From fad5d6837d7d233085fe154cef88338aca051e9d Mon Sep 17 00:00:00 2001 From: Jim Miller Date: Sat, 11 Apr 2015 16:51:18 -0500 Subject: [PATCH] Fix problems found during trawl through all sites. --- calibre-plugin/plugin-defaults.ini | 34 +- .../adapters/adapter_bloodtiesfancom.py | 52 ++- fanficfare/adapters/adapter_dramioneorg.py | 10 +- fanficfare/adapters/adapter_finestoriescom.py | 2 +- .../adapters/adapter_libraryofmoriacom.py | 237 +------------- fanficfare/adapters/adapter_portkeyorg.py | 4 + .../adapters/adapter_pretendercentrecom.py | 2 +- .../adapters/adapter_thehookupzonenet.py | 297 +----------------- fanficfare/defaults.ini | 34 +- 9 files changed, 127 insertions(+), 545 deletions(-) diff --git a/calibre-plugin/plugin-defaults.ini b/calibre-plugin/plugin-defaults.ini index f6bd44f6..a1b7ad22 100644 --- a/calibre-plugin/plugin-defaults.ini +++ b/calibre-plugin/plugin-defaults.ini @@ -1,4 +1,4 @@ -# Copyright 2013 Fanficdownloader team +# Copyright 2015 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. @@ -1002,6 +1002,12 @@ dislikes_label:Dislikes #username:YourName #password:yourpassword +# shows size as "10 KB", not word count +extra_valid_entries:size + +# don't show twitter icon. +cover_exclusion_regexp:/res/css/bir.png + [grangerenchanted.com] ## Some sites require login (or login for some rated stories) The ## program can prompt you, or you can save it in config. In @@ -1338,6 +1344,11 @@ extraships:Harry Potter/Draco Malfoy ## personal.ini, not defaults.ini. #is_adult:true +## Virtually all eFiction-based sites allow downloading the whole story in +## bulk using the 'Print' feature. If 'bulk_load' is set to 'true', both +## metadata and chapters can be loaded in one step +bulk_load:true + ## Site dedicated to these categories/characters/ships extracategories:Criminal Minds @@ -1590,6 +1601,22 @@ extratags: ## for examples of how to use them. extra_valid_entries:reviews,favs,follows +## fanfiction.net shows the user's +cover_exclusion_regexp:(/imageu/|d_60_90\.jpg) + +## fanfiction.net is blocking people more aggressively. If you +## download fewer stories less often you can likely get by with +## reducing this sleep. +slow_down_sleep_time:4 + +## Date formats used by FFDL. Published and Update don't usually have +## time, but they do now on ffnet. +## See http://docs.python.org/library/datetime.html#strftime-strptime-behavior +## Note that ini format requires % to be escaped as %%. +#dateCreated_format:%%Y-%%m-%%d %%H:%%M:%%S +datePublished_format:%%Y-%%m-%%d %%H:%%M:%%S +dateUpdated_format:%%Y-%%m-%%d %%H:%%M:%%S + [www.fimfiction.net] ## Some sites do not require a login, but do require the user to ## confirm they are adult for adult content. In commandline version, @@ -1700,6 +1727,11 @@ extraships:InuYasha/Kagome ## Site dedicated to these categories/characters/ships extracategories:Lord of the Rings +## Virtually all eFiction-based sites allow downloading the whole story in +## bulk using the 'Print' feature. If 'bulk_load' is set to 'true', both +## metadata and chapters can be loaded in one step +bulk_load:true + [www.mediaminer.org] [www.midnightwhispers.ca] diff --git a/fanficfare/adapters/adapter_bloodtiesfancom.py b/fanficfare/adapters/adapter_bloodtiesfancom.py index 28ab7710..03c63d2e 100644 --- a/fanficfare/adapters/adapter_bloodtiesfancom.py +++ b/fanficfare/adapters/adapter_bloodtiesfancom.py @@ -82,7 +82,7 @@ class BloodTiesFansComAdapter(BaseSiteAdapter): # XXX # The date format will vary from site to site. # http://docs.python.org/library/datetime.html#strftime-strptime-behavior - self.dateformat = "%b %d, %Y" # XXX + self.dateformat = "%d %b %Y" # XXX @staticmethod # must be @staticmethod, don't remove it. def getSiteDomain(): @@ -233,25 +233,27 @@ class BloodTiesFansComAdapter(BaseSiteAdapter): # XXX except: return "" - # Rated: NC-17
etc - labels = soup.findAll('span',{'class':'label'}) + listbox = soup.find('div',{'class':'listbox'}) + # Rating: M
