Fix New England Journal of Medicine and Journal of Hospital Medicine

resources/recipes/johm.recipe

@@ -1,78 +1,72 @@
-# -*- coding: utf-8 -*-
+import re
-
 from calibre.web.feeds.recipes import BasicNewsRecipe
 
 class JournalofHospitalMedicine(BasicNewsRecipe):
 
     title       = 'Journal of Hospital Medicine'
-    __author__  = 'Krittika Goyal'
+    __author__  = 'Kovid Goyal'
     description = 'Medical news'
     timefmt = ' [%d %b, %Y]'
     needs_subscription = True
     language = 'en'
 
     no_stylesheets = True
+    keep_only_tags = [dict(id=['articleTitle', 'articleMeta', 'fulltext'])]
+    remove_tags = [dict(attrs={'class':'licensedContent'})]
 
 
    # TO LOGIN
     def get_browser(self):
         br = BasicNewsRecipe.get_browser()
         br.open('http://www3.interscience.wiley.com/cgi-bin/home')
-        br.select_form(name='siteLogin')
+        br.select_form(nr=0)
-        br['LoginName'] = self.username
+        br['j_username'] = self.username
-        br['Password'] = self.password
+        br['j_password'] = self.password
         response = br.submit()
         raw = response.read()
-        if 'userName = ""' in raw:
+        if '<h2>LOGGED IN</h2>' not in raw:
             raise Exception('Login failed. Check your username and password')
         return br
 
     #TO GET ARTICLE TOC
     def johm_get_index(self):
-        return self.index_to_soup('http://www3.interscience.wiley.com/journal/111081937/home')
+        return self.index_to_soup('http://onlinelibrary.wiley.com/journal/10.1002/(ISSN)1553-5606/currentissue')
 
     # To parse artice toc
     def parse_index(self):
-        parse_soup = self.johm_get_index()
+        soup = self.johm_get_index()
-
+        toc = soup.find(id='issueTocGroups')
-        div = parse_soup.find(id='contentCell')
-
-        current_section = None
-        current_articles = []
         feeds = []
-        for x in div.findAll(True):
+        for group in toc.findAll('li', id=re.compile(r'group\d+')):
-            if x.name == 'h4':
+            gtitle = group.find(attrs={'class':'subSectionHeading'})
-                # Section heading found
+            if gtitle is None:
-                if current_articles and current_section:
-                    feeds.append((current_section, current_articles))
-                current_section = self.tag_to_string(x)
-                current_articles = []
-                self.log('\tFound section:', current_section)
-            if current_section is not None and x.name == 'strong':
-                title = self.tag_to_string(x)
-                p = x.parent.parent.find('a', href=lambda x: x and '/HTMLSTART' in x)
-                if p is None:
                 continue
-                url = p.get('href', False)
+            gtitle = self.tag_to_string(gtitle)
-                if not url or not title:
+            arts = group.find(attrs={'class':'articles'})
+            if arts is None:
                 continue
+            self.log('Found section:', gtitle)
+            articles = []
+            for art in arts.findAll(attrs={'class':lambda x: x and 'tocArticle'
+                in x}):
+                a = art.find('a', href=True)
+                if a is None:
+                    continue
+                url = a.get('href')
                 if url.startswith('/'):
-                        url = 'http://www3.interscience.wiley.com'+url
+                    url = 'http://onlinelibrary.wiley.com' + url
-                url = url.replace('/HTMLSTART', '/main.html,ftx_abs')
+                url = url.replace('/abstract', '/full')
-                self.log('\t\tFound article:', title)
+                title = self.tag_to_string(a)
-                self.log('\t\t\t', url)
+                a.extract()
-                #if url.startswith('/'):
+                pm = art.find(attrs={'class':'productMenu'})
-                    #url = 'http://online.wsj.com'+url
+                if pm is not None:
-                current_articles.append({'title': title, 'url':url,
+                    pm.extract()
-                    'description':'', 'date':''})
+                desc = self.tag_to_string(art)
-
+                self.log('\tFound article:', title, 'at', url)
-        if current_articles and current_section:
+                articles.append({'title':title, 'url':url, 'description':desc,
-            feeds.append((current_section, current_articles))
+                    'date':''})
+            if articles:
+                feeds.append((gtitle, articles))
 
         return feeds
 
-    def preprocess_html(self, soup):
-        for img in soup.findAll('img', src=True):
-            img['src'] = img['src'].replace('tfig', 'nfig')
-        return soup
-

resources/recipes/nejm.recipe

@@ -4,7 +4,7 @@ from calibre.web.feeds.recipes import BasicNewsRecipe
 class NYTimes(BasicNewsRecipe):
 
     title       = 'New England Journal of Medicine'
-    __author__  = 'Krittika Goyal'
+    __author__  = 'Kovid Goyal'
     description = 'Medical news'
     timefmt = ' [%d %b, %Y]'
     needs_subscription = True