diff --git a/fanficfare/adapters/__init__.py b/fanficfare/adapters/__init__.py index a187012a..e7543a0c 100644 --- a/fanficfare/adapters/__init__.py +++ b/fanficfare/adapters/__init__.py @@ -45,7 +45,6 @@ import adapter_whoficcom import adapter_siyecouk import adapter_archiveofourownorg import adapter_ficbooknet -import adapter_portkeyorg import adapter_mugglenetcom import adapter_hpfandomnet import adapter_nfacommunitycom @@ -100,7 +99,6 @@ import adapter_efictionestelielde import adapter_pommedesangcom import adapter_restrictedsectionorg import adapter_imagineeficcom -import adapter_psychficcom import adapter_asr3slashzoneorg import adapter_potterheadsanonymouscom import adapter_fictionpadcom diff --git a/fanficfare/adapters/adapter_portkeyorg.py b/fanficfare/adapters/adapter_portkeyorg.py deleted file mode 100644 index 0c045439..00000000 --- a/fanficfare/adapters/adapter_portkeyorg.py +++ /dev/null @@ -1,290 +0,0 @@ -# -*- coding: utf-8 -*- - -# Copyright 2011 Fanficdownloader team, 2016 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. -# - -import time -import logging -logger = logging.getLogger(__name__) -import re -import urllib2 -import cookielib as cl - - -from ..htmlcleanup import stripHTML -from .. import exceptions as exceptions - -from base_adapter import BaseSiteAdapter, makeDate - -# Search for XXX comments--that's where things are most likely to need changing. - -# This function is called by the downloader in all adapter_*.py files -# in this dir to register the adapter class. So it needs to be -# updated to reflect the class below it. That, plus getSiteDomain() -# take care of 'Registering'. -def getClass(): - return PortkeyOrgAdapter # XXX - -# Class name has to be unique. Our convention is camel case the -# sitename with Adapter at the end. www is skipped. -class PortkeyOrgAdapter(BaseSiteAdapter): # XXX - - 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.path.split('/',)[2]) - - - # normalized story URL. - self._setURL('http://' + self.getSiteDomain() + '/story/'+self.story.getMetadata('storyId')) - - # Each adapter needs to have a unique site abbreviation. - self.story.setMetadata('siteabbrev','prtky') # XXX - - # The date format will vary from site to site. - # http://docs.python.org/library/datetime.html#strftime-strptime-behavior - self.dateformat = "%d/%m/%y" # XXX - - @staticmethod # must be @staticmethod, don't remove it. - def getSiteDomain(): - # The site domain. Does have www here, if it uses it. - return 'fanfiction.portkey.org' # XXX - - @classmethod - def getSiteExampleURLs(cls): - return "http://"+cls.getSiteDomain()+"/story/1234" - - def getSiteURLPattern(self): - return re.escape("http://"+self.getSiteDomain()+"/story/")+r"\d+(/\d+)?$" - - def use_pagecache(self): - ''' - adapters that will work with the page cache need to implement - this and change it to True. - ''' - return True - - ## Getting the chapter list and the meta data, plus 'is adult' checking. - def extractChapterUrlsAndMetadata(self): - - url = self.url - logger.debug("URL: "+url) - - # portkey screws around with using a different URL to set the - # cookie and it's a pain. So... cheat! - if self.is_adult or self.getConfig("is_adult"): - cookie = cl.Cookie(version=0, name='verify17', value='1', - port=None, port_specified=False, - domain=self.getSiteDomain(), domain_specified=False, domain_initial_dot=False, - path='/', path_specified=True, - secure=False, - expires=time.time()+10000, - discard=False, - comment=None, - comment_url=None, - rest={'HttpOnly': None}, - rfc2109=False) - self.get_cookiejar().set_cookie(cookie) - - try: - data = self._fetchUrl(url,usecache=False) - except urllib2.HTTPError, e: - if e.code == 404: - raise exceptions.StoryDoesNotExist(self.url) - else: - raise e - - if "You must be over 18 years of age to view it" in data: # XXX - raise exceptions.AdultCheckRequired(self.url) - - # use BeautifulSoup HTML parser to make everything easier to find. - soup = self.make_soup(data) - #print data - - # Now go hunting for all the meta data and the chapter list. - - # Find authorid and URL from... author url. - a = soup.find('a', href=re.compile(r"/profile/\d+")) - #print("======a:%s"%a) - self.story.setMetadata('authorId',a['href'].split('/')[-1]) - self.story.setMetadata('authorUrl','http://'+self.host+a['href']) - self.story.setMetadata('author',a.string) - - ## Going to get the rest from the author page. - authsoup = self.make_soup(self._fetchUrl(self.story.getMetadata('authorUrl'))) - - ## Title - titlea = authsoup.find('a', href=re.compile(r'/story/'+self.story.getMetadata('storyId')+"$")) - self.story.setMetadata('title',stripHTML(titlea)) - metablock = titlea.parent - - # Find the chapters: - for chapter in soup.find('select',{'name':'select5'}).findAll('option', {'value':re.compile(r'/story/'+self.story.getMetadata('storyId')+"/\d+$")}): - # just in case there's tags, like in chapter titles. - chtitle = stripHTML(chapter) - if not chtitle: - chtitle = "(Untitled Chapter)" - self.chapterUrls.append((chtitle,'http://'+self.host+chapter['value'])) - - if len(self.chapterUrls) == 0: - self.chapterUrls.append((stripHTML(self.story.getMetadata('title')),url)) - - 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 "" - # Contents: NC17 - # Published: 12/11/07 - #
- # Description: A special book helps Harry tap into the power the Dark Lord knows not. Of course it’s a book on sex magic and rituals… but Harry’s not complaining. Spurned on by the ghost of a pervert founder, Harry leads his friends in the hunt for Voldemort’s Horcruxes. - # EROTIC COMEDY! Loads of crude humor and sexual situations! - # - labels = metablock.findAll('span',{'class':'dark-small-bold'}) - for labelspan in labels: - value = labelspan.findNext('span').string - label = stripHTML(labelspan) -# print("\nlabel:%s\nlabel:%s\nvalue:%s\n"%(labelspan,label,value)) - - if 'Description' in label: - self.setDescription(url,value) - - if 'Contents' in label: - self.story.setMetadata('rating', value) - - if 'Words' 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: - # genre is typo'ed on the site--it falls between the - # dark-small-bold label and dark-small-bold content - # spans. - svalue = "" - value = labelspan.nextSibling - while 'dark-small-bold' not in defaultGetattr(value,'class'): - svalue += unicode(value) - value = value.nextSibling - - for genre in svalue.split("/"): - genre = genre.strip() - if genre != 'None': - self.story.addToList('genre',genre) - - ## 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 'Status' in label: - if 'Completed' 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 = metablock.find('a', href=re.compile(r"viewseries.php\?seriesid=\d+")) - # series_name = a.string - # series_url = 'http://'+self.host+'/'+a['href'] - - # # use BeautifulSoup HTML parser to make everything easier to find. - # seriessoup = self.make_soup(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) - # 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) - data = self._fetchUrl(url) - - data = data.replace("HTML>","div>") - data = data.replace("html>","div>") - - soup = self.make_soup(data) - - # remove ad blocks so they don't become covers. - for ns in soup.findAll('noscript'): - ns.extract() - - #print("soup:%s"%soup) - tag = soup.find('td', {'class' : 'story'}) - if tag == None and "
Chapter does not exist!
" in data: - logger.error("Chapter is missing at: %s"%url) - return self.utf8FromSoup(url,self.make_soup("

