mirror of
https://github.com/JimmXinu/FanFicFare.git
synced 2025-12-06 08:52:55 +01:00
Support for thewriterscoffeeshop.com, allow both login/pass and Are Adult in one site.
This commit is contained in:
Jim Miller
parent
9b2450a609
commit
6d2f657729
9 changed files with 232 additions and 23 deletions
|
|
@ -45,9 +45,9 @@ class HarryPotterFanFictionComSiteAdapter(BaseSiteAdapter):
|
|||
return re.escape("http://")+r"(www\.)?"+re.escape("harrypotterfanfiction.com/viewstory.php?psid=")+r"\d+$"
|
||||
|
||||
def needToLoginCheck(self, data):
|
||||
if 'Registered Users Only.' in data \
|
||||
if 'Registered Users Only' in data \
|
||||
or 'There is no such account on our website' in data \
|
||||
or "That password doesn't match the one in our database." in data:
|
||||
or "That password doesn't match the one in our database" in data:
|
||||
return True
|
||||
else:
|
||||
return False
|
||||
|
|
|
|||
|
|
@ -44,9 +44,9 @@ class PotionsAndSnitchesNetSiteAdapter(BaseSiteAdapter):
|
|||
return re.escape("http://")+r"(www\.)?"+re.escape("potionsandsnitches.net/fanfiction/viewstory.php?sid=")+r"\d+$"
|
||||
|
||||
def needToLoginCheck(self, data):
|
||||
if 'Registered Users Only.' in 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:
|
||||
or "That password doesn't match the one in our database" in data:
|
||||
return True
|
||||
else:
|
||||
return False
|
||||
|
|
|
|||
|
|
@ -43,8 +43,11 @@ class TestSiteAdapter(BaseSiteAdapter):
|
|||
|
||||
if self.story.getMetadata('storyId') == '668' and self.username != "Me" :
|
||||
raise exceptions.FailedToLogin(self.url,self.username)
|
||||
|
||||
self.story.setMetadata(u'title',"Test Story Title "+self.crazystring)
|
||||
|
||||
if self.story.getMetadata('storyId') == '664':
|
||||
self.story.setMetadata(u'title',"Test Story Title "+self.crazystring)
|
||||
else:
|
||||
self.story.setMetadata(u'title',"Test Story Title")
|
||||
self.story.setMetadata('storyUrl',self.url)
|
||||
self.story.setMetadata('description',u'Description '+self.crazystring+u''' Done
|
||||
|
||||
|
|
@ -92,6 +95,7 @@ Some more longer description. "I suck at summaries!" "Better than it sounds!"
|
|||
<div>
|
||||
<h3>Prologue</h3>
|
||||
<p>This is a fake adapter for testing purposes. Different storyId's will give different errors:</p>
|
||||
<p>http://test1.com?sid=664 - Crazy string title</p>
|
||||
<p>http://test1.com?sid=665 - raises AdultCheckRequired</p>
|
||||
<p>http://test1.com?sid=666 - raises StoryDoesNotExist</p>
|
||||
<p>http://test1.com?sid=667 - raises FailedToDownload on chapter 1</p>
|
||||
|
|
|
|||
201
fanficdownloader/adapters/adapter_thewriterscoffeeshopcom.py
Normal file
201
fanficdownloader/adapters/adapter_thewriterscoffeeshopcom.py
Normal file
|
|
@ -0,0 +1,201 @@
|
|||
# -*- coding: utf-8 -*-
|
||||
|
||||
import time
|
||||
import datetime
|
||||
import logging
|
||||
import re
|
||||
import urllib
|
||||
import urllib2
|
||||
|
||||
import fanficdownloader.BeautifulSoup as bs
|
||||
from fanficdownloader.htmlcleanup import stripHTML
|
||||
import fanficdownloader.exceptions as exceptions
|
||||
|
||||
from base_adapter import BaseSiteAdapter, utf8FromSoup
|
||||
|
||||
class TheWritersCoffeeShopComSiteAdapter(BaseSiteAdapter):
|
||||
|
||||
def __init__(self, config, url):
|
||||
BaseSiteAdapter.__init__(self, config, url)
|
||||
self.story.setMetadata('siteabbrev','twcs')
|
||||
self.decode = "ISO-8859-1"
|
||||
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() + '/library/viewstory.php?sid='+self.story.getMetadata('storyId'))
|
||||
|
||||
|
||||
@staticmethod
|
||||
def getSiteDomain():
|
||||
