d61e15cf84
weboob.tools.browser -> weboob.deprecated.browser weboob.tools.parsers -> weboob.deprecated.browser.parsers weboob.tools.mech -> weboob.deprecated.mech weboob.browser2 -> weboob.browser weboob.core.exceptions -> weboob.exceptions Also, the new tree for browser2 is: weboob.browser: import weboob.browser.browsers.* and weboob.browser.url.* weboob.browser.browsers: all browsers (including PagesBrowser and LoginBrowser) weboob.browser.url: the URL class weboob.browser.profiles: all Profile classes weboob.browser.sessions: WeboobSession and FuturesSession weboob.browser.cookies: that's a cookies thing weboob.browser.pages: all Page and derivated classes, and Form class weboob.browser.exceptions: specific browser exceptions weboob.browser.elements: AbstractElement classes, and 'method' decorator weboob.browser.filters.*: all filters
64 lines
2.7 KiB
Python
64 lines
2.7 KiB
Python
# -*- coding: utf-8 -*-
|
|
|
|
# Copyright(C) 2012 Lucien Loiseau
|
|
#
|
|
# 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.deprecated.browser import Page
|
|
import re
|
|
|
|
|
|
LAST_THING_IN_PARENTHESIS = re.compile("\([^)]\)$")
|
|
|
|
|
|
class TranslatePage(Page):
|
|
def get_translation(self):
|
|
trs = self.document.getroot().xpath("//table[@class='WRD']/tr[@class='even']")
|
|
if trs and len(trs) > 0:
|
|
# taking the first signification in the case several were found
|
|
return self.parser.select(trs[0], "td[@class='ToWrd']", 1, method='xpath').text
|
|
"""
|
|
# taking the first signification in the case several were found
|
|
for tr in self.document.getiterator('tr'):
|
|
prev_was_nums1 = False
|
|
for td in tr.getiterator('td'):
|
|
if prev_was_nums1:
|
|
result = u''+td.text_content().split(';')[0].strip()
|
|
result = LAST_THING_IN_PARENTHESIS.sub("",result)
|
|
return result
|
|
if td.attrib.get('class','') == 'nums1':
|
|
prev_was_nums1 = True
|
|
# if only one signification is found
|
|
for div in self.document.getiterator('div'):
|
|
if div.attrib.get('class','') == "trans clickable":
|
|
if ']' in div.text_content():
|
|
tnames = div.text_content().split(']')[1].split()[1:]
|
|
else:
|
|
tnames = div.text_content().split()[1:]
|
|
names = u''+" ".join(tnames).split(';')[0]
|
|
names = LAST_THING_IN_PARENTHESIS.sub("",names)
|
|
return names.strip()
|
|
# another numerotation possibility...
|
|
for table in self.document.getiterator('table'):
|
|
if table.attrib.get('class','') == "trans clickable":
|
|
prev_was_roman1 = False
|
|
for td in table.getiterator('td'):
|
|
if prev_was_roman1:
|
|
return u''+td.text_content().split(';')[0].strip()
|
|
if td.attrib.get('class','') == 'roman1':
|
|
prev_was_roman1 = True
|
|
"""
|