Site says: Chapter does not exist!

Chapter is missing at: %s

"%(url,url))) - elif tag == None and "
This chapter has corrupted or a blank chapter was uploaded. Please contact the author and request that they re-upload the chapter
" in data: - logger.error("Chapter is missing at: %s"%url) - return self.utf8FromSoup(url,self.make_soup("

Site says: This chapter has corrupted or a blank chapter was uploaded.

Chapter is missing at: %s

"%(url,url))) - tag.name='div' # force to be a div to avoid problems with nook. - - centers = tag.findAll('center') - # first two and last two center tags are some script, 'report - # story', 'report story' and an ad. - centers[0].extract() - centers[1].extract() - centers[-1].extract() - centers[-2].extract() - - if None == tag: - raise exceptions.FailedToDownload("Error downloading Chapter: %s! Missing required element!" % url) - - return self.utf8FromSoup(url,tag) diff --git a/fanficfare/adapters/adapter_psychficcom.py b/fanficfare/adapters/adapter_psychficcom.py deleted file mode 100644 index 88613835..00000000 --- a/fanficfare/adapters/adapter_psychficcom.py +++ /dev/null @@ -1,248 +0,0 @@ -# -*- coding: utf-8 -*- - -# Copyright 2013 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 PsychFicComAdapter - -# Class name has to be unique. Our convention is camel case the -# sitename with Adapter at the end. www is skipped. -class PsychFicComAdapter(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]) - - - # 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','psyf') - - # The date format will vary from site to site. - # http://docs.python.org/library/datetime.html#strftime-strptime-behavior - self.dateformat = "%B %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.psychfic.com' - - @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+$" - - ## Getting the chapter list and the meta data, plus 'is adult' checking. - def extractChapterUrlsAndMetadata(self): - - if self.is_adult or self.getConfig("is_adult"): - # Weirdly, different sites use different warning numbers. - # If the title search below fails, there's a good chance - # you need a different number. print data at that point - # and see what the 'click here to continue' url says. - addurl = "&ageconsent=ok&warning=4" - else: - addurl="" - - # index=1 makes sure we see the story chapter index. Some - # sites skip that for one-chapter stories. - url = self.url+'&index=1'+addurl - logger.debug("URL: "+url) - - try: - data = self._fetchUrl(url) - except urllib2.HTTPError, e: - if e.code == 404: - raise exceptions.StoryDoesNotExist(self.url) - else: - raise e - - m = re.search(r"'viewstory.php\?sid=\d+((?:&ageconsent=ok)?&warning=\d+)'",data) - if m != None: - if self.is_adult or self.getConfig("is_adult"): - # We tried the default and still got a warning, so - # let's pull the warning number from the 'continue' - # link and reload data. - addurl = m.group(1) - # correct stupid & error in url. - addurl = addurl.replace("&","&") - url = self.url+'&index=1'+addurl - logger.debug("URL 2nd try: "+url) - - try: - data = self._fetchUrl(url) - except urllib2.HTTPError, e: - if e.code == 404: - raise exceptions.StoryDoesNotExist(self.url) - else: - raise e - else: - raise exceptions.AdultCheckRequired(self.url) - - if "Access denied. This story has not been validated by the adminstrators of this site." in data: - raise exceptions.AccessDenied(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.") - - # use BeautifulSoup HTML parser to make everything easier to find. - soup = self.make_soup(data) - # print data - - # Now go hunting for all the meta data and the chapter list. - - ## Title - a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$")) - 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+'/'+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.text - - 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+'/'+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)