/modules/inrocks/pages.py

https://github.com/laurentb/weboob · Python · 65 lines · 38 code · 10 blank · 17 comment · 9 complexity · 270b790d3091f5591056b67461f2493b MD5 · raw file 

    

  1. "ArticlePage object for inrocks"
    2. 

  2. # -*- coding: utf-8 -*-
    3. 

  3. 

  4. # Copyright(C) 2011  Julien Hebert
    5. 

  5. #
    6. 

  6. # This file is part of a weboob module.
    7. 

  7. #
    8. 

  8. # This weboob module is free software: you can redistribute it and/or modify
    9. 

  9. # it under the terms of the GNU Affero General Public License as published by
    10. 

  10. # the Free Software Foundation, either version 3 of the License, or
    11. 

  11. # (at your option) any later version.
    12. 

  12. #
    13. 

  13. # This weboob module is distributed in the hope that it will be useful,
    14. 

  14. # but WITHOUT ANY WARRANTY; without even the implied warranty of
    15. 

  15. # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
    16. 

  16. # GNU Affero General Public License for more details.
    17. 

  17. #
    18. 

  18. # You should have received a copy of the GNU Affero General Public License
    19. 

  19. # along with this weboob module. If not, see <http://www.gnu.org/licenses/>.
    20. 

  20. 

  21. from weboob.browser.pages import AbstractPage
    22. 

  22. from weboob.browser.filters.html import XPathNotFound, CSS, CleanHTML
    23. 

  23. 

  24. 

  25. class ArticlePage(AbstractPage):
    26. 

  26.     "ArticlePage object for inrocks"
    27. 

  27.     _selector = CSS
    28. 

  28.     PARENT = 'genericnewspaper'
    29. 

  29.     PARENT_URL = 'generic_news_page'
    30. 

  30. 

  31.     def on_loaded(self):
    32. 

  32.         main = self._selector("div#block-article")(self.doc.getroot())
    33. 

  33.         self.main_div = main[0] if len(main) else None
    34. 

  34.         self.element_title_selector = "div.header>h1"
    35. 

  35.         self.element_author_selector = "div.name"
    36. 

  36.         self.element_body_selector = "div.maincol"
    37. 

  37. 

  38.     def get_title(self):
    39. 

  39.         try:
    40. 

  40.             return super(self.__class__, self).get_title()
    41. 

  41.         except(XPathNotFound):
    42. 

  42.             if self.main_div is None:
    43. 

  43.                 return u""
    44. 

  44.             else:
    45. 

  45.                 raise
    46. 

  46. 

  47.     def get_body(self):
    48. 

  48.         try:
    49. 

  49.             element_body = self.get_element_body()
    50. 

  50.         except XPathNotFound:
    51. 

  51.             return u'Ceci est un article payant'
    52. 

  52.         else:
    53. 

  53.             self.drop_comments(element_body)
    54. 

  54. 

  55.             div_header_element = self._selector("div.header")(element_body)[0]
    56. 

  56.             div_content_element = self._selector("div#the-content")(element_body)[0]
    57. 

  57. 

  58.             self.try_remove_from_selector_list(div_header_element,
    59. 

  59.                                                ["h1", "div.picture", "div.date",
    60. 

  60.                                                 "div.news-single-img", "div.article-top",
    61. 

  61.                                                 "div.metas_img", "strong"])
    62. 

  62.             self.try_remove_from_selector_list(div_content_element, ["div.tw_button", "div.wpfblike",
    63. 

  63.                                                                      "blockquote", "p.wp-caption-text", "img"])
    64. 

  64. 

  65.             return '%s\n%s' % (CleanHTML('.')(div_header_element), CleanHTML('.')(div_content_element))
    66.