From dd4a22e7d8560e2d4e39a0b8bdbc520c984fc6d1 Mon Sep 17 00:00:00 2001 From: Jim Miller Date: Fri, 11 Mar 2016 11:20:37 -0600 Subject: [PATCH] Change fanfiction.mugglenet.com to base_efiction after site update. --- fanficfare/adapters/adapter_mugglenetcom.py | 305 +------------------- 1 file changed, 10 insertions(+), 295 deletions(-) diff --git a/fanficfare/adapters/adapter_mugglenetcom.py b/fanficfare/adapters/adapter_mugglenetcom.py index 21d887c6..4d3ef335 100644 --- a/fanficfare/adapters/adapter_mugglenetcom.py +++ b/fanficfare/adapters/adapter_mugglenetcom.py @@ -1,6 +1,6 @@ # -*- coding: utf-8 -*- -# Copyright 2011 Fanficdownloader team, 2015 FanFicFare team +# 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. @@ -16,58 +16,12 @@ # # Software: eFiction -import time -import logging -logger = logging.getLogger(__name__) -import re -import urllib2 +from base_efiction_adapter import BaseEfictionAdapter - -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 MuggleNetComAdapter # XXX - -# Class name has to be unique. Our convention is camel case the -# sitename with Adapter at the end. www is skipped. -class MuggleNetComAdapter(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. - 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','mgln') # 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 +class MuggleNetComAdapter(BaseEfictionAdapter): @staticmethod # must be @staticmethod, don't remove it. def getSiteDomain(): - # The site domain. return 'fanfiction.mugglenet.com' @classmethod @@ -75,251 +29,12 @@ class MuggleNetComAdapter(BaseSiteAdapter): # XXX return ['fanfiction.mugglenet.com','fanfic.mugglenet.com'] @classmethod - def getSiteExampleURLs(cls): - return "http://"+cls.getSiteDomain()+"/viewstory.php?sid=1234" + def getSiteAbbrev(self): + return 'mgln' - def getSiteURLPattern(self): - return re.escape("http://")+r"fanfic(tion)?\.mugglenet\.com"+re.escape("/viewstory.php?sid=")+r"\d+$" + @classmethod + def getDateFormat(self): + return "%m/%d/%y" - ## Login seems to be reasonably standard across eFiction sites. - def needToLoginCheck(self, data): - if "class='errortext'>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&sid='+self.story.getMetadata('storyId') - 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. - # http://fanfiction.mugglenet.com/viewstory.php?sid=91079&ageconsent=ok&warning=3 - addurl = "&ageconsent=ok&warning=3" # XXX &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) - #print("\nurl:%s\ndata:\n%s\n"%(url,data)) - - # 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. - - # Since the warning text can change by warning level, let's - # look for the warning pass url. nfacommunity 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=%s((?:&ageconsent=ok)?&warning=\d+)'"%self.story.getMetadata('storyId'),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)) - - - # Not good enough-- content can contain a ('), which ends the content prematurely. - # metadesc = soup.find('meta',{'name':'description'}) - # print("removeAllEntities(metadesc['content']):\n%s\n"%removeAllEntities(metadesc['content'])) - start='Summary: ' - end='Rated:' - summarydata = data[data.index(start)+len(start):data.index(end)] - #print("summarydata:\n%s\n"%summarydata) - self.setDescription(url,self.make_soup(summarydata)) - - # 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 '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=2')) # 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+'/'+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: - # 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) +def getClass(): + return MuggleNetComAdapter