etc + labels = listbox.findAll('strong') for labelspan in labels: value = labelspan.nextSibling label = labelspan.string if 'Summary' in label: - ## Everything until the next span class='label' + ## Everything until the next strong tag. svalue = "" - while not defaultGetattr(value,'class') == 'label': + while not isinstance(value,bs.Tag) or value.name != 'strong': svalue += str(value) value = value.nextSibling self.setDescription(url,svalue) #self.story.setMetadata('description',stripHTML(svalue)) - if 'Rated' in label: + if 'Rating' in label: self.story.setMetadata('rating', value) - if 'Word count' in label: + if 'Words' in label: + value=re.sub(r"\|",r"",value) self.story.setMetadata('numWords', value) if 'Categories' in label: @@ -266,26 +268,6 @@ class BloodTiesFansComAdapter(BaseSiteAdapter): # XXX 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') @@ -293,13 +275,25 @@ class BloodTiesFansComAdapter(BaseSiteAdapter): # XXX self.story.setMetadata('status', 'In-Progress') if 'Published' in label: + value=re.sub(r"\|",r"",value) self.story.setMetadata('datePublished', makeDate(stripHTML(value), self.dateformat)) if 'Updated' in label: - # there's a stray [ at the end. - #value = value[0:-1] + value=re.sub(r"\|",r"",value) self.story.setMetadata('dateUpdated', makeDate(stripHTML(value), self.dateformat)) + # moved outside because they changed *most*, but not *all* labels to + ships = listbox.findAll('a',href=re.compile(r'browse.php.type=class&(amp;)?type_id=2')) # crappy html: & vs & in url. + shipstext = [ship.string for ship in ships] + for ship in shipstext: + self.story.addToList('ships',ship.string) + + genres = listbox.findAll('a',href=re.compile(r'browse.php\?type=class&(amp;)?type_id=1')) # crappy html: & vs & in url. + genrestext = [genre.string for genre in genres] + for genre in genrestext: + 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+")) diff --git a/fanficfare/adapters/adapter_dramioneorg.py b/fanficfare/adapters/adapter_dramioneorg.py index 2d2a4f05..52a896dc 100644 --- a/fanficfare/adapters/adapter_dramioneorg.py +++ b/fanficfare/adapters/adapter_dramioneorg.py @@ -218,20 +218,20 @@ class DramioneOrgAdapter(BaseSiteAdapter): except: return "" - # Rated: NC-17
etc - labels = soup.findAll('span',{'class':'label'}) + listbox = soup.find('div',{'class':'listbox'}) + # Rated: M
etc + labels = listbox.findAll('strong') for labelspan in labels: value = labelspan.nextSibling label = labelspan.string if 'Summary' in label: - ## Everything until the next span class='label' + ## Everything until the next strong tag. svalue = "" - while not defaultGetattr(value,'class') == 'label': + while not isinstance(value,bs.Tag) or value.name != 'strong': 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) diff --git a/fanficfare/adapters/adapter_finestoriescom.py b/fanficfare/adapters/adapter_finestoriescom.py index e0d798df..20fabbae 100644 --- a/fanficfare/adapters/adapter_finestoriescom.py +++ b/fanficfare/adapters/adapter_finestoriescom.py @@ -173,7 +173,7 @@ class FineStoriesComAdapter(BaseSiteAdapter): for cat in lc2.findAll('div', {'class' : 'typediv'}): self.story.addToList('category',cat.text) - self.story.setMetadata('numWords', lc2.findNext('td', {'class' : 'num'}).text) + self.story.setMetadata('size', lc2.findNext('td', {'class' : 'num'}).text) lc4 = lc2.findNext('td', {'class' : 'lc4'}) diff --git a/fanficfare/adapters/adapter_libraryofmoriacom.py b/fanficfare/adapters/adapter_libraryofmoriacom.py index 4c58e582..08196cfb 100644 --- a/fanficfare/adapters/adapter_libraryofmoriacom.py +++ b/fanficfare/adapters/adapter_libraryofmoriacom.py @@ -16,236 +16,25 @@ # # Software: eFiction -import time -import logging -logger = logging.getLogger(__name__) -import re -import urllib2 +from base_efiction_adapter import BaseEfictionAdapter -from .. import BeautifulSoup as bs -from ..htmlcleanup import stripHTML -from .. import exceptions as exceptions +class LibraryOfMoriaComAdapter(BaseEfictionAdapter): -from