China Press by rty

resources/recipes/china_press.recipe

@@ -0,0 +1,71 @@
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class AdvancedUserRecipe1277228948(BasicNewsRecipe):
+    title          = u'China Press USA'
+    oldest_article = 7
+    max_articles_per_feed = 100
+
+    __author__            = 'rty'
+    __version__            = '1.0'
+    language = 'zh_CN'
+    pubisher  = 'www.chinapressusa.com'
+    description           = 'Overseas Chinese Network Newspaper in the USA'
+    category              = 'News in Chinese, USA'
+    remove_javascript = True
+    use_embedded_content   = False
+    no_stylesheets = True
+    #encoding               = 'GB2312'
+    encoding               = 'UTF-8'
+    conversion_options = {'linearize_tables':True}
+    masthead_url ='http://www.chinapressusa.com/common/images/logo.gif'
+    extra_css = '''
+             @font-face { font-family: "DroidFont", serif, sans-serif;  src: url(res:///system/fonts/DroidSansFallback.ttf); }\n
+             body {
+                  margin-right: 8pt;
+                  font-family: 'DroidFont', serif;}
+              h1  {font-family: 'DroidFont', serif, sans-serif}
+            .show {font-family: 'DroidFont', serif, sans-serif}
+            '''
+    feeds          = [
+	(u'\u65b0\u95fb\u9891\u9053', u'http://news.uschinapress.com/news.xml'),
+	(u'\u534e\u4eba\u9891\u9053', u'http://chinese.uschinapress.com/chinese.xml'),
+	(u'\u8bc4\u8bba\u9891\u9053', u'http://review.uschinapress.com/review.xml'),
+	]
+    keep_only_tags = [
+                              dict(name='div', attrs={'class':'show'}),
+                               ]
+    remove_tags = [
+     #               dict(name='table', attrs={'class':'xle'}),
+                    dict(name='div', attrs={'class':'time'}),
+                         ]
+    remove_tags_after = [
+                  dict(name='div', attrs={'class':'bank17'}),
+         #         dict(name='a', attrs={'class':'ab12'}),
+                         ]
+
+
+    def append_page(self, soup, appendtag, position):
+        pager = soup.find('div',attrs={'id':'displaypagenum'})
+        if pager:
+           nexturl = self.INDEX + pager.a['href']
+           soup2 = self.index_to_soup(nexturl)
+           texttag = soup2.find('div', attrs={'class':'show'})
+           for it in texttag.findAll(style=True):
+               del it['style']
+           newpos = len(texttag.contents)
+           self.append_page(soup2,texttag,newpos)
+           texttag.extract()
+           appendtag.insert(position,texttag)
+
+
+    def preprocess_html(self, soup):
+        mtag = '<meta http-equiv="Content-Language" content="zh-CN"/>\n<meta http-equiv="Content-Type" content="text/html; charset=utf-8"/>'
+        soup.head.insert(0,mtag)
+
+        for item in soup.findAll(style=True):
+            del item['style']
+        self.append_page(soup, soup.body, 3)
+        pager = soup.find('div',attrs={'id':'displaypagenum'})
+        if pager:
+           pager.extract()
+        return soup