From 340fe65bf68fedac2830b1a1cc6eba84068bd97b Mon Sep 17 00:00:00 2001 From: Jim Miller Date: Thu, 24 Sep 2015 16:02:20 -0500 Subject: [PATCH] Remove thequidditchpitch.org, domain is parked. --- .../adapters/adapter_thequidditchpitchorg.py | 292 ------------------ 1 file changed, 292 deletions(-) delete mode 100644 fanficfare/adapters/adapter_thequidditchpitchorg.py diff --git a/fanficfare/adapters/adapter_thequidditchpitchorg.py b/fanficfare/adapters/adapter_thequidditchpitchorg.py deleted file mode 100644 index 37ea9301..00000000 --- a/fanficfare/adapters/adapter_thequidditchpitchorg.py +++ /dev/null @@ -1,292 +0,0 @@ -# -*- coding: utf-8 -*- - -# Copyright 2011 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 .. import BeautifulSoup as bs -from ..htmlcleanup import stripHTML -from .. import exceptions as exceptions - -from base_adapter import BaseSiteAdapter, makeDate - -# 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 TheQuidditchPitchOrgAdapter # XXX - -# Class name has to be unique. Our convention is camel case the -# sitename with Adapter at the end. www is skipped. -class TheQuidditchPitchOrgAdapter(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.query.split('=',)[1]) - - - # normalized story URL. - # XXX Most sites don't have the part. Replace all to remove it usually. - 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','tqdpch') # XXX - - # The date format will vary from site to site. - # http://docs.python.org/library/datetime.html#strftime-strptime-behavior - self.dateformat = "%m/%d/%Y" # XXX - - @staticmethod # must be @staticmethod, don't remove it. - def getSiteDomain(): - # The site domain. Does have www here, if it uses it. - return 'thequidditchpitch.org' # XXX - - @classmethod - def getAcceptDomains(cls): - return ['www.thequidditchpitch.org','thequidditchpitch.org'] - - @classmethod - def getSiteExampleURLs(cls): - return "http://"+cls.getSiteDomain()+"/viewstory.php?sid=1234" - - def getSiteURLPattern(self): - return re.escape("http://")+"(www\.)?"+re.escape(self.getSiteDomain()+"/viewstory.php?sid=")+r"\d+$" - - ## Login seems to be reasonably standard across eFiction sites. - def needToLoginCheck(self, data): - if 'Registered Users Only - Not suitable for readers under the age of legal consent in their country.' 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=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 - - if self.needToLoginCheck(data): - # need to log in for this one. - self.performLogin(url) - data = self._fetchUrl(url) - - # The actual text that is used to announce you need to be an - # adult varies from site to site. Again, print data before - # the title search to troubleshoot. - if ("Not suitable for readers under the age of legal consent in their country." in data \ - or "Not suitable for readers under 16 yrs. \r\nStories may contain violence, slight nudity, and/or sexual situations." in data ) \ - and not (self.is_adult or self.getConfig("is_adult")): # XXX - 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. - - ## 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.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) - - 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) - - 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+'/'+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.BeautifulStoneSoup(self._fetchUrl(url), - selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags. - - # span? Really? span? Yeah... I don't think so. - div = soup.find('span', {'style' : 'font-size: 100%;'}) - div.name='div' - - if None == div: - raise exceptions.FailedToDownload("Error downloading Chapter: %s! Missing required element!" % url) - - return self.utf8FromSoup(url,div)