From edf557e7e4770b000a4ee999bbe07632a227bd6f Mon Sep 17 00:00:00 2001 From: Ida Date: Fri, 13 Jul 2012 23:22:20 -0400 Subject: [PATCH] New adapters for finestories.com, hpfanficarchive.com, svufiction.com, twilightarchives.com, and wizardtales.net --- .../adapters/adapter_finestoriescom.py | 282 +++++++++++++++++ .../adapters/adapter_hpfanficarchivecom.py | 221 +++++++++++++ .../adapters/adapter_svufictioncom.py | 271 ++++++++++++++++ .../adapters/adapter_twilightarchivescom.py | 190 +++++++++++ .../adapters/adapter_wizardtalesnet.py | 299 ++++++++++++++++++ 5 files changed, 1263 insertions(+) create mode 100644 fanficdownloader/adapters/adapter_finestoriescom.py create mode 100644 fanficdownloader/adapters/adapter_hpfanficarchivecom.py create mode 100644 fanficdownloader/adapters/adapter_svufictioncom.py create mode 100644 fanficdownloader/adapters/adapter_twilightarchivescom.py create mode 100644 fanficdownloader/adapters/adapter_wizardtalesnet.py diff --git a/fanficdownloader/adapters/adapter_finestoriescom.py b/fanficdownloader/adapters/adapter_finestoriescom.py new file mode 100644 index 0000000..f2087f3 --- /dev/null +++ b/fanficdownloader/adapters/adapter_finestoriescom.py @@ -0,0 +1,282 @@ +# -*- coding: utf-8 -*- + +# Copyright 2012 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 +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 FineStoriesComAdapter + +# Class name has to be unique. Our convention is camel case the +# sitename with Adapter at the end. www is skipped. +class FineStoriesComAdapter(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 + self.story.setMetadata('storyId',self.parsedUrl.path.split('/',)[2].split(':')[0]) + logging.debug("storyId: (%s)"%self.story.getMetadata('storyId')) + + # normalized story URL. + self._setURL('http://' + self.getSiteDomain() + '/s/storyInfo.php?id='+self.story.getMetadata('storyId')) + + # Each adapter needs to have a unique site abbreviation. + self.story.setMetadata('siteabbrev','fnst') + + # The date format will vary from site to site. + # http://docs.python.org/library/datetime.html#strftime-strptime-behavior + self.dateformat = "%Y-%m-%d" + + @staticmethod # must be @staticmethod, don't remove it. + def getSiteDomain(): + # The site domain. Does have www here, if it uses it. + return 'finestories.com' + + def getSiteExampleURLs(self): + return "http://"+self.getSiteDomain()+"/s/10537 http://"+self.getSiteDomain()+"/s/10537:4010" + + def getSiteURLPattern(self): + return re.escape("http://"+self.getSiteDomain()+"/s/")+r"\d+(:\d+)?(;\d+)?$" + + ## Login seems to be reasonably standard across eFiction sites. + def needToLoginCheck(self, data): + if 'Free Registration' in data \ + or "Invalid Password!" in data \ + or "Invalid User Name!" in data: + return True + else: + return False + + def performLogin(self, url): + params = {} + + if self.password: + params['theusername'] = self.username + params['thepassword'] = self.password + else: + params['theusername'] = self.getConfig("username") + params['thepassword'] = self.getConfig("password") + params['rememberMe'] = '1' + params['page'] = 'http://finestories.com/' + params['submit'] = 'Login' + + loginUrl = 'http://' + self.getSiteDomain() + '/login.php' + logging.debug("Will now login to URL (%s) as (%s)" % (loginUrl, + params['theusername'])) + + d = self._fetchUrl(loginUrl, params) + + if "My Account" not in d : #Member Account + logging.info("Failed to login to URL %s as %s" % (loginUrl, + params['theusername'])) + raise exceptions.FailedToLogin(url,params['theusername']) + return False + else: + return True + + ## Getting the chapter list and the meta data, plus 'is adult' checking. + def extractChapterUrlsAndMetadata(self): + + # index=1 makes sure we see the story chapter index. Some + # sites skip that for one-chapter stories. + url = self.url + logging.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) + + 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'/s/'+self.story.getMetadata('storyId')+"$")) + self.story.setMetadata('title',a.text) + + # Find authorid and URL from... author url. + a = soup.find('a', href=re.compile(r"/a/\w+")) + self.story.setMetadata('authorId',a['href'].split('/')[2]) + self.story.setMetadata('authorUrl','http://'+self.host+a['href']) + self.story.setMetadata('author',a.text) + + # Find the chapters: + chapters = soup.findAll('a', href=re.compile(r'/s/'+self.story.getMetadata('storyId')+":\d+$")) + if len(chapters) != 0: + for chapter in chapters: + # just in case there's tags, like in chapter titles. + self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+chapter['href'])) + else: + self.chapterUrls.append((self.story.getMetadata('title'),'http://'+self.host+'/s/'+self.story.getMetadata('storyId'))) + + self.story.setMetadata('numChapters',len(self.chapterUrls)) + + # surprisingly, the detailed page does not give enough details, so go to author's page + asoup = bs.BeautifulSoup(self._fetchUrl(self.story.getMetadata('authorUrl'))) + + for lc2 in asoup.findAll('td', {'class' : 'lc2'}): + if lc2.find('a')['href'] == '/s/'+self.story.getMetadata('storyId'): + break + + self.story.addToList('category',lc2.find('div', {'class' : 'typediv'}).text) + + self.story.setMetadata('numWords', lc2.findNext('td', {'class' : 'num'}).text) + + lc4 = lc2.findNext('td', {'class' : 'lc4'}) + + + try: + a = lc4.find('a', href=re.compile(r"/library/show_series.php\?id=\d+")) + i = a.parent.text.split('(')[1].split(')')[0] + self.setSeries(a.text, i) + except: + pass + try: + a = lc4.find('a', href=re.compile(r"/library/universe.php\?id=\d+")) + self.story.addToList("category",a.text) + except: + pass + + for a in lc4.findAll('span', {'class' : 'help'}): + a.extract() + + self.setDescription('http://'+self.host+'/s/'+self.story.getMetadata('storyId'),lc4.text.split('[More Info')[0]) + + for b in lc4.findAll('b'): + label = b.text + value = b.nextSibling + + if 'For Age' in label: + self.story.setMetadata('rating', value) + + if 'Tags' in label: + for genre in value.split(', '): + self.story.addToList('genre',genre) + + if 'Posted' in label: + self.story.setMetadata('datePublished', makeDate(stripHTML(value), self.dateformat)) + self.story.setMetadata('dateUpdated', makeDate(stripHTML(value), self.dateformat)) + + if 'Concluded' in label: + self.story.setMetadata('dateUpdated', makeDate(stripHTML(value), self.dateformat)) + + if 'Updated' in label: + self.story.setMetadata('dateUpdated', makeDate(stripHTML(value), self.dateformat)) + + status = lc4.find('span', {'class' : 'ab'}) + if status != None: + self.story.setMetadata('status', 'In-Progress') + if "Last Activity" in status.text: + self.story.setMetadata('dateUpdated', makeDate(status.text.split('Activity: ')[1].split(')')[0], self.dateformat)) + else: + self.story.setMetadata('status', 'Completed') + + + # grab the text for an individual chapter. + def getChapterText(self, url): + + logging.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'}) + + # some big chapters are split over several pages + pager = div.find('span', {'class' : 'pager'}) + if pager != None: + urls=pager.findAll('a') + urls=urls[:len(urls)-1] + + + for ur in urls: + soup = bs.BeautifulSoup(self._fetchUrl("http://"+self.getSiteDomain()+ur['href']), + selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags. + + div1 = soup.find('div', {'id' : 'story'}) + + # appending next section + last=div.findAll('p') + next=div1.find('span', {'class' : 'conTag'}).nextSibling + + last[len(last)-1]=last[len(last)-1].append(next) + div.append(div1) + + + + # removing all the left-over stuff + for a in div.findAll('span'): + a.extract() + + for a in div.findAll('h1'): + a.extract() + for a in div.findAll('h2'): + a.extract() + for a in div.findAll('h3'): + a.extract() + for a in div.findAll('h4'): + a.extract() + for a in div.findAll('br'): + a.extract() + for a in div.findAll('div', {'class' : 'date'}): + a.extract() + + a = div.find('form') + if a != None: + b = a.nextSibling + while b != None: + a.extract() + a=b + b=b.nextSibling + + + if None == div: + raise exceptions.FailedToDownload("Error downloading Chapter: %s! Missing required element!" % url) + + return self.utf8FromSoup(url,div) diff --git a/fanficdownloader/adapters/adapter_hpfanficarchivecom.py b/fanficdownloader/adapters/adapter_hpfanficarchivecom.py new file mode 100644 index 0000000..5305f67 --- /dev/null +++ b/fanficdownloader/adapters/adapter_hpfanficarchivecom.py @@ -0,0 +1,221 @@ +# -*- coding: utf-8 -*- + +# Copyright 2012 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 +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 HPFanficArchiveComAdapter + +# Class name has to be unique. Our convention is camel case the +# sitename with Adapter at the end. www is skipped. +class HPFanficArchiveComAdapter(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]) + logging.debug("storyId: (%s)"%self.story.getMetadata('storyId')) + + # normalized story URL. + self._setURL('http://' + self.getSiteDomain() + '/stories/viewstory.php?sid='+self.story.getMetadata('storyId')) + + # Each adapter needs to have a unique site abbreviation. + self.story.setMetadata('siteabbrev','hpffa') + + # If all stories from the site fall into the same category, + # the site itself isn't likely to label them as such, so we + # do. + self.story.addToList("category","Harry Potter") + + # 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.hpfanficarchive.com' + + def getSiteExampleURLs(self): + return "http://"+self.getSiteDomain()+"/stories/viewstory.php?sid=1234" + + def getSiteURLPattern(self): + return re.escape("http://"+self.getSiteDomain()+"/stories/viewstory.php?sid=")+r"\d+$" + + ## Getting the chapter list and the meta data, plus 'is adult' checking. + def extractChapterUrlsAndMetadata(self): + + # index=1 makes sure we see the story chapter index. Some + # sites skip that for one-chapter stories. + url = self.url + logging.