Fix #405 (New news feed). Apple daily by MrLai

resources/recipes/apple_daily.recipe

@@ -0,0 +1,161 @@
+# -*- coding: utf-8 -*-
+import re
+from calibre.web.feeds.recipes import BasicNewsRecipe
+
+class AppleDaily(BasicNewsRecipe):
+
+    title       = u'蘋果日報'
+    __author__  = u'蘋果日報'
+    __publisher__  = u'蘋果日報'
+    description = u'蘋果日報'
+    masthead_url = 'http://hk.apple.nextmedia.com/template/common/header/2009/images/atnextheader_logo_appledaily.gif'
+    language = 'zh_TW'
+    encoding = 'UTF-8'
+    timefmt = ' [%a, %d %b, %Y]'
+    needs_subscription = False
+    remove_javascript = True
+    remove_tags_before = dict(name=['ul', 'h1'])
+    remove_tags_after  = dict(name='form')
+    remove_tags = [dict(attrs={'class':['articleTools', 'post-tools', 'side_tool', 'nextArticleLink clearfix']}),
+                dict(id=['footer', 'toolsRight', 'articleInline', 'navigation', 'archive', 'side_search', 'blog_sidebar', 'side_tool', 'side_index']),
+                dict(name=['script', 'noscript', 'style', 'form'])]
+    no_stylesheets = True
+    extra_css = '''
+    	@font-face {font-family: "uming", serif, sans-serif;  src: url(res:///usr/share/fonts/truetype/arphic/uming.ttc); }\n
+	    body {margin-right: 8pt; font-family: 'uming', serif;}
+        h1 {font-family: 'uming', serif, sans-serif}
+            '''
+    #extra_css = 'h1 {font: sans-serif large;}\n.byline {font:monospace;}'
+
+    preprocess_regexps = [
+       (re.compile(r'img.php?server=(?P<server>[^&]+)&path=(?P<path>[^&]+).*', re.DOTALL|re.IGNORECASE),
+        lambda match: 'http://' + match.group('server') + '/' + match.group('path')),
+    ]
+
+    def get_cover_url(self):
+        return 'http://hk.apple.nextmedia.com/template/common/header/2009/images/atnextheader_logo_appledaily.gif'
+
+
+    #def get_browser(self):
+        #br = BasicNewsRecipe.get_browser()
+        #if self.username is not None and self.password is not None:
+        #    br.open('http://www.nytimes.com/auth/login')
+        #    br.select_form(name='login')
+        #    br['USERID']   = self.username
+        #    br['PASSWORD'] = self.password
+        #    br.submit()
+        #return br
+
+    def preprocess_html(self, soup):
+        #process all the images
+        for tag in soup.findAll(lambda tag: tag.name.lower()=='img' and tag.has_key('src')):
+            iurl = tag['src']
+            #print 'checking image: ' + iurl
+
+            #img\.php?server\=(?P<server>[^&]+)&path=(?P<path>[^&]+)
+            p = re.compile(r'img\.php\?server=(?P<server>[^&]+)&path=(?P<path>[^&]+)', re.DOTALL|re.IGNORECASE)
+
+            m = p.search(iurl)
+
+            if m is not None:
+                iurl = 'http://' + m.group('server') + '/' + m.group('path')
+                #print 'working! new url: ' + iurl
+                tag['src'] = iurl
+            #else:
+                #print 'not good'
+
+        for tag in soup.findAll(lambda tag: tag.name.lower()=='a' and tag.has_key('href')):
+            iurl = tag['href']
+            #print 'checking image: ' + iurl
+
+            #img\.php?server\=(?P<server>[^&]+)&path=(?P<path>[^&]+)
+            p = re.compile(r'img\.php\?server=(?P<server>[^&]+)&path=(?P<path>[^&]+)', re.DOTALL|re.IGNORECASE)
+
+            m = p.search(iurl)
+
+            if m is not None:
+                iurl = 'http://' + m.group('server') + '/' + m.group('path')
+                #print 'working! new url: ' + iurl
+                tag['href'] = iurl
+            #else:
+                #print 'not good'
+
+        return soup
+
+
+    def parse_index(self):
+        base = 'http://news.hotpot.hk/fruit'
+        soup = self.index_to_soup('http://news.hotpot.hk/fruit/index.php')
+
+        #def feed_title(div):
+        #    return ''.join(div.findAll(text=True, recursive=False)).strip()
+
+        articles = {}
+        key = None
+        ans = []
+        for div in soup.findAll('li'):
+            key = div.find(text=True, recursive=True);
+            #if key == u'豪情':
+           #    continue;
+
+            print 'section=' + key
+
+            articles[key] = []
+
+            ans.append(key)
+
+            a = div.find('a', href=True)
+
+            if not a:
+                continue
+
+            url = base + '/' + a['href']
+            print 'url=' + url
+
+            if not articles.has_key(key):
+                articles[key] = []
+            else:
+                # sub page
+                subSoup = self.index_to_soup(url)
+
+                for subDiv in subSoup.findAll('li'):
+                    subA = subDiv.find('a', href=True)
+                    subTitle = subDiv.find(text=True, recursive=True)
+                    subUrl = base + '/' + subA['href']
+
+                    print 'subUrl' + subUrl
+
+                    articles[key].append(
+                        dict(title=subTitle,
+                         url=subUrl,
+                         date='',
+                         description='',
+                         content=''))
+
+
+#             elif div['class'] in ['story', 'story headline']:
+#                 a = div.find('a', href=True)
+#                 if not a:
+#                     continue
+#                 url = re.sub(r'\?.*', '', a['href'])
+#                 url += '?pagewanted=all'
+#                 title = self.tag_to_string(a, use_alt=True).strip()
+#                 description = ''
+#                 pubdate = strftime('%a, %d %b')
+#                 summary = div.find(True, attrs={'class':'summary'})
+#                 if summary:
+#                     description = self.tag_to_string(summary, use_alt=False)
+#
+#                 feed = key if key is not None else 'Uncategorized'
+#                 if not articles.has_key(feed):
+#                     articles[feed] = []
+#                 if not 'podcasts' in url:
+#                     articles[feed].append(
+#                               dict(title=title, url=url, date=pubdate,
+#                                    description=description,
+#                                    content=''))
+#        ans = self.sort_index_by(ans, {'The Front Page':-1, 'Dining In, Dining Out':1, 'Obituaries':2})
+        ans = [(unicode(key), articles[key]) for key in ans if articles.has_key(key)]
+        return ans
+
+