From dc2116dd3efc70d573d425f6514af3ea284fc6c4 Mon Sep 17 00:00:00 2001 From: iatheia Date: Mon, 8 Jul 2013 22:19:35 -0400 Subject: [PATCH] New adapter for scarhead.net --- defaults.ini | 16 + fanficdownloader/adapters/__init__.py | 1 + .../adapters/adapter_scarheadnet.py | 298 ++++++++++++++++++ plugin-defaults.ini | 16 + 4 files changed, 331 insertions(+) create mode 100644 fanficdownloader/adapters/adapter_scarheadnet.py diff --git a/defaults.ini b/defaults.ini index 4b99caf..6e08515 100644 --- a/defaults.ini +++ b/defaults.ini @@ -886,6 +886,22 @@ extracategories:Supernatural extracharacters:Sam,Dean extraships:Sam/Dean +[scarhead.net] +## Site dedicated to these categories/characters/ships +extracategories:Harry Potter + +## 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 + [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, diff --git a/fanficdownloader/adapters/__init__.py b/fanficdownloader/adapters/__init__.py index 86d1abd..958bfed 100644 --- a/fanficdownloader/adapters/__init__.py +++ b/fanficdownloader/adapters/__init__.py @@ -118,6 +118,7 @@ import adapter_asr3slashzoneorg import adapter_nickandgregnet import adapter_potterheadsanonymouscom import adapter_simplyundeniablecom +import adapter_scarheadnet ## This bit of complexity allows adapters to be added by just adding ## importing. It eliminates the long if/else clauses we used to need diff --git a/fanficdownloader/adapters/adapter_scarheadnet.py b/fanficdownloader/adapters/adapter_scarheadnet.py new file mode 100644 index 0000000..202cf62 --- /dev/null +++ b/fanficdownloader/adapters/adapter_scarheadnet.py @@ -0,0 +1,298 @@ +# -*- 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 ScarHeadNetAdapter + +# Class name has to be unique. Our convention is camel case the +# sitename with Adapter at the end. www is skipped. +class ScarHeadNetAdapter(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]) + logger.debug("storyId: (%s)"%self.story.getMetadata('storyId')) + + # 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','shn') + + # 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. Does have www here, if it uses it. + return 'scarhead.net' + + def getSiteExampleURLs(self): + return "http://"+self.getSiteDomain()+"/viewstory.php?sid=1234" + + def getSiteURLPattern(self): + return re.escape("http://"+self.getSiteDomain()+"/viewstory.php?sid=")+r"\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() + '/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 = "&ageconsent=ok&warning=5" + 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 + + if self.needToLoginCheck(data): + # need to log in for this one. + self.performLogin(url) + data = self._fetchUrl(url) + + # Since the warning text can change by warning level, let's + # look for the warning pass url. ksarchive uses + # &warning= -- actually, so do other sites. Must be an + # eFiction book. + + # viewstory.php?sid=1882&warning=4 + # viewstory.php?sid=1654&ageconsent=ok&warning=5 + #print data + #m = re.search(r"'viewstory.php\?sid=1882(&warning=4)'",data) + 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) + # print data + + # Now go hunting for all the meta data and the chapter list. + + pagetitle = soup.find('tr',{'valign':'top'}) + + ## Title + a = pagetitle.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 = pagetitle.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. + + cats = soup.findAll('a',href=re.compile(r'browse.php\?type=categories')) + for cat in cats: + if '/' == cat.string[0]: + self.story.addToList('ships','Harry Potter'+cat.string.split('(')[0]) + elif 'Harry' in cat.string: + self.story.addToList('ships',cat.string.split('(')[0]) + else: + self.story.addToList('category',cat.string) + if '(' in cat.string: + self.story.addToList('category',cat.string.split('(')[1].split(')')[0]) + + + + + chars = soup.findAll('a',href=re.compile(r'browse.php\?type=characters')) + for char in chars: + self.story.addToList('characters',char.string) + + genres = soup.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=2')) + for genre in genres: + self.story.addToList('genre',genre.string) + + warnings = soup.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=1')) + for warning in warnings: + self.story.addToList('warnings',warning.string) + + textsoup = stripHTML(soup) + + a = textsoup.split('Published: ')[1].split(' ')[0] + self.story.setMetadata('datePublished', makeDate(stripHTML(a), self.dateformat)) + a = textsoup.split('Updated: ')[1].split(' ')[0] + self.story.setMetadata('dateUpdated', makeDate(stripHTML(a), self.dateformat)) + a = textsoup.split('Rating: ')[1].split(' ')[0] + self.story.setMetadata('rating', a) + a = textsoup.split('Length: ')[1].split('(')[1].split(' ')[0] + self.story.setMetadata('numWords', a) + a = textsoup.split('Completed: ')[1].split(' ')[0] + if 'Yes' in a: + self.story.setMetadata('status', 'Completed') + else: + self.story.setMetadata('status', 'In-Progress') + #a = textsoup.split('Summary: ')[1].split('Add Story to Favorites')[0] + #self.setDescription(url,a) + + + + a=soup.find(text=re.compile("Summary: ")) + i=0 + svalue = "" + while i == 0: + try: + b = str(a) + svalue += b.split('Summary: ')[1] + except: + svalue += str(a) + if a.nextSibling != None: + a = a.nextSibling + else: + a = a.parent.nextSibling + if 'Disclaimer: ' in stripHTML(a): + i=1 + self.setDescription(url,svalue) + + 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 = 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/plugin-defaults.ini b/plugin-defaults.ini index f42e690..ee8f945 100644 --- a/plugin-defaults.ini +++ b/plugin-defaults.ini @@ -873,6 +873,22 @@ extracategories:Supernatural extracharacters:Sam,Dean extraships:Sam/Dean +[scarhead.net] +## Site dedicated to these categories/characters/ships +extracategories:Harry Potter + +## 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 + [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,