return 'www.thewriterscoffeeshop.com'
|
||||
|
||||
@classmethod
|
||||
def getAcceptDomains(cls):
|
||||
return [cls.getSiteDomain()]
|
||||
|
||||
def getSiteExampleURLs(self):
|
||||
return "http://"+self.getSiteDomain()+"/library/viewstory.php?sid=1234"
|
||||
|
||||
def getSiteURLPattern(self):
|
||||
return re.escape("http://"+self.getSiteDomain()+"/library/viewstory.php?sid=")+r"\d+$"
|
||||
|
||||
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() + '/library/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
|
||||
|
||||
def extractChapterUrlsAndMetadata(self):
|
||||
|
||||
if self.is_adult or self.getConfig("is_adult"):
|
||||
addurl = "&ageconsent=ok&warning=3"
|
||||
else:
|
||||
addurl=""
|
||||
|
||||
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)
|
||||
|
||||
if "Age Consent Required" in data:
|
||||
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)
|
||||
|
||||
## 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+'/library/'+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 <i> in chapter titles.
|
||||
self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+'/library/'+chapter['href']+addurl))
|
||||
|
||||
self.story.setMetadata('numChapters',len(self.chapterUrls))
|
||||
|
||||
def defaultGetattr(d,k):
|
||||
try:
|
||||
return d[k]
|
||||
except:
|
||||
return ""
|
||||
|
||||
# <span class="label">Rated:</span> NC-17<br /> 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.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 'Genre' in label:
|
||||
genres = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class'))
|
||||
genrestext = [genre.string for genre in genres]
|
||||
self.genre = ', '.join(genrestext)
|
||||
for genre in genrestext:
|
||||
self.story.addToList('genre',genre.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', datetime.datetime.fromtimestamp(time.mktime(time.strptime(stripHTML(value), "%B %d, %Y"))))
|
||||
|
||||
if 'Updated' in label:
|
||||
# there's a stray [ at the end.
|
||||
#value = value[0:-1]
|
||||
self.story.setMetadata('dateUpdated', datetime.datetime.fromtimestamp(time.mktime(time.strptime(stripHTML(value), "%B %d, %Y"))))
|
||||
|
||||
|
||||
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.
|
||||
|
||||
span = soup.find('div', {'id' : 'story'})
|
||||
|
||||
if None == span:
|
||||
raise exceptions.FailedToDownload("Error downloading Chapter: %s! Missing required element!" % url)
|
||||
|
||||
return utf8FromSoup(span)
|
||||
|
||||
def getClass():
|
||||
return TheWritersCoffeeShopComSiteAdapter
|
||||
|
||||
|
|
@ -20,7 +20,7 @@ class TwilightedNetSiteAdapter(BaseSiteAdapter):
|
|||
self.story.setMetadata('siteabbrev','tw')
|
||||
self.decode = "utf8"
|
||||
self.story.addToList("category","Twilight")
|
||||
self.username = "NoneGiven" # if left empty, twilighted.net doesn't return any message at all.
|
||||
self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
|
||||
self.password = ""
|
||||
|
||||
# get storyId from url--url validation guarantees query is only sid=1234
|
||||
|
|
@ -46,9 +46,9 @@ class TwilightedNetSiteAdapter(BaseSiteAdapter):
|
|||
return re.escape("http://")+r"(www\.)?"+re.escape("twilighted.net/viewstory.php?sid=")+r"\d+$"
|
||||
|
||||
def needToLoginCheck(self, data):
|
||||
if 'Registered Users Only.' in 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:
|
||||
or "That password doesn't match the one in our database" in data:
|
||||
return True
|
||||
else:
|
||||
return False
|
||||
|
|
@ -120,14 +120,6 @@ class TwilightedNetSiteAdapter(BaseSiteAdapter):
|
|||
|
||||
self.story.setMetadata('numChapters',len(self.chapterUrls))