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 "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')+"$")) + self.story.setMetadata('title',a.string) + + # Find authorid and URL from... author url. + a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+")) + self.story.setMetadata('authorId',a['href'].split('=')[1]) + self.story.setMetadata('authorUrl','http://'+self.host+'/stories/'+a['href']) + self.story.setMetadata('author',a.string) + + # Find the chapters: + for chapter in soup.findAll('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"&chapter=\d+$")): + # just in case there's tags, like in chapter titles. + self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+'/stories/'+chapter['href'])) + + 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')) + 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')) # XXX + 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')) # XXX + 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+'/stories/'+a['href'] + + # use BeautifulSoup HTML parser to make everything easier to find. + seriessoup = bs.BeautifulSoup(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) + 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): + + logging.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/fanficdownloader/adapters/adapter_svufictioncom.py b/fanficdownloader/adapters/adapter_svufictioncom.py new file mode 100644 index 0000000..387188a --- /dev/null +++ b/fanficdownloader/adapters/adapter_svufictioncom.py @@ -0,0 +1,271 @@ +# -*- coding: utf-8 -*- + +# Copyright 2012 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 +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 SVUFictionComAdapter + +# Class name has to be unique. Our convention is camel case the +# sitename with Adapter at the end. www is skipped. +class SVUFictionComAdapter(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]) + logging.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','svuf') + + # 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 'svufiction.com' + + 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' + logging.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 + logging.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=6" + 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 + logging.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) + + 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 + logging.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. + + ## Title + pt = soup.find('div', {'class' : 'title'}) + a = pt.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$")) + if a.text != "": + self.story.setMetadata('title',a.text) + else: + self.story.setMetadata('title','Banner') + + # Find authorid and URL from... author url. + a = pt.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) + + rating=pt.text.split('[')[1].split(']')[0] + self.story.setMetadata('rating', rating) + + # 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 "" + + bottom=soup.find('div', {'class' : 'bottom'}).text + self.story.setMetadata('numWords', bottom.split('Word count: ')[1].split(' Read:')[0]) + self.story.setMetadata('datePublished', makeDate(bottom.split('Published: ')[1].split(' Updated:')[0], self.dateformat)) + self.story.setMetadata('dateUpdated', makeDate(bottom.split('Updated: ')[1], self.dateformat)) + + + content=soup.find('div', {'class' : 'content'}) + value=content.find('h1').nextSibling + svalue = "" + while not defaultGetattr(value,'class') == 'smaller': + svalue += str(value) + value = value.nextSibling + self.setDescription(url,svalue) + + status = content.text.split('Completed: ')[1] + if 'Yes' in status: + self.story.setMetadata('status', 'Completed') + else: + self.story.setMetadata('status', 'In-Progress') + + cats = content.findAll('a',href=re.compile(r'browse.php\?type=categories')) + for cat in cats: + self.story.addToList('category',cat.string) + + chars = content.findAll('a',href=re.compile(r'browse.php\?type=characters')) + for char in chars: + self.story.addToList('characters',char.string) + + genres = content.