pastealacon: Port to Browser2

It works, but there are a lot of things that could be improved.
This commit is contained in:
Laurent Bachelier 2014-03-22 22:31:01 +01:00
commit 22ce4438e5
5 changed files with 88 additions and 147 deletions

View file

@ -1,6 +1,6 @@
# -*- coding: utf-8 -*-
# Copyright(C) 2011 Laurent Bachelier
# Copyright(C) 2011-2014 Laurent Bachelier
#
# This file is part of weboob.
#
@ -18,19 +18,13 @@
# along with weboob. If not, see <http://www.gnu.org/licenses/>.
import re
from weboob.tools.capabilities.paste import BasePasteBackend
from weboob.tools.backend import BaseBackend
from weboob.capabilities.base import NotLoaded
from .browser import PastealaconBrowser
from .paste import PastealaconPaste
__all__ = ['PastealaconBackend']
from .browser import PastealaconBrowser, PastealaconPaste
class PastealaconBackend(BaseBackend, BasePasteBackend):
@ -53,7 +47,7 @@ class PastealaconBackend(BaseBackend, BasePasteBackend):
def can_post(self, contents, title=None, public=None, max_age=None):
try:
contents.encode(self.browser.ENCODING)
contents.encode('ISO-8859-1')
except UnicodeEncodeError:
return 0
if public is False:
@ -67,20 +61,17 @@ class PastealaconBackend(BaseBackend, BasePasteBackend):
return 1
def get_paste(self, _id):
with self.browser:
return self.browser.get_paste(_id)
return self.browser.get_paste(_id)
def fill_paste(self, paste, fields):
# if we only want the contents
if fields == ['contents']:
if paste.contents is NotLoaded:
with self.browser:
contents = self.browser.get_contents(paste.id)
paste.contents = contents
contents = self.browser.get_contents(paste.id)
paste.contents = contents
# get all fields
elif fields is None or len(fields):
with self.browser:
self.browser.fill_paste(paste)
self.browser.fill_paste(paste)
return paste
def post_paste(self, paste, max_age=None):
@ -88,7 +79,6 @@ class PastealaconBackend(BaseBackend, BasePasteBackend):
expiration = self.get_closest_expiration(max_age)
else:
expiration = None
with self.browser:
self.browser.post_paste(paste, expiration=self.EXPIRATIONS.get(expiration))
self.browser.post_paste(paste, expiration=self.EXPIRATIONS.get(expiration))
OBJECTS = {PastealaconPaste: fill_paste}

View file

@ -1,6 +1,6 @@
# -*- coding: utf-8 -*-
# Copyright(C) 2011 Laurent Bachelier
# Copyright(C) 2011-2014 Laurent Bachelier
#
# This file is part of weboob.
#
@ -17,43 +17,84 @@
# You should have received a copy of the GNU Affero General Public License
# along with weboob. If not, see <http://www.gnu.org/licenses/>.
from mechanize import RobustFactory
import re
from weboob.tools.browser import BaseBrowser, BrowserUnavailable, BrowserHTTPNotFound
import requests
from weboob.capabilities.paste import PasteNotFound
from weboob.tools.browser.decorators import id2url, check_url
from .pages import PastePage, CaptchaPage, PostPage
from .paste import PastealaconPaste
__all__ = ['PastealaconBrowser']
from weboob.capabilities.paste import BasePaste, PasteNotFound
from weboob.tools.browser2 import HTMLPage, PagesBrowser, URL
class PastealaconBrowser(BaseBrowser):
DOMAIN = 'pastealacon.com'
ENCODING = 'ISO-8859-1'
PASTE_URL = 'http://%s/(?P<id>\d+)' % DOMAIN
PAGES = {PASTE_URL: PastePage,
'http://%s/%s' % (DOMAIN, re.escape('pastebin.php?captcha=1')): CaptchaPage,
'http://%s/' % DOMAIN: PostPage}
class Spam(Exception):
def __init__(self):
super(Spam, self).__init__("Detected as spam and unable to handle the captcha")
def __init__(self, *args, **kwargs):
kwargs['factory'] = RobustFactory()
BaseBrowser.__init__(self, *args, **kwargs)
@id2url(PastealaconPaste.id2url)
@check_url(PASTE_URL)
class PastealaconPaste(BasePaste):
# all pastes are public
public = True
# TODO perhaps move this logic elsewhere, remove this and id2url from capability
# (page_url is required by pastoob)
@property
def page_url(self):
return '%s%s' % (PastealaconBrowser.BASEURL, self.id)
class PastePage(HTMLPage):
# TODO use magic Browser2 methods (if possible)
def fill_paste(self, paste):
# there is no 404, try to detect if there really is a content
if len(self.doc.xpath('id("content")/div[@class="syntax"]//ol')) != 1:
raise PasteNotFound()
header = self.doc.xpath('id("content")/h3')[0]
matches = re.match(r'Posted by (?P<author>.+) on (?P<date>.+) \(', header.text)
paste.title = matches.groupdict().get('author')
paste.contents = unicode(self.doc.xpath('//textarea[@id="code"]')[0].text)
return paste
def get_id(self):
return self.params['id']
class CaptchaPage(HTMLPage):
pass
class PostPage(HTMLPage):
# TODO handle encoding in Browser2
def post(self, paste, expiration=None):
encoding = 'ISO-8859-1'
form = self.get_form(name='editor')
form['code2'] = paste.contents.encode(encoding)
form['poster'] = paste.title.encode(encoding)
if expiration:
form['expiry'] = expiration
form.submit()
class PastealaconBrowser(PagesBrowser):
BASEURL = 'http://pastealacon.com/'
paste = URL(r'(?P<id>\d+)', PastePage)
captcha = URL(r'%s' % re.escape('pastebin.php?captcha=1'), CaptchaPage)
raw = URL(r'%s(?P<id>\d+)' % re.escape('pastebin.php?dl='))
post = URL(r'$', PostPage)
@paste.id2url
def get_paste(self, url):
_id = re.match('^%s$' % self.PASTE_URL, url).groupdict()['id']
return PastealaconPaste(_id)
url = self.absurl(url, base=True)
m = self.paste.match(url)
if m:
return PastealaconPaste(m.groupdict()['id'])
def fill_paste(self, paste):
"""
Get as much as information possible from the paste page
"""
self.location(paste.page_url)
self.paste.stay_or_go(id=paste.id)
return self.page.fill_paste(paste)
def get_contents(self, _id):
@ -63,13 +104,16 @@ class PastealaconBrowser(BaseBrowser):
Returns unicode.
"""
try:
return self.readurl('http://%s/pastebin.php?dl=%s' % (self.DOMAIN, _id), if_fail='raise').decode(self.ENCODING)
except BrowserHTTPNotFound:
raise PasteNotFound()
return self.raw.open(id=_id).text
# TODO maybe have Browser2 raise a specialized exception
except requests.exceptions.HTTPError as e:
if e.response.status_code == requests.codes.not_found:
raise PasteNotFound()
else:
raise e
def post_paste(self, paste, expiration=None):
self.home()
self.page.post(paste, expiration=expiration)
if self.is_on_page(CaptchaPage):
raise BrowserUnavailable("Detected as spam and unable to handle the captcha")
self.post.stay_or_go().post(paste, expiration=expiration)
if self.captcha.is_here():
raise Spam()
paste.id = self.page.get_id()