base_adapter import BaseSiteAdapter, makeDate - - -def getClass(): - return LibraryOfMoriaComAdapter - -# Class name has to be unique. Our convention is camel case the -# sitename with Adapter at the end. www is skipped. -class LibraryOfMoriaComAdapter(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]) - - - # normalized story URL. - self._setURL('http://' + self.getSiteDomain() + '/a/viewstory.php?sid='+self.story.getMetadata('storyId')) - - # Each adapter needs to have a unique site abbreviation. - self.story.setMetadata('siteabbrev','lom') - - # 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. + @staticmethod def getSiteDomain(): - # The site domain. Does have www here, if it uses it. return 'www.libraryofmoria.com' @classmethod - def getSiteExampleURLs(cls): - return "http://"+cls.getSiteDomain()+"/a/viewstory.php?sid=1234" + def getPathToArchive(self): + return '/a' - def getSiteURLPattern(self): - return re.escape("http://"+self.getSiteDomain()+"/a/viewstory.php?sid=")+r"\d+$" + @classmethod + def getSiteAbbrev(seluuf): + return 'lom' + @classmethod + def getDateFormat(self): + return "%B %d, %Y" - - ## Getting the chapter list and the meta data, plus 'is adult' checking. - def extractChapterUrlsAndMetadata(self): - - if self.is_adult or self.getConfig("is_adult"): - addurl = "&ageconsent=ok&warning=3" - else: - addurl="" - - # index=1 makes sure we see the story chapter index. Some - # sites skip that for one-chapter stories. - url = self.url+addurl - logger.debug("URL: "+url) - - try: - data = self._fetchUrl(url) - except urllib2.HTTPError, e: - if e.code == 404: - raise exceptions.StoryDoesNotExist(self.url) - else: - raise e - - m = re.search(r"'viewstory.php\?sid=\d+((?:&ageconsent=ok)?&warning=\d+)'",data) - if m != None: - if self.is_adult or self.getConfig("is_adult"): - # We tried the default and still got a warning, so - # let's pull the warning number from the 'continue' - # link and reload data. - addurl = m.group(1) - # correct stupid & error in url. - addurl = addurl.replace("&","&") - url = self.url+'&index=1'+addurl - logger.debug("URL 2nd try: "+url) - - try: - data = self._fetchUrl(url) - except urllib2.HTTPError, e: - if e.code == 404: - raise exceptions.StoryDoesNotExist(self.url) - else: - raise e - else: - raise exceptions.AdultCheckRequired(self.url) - - if "Access denied. This story has not been validated by the adminstrators of this site." in data: - raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.") - - # use BeautifulSoup HTML parser to make everything easier to find. - soup = bs.BeautifulSoup(data) - # print data - - # Now go hunting for all the meta data and the chapter list. - - ## Title - a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$")) - 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/'+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+'/a/'+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 'Type' 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 'Warning' in label: - warnings = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=5')) - 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: - # 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/'+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: - # 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 = 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) +def getClass(): + return LibraryOfMoriaComAdapter diff --git a/fanficfare/adapters/adapter_portkeyorg.py b/fanficfare/adapters/adapter_portkeyorg.py index 6e71a366..b5b1beff 100644 --- a/fanficfare/adapters/adapter_portkeyorg.py +++ b/fanficfare/adapters/adapter_portkeyorg.py @@ -261,6 +261,10 @@ class PortkeyOrgAdapter(BaseSiteAdapter): # XXX soup = bs.BeautifulSoup(data) + # remove ad blocks so they don't become covers. + for ns in soup.findAll('noscript'): + ns.extract() + #print("soup:%s"%soup) tag = soup.find('td', {'class' : 'story'}) if tag == None and "
Chapter does not exist!