|
||||
|
||||
## <meta name='description' content='<p>Description</p> ...' >
|
||||
## Summary, strangely, is in the content attr of a <meta name='description'> tag
|
||||
## which is escaped HTML. Unfortunately, we can't use it because they don't
|
||||
## escape (') chars in the desc, breakin the tag.
|
||||
#meta_desc = soup.find('meta',{'name':'description'})
|
||||
#metasoup = bs.BeautifulStoneSoup(meta_desc['content'])
|
||||
#self.story.setMetadata('description',stripHTML(metasoup))
|
||||
|
||||
def defaultGetattr(d,k):
|
||||
try:
|
||||
return d[k]
|
||||
|
|
|
|||
|
|
@ -48,7 +48,7 @@ class TwiwriteNetSiteAdapter(BaseSiteAdapter):
|
|||
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:
|
||||
or "That password doesn't match the one in our database" in data:
|
||||
return True
|
||||
else:
|
||||
return False
|
||||
|
|
|
|||
|
|
@ -56,10 +56,10 @@
|
|||
This version is a new re-org/re-write of the code.
|
||||
</p>
|
||||
<p>
|
||||
So far, the only sites supported are: fanfiction.net, fictionalley.com, ficwad.com, twilighted.net and whofic.com.
|
||||
fictionalley.org and mediaminer.org aren't support yet.
|
||||
</p>
|
||||
<p>
|
||||
Login/Password is asked for when required now.
|
||||
Login/Password is asked for when required now, as is 'Are you an Adult?' where required.
|
||||
</p>
|
||||
<p>
|
||||
Mobi support (for Kindle) is only via EPub conversion in this version.
|
||||
|
|
@ -164,6 +164,11 @@
|
|||
Use the URL of the story's chapter list, such as
|
||||
<br /><a href="http://www.whofic.com/viewstory.php?sid=16334">http://www.whofic.com/viewstory.php?sid=16334</a>.
|
||||
</dd>
|
||||
<dt>thewriterscoffeeshop.com</dt>
|
||||
<dd>
|
||||
Use the URL of the story's chapter list, such as
|
||||
<br /><a href="http://www.thewriterscoffeeshop.com/library/viewstory.php?sid=2110">http://www.thewriterscoffeeshop.com/library/viewstory.php?sid=2110</a>.
|
||||
</dd>
|
||||
</dl>
|
||||
|
||||
|
||||
|
|
|
|||
|
|
@ -49,7 +49,7 @@
|
|||
<input type="hidden" name="format" value='{{ format }}'>
|
||||
<div id='logpasswordtable'>
|
||||
|
||||
{% if login %}
|
||||
{% if is_login %}
|
||||
|
||||
<h3>Login and Password</h3>
|
||||
<div id='logpassword'>
|
||||
|
|
@ -69,6 +69,8 @@
|
|||
|
||||
{% else %}
|
||||
|
||||
<input type="hidden" name="login" value='{{ login }}'>
|
||||
<input type="hidden" name="password" value='{{ password }}'>
|
||||
<div class='fieldandlabel'>
|
||||
<div class='label'>Are you an Adult? <input type='checkbox' name='is_adult'></div>
|
||||
</div>
|
||||
|
|
|
|||
9
main.py
9
main.py
|
|
@ -316,14 +316,19 @@ class FanfictionDownloader(UserConfigServer):
|
|||
download.failure = str(e)
|
||||
download.put()
|
||||
logging.debug('Need to Login, display log in page')
|
||||
login= ( isinstance(e, exceptions.FailedToLogin) )
|
||||
is_login= ( isinstance(e, exceptions.FailedToLogin) )
|
||||
template_values = dict(nickname = user.nickname(),
|
||||
url = url,
|
||||
format = format,
|
||||
site = adapter.getSiteDomain(),
|
||||
fic = download,
|
||||
login=login,
|
||||
is_login=is_login,
|
||||
)
|
||||
# thewriterscoffeeshop.com can do adult check *and* user required.
|
||||
if isinstance(e,exceptions.AdultCheckRequired):
|
||||
template_values['login']=login
|
||||
template_values['password']=password
|
||||
|
||||
path = os.path.join(os.path.dirname(__file__), 'login.html')
|
||||
self.response.out.write(template.render(path, template_values))
|
||||
return
|
||||
|
|
|
|||
Loading…
Reference in a new issue