New recipe for The Yemen Times by kwetal

resources/recipes/yementimes.recipe

@@ -0,0 +1,125 @@
+from calibre.web.feeds.news import BasicNewsRecipe
+from calibre.ebooks.BeautifulSoup import BeautifulSoup, Tag
+
+class YemenTimesRecipe(BasicNewsRecipe):
+    __license__  = 'GPL v3'
+    __author__ = 'kwetal'
+    language = 'en_YE'
+    country = 'YE'
+    version = 1
+
+    title = u'Yemen Times'
+    publisher = u'yementimes.com'
+    category = u'News, Opinion, Yemen'
+    description = u'Award winning weekly from Yemen, promoting press freedom, professional journalism and the defense of human rights.'
+
+    oldest_article = 7
+    max_articles_per_feed = 100
+    use_embedded_content = False
+    encoding = 'utf-8'
+
+    remove_empty_feeds = True
+    no_stylesheets = True
+    remove_javascript = True
+
+    keep_only_tags = []
+    keep_only_tags.append(dict(name = 'div', attrs = {'id': 'ctl00_ContentPlaceHolder1_MAINNEWS0_Panel1',
+                                                      'class': 'DMAIN2'}))
+    remove_attributes = ['style']
+
+    INDEX = 'http://www.yementimes.com/'
+    feeds = []
+    feeds.append((u'Our Viewpoint', u'http://www.yementimes.com/DEFAULTSUB.ASPX?pnc=6&pnm=OUR%20VIEWPOINT'))
+    feeds.append((u'Local News', u'http://www.yementimes.com/DEFAULTSUB.ASPX?pnc=3&pnm=Local%20news'))
+    feeds.append((u'Their News', u'http://www.yementimes.com/DEFAULTSUB.ASPX?pnc=80&pnm=Their%20News'))
+    feeds.append((u'Report', u'http://www.yementimes.com/DEFAULTSUB.ASPX?pnc=8&pnm=report'))
+    feeds.append((u'Health', u'http://www.yementimes.com/DEFAULTSUB.ASPX?pnc=51&pnm=health'))
+    feeds.append((u'Interview', u'http://www.yementimes.com/DEFAULTSUB.ASPX?pnc=77&pnm=interview'))
+    feeds.append((u'Opinion', u'http://www.yementimes.com/DEFAULTSUB.ASPX?pnc=7&pnm=opinion'))
+    feeds.append((u'Business', u'http://www.yementimes.com/DEFAULTSUB.ASPX?pnc=5&pnm=business'))
+    feeds.append((u'Op-Ed', u'http://www.yementimes.com/DEFAULTSUB.ASPX?pnc=81&pnm=Op-Ed'))
+    feeds.append((u'Culture', u'http://www.yementimes.com/DEFAULTSUB.ASPX?pnc=75&pnm=Culture'))
+    feeds.append((u'Readers View', u'http://www.yementimes.com/DEFAULTSUB.ASPX?pnc=4&pnm=Readers%20View'))
+    feeds.append((u'Variety', u'http://www.yementimes.com/DEFAULTSUB.ASPX?pnc=9&pnm=Variety'))
+    feeds.append((u'Education', u'http://www.yementimes.com/DEFAULTSUB.ASPX?pnc=57&pnm=Education'))
+
+    extra_css = '''
+                body {font-family:verdana, arial, helvetica, geneva, sans-serif;}
+                div.yemen_byline {font-size: medium; font-weight: bold;}
+                div.yemen_date {font-size: small; color: #666666; margin-bottom: 0.6em;}
+                .yemen_caption {font-size: x-small; font-style: italic; color: #696969;}
+                '''
+
+    conversion_options = {'comments': description, 'tags': category, 'language': 'en',
+                          'publisher': publisher, 'linearize_tables': True}
+
+    def get_browser(self):
+        br = BasicNewsRecipe.get_browser()
+        br.set_handle_gzip(True)
+
+        return br
+
+    def parse_index(self):
+        answer = []
+        for feed_title, feed in self.feeds:
+            soup = self.index_to_soup(feed)
+
+            newsbox = soup.find('div', 'newsbox')
+            main = newsbox.findNextSibling('table')
+
+            articles = []
+            for li in main.findAll('li'):
+                title = self.tag_to_string(li.a)
+                url = self.INDEX + li.a['href']
+                articles.append({'title': title, 'date': None, 'url': url, 'description': '<br/>&nbsp;'})
+
+            answer.append((feed_title, articles))
+
+        return answer
+
+    def preprocess_html(self, soup):
+        freshSoup = self.getFreshSoup(soup)
+
+        headline = soup.find('div', attrs = {'id': 'DVMTIT'})
+        if headline:
+            div = headline.findNext('div', attrs = {'id': 'DVTOP'})
+            img = None
+            if div:
+                img = div.find('img')
+
+            headline.name = 'h1'
+            freshSoup.body.append(headline)
+            if img is not None:
+                freshSoup.body.append(img)
+
+        byline = soup.find('div', attrs = {'id': 'DVTIT'})
+        if byline:
+            date_el = byline.find('span')
+            if date_el:
+                pub_date = self.tag_to_string(date_el)
+                date = Tag(soup, 'div', attrs = [('class', 'yemen_date')])
+                date.append(pub_date)
+                date_el.extract()
+
+            raw = '<br/>'.join(['%s' % (part) for part in byline.findAll(text = True)])
+            author = BeautifulSoup('<div class="yemen_byline">' + raw + '</div>')
+
+            if date is not None:
+                freshSoup.body.append(date)
+            freshSoup.body.append(author)
+
+        story = soup.find('div', attrs = {'id': 'DVDET'})
+        if story:
+            for table in story.findAll('table'):
+                if table.find('img'):
+                    table['class'] = 'yemen_caption'
+
+            freshSoup.body.append(story)
+
+        return freshSoup
+
+    def getFreshSoup(self, oldSoup):
+        freshSoup = BeautifulSoup('<html><head><title></title></head><body></body></html>')
+        if oldSoup.head.title:
+            freshSoup.head.title.append(self.tag_to_string(oldSoup.head.title))
+        return freshSoup

src/calibre/utils/localization.py

@@ -104,6 +104,7 @@ _extra_lang_codes = {
         'en_CY' : _('English (Cyprus)'),
         'en_PK' : _('English (Pakistan)'),
         'en_SG' : _('English (Singapore)'),
+        'en_YE' : _('English (Yemen)'),
         'de_AT' : _('German (AT)'),
         'nl'    : _('Dutch (NL)'),
         'nl_BE' : _('Dutch (BE)'),