" in data: diff --git a/fanficfare/adapters/adapter_pretendercentrecom.py b/fanficfare/adapters/adapter_pretendercentrecom.py index 5d38f3f7..23c3cdfa 100644 --- a/fanficfare/adapters/adapter_pretendercentrecom.py +++ b/fanficfare/adapters/adapter_pretendercentrecom.py @@ -246,7 +246,7 @@ class PretenderCenterComAdapter(BaseSiteAdapter): soup = bs.BeautifulStoneSoup(self._fetchUrl(url), selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags. - div = soup.findAll('div', {'id' : 'story'})[1] + div = soup.find('div', {'id' : 'story1'}) if None == div: raise exceptions.FailedToDownload("Error downloading Chapter: %s! Missing required element!" % url) diff --git a/fanficfare/adapters/adapter_thehookupzonenet.py b/fanficfare/adapters/adapter_thehookupzonenet.py index 2dfee944..65cce295 100644 --- a/fanficfare/adapters/adapter_thehookupzonenet.py +++ b/fanficfare/adapters/adapter_thehookupzonenet.py @@ -16,294 +16,25 @@ # # Software: eFiction -import time -import logging -logger = logging.getLogger(__name__) -import re -import urllib2 +from base_efiction_adapter import BaseEfictionAdapter -from .. import BeautifulSoup as bs -from ..htmlcleanup import stripHTML -from .. import exceptions as exceptions +class TheHookupZoneNetAdapter(BaseEfictionAdapter): -from base_adapter import BaseSiteAdapter, makeDate - -# By virtue of being recent and requiring both is_adult and user/pass, -# adapter_fanficcastletvnet.py is the best choice for learning to -# write adapters--especially for sites that use the eFiction system. -# Most sites that have ".../viewstory.php?sid=123" in the story URL -# are eFiction. - -# For non-eFiction sites, it can be considerably more complex, but -# this is still a good starting point. - -# In general an 'adapter' needs to do these five things: - -# - 'Register' correctly with the downloader -# - Site Login (if needed) -# - 'Are you adult?' check (if needed--some do one, some the other, some both) -# - Grab the chapter list -# - Grab the story meta-data (some (non-eFiction) adapters have to get it from the author page) -# - Grab the chapter texts - -# Search for XXX comments--that's where things are most likely to need changing. - -# 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 TheHookupZoneNetAdapter # XXX - -# Class name has to be unique. Our convention is camel case the -# sitename with Adapter at the end. www is skipped. -class TheHookupZoneNetAdapter(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 /fanfic part. Replace all to remove it usually. - self._setURL('http://' + self.getSiteDomain() + '/CriminalMinds/viewstory.php?sid='+self.story.getMetadata('storyId')) - - # Each adapter needs to have a unique site abbreviation. - self.story.setMetadata('siteabbrev','thupz') # XXX - - # The date format will vary from site to site. - # http://docs.python.org/library/datetime.html#strftime-strptime-behavior - self.dateformat = "%b %d, %Y" # XXX - - @staticmethod # must be @staticmethod, don't remove it. + @staticmethod def getSiteDomain(): - # The site domain. Does have www here, if it uses it. - return 'thehookupzone.net' # XXX + return 'thehookupzone.net' @classmethod - def getSiteExampleURLs(cls): - return "http://"+cls.getSiteDomain()+"/CriminalMinds/viewstory.php?sid=1234" + def getPathToArchive(self): + return '/CriminalMinds' - def getSiteURLPattern(self): - return re.escape("http://"+self.getSiteDomain()+"/CriminalMinds/viewstory.php?sid=")+r"\d+$" + @classmethod + def getSiteAbbrev(seluuf): + return 'thupz' - ## 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 = {} + @classmethod + def getDateFormat(self): + return "%d/%m/%y" - 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() + '/CriminalMinds/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 "Age Consent Required" in data: # 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')+"$")) - self.story.setMetadata('title',stripHTML(a)) - - # Find authorid and URL from... author url. - a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+")) - self.story.setMetadata('authorId',a['href'].split('=')[1]) - self.story.setMetadata('authorUrl','http://'+self.host+'/CriminalMinds/'+a['href']) - self.story.setMetadata('author',a.string) - - # Find the chapters: - for chapter in soup.findAll('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"&chapter=\d+$")): - # just in case there's tags, like in chapter titles. - self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+'/CriminalMinds/'+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) - - ## 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+'/CriminalMinds/'+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. - - 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 TheHookupZoneNetAdapter diff --git a/fanficfare/defaults.ini b/fanficfare/defaults.ini index b1b527a6..7b6f5814 100644 --- a/fanficfare/defaults.ini +++ b/fanficfare/defaults.ini @@ -1,4 +1,4 @@ -# Copyright 2015 Fanficdownloader team +# Copyright 2015 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. @@ -1008,6 +1008,12 @@ dislikes_label:Dislikes #username:YourName #password:yourpassword +# shows size as "10 KB", not word count +extra_valid_entries:size + +# don't show twitter icon. +cover_exclusion_regexp:/res/css/bir.png + [grangerenchanted.com] ## Some sites require login (or login for some rated stories) The ## program can prompt you, or you can save it in config. In @@ -1344,6 +1350,11 @@ extraships:Harry Potter/Draco Malfoy ## personal.ini, not defaults.ini. #is_adult:true +## Virtually all eFiction-based sites allow downloading the whole story in +## bulk using the 'Print' feature. If 'bulk_load' is set to 'true', both +## metadata and chapters can be loaded in one step +bulk_load:true + ## Site dedicated to these categories/characters/ships extracategories:Criminal Minds @@ -1590,6 +1601,22 @@ extratags: ## for examples of how to use them. extra_valid_entries:reviews,favs,follows +## fanfiction.net shows the user's +cover_exclusion_regexp:(/imageu/|d_60_90\.jpg) + +## fanfiction.net is blocking people more aggressively. If you +## download fewer stories less often you can likely get by with +## reducing this sleep. +slow_down_sleep_time:4 + +## Date formats used by FFDL. Published and Update don't usually have +## time, but they do now on ffnet. +## See http://docs.python.org/library/datetime.html#strftime-strptime-behavior +## Note that ini format requires % to be escaped as %%. +#dateCreated_format:%%Y-%%m-%%d %%H:%%M:%%S +datePublished_format:%%Y-%%m-%%d %%H:%%M:%%S +dateUpdated_format:%%Y-%%m-%%d %%H:%%M:%%S + [www.fimfiction.net] ## Some sites do not require a login, but do require the user to ## confirm they are adult for adult content. In commandline version, @@ -1700,6 +1727,11 @@ extraships:InuYasha/Kagome ## Site dedicated to these categories/characters/ships extracategories:Lord of the Rings +## Virtually all eFiction-based sites allow downloading the whole story in +## bulk using the 'Print' feature. If 'bulk_load' is set to 'true', both +## metadata and chapters can be loaded in one step +bulk_load:true + [www.mediaminer.org] [www.midnightwhispers.ca]