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=1')) + for genre in genres: + self.story.addToList('genre',genre.string) + + 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)) + # 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) + 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): + + logging.debug('Getting chapter text from: %s' % url) + + soup = bs.BeautifulStoneSoup(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/fanficdownloader/adapters/adapter_twilightarchivescom.py b/fanficdownloader/adapters/adapter_twilightarchivescom.py new file mode 100644 index 0000000..704b2e1 --- /dev/null +++ b/fanficdownloader/adapters/adapter_twilightarchivescom.py @@ -0,0 +1,190 @@ +# -*- coding: utf-8 -*- + +# Copyright 2012 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 +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 TwilightArchivesComAdapter + +# Class name has to be unique. Our convention is camel case the +# sitename with Adapter at the end. www is skipped. +class TwilightArchivesComAdapter(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.path.split('/',)[2]) + logging.debug("storyId: (%s)"%self.story.getMetadata('storyId')) + + # normalized story URL. http://www.twilightarchives.com/read/9353 + self._setURL('http://' + self.getSiteDomain() + '/read/'+self.story.getMetadata('storyId')) + + # Each adapter needs to have a unique site abbreviation. + self.story.setMetadata('siteabbrev','twa') + + # If all stories from the site fall into the same category, + # the site itself isn't likely to label them as such, so we + # do. + self.story.addToList("category","Twilight") + + # The date format will vary from site to site. + # http://docs.python.org/library/datetime.html#strftime-strptime-behavior + self.dateformat = "%d %b %y" + + @staticmethod # must be @staticmethod, don't remove it. + def getSiteDomain(): + # The site domain. Does have www here, if it uses it. + return 'www.twilightarchives.com' + + + def getSiteExampleURLs(self): + return "http://"+self.getSiteDomain()+"/read/1234" + + def getSiteURLPattern(self): + return re.escape("http://" + self.getSiteDomain()+"/read/")+r"\d+(/d+)?$" + + ## Getting the chapter list and the meta data, plus 'is adult' checking. + def extractChapterUrlsAndMetadata(self): + + # index=1 makes sure we see the story chapter index. Some + # sites skip that for one-chapter stories. + url = self.url + logging.debug("URL: "+url) + + try: + data = self._fetchUrl(url) + except urllib2.HTTPError, e: + if e.code == 404: + raise exceptions.StoryDoesNotExist(self.url) + else: + raise e + + if "Access denied. This story has not been validated by the adminstrators of this site." in data: + raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.") + + # use BeautifulSoup HTML parser to make everything easier to find. + soup = bs.BeautifulSoup(data) + # print data + + # Now go hunting for all the meta data and the chapter list. + + ## Title + a = soup.find('h1') + self.story.setMetadata('title',a.string) + + # Find the chapters: + chapters=soup.find('ol', {'class' : 'chapters'}) + if chapters != None: + for chapter in chapters.findAll('a', href=re.compile(r'/read/'+self.story.getMetadata('storyId')+"/\d+$")): + self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+chapter['href'])) + else: + self.chapterUrls.append((self.story.getMetadata('title'),url)) + + self.story.setMetadata('numChapters',len(self.chapterUrls)) + +# rated, genre, warnings, seires + + summary = soup.find('p', {'class' : 'images'}) + self.setDescription(url,summary) + + for c in soup.findAll('h2', {'class' : 'title'}): + div = c.nextSibling.nextSibling + + if 'Information' in c.text: + for dt in div.findAll('dt'): + dd=dt.nextSibling.nextSibling + + if 'Author' in dt.text: + a=dd.find('a') + self.story.setMetadata('authorId',a['href'].split('/')[2]) + self.story.setMetadata('authorUrl','http://'+self.host+a['href']) + self.story.setMetadata('author',a.text) + + if 'Words' in dt.text: + self.story.setMetadata('numWords', dd.text) + + if 'Published' in dt.text: + self.story.setMetadata('datePublished', makeDate(stripHTML(dd.text), self.dateformat)) + + if 'Updated' in dt.text: + self.story.setMetadata('dateUpdated', makeDate(stripHTML(dd.text), self.dateformat)) + + if 'Status' in dt.text: + if 'Complete' in dd.text: + self.story.setMetadata('status', 'Completed') + else: + self.story.setMetadata('status', 'In-Progress') + + if 'Categories' in c.text: + for a in div.findAll('a'): + self.story.addToList('category',a.text) + + if 'Characters' in c.text: + for a in div.findAll('a'): + self.story.addToList('category',a.text) + + if 'Series' in c.text: + a=div.find('a') + series_name = a.text + series_url = 'http://'+self.host+a['href'] + + seriessoup = bs.BeautifulSoup(self._fetchUrl(series_url)) + storyas = seriessoup.find('tbody').findAll('a', href=re.compile(r'^/read/\d+$')) + i=1 + for a in storyas: + if a['href'] == ('/read/'+self.story.getMetadata('storyId')): + self.setSeries(series_name, i) + break + i+=1 + + asoup = bs.BeautifulSoup(self._fetchUrl(self.story.getMetadata('authorUrl'))) + a=asoup.find('tbody').find('a', href=re.compile(r'^/read/'+self.story.getMetadata('storyId'))) + self.story.setMetadata('rating',a.parent.nextSibling.nextSibling.text) + + # grab the text for an individual chapter. + def getChapterText(self, url): + + logging.debug('Getting chapter text from: %s' % url) + + soup = bs.BeautifulStoneSoup(self._fetchUrl(url), + selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags. + + div = soup.find('div', {'class' : 'size images medium'}) + + if None == div: + raise exceptions.FailedToDownload("Error downloading Chapter: %s! Missing required element!" % url) + + return self.utf8FromSoup(url,div) diff --git a/fanficdownloader/adapters/adapter_wizardtalesnet.py b/fanficdownloader/adapters/adapter_wizardtalesnet.py new file mode 100644 index 0000000..419dc54 --- /dev/null +++ b/fanficdownloader/adapters/adapter_wizardtalesnet.py @@ -0,0 +1,299 @@ +# -*- coding: utf-8 -*- + +# Copyright 2012 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 +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 WizardTalesNetAdapter + +# Class name has to be unique. Our convention is camel case the +# sitename with Adapter at the end. www is skipped. +class WizardTalesNetAdapter(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]) + logging.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','wzt') + + # 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.wizardtales.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' + logging.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 + logging.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" + else: + addurl="" + + # index=1 makes sure we see the story chapter index. Some + # sites skip that for one-chapter stories. + url = self.url+addurl + logging.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) + + 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 + logging.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. + + ## Title + pt = soup.find('div', {'id' : 'pagetitle'}) + a = pt.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$")) + self.story.setMetadata('title',a.text) + + # Find authorid and URL from... author url. + a = pt.find('a', href=re.compile(r"viewuser.php\?uid=\d+")) + self.story.setMetadata('authorId',a['href'].split('=')[1]) + self.story.setMetadata('authorUrl','http://'+self.host+'/'+a['href']) + self.story.setMetadata('author',a.string) + + rating=pt.text.split('[')[1].split(']')[0] + self.story.setMetadata('rating', rating) + + # Find the chapters: + for chapter in soup.findAll('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"&chapter=\d+$")): + # 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. + + # Rated: NC-17
etc + content=soup.find('div',{'class' : 'content'}) + + for genre in content.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=1')): + self.story.addToList('genre',genre.string) + + for warning in content.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=2')): + self.story.addToList('warnings',warning.string) + + labels = content.findAll('b') + + value = labels[0].previousSibling + svalue = "" + while value != None: + val = value + value = value.previousSibling + while "Categories" not in val: + svalue += str(val) + val = val.nextSibling + self.setDescription(url,svalue) + + + + 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) + + if 'Word count' in label: + self.story.setMetadata('numWords', stripHTML(value).split(': ')[1].split(';')[0]) + + 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).split(': ')[1].split(';')[0], self.dateformat)) + + if 'Updated' in label: + self.story.setMetadata('dateUpdated', makeDate(stripHTML(value).split(': ')[1], 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)) + # 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) + 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): + + logging.debug('Getting chapter text from: %s' % url) + + soup = bs.BeautifulStoneSoup(self._fetchUrl(url), + selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags. + + div = soup.findAll('div', {'id' : 'story'})[1] + + if None == div: + raise exceptions.FailedToDownload("Error downloading Chapter: %s! Missing required element!" % url) + + return self.utf8FromSoup(url,div)