'check' page - 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) - - # use BeautifulSoup HTML parser to make everything easier to find. - soup = bs.BeautifulSoup(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',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+'/eFiction1.1/'+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 not defaultGetattr(value,'class') == 'label': - svalue += str(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')) - 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) - - ## Not all sites use Genre, but there's no harm to - ## leaving it in. Check to make sure the type_id number - ## is correct, though--it's site specific. - if 'Genre' in label: - genres = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=1')) # XXX - genrestext = [genre.string for genre in genres] - self.genre = ', '.join(genrestext) - for genre in genrestext: - self.story.addToList('genre',genre.string) - - ## Not all sites use Warnings, but there's no harm to - ## leaving it in. Check to make sure the type_id number - ## is correct, though--it's site specific. - if 'Warnings' in label: - warnings = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=2')) # XXX - 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(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+'/fanfic/'+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), - 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 d15a4244..6fdb565c 100644 --- a/index.html +++ b/index.html @@ -60,6 +60,16 @@
  • New site: netraptor.org
  • New site: asr3.slashzone.org
  • New site: tokra.fandomnet.com
  • +
  • Remove defunct site: www.jlaunlimited.com
    • +
  • Fix author URLs for several sites with leading 'dir' in URL.
    • +
  • Fix for no chapter name for one chapter stories on TtH.
    • +
  • Improved error handling for mobi issues.
    • +
  • Add 'url' to chapter custom formats and class="skip_on_ffdl_update" for updates.
    • +
    + Use the URL of the story's first chapter, such as +
    http://www.jlaunlimited.com/eFiction1.1/viewstory.php?sid=1234 +
    +

    @@ -544,11 +554,6 @@ Use the URL of the story's chapter list, such as
    http://www.indeath.net/blog/25-nightmare-in-death/ -

    www.jlaunlimited.com
    -
    - Use the URL of the story's first chapter, such as -
    http://www.jlaunlimited.com/eFiction1.1/viewstory.php?sid=1234 -
    www.efpfanfic.net
    Use the URL of any story chapter, such as