View file

@ -1,62 +0,0 @@
# -*- coding: utf-8 -*-
# Copyright(C) 2011 Laurent Bachelier
#
# This file is part of weboob.
#
# weboob is free software: you can redistribute it and/or modify
# it under the terms of the GNU Affero General Public License as published by
# the Free Software Foundation, either version 3 of the License, or
# (at your option) any later version.
#
# weboob is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU Affero General Public License for more details.
#
# You should have received a copy of the GNU Affero General Public License
# along with weboob. If not, see <http://www.gnu.org/licenses/>.
import re
from weboob.tools.browser import BasePage, BrokenPageError
from weboob.capabilities.paste import PasteNotFound
__all__ = ['PastePage', 'PostPage', 'CaptchaPage']
class PastePage(BasePage):
def fill_paste(self, paste):
root = self.document.getroot()
try:
# there is no 404, try to detect if there really is a content
self.parser.select(root, 'id("content")/div[@class="syntax"]//ol', 1, 'xpath')
except BrokenPageError:
raise PasteNotFound()
header = self.parser.select(root, 'id("content")/h3', 1, 'xpath')
matches = re.match(r'Posted by (?P<author>.+) on (?P<date>.+) \(', header.text)
paste.title = matches.groupdict().get('author')
paste.contents = self.parser.select(root, '//textarea[@id="code"]', 1, 'xpath').text
return paste
def get_id(self):
"""
Find out the ID from the URL
"""
return self.group_dict['id']
class PostPage(BasePage):
def post(self, paste, expiration=None):
self.browser.select_form(name='editor')
self.browser['code2'] = paste.contents.encode(self.browser.ENCODING)
self.browser['poster'] = paste.title.encode(self.browser.ENCODING)
if expiration:
self.browser['expiry'] = [expiration]
self.browser.submit()
class CaptchaPage(BasePage):
pass

View file

@ -1,33 +0,0 @@
# -*- coding: utf-8 -*-
# Copyright(C) 2011 Laurent Bachelier
#
# This file is part of weboob.
#
# weboob is free software: you can redistribute it and/or modify
# it under the terms of the GNU Affero General Public License as published by
# the Free Software Foundation, either version 3 of the License, or
# (at your option) any later version.
#
# weboob is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU Affero General Public License for more details.
#
# You should have received a copy of the GNU Affero General Public License
# along with weboob. If not, see <http://www.gnu.org/licenses/>.
from weboob.capabilities.paste import BasePaste
__all__ = ['PastealaconPaste']
class PastealaconPaste(BasePaste):
# all pastes are public
public = True
@classmethod
def id2url(cls, _id):
return 'http://pastealacon.com/%s' % _id

View file

@ -1,6 +1,6 @@
# -*- coding: utf-8 -*-
# Copyright(C) 2011 Laurent Bachelier
# Copyright(C) 2011-2014 Laurent Bachelier
#
# This file is part of weboob.
#
@ -20,10 +20,11 @@
from weboob.tools.test import BackendTest
from weboob.capabilities.base import NotLoaded
from weboob.tools.browser import BrowserUnavailable
from weboob.capabilities.paste import PasteNotFound
from .browser import Spam
class PastealaconTest(BackendTest):
BACKEND = 'pastealacon'
@ -62,10 +63,11 @@ class PastealaconTest(BackendTest):
def test_spam(self):
p = self.backend.new_paste(None, title=u'viagra', contents=u'http://example.com/')
self.assertRaises(BrowserUnavailable, self.backend.post_paste, p)
self.assertRaises(Spam, self.backend.post_paste, p)
def test_notfound(self):
for _id in ('424242424242424242424242424242424242', 'http://pastealacon.com/424242424242424242424242424242424242'):
for _id in ('424242424242424242424242424242424242',
'http://pastealacon.com/424242424242424242424242424242424242'):
# html method
p = self.backend.get_paste(_id)
self.assertRaises(PasteNotFound, self.backend.fillobj, p, ['title'])