diff --git a/fanficdownloader/adapters/adapter_dracoandginnycom.py b/fanficdownloader/adapters/adapter_dracoandginnycom.py new file mode 100644 index 00000000..389c42cc --- /dev/null +++ b/fanficdownloader/adapters/adapter_dracoandginnycom.py @@ -0,0 +1,300 @@ +# -*- 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 DracoAndGinnyComAdapter + +# Class name has to be unique. Our convention is camel case the +# sitename with Adapter at the end. www is skipped. +class DracoAndGinnyComAdapter(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','dcagn') + + # 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.dracoandginny.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=2" + 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 + 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+'/'+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 + content=soup.find('div',{'class' : 'listbox'}) + + self.setDescription(url,content.find('blockquote')) + + 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') + + 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', value.split(' |')[0]) + + if 'Rating' in label: + self.story.setMetadata('rating', 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.nextSibling).split(' |')[0], 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 = 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', {'class' : 'listbox'}) + + 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_scarvesandcoffeenet.py b/fanficdownloader/adapters/adapter_scarvesandcoffeenet.py new file mode 100644 index 00000000..b5549a56 --- /dev/null +++ b/fanficdownloader/adapters/adapter_scarvesandcoffeenet.py @@ -0,0 +1,249 @@ +# -*- 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 ScarvesAndCoffeeNetAdapter + +# Class name has to be unique. Our convention is camel case the +# sitename with Adapter at the end. www is skipped. +class ScarvesAndCoffeeNetAdapter(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','scacf') + + # 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","Glee") + + # 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.scarvesandcoffee.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 + + ## 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=20" + 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 + + 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 + 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+'/'+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')) + for cat in cats: + self.story.addToList('genre',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 '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 = 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_thepetulantpoetesscom.py b/fanficdownloader/adapters/adapter_thepetulantpoetesscom.py new file mode 100644 index 00000000..11c53cdc --- /dev/null +++ b/fanficdownloader/adapters/adapter_thepetulantpoetesscom.py @@ -0,0 +1,239 @@ +# -*- 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 ThePetulantPoetessComAdapter + +# Class name has to be unique. Our convention is camel case the +# sitename with Adapter at the end. www is skipped. +class ThePetulantPoetessComAdapter(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') +'&i=1') + + # Each adapter needs to have a unique site abbreviation. + self.story.setMetadata('siteabbrev','tpp') + + # 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 'www.thepetulantpoetess.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 'You must be a member to read this story.' in data \ + or "The Ministry of Magic does not have a record of that password. " 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 "My Account Page" 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): + + # 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. + + # 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: + chapters=soup.find('select', {'name' : 'sid'}) + if chapters == None: + self.chapterUrls.append((self.story.getMetadata('title'),url)) + else: + for chapter in chapters.findAll('option', value=re.compile(r"viewstory.php\?sid=\d+&i=1")): + # just in case there's tags, like in chapter titles. + self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+'/'+chapter['value'])) + + self.story.setMetadata('numChapters',len(self.chapterUrls)) + + # make sure that the story id is from the first chapter + self.story.setMetadata('storyId',self.chapterUrls[0][1].split('=')[1].split('&')[0]) + + #locate the story on author's page + index = 1 + found = 0 + while found == 0: + asoup = bs.BeautifulSoup(self._fetchUrl(self.story.getMetadata('authorUrl')+"&page="+str(index))) + + for info in asoup.findAll('td', {'class' : 'highlightcolor1'}): + a = info.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$")) + if a != None: + self.story.setMetadata('title',a.text) + found = 1 + break + index=index+1 + + # extract metadata + b=info.find('b') + b.find('a').extract() + self.story.setMetadata('rating', b.text.split('[')[1].split(']')[0]) + + info = info.findNext('td', {'colspan' : '2'}) + for label in info.findAll('b'): + value = label.nextSibling + + if "Category" in label.text: + for cat in info.findAll('a'): + self.story.addToList('category',cat.string) + + if "Characters" in label.text: + for char in value.split(', '): + self.story.addToList('characters',char) + + if "Genres" in label.text: + for genre in value.split(', '): + if "General" not in genre: + self.story.addToList('genre',genre) + + if "Warnings" in label.text: + for warning in value.split(', '): + if "none" not in warning.lower(): + self.story.addToList('warnings',warning) + + + info = info.findNext('td', {'class' : 'tblborder'}) + info.find('b').extract() + self.setDescription(url,info) + + info = info.findNext('td', {'class' : 'highlightcolor2'}) + for label in info.findAll('b'): + value = label.nextSibling + + if "Completed" in label.text: + if 'Yes' in value: + self.story.setMetadata('status', 'Completed') + else: + self.story.setMetadata('status', 'In-Progress') + + if 'Published' in label.text: + self.story.setMetadata('datePublished', makeDate(stripHTML(value), self.dateformat)) + + if 'Updated' in label.text: + self.story.setMetadata('dateUpdated', makeDate(stripHTML(value), self.dateformat)) + + if 'Word Count' in label.text: + self.story.setMetadata('numWords', value) + + + # 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('table')[2].findAll('td')[1] + for a in div.findAll('div'): + a.extract() + div.name='div' + + 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_wolverineandroguecom.py b/fanficdownloader/adapters/adapter_wolverineandroguecom.py new file mode 100644 index 00000000..095dff57 --- /dev/null +++ b/fanficdownloader/adapters/adapter_wolverineandroguecom.py @@ -0,0 +1,222 @@ +# -*- 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 WolverineAndRogueComAdapter + +# Class name has to be unique. Our convention is camel case the +# sitename with Adapter at the end. www is skipped. +class WolverineAndRogueComAdapter(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() + '/wrfa/viewstory.php?sid='+self.story.getMetadata('storyId')) + + # Each adapter needs to have a unique site abbreviation. + self.story.setMetadata('siteabbrev','wrfa') + + # 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","Wolverine") + self.story.addToList("category","Rogue") + + # 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.wolverineandrogue.com' + + def getSiteExampleURLs(self): + return "http://"+self.getSiteDomain()+"/wrfa/viewstory.php?sid=1234" + + def getSiteURLPattern(self): + return re.escape("http://"+self.getSiteDomain()+"/wrfa/viewstory.php?sid=")+r"\d+$" + + + ## Getting the chapter list and the meta data, plus 'is adult' checking. + def extractChapterUrlsAndMetadata(self): + + # index=1 makes sure we see the story chapter index. Some + # sites skip that for one-chapter stories. + url = self.url+'&index=1' + logging.debug("URL: "+url) + + try: + data = self._fetchUrl(url) + except urllib2.HTTPError, e: + if e.code == 404: + raise exceptions.StoryDoesNotExist(self.url) + else: + raise e + + if "Access denied. This story has not been validated by the adminstrators of this site." in data: + raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.") + + # use BeautifulSoup HTML parser to make everything easier to find. + soup = bs.BeautifulSoup(data) + # print data + + # Now go hunting for all the meta data and the chapter list. + + ## Title + pt = soup.find('div', {'id' : 'pagetitle'}) + a = pt.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$")) + 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+'/wrfa/'+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+'/wrfa/'+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. + + # Rated: NC-17
etc + content=soup.find('div',{'class' : 'content'}) + labels = soup.findAll('span',{'class':'label'}) + + value = labels[0].previousSibling + svalue = "" + while value != None: + val = value + value = value.previousSibling + while "Categories" not in str(val): + svalue += str(val) + val = val.nextSibling + self.setDescription(url,svalue) + + + 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.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 'Complete' 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(value.split(' -')[0], 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+'/wrfa/'+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)