From 391c7183ca97b8c5ca0b1313de4d1ac7d745c155 Mon Sep 17 00:00:00 2001 From: Kovid Goyal Date: Sat, 25 Apr 2020 14:48:43 +0530 Subject: [PATCH] Update Animal Politico --- recipes/animal_politico.recipe | 153 ++++++++++++--------------------- 1 file changed, 54 insertions(+), 99 deletions(-) diff --git a/recipes/animal_politico.recipe b/recipes/animal_politico.recipe index 16315e9137..4ce7a467d6 100644 --- a/recipes/animal_politico.recipe +++ b/recipes/animal_politico.recipe @@ -1,111 +1,66 @@ #!/usr/bin/python2 # encoding: utf-8 +import re from calibre.web.feeds.news import BasicNewsRecipe -class AdvancedUserRecipe1290663986(BasicNewsRecipe): - title = u'Animal Pol\u00EDtico' - publisher = u'Animal Pol\u00EDtico' - category = u'News, Mexico' - description = u'Noticias Pol\u00EDticas' - __author__ = 'leamsi' - masthead_url = 'http://www.animalpolitico.com/wp-content/themes/animal_mu/images/logo.png' - oldest_article = 1 - max_articles_per_feed = 100 +def classes(classes): + q = frozenset(classes.split(' ')) + return dict( + attrs={'class': lambda x: x and frozenset(x.split()).intersection(q)} + ) + + +class AnimalPolitico(BasicNewsRecipe): + title = u'Animal Político' + description = u'Noticias Políticas' + __author__ = 'Jose Ortiz' + masthead_url = 'https://www.animalpolitico.com/wp-content/themes/animalpolitico-2019/static/assets/logo_black.svg' language = 'es_MX' + ignore_duplicate_articles = {'title', 'url'} + conversion_options = { + 'tags': 'News, Mexico', + 'publisher': 'Animal Politico', + 'comments': description + } - remove_tags_before = dict(name='div', id='main') - remove_tags = [dict(name='div', attrs={'class': 'fb-like-button'})] - keep_only_tags = [dict(name='h1', attrs={'class': 'entry-title'}), - dict(name='div', attrs={'class': 'entry-content'})] - remove_javascript = True - INDEX = 'http://www.animalpolitico.com/' - - def generic_parse(self, soup): - articles = [] - # soup.findAll('li', 'hentry'): - for entry in soup.findAll('li', attrs={'class': lambda x: x and 'hentry' in x}): - article_url = entry.a['href'] + '?print=yes' - article_title = entry.find('h3', 'entry-title') - article_title = self.tag_to_string(article_title) - article_date = entry.find('span', 'the-time') - article_date = self.tag_to_string(article_date) - article_desc = self.tag_to_string(entry.find('p')) - - # print 'Article:',article_title, article_date,article_url - # print entry['class'] - - articles.append({'title': article_title, - 'date': article_date, - 'description': article_desc, - 'url': article_url}) - # Avoid including the multimedia stuff. - if ''.join(entry['class']).find('last') != -1: - break - - return articles - - def plumaje_parse(self, soup): - articles = [] - blogs_soup = soup.find('ul', attrs={'class': lambda x: x and 'bloglist-fecha' in x}) - for entry in blogs_soup.findAll('li'): - article_title = entry.p - article_url = article_title.a['href'] + '?print=yes' - article_date = article_title.nextSibling - article_title = self.tag_to_string(article_title) - article_date = self.tag_to_string( - article_date).replace(u'Last Updated: ', '') - article_desc = self.tag_to_string(entry.find('h4')) - - # print 'Article:',article_title, article_date,article_url - articles.append({'title': article_title, - 'date': article_date, - 'description': article_desc, - 'url': article_url}) - - return articles - - def boca_parse(self, soup): - articles = [] - # soup.findAll('li', 'hentry'): - for entry in soup.findAll('div', attrs={'class': lambda x: x and 'hentry' in x}): - article_title = entry.find('h2', 'entry-title') - article_url = article_title.a['href'] + '?print=yes' - article_title = self.tag_to_string(article_title) - article_date = entry.find('span', 'entry-date') - article_date = self.tag_to_string(article_date) - article_desc = self.tag_to_string( - entry.find('div', 'entry-content')) - - # print 'Article:',article_title, article_date,article_url - # print entry['class'] - - articles.append({'title': article_title, - 'date': article_date, - 'description': article_desc, - 'url': article_url}) - # Avoid including the multimedia stuff. - if ''.join(entry['class']).find('last') != -1: - break - - return articles + keep_only_tags = [classes('ap_single_first ap_single_content ax_single')] + remove_tags = [classes('ap_single_sharers_head ap_single_sharers_share')] def parse_index(self): - gobierno_soup = self.index_to_soup(self.INDEX + 'gobierno/') - congreso_soup = self.index_to_soup(self.INDEX + 'congreso/') - seguridad_soup = self.index_to_soup(self.INDEX + 'seguridad/') - comunidad_soup = self.index_to_soup(self.INDEX + 'comunidad/') - plumaje_soup = self.index_to_soup(self.INDEX + 'plumaje/') - la_boca_del_lobo_soup = self.index_to_soup( - self.INDEX + 'category/la-boca-del-lobo/') + soup = self.index_to_soup('http://www.animalpolitico.com/') + articles = [] + for a in soup(**{ + 'name': 'a', + 'attrs': { + 'href': True, 'title': True, + 'data-author': True, 'data-type': True, + 'data-home-title': True + } + }): + title = a['title'] + url = a['href'] + author = a['data-author'] + self.log('\t', title, ' at ', url) - gobierno_articles = self.generic_parse(gobierno_soup) - congreso_articles = self.generic_parse(congreso_soup) - seguridad_articles = self.generic_parse(seguridad_soup) - comunidad_articles = self.generic_parse(comunidad_soup) - plumaje_articles = self.plumaje_parse(plumaje_soup) - la_boca_del_lobo_articles = self.boca_parse(la_boca_del_lobo_soup) + articles.append({'title': title, + 'author': author, + 'url': url}) + ans = {} + for article in articles: + if re.match(r'https?://www\.animalpolitico\.com/elsabueso/.', article['url'], re.I): + ans.setdefault('El Sabueso', []).append(article) + elif re.match(r'https?://www\.animalpolitico\.com/.', article['url'], re.I): + ans.setdefault('Noticias', []).append(article) + elif re.match(r'https?://www\.animalgourmet\.com/.', article['url'], re.I): + ans.setdefault('Comida', []).append(article) - return [(u'Gobierno', gobierno_articles), (u'Congreso', congreso_articles), (u'Seguridad', seguridad_articles), - (u'Comunidad', comunidad_articles), (u'Plumaje', plumaje_articles), (u'La Boca del Lobo', la_boca_del_lobo_articles), ] + return [(sec, ans[sec]) for sec in sorted(ans)] + + def populate_article_metadata(self, article, soup, first): + if re.match(r'https?://www\.animalpolitico\.com/.', article.url, re.I): + article.formatted_date = self.tag_to_string( + soup.find( + **classes('ap_single_first')).find( + **classes('ap_single_first_info_date')))