Nan Feng Chuang by Chen Wei

recipes/nanfengchuang.recipe

@@ -0,0 +1,108 @@
+# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:fdm=marker:ai
+from __future__ import unicode_literals
+from calibre.web.feeds.recipes import BasicNewsRecipe
+from lxml import html
+
+__license__   = 'GPL v3'
+
+
+class Nfcmag(BasicNewsRecipe):
+
+    __author__  = '2014, Chen Wei <weichen302@gmx.com>'
+    title = 'Nan Feng Chuang / South Reviews Magazine'
+    description = '''
+South Reviews Magazine, established in 1985, is a Guangzhou-based political and
+economic biweekly. South Reviews enjoys a reputation of being fair and objective, with graceful
+narration, insightful expression among its readers, mostly government
+officials, economic leaders and intellectuals. It has been praised as “the No.1
+Political& Economical Magazine in China”.
+
+The US magazine Time described South Reviews as "a highbrow news magazine".
+Other international media organizations such as BBC and NHK have conducted
+tracking shots of South Reviews journalists, to record their unique value
+special position in China’s media industry. Harvard-Yenching Library, Stanford
+University's East Asia Library and UC Berkeley Library have collections of the
+magazine since its first issue, taking them as an important source to
+understand China's economic and social reform.
+
+Since 2008, South Reviews has been committed to transforming into a
+research-based media organization. Most of its editors, reporters and
+contributors have remarkably strong academic backgrounds, coming from Peking
+University, Tsinghua University, London School of Economics and Political
+Science, the Chinese University of Hong Kong, Renmin University of China, and
+other well-known institutions. The magazine has established research divisions,
+including the State Policy Research Center and the Brand Promotion Research
+Center, working in cooperation with well-known academic institutions and
+providing valuable research reports for governments and companies.
+
+'''
+    language = 'zh'
+    encoding = 'UTF-8'
+    publisher = 'South Reviews Magazine'
+    publication_type = 'magazine'
+    category = 'news, Business, China'
+    timefmt = ' [%a, %d %b, %Y]'
+    needs_subscription = False
+
+    remove_tags = [dict(attrs={'class':['side-left', 'side-right',
+                                        'breadcrumbs', 'score', 'weboNav']}),
+                   dict(attrs={'id': ['header', 'footer']}),
+                   dict(name=['script', 'noscript', 'style'])]
+    no_stylesheets = True
+    remove_javascript = True
+    current_issue_url = ""
+    current_issue_cover = ""
+
+    def parse_index(self):
+
+        baseurl = 'http://www.nfcmag.com/'
+        raw = self.index_to_soup('http://www.nfcmag.com/magazine', raw=True)
+        soup_start = html.fromstring(raw)
+
+        #pageDoc = html.parse(sectionUrl)
+        els = soup_start.xpath("""//div[contains(@class, 'lastest-magazine')
+                         and contains(@class, 'comBox')]
+                         //a[@href and not(@id) and not(child::img)]
+                         """)
+        for x in els:
+            issueurl = x.get('href')
+            if not issueurl.lower().startswith('http://'):
+                issueurl = baseurl + issueurl
+            break
+
+        raw = self.index_to_soup(issueurl, raw=True)
+        soup_issue = html.fromstring(raw)
+
+        coverimg = soup_issue.xpath("""//div[contains(@class, 'lastest-magazine')
+                         and contains(@class, 'comBox')]
+                         //img[@*] """)
+        imgurl = coverimg[0].get('src')
+        if not imgurl.lower().startswith('http://'):
+            imgurl = baseurl + imgurl
+        self.current_issue_cover = imgurl
+        feeds = []
+
+        sections = soup_issue.xpath("""//div[contains(@class, 'article-box')
+                         and contains(@class, 'comBox')] """)
+        for sec in sections:
+            pages = sec.xpath('.//h5')
+            sec_title = sec.xpath('.//h4')[0].text_content()
+            self.log('Found section:', sec_title)
+            articles = []
+            for x in pages:
+                url = x.xpath('.//a')[0].get('href')
+                if not url.lower().startswith('http://'):
+                    url = baseurl + url
+                url = url[:-5] + '-s.html'  # to print view
+
+                title =  x.text_content()
+
+                articles.append({'title': title, 'url': url, 'date': None})
+
+            if articles:
+                feeds.append((sec_title, articles))
+        return feeds
+
+    def get_cover_url(self):
+        return self.current_issue_cover
+